Search

Abstract Chronic obstructive pulmonary disease (COPD) stands as a significant global health challenge, with its intricate pathophysiological manifestations often demanding advanced diagnostic strategies. The recent applications of artificial intelligence (AI) within the realm of medical imaging, especially in computed tomography, present a promising avenue for transformative changes in COPD diagnosis and management. This review delves deep into the capabilities and advancements of AI, particularly focusing on machine learning and deep learning, and their applications in COPD identification, staging, and imaging phenotypes. Emphasis is laid on the AI-powered insights into emphysema, airway dynamics, and vascular structures. The challenges linked with data intricacies and the integration of AI in the clinical landscape are discussed. Lastly, the review casts a forward-looking perspective, highlighting emerging innovations in AI for COPD imaging and the potential of interdisciplinary collaborations, hinting at a future where AI doesn’t just support but pioneers breakthroughs in COPD care. Through this review, we aim to provide a comprehensive understanding of the current state and future potential of AI in shaping the landscape of COPD diagnosis and management.

Abstract Background The diagnosis of solitary pulmonary nodules has always been a difficult and important point in clinical research, especially granulomatous nodules (GNs) with lobulation and spiculation signs, which are easily misdiagnosed as malignant tumors. Therefore, in this study, we utilised a CT deep learning (DL) model to distinguish GNs with lobulation and spiculation signs from solid lung adenocarcinomas (LADCs), to improve the diagnostic accuracy of preoperative diagnosis. Methods 420 patients with pathologically confirmed GNs and LADCs from three medical institutions were retrospectively enrolled. The regions of interest in non-enhanced CT (NECT) and venous contrast-enhanced CT (VECT) were identified and labeled, and self-supervised labels were constructed. Cases from institution 1 were randomly divided into a training set (TS) and an internal validation set (IVS), and cases from institutions 2 and 3 were treated as an external validation set (EVS). Training and validation were performed using self-supervised transfer learning, and the results were compared with the radiologists’ diagnoses. Results The DL model achieved good performance in distinguishing GNs and LADCs, with area under curve (AUC) values of 0.917, 0.876, and 0.896 in the IVS and 0.889, 0.879, and 0.881 in the EVS for NECT, VECT, and non-enhanced with venous contrast-enhanced CT (NEVECT) images, respectively. The AUCs of radiologists 1, 2, 3, and 4 were, respectively, 0.739, 0.783, 0.883, and 0.901 in the (IVS) and 0.760, 0.760, 0.841, and 0.844 in the EVS. Conclusions A CT DL model showed great value for preoperative differentiation of GNs with lobulation and spiculation signs from solid LADCs, and its predictive performance was higher than that of radiologists.

Abstract Background Chronic obstructive pulmonary disease (COPD) is a prevalent and debilitating respiratory condition that imposes a significant healthcare burden worldwide. Accurate staging of COPD severity is crucial for patient management and treatment planning. Methods The retrospective study included 530 hospital patients. A lobe-based radiomics method was proposed to classify COPD severity using computed tomography (CT) images. First, we segmented the lung lobes with a convolutional neural network model. Secondly, the radiomic features of each lung lobe are extracted from CT images, the features of the five lung lobes are merged, and the selection of features is accomplished through the utilization of a variance threshold, t-Test, least absolute shrinkage and selection operator (LASSO). Finally, the COPD severity was classified by a support vector machine (SVM) classifier. Results 104 features were selected for staging COPD according to the Global initiative for chronic Obstructive Lung Disease (GOLD). The SVM classifier showed remarkable performance with an accuracy of 0.63. Moreover, an additional set of 132 features were selected to distinguish between milder (GOLD I + GOLD II) and more severe instances (GOLD III + GOLD IV) of COPD. The accuracy for SVM stood at 0.87. Conclusions The proposed method proved that the novel lobe-based radiomics method can significantly contribute to the refinement of COPD severity staging. By combining radiomic features from each lung lobe, it can obtain a more comprehensive and rich set of features and better capture the CT radiomic features of the lung than simply observing the lung as a whole.

Abstract To predict massive cerebral infarction (MCI) occurrence after anterior circulation occlusion (ACO) by cASPECTS-CTA-CS (combined ASPECTS and CTA-CS). Of 185 cerebral infarction patients with the ACO, their collateral circulation scores from CT angiography (CTA) images in two groups (MCI and non-MCI) were evaluated using Alberta Stroke Program Early CT Score (ASPECTS) and CT angiography collateral score (CTA-CS) approaches. The cASPECTS-CTA-CS was validated internally using the bootstrap sampling method with 1000 bootstrap repetitions and compared to CTA-CS. Receiver-operating characteristic curve (ROC), clinical impact curve (CIC), and decision curve analysis (DCA) strategies were used to assess the clinical practicality and predictability of both approaches (cASPECTS-CTA-CS and CTA-CS). Using net reclassification improvement (NRI) and integrated discrimination improvement (IDI) analyses, discrimination levels of the cASPECTS-CTA-CS were compared with CTA-CS. Classification and regression tree (CART) analyses was conducted to identify the best predictive values and identify subgroup of MCI. The discrimination ability of collateral circulation evaluation score using the cASPECTS-CTA-CS [AUC: 0.918, 95% confidence interval (CI): 0.869–0.967, P 80%. Less than 23 of cASPECTS-CTA-CS by CART was important factor in determining MCI occurrence, and ASPECTS

Abstract Background Prostate cancer (PCa) is one of the most common cancers in men worldwide, and its timely diagnosis and treatment are becoming increasingly important. MRI is in increasing use to diagnose cancer and to distinguish between non-clinically significant and clinically significant PCa, leading to more precise diagnosis and treatment. The purpose of this study is to present a radiomics-based method for determining the Gleason score (GS) for PCa using tumour heterogeneity on multiparametric MRI (mp-MRI). Methods Twenty-six patients with biopsy-proven PCa were included in this study. The quantitative T2 values, apparent diffusion coefficient (ADC) and signal enhancement rates (α) were calculated using multi-echo T2 images, diffusion-weighted imaging (DWI) and dynamic contrast-enhanced MRI (DCE-MRI), for the annotated region of interests (ROI). After texture feature analysis, ROI range expansion and feature filtering was performed. Then obtained data were put into support vector machine (SVM), K-Nearest Neighbor (KNN) and other classifiers for binary classification. Results The highest classification accuracy was 73.96% for distinguishing between clinically significant (Gleason 3 + 4 and above) and non-significant cancers (Gleason 3 + 3) and 83.72% for distinguishing between Gleason 3 + 4 from Gleason 4 + 3 and above, which was achieved using initial ROIs drawn by the radiologists. The accuracy improved when using expanded ROIs to 80.67% using SVM and 88.42% using Bayesian classification for distinguishing between clinically significant and non-significant cancers and Gleason 3 + 4 from Gleason 4 + 3 and above, respectively. Conclusions Our results indicate the research significance and value of this study for determining the GS for prostate cancer using the expansion of the ROI region.

ObjectiveTo investigate the abnormalities of the three-dimensional pseudo-continuous arterial spin labeling (3D PCASL) based cerebral blood flow (CBF) correlation networks in mild cognitive impairment (MCI) and Alzheimer's disease (AD).Methods3D PCASL images of 53 cognitive normal (CN) subjects, 43 subjects with MCI, and 30 subjects with AD were acquired from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. Whole-brain CBF maps were calculated using PCASL and proton density-weighted images (PDWI). The 246 regional CBF values, including the cortex and subcortex, were obtained after registering the Brainnetome Atlas to the individual CBF maps. The Pearson correlation coefficient between every two regions across subjects was calculated to construct the CBF correlation network. Then the topologies of CBF networks with regard to global properties (global network efficiency, clustering coefficient, characteristic path length, and small-world properties), hub regions, nodal properties (betweenness centrality, BC), and connections were compared among CN, MCI, and AD. Significant changes in the global and nodal properties were observed in the permutation tests, and connections with significant differences survived after the z-statistic and false discovery rate (FDR) correction.ResultsThe CBF correlation networks of CN, MCI, and AD all showed small-world properties. Compared with CN, global efficiency decreased significantly in AD. Significant differences in nodal properties and a loss of hub regions are noted in the middle temporal lobe in both MCI and AD. In the frontal lobe, BC is reduced in MCI while it is increased in the occipital lobe in AD. The identified altered hub regions with significant differences in MCI and AD were mainly distributed in the hippocampus and entorhinal cortex. In addition, disrupted hub regions in AD with significantly decreased connections were mainly found in the precuneus/posterior cingulate cortex (PCC) and hippocampus-cortical cortex.ConclusionsNoninvasive 3D PCASL-based CBF correlation networks are capable of showing changes in topological organization in subjects with MCI and AD, and the observed disruption in the topological organization may underlie cognitive decline in MCI and AD.

Abstract Objectives This study aims to establish nomograms to accurately predict the overall survival (OS) and progression-free survival (PFS) in patients with non-small cell lung cancer (NSCLC) who received chemotherapy alone as the first-line treatment. Materials and methods In a training cohort of 121 NSCLC patients, radiomic features were extracted, selected from intra- and peri-tumoral regions, and used to build signatures (S1 and S2) using a Cox regression model. Deep learning features were obtained from three convolutional neural networks and utilized to build signatures (S3, S4, and S5) that were stratified into over- and under-expression subgroups for survival risk using X-tile. After univariate and multivariate Cox regression analyses, a nomogram incorporating the tumor, node, and metastasis (TNM) stages, radiomic signature, and deep learning signature was established to predict OS and PFS, respectively. The performance was validated using an independent cohort (61 patients). Results TNM stages, S2 and S3 were identified as the significant prognosis factors for both OS and PFS; S2 (OS: (HR (95%), 2.26 (1.40–3.67); PFS: (HR (95%), 2.23 (1.36–3.65)) demonstrated the best ability in discriminating patients with over- and under-expression. For the OS nomogram, the C-index (95% CI) was 0.74 (0.70–0.79) and 0.72 (0.67–0.78) in the training and validation cohorts, respectively; for the PFS nomogram, the C-index (95% CI) was 0.71 (0.68–0.81) and 0.72 (0.66–0.79). The calibration curves for the 3- and 5-year OS and PFS were in acceptable agreement between the predicted and observed survival. The established nomogram presented a higher overall net benefit than the TNM stage for predicting both OS and PFS. Conclusion By integrating the TNM stage, CT radiomic signature, and deep learning signatures, the established nomograms can predict the individual prognosis of NSCLC patients who received chemotherapy. The integrated nomogram has the potential to improve the individualized treatment and precise management of NSCLC patients.

The precise segmentation of different regions of the prostate is crucial in the diagnosis and treatment of prostate-related diseases. However, the scarcity of labeled prostate data poses a challenge for the accurate segmentation of its different regions. We perform the segmentation of different regions of the prostate using U-Net- and Vision Transformer (ViT)-based architectures. We use five semi-supervised learning methods, including entropy minimization, cross pseudo-supervision, mean teacher, uncertainty-aware mean teacher (UAMT), and interpolation consistency training (ICT) to compare the results with the state-of-the-art prostate semi-supervised segmentation network uncertainty-aware temporal self-learning (UATS). The UAMT method improves the prostate segmentation accuracy and provides stable prostate region segmentation results. ICT plays a more stable role in the prostate region segmentation results, which provides strong support for the medical image segmentation task, and demonstrates the robustness of U-Net for medical image segmentation. UATS is still more applicable to the U-Net backbone and has a very significant effect on a positive prediction rate. However, the performance of ViT in combination with semi-supervision still requires further optimization. This comparative analysis applies various semi-supervised learning methods to prostate zonal segmentation. It guides future prostate segmentation developments and offers insights into utilizing limited labeled data in medical imaging.

Focal cortical dysplasia (FCD) is a neurological disorder distinguished by faulty brain cell structure and development. Repetitive and uncontrollable seizures may be linked to FCD's aberrant cortical thickness, gyrification, and sulcal depth. Quantitative cortical surface analysis is a crucial alternative to ineffective visual inspection. This study recruited 42 subjects including 22 FCD patients who underwent surgery and 20 healthy controls (HC). For the FCD patients, T1-weighted and PET images were obtained by a PET-MRI scanner, and the confirmed epileptogenic zone (EZ) was collected from postsurgical follow-up. For the HCs, CT and PET images were obtained by a PET-CT scanner. Cortical thickness, gyrification index, and sulcal depth were calculated using a computational anatomical toolbox (CAT12). A cluster-based analysis is carried out to determine each FCD patient's aberrant cortical surface. After parcellating the cerebral cortex into 68 regions by the Desikan-Killiany atlas, a region of interest (ROI) analysis was conducted to know whether the feature in the FCD group is significantly different from that in the HC group. Finally, the features of all ROIs were utilised to train a support vector machine classifier (SVM). The classification performance is evaluated by the leave-one-out cross-validation. The cluster-based analysis can localize the EZ cluster with the highest accuracy of 54.5 % (12/22) for cortical thickness, 40.9 % (9/22) and 13.6 % (3/22) for sulcal depth and gyrification, respectively. Moderate concordance (Kappa, 0.6) is observed between the confirmed EZs and identified clusters by using the cortical thickness. Fair concordance (Kappa, 0.3) and no concordance (Kappa, 0.1) is found by using sulcal depth and gyrification. Significant differences are found in 46 of 68 regions (67.7 %) for the three measures. The trained SVM classifier achieved a prediction accuracy of 95.5 % for the cortical thickness, while the sulcal depth and the gyrification obtained 86.0 % and 81.5 %. Cortical thickness, as determined by quantitative cortical surface analysis of PET data, has a greater ability than sulcal depth and gyrification to locate aberrant EZ clusters in FCD. Surface measures might be different in many regions for FCD and HC. By integrating machine learning and cortical morphologies features, individual prediction of FCD seems to be feasible.

Background: The prognosis of chemotherapy is important in clinical decision-making for non-small cell lung cancer (NSCLC) patients. Objectives: To develop a model for predicting treatment response to chemotherapy in NSCLC patients from pre-chemotherapy CT images. Materials and Methods: This retrospective multicenter study enrolled 485 patients with NSCLC who received chemotherapy alone as a first-line treatment. Two integrated models were developed using radiomic and deep-learning-based features. First, we partitioned pre-chemotherapy CT images into spheres and shells with different radii around the tumor (0–3, 3–6, 6–9, 9–12, 12–15 mm) containing intratumoral and peritumoral regions. Second, we extracted radiomic and deep-learning-based features from each partition. Third, using radiomic features, five sphere–shell models, one feature fusion model, and one image fusion model were developed. Finally, the model with the best performance was validated in two cohorts. Results: Among the five partitions, the model of 9–12 mm achieved the highest area under the curve (AUC) of 0.87 (95% confidence interval: 0.77–0.94). The AUC was 0.94 (0.85–0.98) for the feature fusion model and 0.91 (0.82–0.97) for the image fusion model. For the model integrating radiomic and deep-learning-based features, the AUC was 0.96 (0.88–0.99) for the feature fusion method and 0.94 (0.85–0.98) for the image fusion method. The best-performing model had an AUC of 0.91 (0.81–0.97) and 0.89 (0.79–0.93) in two validation sets, respectively. Conclusions: This integrated model can predict the response to chemotherapy in NSCLC patients and assist physicians in clinical decision-making.

Abstract Background Functioning and non-functioning adrenocortical adenoma are two subtypes of benign adrenal adenoma, and their differential diagnosis is crucial. Current diagnostic procedures use an invasive method, adrenal venous sampling, for endocrinologic assessment. Methods This study proposes establishing an accurate differential model for subtyping adrenal adenoma using computed tomography (CT) radiomic features and machine learning (ML) methods. Dataset 1 (289 patients with adrenal adenoma) was collected to develop the models, and Dataset 2 (54 patients) was utilized for external validation. Cuboids containing the lesion were cropped from the non-contrast, arterial, and venous phase CT images, and 1,967 features were extracted from each cuboid. Ten discriminative features were selected from each phase or the combined phases. Random forest, support vector machine, logistic regression (LR), Gradient Boosting Machine, and eXtreme Gradient Boosting were used to establish prediction models. Results The highest accuracies were 72.7%, 72.7%, and 76.1% in the arterial, venous, and non-contrast phases, respectively, when using radiomic features alone with the ML classifier of LR. When features from the three CT phases were combined, the accuracy of LR reached 83.0%. After adding clinical information, the area under the receiver operating characteristic curve increased for all the machine learning methods except for LR. In Dataset 2, the accuracy of LR was the highest, reaching 77.8%. Conclusion The radiomic features of the lesion in three-phase CT images can potentially suggest the functioning or non-functioning nature of adrenal adenoma. The resulting radiomic models can be a non-invasive, low-cost, and rapid method of minimizing unnecessary testing in asymptomatic patients with incidentally discovered adrenal adenoma.

Abstract The individual prognosis of chemotherapy is quite different in non-small cell lung cancer (NSCLC). There is an urgent need to precisely predict and assess the treatment response. To develop a deep multiple-instance learning (DMIL) based model for predicting chemotherapy response in NSCLC in pretreatment CT images. Two datasets of NSCLC patients treated with chemotherapy as the first-line treatment were collected from two hospitals. Dataset 1 (163 response and 138 nonresponse) was used to train, validate, and test the DMIL model and dataset 2 (22 response and 20 nonresponse) was used as the external validation cohort. Five backbone networks in the feature extraction module and three pooling methods were compared. The DMIL with a pre-trained VGG16 backbone and an attention mechanism pooling performed the best, with an accuracy of 0.883 and area under the curve (AUC) of 0.982 on Dataset 1. While using max pooling and convolutional pooling, the AUC was 0.958 and 0.931, respectively. In Dataset 2, the best DMIL model produced an accuracy of 0.833 and AUC of 0.940. Deep learning models based on the MIL can predict chemotherapy response in NSCLC using pretreatment CT images and the pre-trained VGG16 with attention mechanism pooling yielded better predictions.

Abstract Background Major depressive disorder (MDD) is a common cause of disability and morbidity, affecting about 10% of the population worldwide. Subclinical depression (SD) can be understood as a precursor of MDD, and therefore provides an MDD risk indicator. The pathogenesis of MDD and SD in humans is still unclear, and the current diagnosis lacks accurate biomarkers and gold standards. Methods A total of 40 MDD, 34 SD, and 40 healthy control (HC) participants matched by age, gender, and education were included in this study. Resting-state functional magnetic resonance images (rs-fMRI) were used to analyze the functional connectivity (FC) of the posterior parietal thalamus (PPtha), which includes the lateral habenula, as the region of interest. Analysis of variance with the post hoc t-test test was performed to find significant differences in FC and clarify the variations in FC among the HC, SD, and MDD groups. Results Increased FC was observed between PPtha and the left inferior temporal gyrus (ITG) for MDD versus SD, and between PPtha and the right ITG for SD versus HC. Conversely, decreased FC was observed between PPtha and the right middle temporal gyrus (MTG) for MDD versus SD and MDD versus HC. The FC between PPtha and the middle frontal gyrus (MFG) in SD was higher than that in MDD and HC. Compared with the HC group, the FC of PPtha-ITG (left and right) increased in both the SD and MDD groups, PPtha-MTG (right) decreased in both the SD and MDD groups and PPtha-MFG (right) increased in the SD group and decreased in the MDD group. Conclusion Through analysis of FC measured by rs-fMRI, the altered FC between PPtha and several brain regions (right and left ITG, right MTG, and right MFG) has been identified in participants with SD and MDD. Different alterations in FC between PPtha and these regions were identified for patients with depression. These findings might provide insights into the potential pathophysiological mechanisms of SD and MDD, especially related to PPtha and the lateral habenula.

ObjectiveWhite matter hyperintensities (WMH) are commonly seen on T2-weighted magnetic resonance imaging (MRI) in older adults and are associated with an increased risk of cognitive decline and dementia. This study aims to estimate changes in the structural connectome due to age-related WMH by using a virtual lesion approach.MethodsHigh-quality diffusion-weighted imaging data of 30 healthy subjects were obtained from the Human Connectome Project (HCP) database. Diffusion tractography using q-space diffeomorphic reconstruction (QSDR) and whole brain fiber tracking with 107 seed points was conducted using diffusion spectrum imaging studio and the brainnetome atlas was used to parcellate a total of 246 cortical and subcortical nodes. Previously published WMH frequency maps across age ranges (50’s, 60’s, 70’s, and 80’s) were used to generate virtual lesion masks for each decade at three lesion frequency thresholds, and these virtual lesion masks were applied as regions of avoidance (ROA) in fiber tracking to estimate connectivity changes. Connections showing significant differences in fiber density with and without ROA were identified using paired tests with False Discovery Rate (FDR) correction.ResultsDisconnections appeared first from the striatum to middle frontal gyrus (MFG) in the 50’s, then from the thalamus to MFG in the 60’s and extending to the superior frontal gyrus in the 70’s, and ultimately including much more widespread cortical and hippocampal nodes in the 80’s.ConclusionChanges in the structural disconnectome due to age-related WMH can be estimated using the virtual lesion approach. The observed disconnections may contribute to the cognitive and sensorimotor deficits seen in aging.

The total variation (TV) method favors solutions with the piece-wise constant assumption of the desired image from sparse-view sampling, for example, simple geometric images with flat intensity. When the phantoms become more complex and contain complicated textures, for example, high-resolution phantom and lung CT images, the images reconstructed by TV regularization may lose their contrast and fine structures. One of the optimally sparse transforms for images, the shearlet transform, has C2 without discontinuities on C2 curves, giving excellent sensitive directional information as compared with other wavelet transform approaches. Here, we developed a Shearlet-Sparse Regularization (SSR) algorithm solved with the Alternating Direction Method of Multipliers (ADMM) to overcome this limitation. With the strengthened characteristics of SSR, we performed one simulation experiment and two real experiments using a NeuViz 64 X-ray CT scanning system to measure the performance and properties of proposed algorithm. The results demonstrate that the SSR method exhibits the advantage of providing high-quality directional information and contrast as compared with TV.

ObjectiveEpilepsy is considered as a neural network disorder. Seizure activity in epilepsy may disturb brain networks and damage brain functions. We propose using resting-state functional magnetic resonance imaging (rs-fMRI) data to characterize connectivity patterns in drug-resistant epilepsy.MethodsThis study enrolled 47 participants, including 28 with drug-resistant epilepsy and 19 healthy controls. Functional and effective connectivity was employed to assess drug-resistant epilepsy patients within resting state networks. The resting state functional connectivity (FC) analysis was performed to assess connectivity between each patient and healthy controls within the default mode network (DMN) and the dorsal attention network (DAN). In addition, dynamic causal modeling was used to compute effective connectivity (EC). Finally, a statistical analysis was performed to evaluate our findings.ResultsThe FC analysis revealed significant connectivity changes in patients giving 64.3% (18/28) and 78.6% (22/28) for DMN and DAN, respectively. Statistical analysis of FC was significant between the medial prefrontal cortex, posterior cingulate cortex, and bilateral inferior parietal cortex for DMN. For DAN, it was significant between the left and the right intraparietal sulcus and the frontal eye field. For the DMN, the patient group showed significant EC connectivity in the right inferior parietal cortex and the medial prefrontal cortex for the DMN. There was also bilateral connectivity between the medial prefrontal cortex and the posterior cingulate cortex, as well as between the left and right inferior parietal cortex. For DAN, patients showed significant connectivity in the right frontal eye field and the right intraparietal sulcus. Bilateral connectivity was also found between the left frontal eye field and the left intraparietal sulcus, as well as between the right frontal eye field and the right intraparietal sulcus. The statistical analysis of the EC revealed a significant result in the medial prefrontal cortex and the right intraparietal cortex for the DMN. The DAN was found significant in the left frontal eye field, as well as the left and right intraparietal sulcus.ConclusionOur results provide preliminary evidence to support that the combination of functional and effective connectivity analysis of rs-fMRI can aid in diagnosing epilepsy in the DMN and DAN networks.

ObjectiveThis study proposes a new hybrid brain-computer interface (BCI) system to improve spelling accuracy and speed by stimulating P300 and steady-state visually evoked potential (SSVEP) in electroencephalography (EEG) signals.MethodsA frequency enhanced row and column (FERC) paradigm is proposed to incorporate the frequency coding into the row and column (RC) paradigm so that the P300 and SSVEP signals can be evoked simultaneously. A flicker (white-black) with a specific frequency from 6.0 to 11.5 Hz with an interval of 0.5 Hz is assigned to one row or column of a 6 × 6 layout, and the row/column flashes are carried out in a pseudorandom sequence. A wavelet and support vector machine (SVM) combination is adopted for P300 detection, an ensemble task-related component analysis (TRCA) method is used for SSVEP detection, and the two detection possibilities are fused using a weight control approach.ResultsThe implemented BCI speller achieved an accuracy of 94.29% and an information transfer rate (ITR) of 28.64 bit/min averaged across 10 subjects during the online tests. An accuracy of 96.86% is obtained during the offline calibration tests, higher than that of only using P300 (75.29%) or SSVEP (89.13%). The SVM in P300 outperformed the previous linear discrimination classifier and its variants (61.90–72.22%), and the ensemble TRCA in SSVEP outperformed the canonical correlation analysis method (73.33%).ConclusionThe proposed hybrid FERC stimulus paradigm can improve the performance of the speller compared with the classical single stimulus paradigm. The implemented speller can achieve comparable accuracy and ITR to its state-of-the-art counterparts with advanced detection algorithms.

Among numerous functions performed by the human eye, reading is a common task that best reflects an individual’s understanding and cognitive patterns. Previous studies showed that text comprehension may be determined by comprehension monitoring, a metacognitive process that evaluates and regulates the pattern of comprehension. Herein, we propose a hypothesis: an individual’s cognitive pattern during reading is predictive of the level of reading comprehension. According to the criteria of the College English Test Band Six (CET-6), 80 participants (sophomore and junior) were divided into a pass group (n = 40) and a non-pass group (n = 40). Heatmaps of eye fixation counts were collected by an eye-tracker while each participant executed four reading comprehension tests. Using these heatmaps as inputs, we proposed the Siamese convolutional neural network models to predict the English level of participants. Both strategies of “Trained from scratch” and “Pretrained with fine-tuning” were employed. “Soft Voting” was applied to integrate the predictions from four tests. Results showed that the Siamese network model trained by the datasets with the cluster radius of fixation equal to 25 pixels and connection layer by L1 norm distance has a satisfactory or superior performance to other comparative experiments. The AUC values of Siamese networks trained by the two strategies reach 0.941 and 0.956, respectively. This indicates that the individual reading cognitive pattern captured by the eye-tracker can predict the level of reading comprehension through advanced deep learning models.

BackgroundAs one of the most common diseases, major depressive disorder (MDD) has a significant adverse impact on the li of patients. As a mild form of depression, subclinical depression (SD) serves as an indicator of progression to MDD. This study analyzed the degree centrality (DC) for MDD, SD, and healthy control (HC) groups and identified the brain regions with DC alterations.MethodsThe experimental data were composed of resting-state functional magnetic resonance imaging (rs-fMRI) from 40 HCs, 40 MDD subjects, and 34 SD subjects. After conducting a one-way analysis of variance, two-sample t-tests were used for further analysis to explore the brain regions with changed DC. Receiver operating characteristic (ROC) curve analysis of single index and composite index features was performed to analyze the distinguishable ability of important brain regions.ResultsFor the comparison of MDD vs. HC, increased DC was found in the right superior temporal gyrus (STG) and right inferior parietal lobule (IPL) in the MDD group. For SD vs. HC, the SD group showed a higher DC in the right STG and the right middle temporal gyrus (MTG), and a smaller DC in the left IPL. For MDD vs. SD, increased DC in the right middle frontal gyrus (MFG), right IPL, and left IPL, and decreased DC in the right STG and right MTG was found in the MDD group. With an area under the ROC (AUC) of 0.779, the right STG could differentiate MDD patients from HCs and, with an AUC of 0.704, the right MTG could differentiate MDD patients from SD patients. The three composite indexes had good discriminative ability in each pairwise comparison, with AUCs of 0.803, 0.751, and 0.814 for MDD vs. HC, SD vs. HC, and MDD vs. SD, respectively.ConclusionAltered DC in the STG, MTG, IPL, and MFG were identified in depression groups. The DC values of these altered regions and their combinations presented good discriminative ability between HC, SD, and MDD. These findings could help to find effective biomarkers and reveal the potential mechanisms of depression.

Nowadays, the detection of environmental microorganism indicators is essential for us to assess the degree of pollution, but the traditional detection methods consume a lot of manpower and material resources. Therefore, it is necessary for us to make microbial data sets to be used in artificial intelligence. The Environmental Microorganism Image Dataset Seventh Version (EMDS-7) is a microscopic image data set that is applied in the field of multi-object detection of artificial intelligence. This method reduces the chemicals, manpower and equipment used in the process of detecting microorganisms. EMDS-7 including the original Environmental Microorganism (EM) images and the corresponding object labeling files in “.XML” format file. The EMDS-7 data set consists of 41 types of EMs, which has a total of 2,65 images and 13,216 labeled objects. The EMDS-7 database mainly focuses on the object detection. In order to prove the effectiveness of EMDS-7, we select the most commonly used deep learning methods (Faster-Region Convolutional Neural Network (Faster-RCNN), YOLOv3, YOLOv4, SSD, and RetinaNet) and evaluation indices for testing and evaluation. EMDS-7 is freely published for non-commercial purpose at: https://figshare.com/articles/dataset/EMDS-7_DataSet/16869571.

Background and purposeColorectal cancer is a common fatal malignancy, the fourth most common cancer in men, and the third most common cancer in women worldwide. Timely detection of cancer in its early stages is essential for treating the disease. Currently, there is a lack of datasets for histopathological image segmentation of colorectal cancer, which often hampers the assessment accuracy when computer technology is used to aid in diagnosis.MethodsThis present study provided a new publicly available Enteroscope Biopsy Histopathological Hematoxylin and Eosin Image Dataset for Image Segmentation Tasks (EBHI-Seg). To demonstrate the validity and extensiveness of EBHI-Seg, the experimental results for EBHI-Seg are evaluated using classical machine learning methods and deep learning methods.ResultsThe experimental results showed that deep learning methods had a better image segmentation performance when utilizing EBHI-Seg. The maximum accuracy of the Dice evaluation metric for the classical machine learning method is 0.948, while the Dice evaluation metric for the deep learning method is 0.965.ConclusionThis publicly available dataset contained 4,456 images of six types of tumor differentiation stages and the corresponding ground truth images. The dataset can provide researchers with new segmentation algorithms for medical diagnosis of colorectal cancer, which can be used in the clinical setting to help doctors and patients. EBHI-Seg is publicly available at: https://figshare.com/articles/dataset/EBHI-SEG/21540159/1.

Abstract Background Subclinical depression (ScD) is a prevalent condition associated with relatively mild depressive states, and it poses a high risk of developing into major depressive disorder (MDD). However, the neural pathology of ScD is still largely unknown. Identifying the spontaneous neural activity involved in ScD may help clarify risk factors for MDD and explore treatment strategies for mild stages of depression. Methods A total of 34 ScD subjects and 40 age-, sex-, and education-matched healthy controls were screened from 1105 college students. The amplitude of low-frequency fluctuation (ALFF) and regional homogeneity (ReHo) of resting-state fMRI were calculated to reveal neural activity. Strict statistical strategies, including Gaussian random field (GRF), false discovery rate (FDR), and permutation test (PT) with threshold-free cluster enhancement (TFCE), were conducted. Based on the altered ALFF and ReHo, resting-state functional connectivity (RSFC) was further analyzed using a seed-based approach. Results The right precuneus and left middle frontal gyrus (MFG) both showed significantly increased ALFF and ReHo in ScD subjects. Moreover, the left hippocampus and superior frontal gyrus (SFG) showed decreased ALFF and increased ReHo, respectively. In addition, ScD subjects showed increased RSFC between MFG and hippocampus compared to healthy controls, and significant positive correlation was found between the Beck Depression Inventory-II (BDI-II) score and RSFC from MFG to hippocampus in ScD group. Conclusion Spontaneous neural activities in the right precuneus, left MFG, SFG, and hippocampus were altered in ScD subjects. Functional alterations in these dorsolateral prefrontal cortex and default mode network regions are largely related to abnormal emotional processing in ScD, and indicate strong associations with brain impairments in MDD, which provide insight into potential pathophysiology mechanisms of subclinical depression.

PurposeThis study aims to evaluate the ability of peritumoral, intratumoral, or combined computed tomography (CT) radiomic features to predict chemotherapy response in non-small cell lung cancer (NSCLC).MethodsAfter excluding subjects with incomplete data or other types of treatments, 272 (Dataset 1) and 43 (Dataset 2, external validation) NSCLC patients who were only treated with chemotherapy as the first-line treatment were enrolled between 2015 and 2019. All patients were divided into response and nonresponse based on the response evaluation criteria in solid tumors, version 1.1. By using 3D slicer and morphological operations in python, the intra- and peritumoral regions of lung tumors were segmented from pre-treatment CT images (unenhanced) and confirmed by two experienced radiologists. Then radiomic features (the first order, texture, shape, et al.) were extracted from the above regions of interest. The models were trained and tested in Dataset 1 and further validated in Dataset 2. The performance of models was compared using the area under curve (AUC), confusion matrix, accuracy, precision, recall, and F1-score.ResultsThe radiomic model using features from the peritumoral region of 0–3 mm outperformed that using features from 3–6, 6–9, 9–12 mm peritumoral region, and intratumoral region (AUC: 0.95 versus 0.87, 0.86, 0.85, and 0.88). By the fusion of features from 0–3 and 3–6 mm peritumoral regions, the logistic regression model achieved the best performance, with an AUC of 0.97. This model achieved an AUC of 0.85 in the external cohort. Moreover, among the 20 selected features, seven features differed significantly between the two groups (p < 0.05).ConclusionsCT radiomic features from both the peri- and intratumoral regions can predict chemotherapy response in NSCLC using machine learning models. Combined features from two peritumoral regions yielded better predictions.

ObjectiveThe purpose of this study is to establish and evaluate an early biomarker prediction model of massive cerebral infarction caused by anterior circulation occlusion.MethodsOne hundred thirty-four patients with acute cerebral infarction from January 2018 to October 2020 were selected to establish the development cohort for the internal test of the nomogram. Ninety-one patients with acute cerebral infarction hospitalized in our hospital from December 2020 to December 2021 were constituted the validation cohort for the external validation. All patients underwent baseline computed tomography (CT) scans within 12 h of onset and early imaging signs (hyperdense middle cerebral artery sign, obscuration of the lentiform nucleus, insular ribbon sign) of acute cerebral infarction were identified on CT by two neurologists. Based on follow-up CT images, patients were then divided into a massive cerebral infarction group and a non-massive cerebral infarction group. The nomogram model was constructed based on logistic regression analysis with R language. The nomogram was subsequently validated in an independent external validation cohort. Accuracy and discrimination of the prediction model were evaluated by a calibration chart, receiver operating characteristic (ROC) curve, and decision curve.ResultsThe indicators, including insular ribbon sign, reperfusion therapy, National Institutes of Health Stroke Scale (NHISS) score, previous cerebral infarction, and atrial fibrillation, were entered into the prediction model through binary logistic regression analysis. The prediction model showed good predictive ability. The area under the ROC curve of the prediction model was 0.848. The specificity, sensitivity, and Youden index were 0.864, 0.733, and 0.597, respectively. This nomogram to the validation cohort also showed good discrimination (AUC = 0.940, 95% CI 0.894–0.985) and calibration.ConclusionDemonstrating favorable predictive efficacy and reproducibility, this study successfully established a prediction model of CT imaging signs and clinical data as early biomarkers of massive cerebral infarction caused by anterior circulation occlusion.

ObjectiveDiffusion tensor imaging (DTI) studies have investigated white matter (WM) integrity abnormalities in Parkinson’s disease (PD). However, little is known about the topological changes in the brain network. This study aims to reveal these changes by comparing PD without freezing of gait (FOG) (PD FOG–), PD with FOG (PD FOG+), and healthy control (HC).Methods21 PD FOG+, 34 PD FOG-, and 23 HC were recruited, and DTI images were acquired. The graph theoretical analysis and network-based statistical method were used to calculate the topological parameters and assess connections.ResultsPD FOG+ showed a decreased normalized clustering coefficient, small-worldness, clustering coefficient, and increased local network efficiency compared with HCs. PD FOG+ showed decreased centrality, degree centrality, and nodal efficiency in the striatum, frontal gyrus, and supplementary motor area (SMA). PD FOG+ showed decreased connections in the frontal gyrus, cingulate gyrus, and caudate nucleus (CAU). The between centrality of the left SMA and left CAU was negatively correlated with FOG questionnaire scores.ConclusionThis study demonstrates that PD FOG+ exhibits disruption of global and local topological organization in structural brain networks, and the disrupted topological organization can be potential biomarkers in PD FOG+. These new findings may provide increasing insight into the pathophysiological mechanism of PD FOG+.

Ultrasound (US) is one of the most widely used imaging modalities in medical diagnosis. It has the advantages of real-time, low cost, noninvasive nature, and easy to operate. However, it also has the unique disadvantages of strong artifacts and noise and high dependence on the experience of doctors. In order to overcome the shortcomings of ultrasound diagnosis and help doctor improve the accuracy and efficiency of diagnosis, many computer aided diagnosis (CAD) systems have been developed. In recent years, deep learning has achieved great success in computer vision with its unique advantages. In the aspect of medical US image analysis, deep learning has also been exploited for its great potential and more and more researchers apply it to CAD systems. In this paper, we first introduce the deep learning models commonly used in medical US image analysis; Second, we review the data preprocessing methods of medical US images, including data augmentation, denoising, and enhancement; Finally, we analyze the applications of deep learning in medical US imaging tasks (such as image classification, object detection, and image reconstruction).

Identification of congenital sensorineural hearing loss (SNHL) and early intervention, especially by cochlear implantation (CI), are crucial for restoring hearing in patients. However, high accuracy diagnostics of SNHL and prognostic prediction of CI are lacking to date. To diagnose SNHL and predict the outcome of CI, we propose a method combining functional connections (FCs) measured by functional magnetic resonance imaging (fMRI) and machine learning. A total of 68 children with SNHL and 34 healthy controls (HC) of matched age and gender were recruited to construct classification models for SNHL and HC. A total of 52 children with SNHL that underwent CI were selected to establish a predictive model of the outcome measured by the category of auditory performance (CAP), and their resting-state fMRI images were acquired. After the dimensional reduction of FCs by kernel principal component analysis, three machine learning methods including the support vector machine, logistic regression, and k-nearest neighbor and their voting were used as the classifiers. A multiple logistic regression method was performed to predict the CAP of CI. The classification model of voting achieves an area under the curve of 0.84, which is higher than that of three single classifiers. The multiple logistic regression model predicts CAP after CI in SNHL with an average accuracy of 82.7%. These models may improve the identification of SNHL through fMRI images and prognosis prediction of CI in SNHL.

A behavior description helps analyze tiny objects, similar objects, objects with weak visual information, and objects with similar visual information. It plays a fundamental role in the identification and classification of dynamic objects in microscopic videos. To this end, we propose foldover features to describe the behavior of dynamic objects. Foldover is defined as: Each frame of an object's motion is superimposed on the same spatial plane in the spacetime order of the motion, the result of the superposition is the foldover of the object's motion. Foldover of an object contains temporal information, spatial information, behavior features and static features. Therefore, the features extracted based on the foldover of the object are the foldover features. In this work, we first generate foldover for each object in microscopic videos in X, Y and Z directions, respectively. Then, we extract foldover features from the X, Y and Z directions with statistical methods, respectively. The core content of this paper is to construct the foldovers and extract the foldover features. Through these two steps, the temporal information, spatial information, behavior features and static features of the object are enhanced and included in the foldover features. Furthermore, the description of the behavior of dynamic objects by the foldover features is strengthened. Finally, we use four different classifiers to test the effectiveness of the proposed foldover features. In the experiment, we use a microscopic sperm video dataset to evaluate the proposed foldover features, including three types of 1374 sperms, and obtain the highest classification accuracy of 96.5%.

Breast cancer is one of the most common and deadliest cancers among women. Since histopathological images contain sufficient phenotypic information, they play an indispensable role in the diagnosis and treatment of breast cancers. To improve the accuracy and objectivity of Breast Histopathological Image Analysis (BHIA), Artificial Neural Network (ANN) approaches are widely used in the segmentation and classification tasks of breast histopathological images. In this review, we present a comprehensive overview of the BHIA techniques based on ANNs. First of all, we categorize the BHIA systems into classical and deep neural networks for in-depth investigation. Then, the relevant studies based on BHIA systems are presented. After that, we analyze the existing models to discover the most suitable algorithms. Finally, publicly accessible datasets, along with their download links, are provided for the convenience of future researchers.

Chronic obstructive pulmonary disease (COPD) is associated with morphologic abnormalities of airways with various patterns and severities. However, the way of effectively representing these abnormalities is lacking and whether these abnormalities enable to distinguish COPD from healthy controls is unknown. We propose to use deep convolutional neural network (CNN) to assess 3D lung airway tree from the perspective of computer vision, thereby constructing models of identifying COPD. After extracting airway trees from CT images, snapshots of their 3D visualizations are obtained from ventral, dorsal and isometric views. Using snapshots of each view, one deep CNN model is constructed and further optimized by Bayesian optimization algorithm to indentify COPD. The majority voting of three views presents the final prediction. Finally, the class-discriminative localization maps have been drawn to visually explain the CNNs' decisions. The models trained with single view (ventral, dorsal and isometric) of colorful snapshots present the similar accuracy (ACC) (86.8%, 87.5% and 86.7%) and the model after voting achieves the ACC of 88.2%. The ACC of the final voting model using gray and binary snapshots achieves 88.6% and 86.4%, respectively. Our specially designed CNNs outperform the typical off-the-shelf CNNs and the pre-trained CNNs with fine tuning. The class-discriminative regions of COPD are mainly located at central airways; however, regions in HC are scattering and located at peripheral airways. It is feasible to identify COPD using snapshots of 3D lung airway tree extracted from CT images via deep CNN. The CNNs can represent the abnormalities of airway tree in COPD and make accurate CT-based diagnosis of COPD.

In recent years, researches are concentrating on the effectiveness of Transfer Learning (TL) and Ensemble Learning (EL) techniques in cervical histopathology image analysis. However, there have been very few investigations that have described the stages of differentiation of cervical histopathological images. Therefore, in this article, we propose an Ensembled Transfer Learning (ETL) framework to classify well, moderate and poorly differentiated cervical histopathological images. First of all, we have developed Inception-V3, Xception, VGG-16, and Resnet-50 based TL structures. Then, to enhance the classification performance, a weighted voting based EL strategy is introduced. After that, to evaluate the proposed algorithm, a dataset consisting of 307 images, stained by three immunohistochemistry methods (AQP, HIF, and VEGF) is considered. In the experiment, we obtain the highest overall accuracy of 97.03% and 98.61% on AQP staining images and poor differentiation of VEGF staining images, individually. Finally, an additional experiment for classifying the benign cells from the malignant ones is carried out on the Herlev dataset and obtains an overall accuracy of 98.37%.

Cervical cancer is one of the most common and deadliest cancers among women. Despite that, this cancer is entirely treatable if it is detected at a precancerous stage. Pap smear test is the most extensively performed screening method for early detection of cervical cancer. However, this hand-operated screening approach suffers from a high false-positive result because of human errors. To improve the accuracy and manual screening practice, computer-aided diagnosis methods based on deep learning is developed widely to segment and classify the cervical cytology images automatically. In this survey, we provide a comprehensive study of the state of the art approaches based on deep learning for the analysis of cervical cytology images. Firstly, we introduce deep learning and its simplified architectures that have been used in this field. Secondly, we discuss the publicly available cervical cytopathology datasets and evaluation metrics for segmentation and classification tasks. Then, a thorough review of the recent development of deep learning for the segmentation and classification of cervical cytology images is presented. Finally, we investigate the existing methodology along with the most suitable techniques for the analysis of pap smear cells.

The main obstacle to image augmentation with Generative Adversarial Networks (GANs) is the need for a large amount of training data, but this is difficult for small datasets like Environmental Microorganisms (EMs). EM image analysis plays a vital role in environmental monitoring and protection, but it is often encountered with small datasets due to the difficulty of EM image collection. To this end, we propose an Enhanced Framework of GANs (EF-GANs) that combines geometric transformation methods and GANs for EM image augmentation. First of all, the color of an EM image has an insignificant impact on its class label, based on this fact, we perform color space augmentation to the original EM images. Secondly, we train EF-GANs with augmented EM images to generate utterly new EM images. Finally, we rotate the generated samples in various directions to obtain a more natural performance. In this study, we use VGG16 and ResNet50 networks to evaluate the proposed EF-GANs on 21 different types of EMs (420 EM images). It is observed that the average precision (AP) of VGG16 increases between 4.5% and 84.1% in 20 EM classes and one class remains unchanged. The AP of Resnet50 rises between 8.7% and 38.7% in 12 EM classes and reaches 100% in two EM classes. Furthermore, to reflect the generalization performance of EF-GANs, we employ an utterly new EM image dataset (630 EM images) to test the previous VGG16 networks. We select the VGG16 networks with original and optimal settings for all the EM classes, and for testing, optimal settings for a single EM class is considered. In the 20 of 21 one-vs-rest EM image classification tasks, the AP of VGG16 increases between 1.66% and 88.1%. The results demonstrate that the proposed EF-GANs can achieve outstanding performance in augmenting single EM images with high quality and resolution, thus, to improve the APs of EM image classification.

Refractory epilepsy is a complex case of epileptic disease. The quantitative analysis of fluorodeoxyglucose positron emission tomography (FDG-PET) images complements visual assessment and helps localize the epileptogenic zone (EZ) for better curative treatment. Statistical parametric mapping (SPM) and its computational anatomy toolbox (SPM-CAT) are two commonly applied tools in neuroimaging analysis. This study compares SPM and SPM-CAT with different parameters to find the optimal approach for localizing EZ in refractory epilepsy. The current study enrolled 45 subjects, including 25 refractory epilepsy patients and 20 healthy controls. All of the 25 patients underwent surgical operations. Pathological results and the postoperative outcome evaluation by the Engel scale were likewise presented. SPM and SPM-CAT were used to assess FDG-PET images with three different uncorrected p-values and the corresponding cluster sizes (k), as in voxels in the cluster, namely p < 0.0002, k > 25; p < 0.001, k > 100; p < 0.005, and k > 200. When combining three settings, SPM and SPM-CAT yielded overall positive finding scores of 96.0% (24/25) and 100.0% (25/25) respectively. However, for the individual setting, SPM-CAT achieved the diverse positive finding scores of 96.0% (24/25), 96.0% (24/25), and 88.0% (22/24), which are higher than those of SPM [88.0% (22/25), 76.0% (19/25), and 72.0% (18/25)]. SPM and SPM-CAT localized EZ correctly with 28.0% (7/25) and 64.0% (16/25), respectively. SPM-CAT with parameter settings p < 0.0002 and k > 25 yielded a correct localization at 56.0% (14/25), which is slightly higher than that for the other two settings (48.0 and 20.0%). Moderate concordance was found between the confirmed and pre-surgical EZs, identified by SPM-CAT (kappa value = 0.5). Hence, SPM-CAT is more efficient than SPM in localizing EZ for refractory epilepsy by quantitative analysis of FDG-PET images. SPM-CAT with the setting of p < 0.0002 and k > 25 might perform as an objective complementary tool to the visual assessment for EZ localization.

Freezing of gait (FOG) in Parkinson's disease (PD) leads to devastating consequences; however, little is known about its functional brain network. We explored the differences in degree centrality (DC) of functional networks among PD with FOG (PD FOG+), PD without FOG (PD FOG–), and healthy control (HC) groups. In all, 24 PD FOG+, 37 PD FOG–, and 22 HCs were recruited and their resting-state functional magnetic imaging images were acquired. The whole brain network was analyzed using graph theory analysis. DC was compared among groups using the two-sample t-test. The DC values of disrupted brain regions were correlated with the FOG Questionnaire (FOGQ) scores. Receiver operating characteristic curve analysis was performed. We found significant differences in DC among groups. Compared with HCs, PD FOG+ patients showed decreased DC in the middle frontal gyrus (MFG), superior temporal gyrus (STG), parahippocampal gyrus (PhG), inferior temporal gyrus (ITG), and middle temporal gyrus (MTG). Compared with HC, PD FOG– presented with decreased DC in the MFG, STG, PhG, and ITG. Compared with PD FOG–, PD FOG+ showed decreased DC in the MFG and ITG. A negative correlation existed between the DC of ITG and FOGQ scores; the DC in ITG could distinguish PD FOG+ from PD FOG– and HC. The calculated AUCs were 81.3, 89.5, and 77.7% for PD FOG+ vs. HC, PD FOG– vs. HC, and PD FOG+ vs. PD FOG–, respectively. In conclusion, decreased DC of ITG in PD FOG+ patients compared to PD FOG– patients and HCs may be a unique feature for PD FOG+ and can likely distinguish PD FOG+ from PD FOG– and HC groups.

Currently, the field of transparent image analysis has gradually become a hot topic. However, traditional analysis methods are accompanied by large amounts of carbon emissions, and consumes significant manpower and material resources. The continuous development of computer vision enables the use of computers to analyze images. However, the low contrast between the foreground and background of transparent images makes their segmentation difficult for computers. To address this problem, we first analyzed them with pixel patches, and then classified the patches as foreground and background. Finally, the segmentation of the transparent images was completed through the reconstruction of pixel patches. To understand the performance of different deep learning networks in transparent image segmentation, we conducted a series of comparative experiments using patch-level and pixel-level methods. In two sets of experiments, we compared the segmentation performance of four convolutional neural network (CNN) models and a visual transformer (ViT) model on the transparent environmental microorganism dataset fifth version. The results demonstrated that U-Net++ had the highest accuracy rate of 95.32% in the pixel-level segmentation experiment followed by ViT with an accuracy rate of 95.31%. However, ResNet50 had the highest accuracy rate of 90.00% and ViT had the lowest accuracy of 89.25% in the patch-level segmentation experiments. Hence, we concluded that ViT performed the lowest in patch-level segmentation experiments, but outperformed most CNNs in pixel-level segmentation. Further, we combined patch-level and pixel-level segmentation results to reduce the loss of segmentation details in the EM images. This conclusion was also verified by the environmental microorganism dataset sixth version dataset (EMDS-6).

The heterogeneity and complexity of non-small cell lung cancer (NSCLC) tumors mean that NSCLC patients at the same stage can have different chemotherapy prognoses. Accurate predictive models could recognize NSCLC patients likely to respond to chemotherapy so that they can be given personalized and effective treatment. We propose to identify predictive imaging biomarkers from pre-treatment CT images and construct a radiomic model that can predict the chemotherapy response in NSCLC. This single-center cohort study included 280 NSCLC patients who received first-line chemotherapy treatment. Non-contrast CT images were taken before and after the chemotherapy, and clinical information were collected. Based on the Response Evaluation Criteria in Solid Tumors and clinical criteria, the responses were classified into two categories: response (n = 145) and progression (n = 135), then all data were divided into two cohorts: training cohort (224 patients) and independent test cohort (56 patients). In total, 1629 features characterizing the tumor phenotype were extracted from a cube containing the tumor lesion cropped from the pre-chemotherapy CT images. After dimensionality reduction, predictive models of the chemotherapy response of NSCLC with different feature selection methods and different machine-learning classifiers (support vector machine, random forest, and logistic regression) were constructed. For the independent test cohort, the predictive model based on a random-forest classifier with 20 radiomic features achieved the best performance, with an accuracy of 85.7% and an area under the receiver operating characteristic curve of 0.941 (95% confidence interval, 0.898–0.982). Of the 20 selected features, four were first-order statistics of image intensity and the others were texture features. For nine features, there were significant differences between the response and progression groups (p < 0.001). In the response group, three features, indicating heterogeneity, were overrepresented and one feature indicating homogeneity was underrepresented. The proposed radiomic model with pre-chemotherapy CT features can predict the chemotherapy response of patients with non-small cell lung cancer. This radiomic model can help to stratify patients with NSCLC, thereby offering the prospect of better treatment.

Abstract Background Pulmonary lobectomy has been a well-established curative treatment method for localized lung cancer. After left upper pulmonary lobectomy, the upward displacement of remaining lower lobe causes the distortion or kink of bronchus, which is associated with intractable cough and breathless. However, the quantitative study on structural and functional alterations of the tracheobronchial tree after lobectomy has not been reported. We sought to investigate these alterations using CT imaging analysis and computational fluid dynamics (CFD) method. Methods Both preoperative and postoperative CT images of 18 patients who underwent left upper pulmonary lobectomy are collected. After the tracheobronchial tree models are extracted, the angles between trachea and bronchi, the surface area and volume of the tree, and the cross-sectional area of left lower lobar bronchus are investigated. CFD method is further used to describe the airflow characteristics by the wall pressure, airflow velocity, lobar flow rate, etc. Results It is found that the angle between the trachea and the right main bronchus increases after operation, but the angle with the left main bronchus decreases. No significant alteration is observed for the surface area or volume of the tree between pre-operation and post-operation. After left upper pulmonary lobectomy, the cross-sectional area of left lower lobar bronchus is reduced for most of the patients (15/18) by 15–75%, especially for 4 patients by more than 50%. The wall pressure, airflow velocity and pressure drop significantly increase after the operation. The flow rate to the right lung increases significantly by 2–30% (but there is no significant difference between each lobe), and the flow rate to the left lung drops accordingly. Many vortices are found in various places with severe distortions. Conclusions The favorable and unfavorable adaptive alterations of tracheobronchial tree will occur after left upper pulmonary lobectomy, and these alterations can be clarified through CT imaging and CFD analysis. The severe distortions at left lower lobar bronchus might exacerbate postoperative shortness of breath.

Numerous automatic systems of pulmonary nodules detection have been proposed, but very few of them have been consecrated to micro-nodules (diameter < 3 mm) even though they are regarded as the earliest manifestations of lung cancer. Moreover, most available systems present high false positive rate resulting from their incapability of discriminating between micro-nodules and non-nodules. Thus, this paper proposes a system to differentiate between the micro-nodules and non-nodules in computed tomography (CT) images by an ensemble learning of multiple-view 3-D convolutional neural networks (3D-CNNs). A total of 34 494 volumetric image samples, including 13 179 micro-nodules and 21 315 non-nodules, are acquired from the 1010 CT scans of the LIDC/IDRI database. The pulmonary nodule candidates are cropped with five different sizes, including $20\times 20\times 3$ , $16\times 16\times 3$ , $12\times 12\times 3$ , $8\times 8\times 3$ , and $4\times 4\times 3$ . Then, five distinct 3D-CNN models are built and implemented on one size of the nodule candidates. An extreme learning machine (ELM) network is utilized to integrate the five 3D-CNN outputs, yielding the final classification results. The performance of the proposed system is assessed in terms of accuracy, area under the curve (AUC), F-score, and sensitivity. It is found that the proposed system yields an accuracy, AUC, F-score, and sensitivity of 97.35%, 0.98, 96.42%, and 96.57%, respectively. These performances are highly superior to those of 2D-CNNs, single 3D-CNN model, as well as those by the state-of-the-art methods implemented on the same dataset. For the ensemble method, ELM achieves better performance than the majority voting, averaging, AND operator, and autoencoder. The results demonstrate that developing an automatic system for discriminating between micro-nodules and non-nodules in CT images is feasible, which extends lung cancer studies to micro-nodules. The combination of multiple-view 3D-CNNs and ensemble learning contribute to excellent identification performance, and this strategy may help develop other reliable clinical-decision support systems.

CT screening has been proven to be effective for diagnosing lung cancer at its early manifestation in the form of pulmonary nodules, thus decreasing the mortality. However, the exponential increase of image data makes their accurate assessment a very challenging task given that the number of radiologists is limited and they have been overworked. Recently, numerous methods, especially ones based on deep learning with convolutional neural network (CNN), have been developed to automatically detect and classify pulmonary nodules in medical images. In this paper, we present a comprehensive analysis of these methods and their performances. First, we briefly introduce the fundamental knowledge of CNN as well as the reasons for their suitability to medical images analysis. Then, a brief description of various medical images datasets, as well as the environmental setup essential for facilitating lung nodule investigations with CNNs, is presented. Furthermore, comprehensive overviews of recent progress in pulmonary nodule analysis using CNNs are provided. Finally, existing challenges and promising directions for further improving the application of CNN to medical images analysis and pulmonary nodule assessment, in particular, are discussed. It is shown that CNNs have transformed greatly the early diagnosis and management of lung cancer. We believe that this review will provide all the medical research communities with the necessary knowledge to master the concept of CNN so as to utilize it for improving the overall human healthcare system.

Accurate segmentation of bi-ventricle from cardiac magnetic resonance images (MRI) is a critical step in cardiac function analysis and disease diagnosis. Due to the morphological diversification of the heart and the factors of MRI itself, fully automated and concurrent bi-ventricle segmentation is a well-known challenge. In this paper, we propose cascaded conditional generative adversarial networks (C-cGANs) to divide the problem into two segmentation subtasks: binary segmentation for region of interest (ROI) extraction and bi-ventricle segmentation. In both subtasks, we adopt adversarial training that makes discriminator network to discriminate segmentation maps either from generator network or ground-truth which aims to detect and correct pixel-wise inconsistency between the sources of segmentation maps. For capturing more spatial information with multi-scale semantic features, in the generator network, we insert a multi-scale attention fusion (MSAF) module between the encoder and decoder paths. The experiment on ACDC 2017 dataset shows that the proposed model outperforms other state-of-the-art methods in most metrics. Moreover, we validate the generalization capability of this model on MS-CMRSeg 2019 and RVSC 2012 datasets without fine-tuning, and the results demonstrate the effectiveness and robustness of the proposed method for bi-ventricle segmentation.

In this paper, a novel microscopic machine vision system is proposed to solve a degradation monitoring problem of low-voltage electromagnetic coil insulation in practical industrial fields, where an ensemble learning approach in a compound membrane computing framework is newly introduced. This membrane computing framework is constituted by eight layers, 29 membranes, 72 objects, and 35 rules. In this framework, multiple machine learning methods, including classical pattern recognition methods and novel deep learning methods, are tested and compared. First, the most optimal feature extraction approaches are selected. Then, the selected approaches are fused together to achieve an even better monitoring performance. Third, a large number of experiments are used to evaluate and prove the usefulness and potential of the proposed system, where a mean accuracy of 61.4% is achieved on 1035 validation images of six degradation states with single state matching, and mean accuracies of 61.0% and 77.4% are achieved on 622 test images of six degradation states with single state matching and state range matching, respectively. Finally, a mechanical device is designed to apply the system to real industrial tasks.

Various deep convolutional neural networks (CNNs) have been used to distinguish between benign and malignant pulmonary nodules using CT images. However, single learner usually presents unsatisfied performance due to limited hypothesis space, or falling into local minima, or wrong selection of hypothesis space. To tackle these issues, we propose to build ensemble learners through fusing multiple deep CNN learners for pulmonary nodules classification. CT image patches of 743 nodules are extracted from LIDC-IDRI database and utilized. First, eight deep CNN learners with different architectures are trained and evaluated by 10-fold cross-validation. Each nodule has eight predictions from the eight primary learners. Second, we fuse these eight predictions by the strategies of majority voting (VOT), averaging (AVE), or machine learning. Specifically, different machine learning algorithms including K-Nearest-Neighbor (KNN), Support Vector Machines (SVM), Naive Bayes (NB), Decision Trees (DT), Multi-layer Perceptron (MLP), Random Forests (RF), Gradient Boosting Regression Trees (GBRT) and Adaptive Boosting (AdaBoost) are implemented. Moreover, the correlation coefficients between the predictions of 10 ensemble learners are calculated, and the hierarchical clustering dendrogram is drawn. It is found that the ensemble learners achieve higher prediction accuracy (84.0% vs 81.7%) than single CNN learner. The overlap ratio among the 10 ensemble learners is much higher than that of the 8 primary learners (62.9% vs 33.2%). In addition, it is shown that ensemble learners are roughly divided into three categories: the first (SVM, MLP, GBRT and RF) achieves the best performance; the second (VOT and AVE) is better than the third (AdaBoost, DT, NB and KNN). VOT and AVE yield higher recall than the machine learning algorithms. These results indicate that ensemble learners based on multiple CNN learners can achieve better performances for pulmonary nodules classification using CT images and that preferred fusion strategies include SVM, MLP, GBRT and RF.

Microorganisms play a great role in ecosystem, wastewater treatment, monitoring of environmental changes, and decomposition of waste materials. However, some of them are harmful to humans and animals such as tuberculosis bacteria and plasmodium. In such course, it is important to identify, track, analyze, consider the beneficial side and get rid of the negative effects of microorganisms using fast, accurate, and reliable methods. In recent decades, image analysis techniques have been used to address the drawbacks of manual traditional approaches in the identification and analysis of microorganisms. As image segmentation being an important step (technique) in the detection, tracking, monitoring, feature extraction, modeling, and analysis of microorganisms, different methods have been deployed, from classical approaches to current deep neural networks upon different challenges on microorganism images. This survey comprehensively analyses the various studies focused on developing microorganism image segmentation methods in the last 30 years (since 1989). In this survey, segmentation methods are categorized into classical and machine learning methods. Furthermore, these methods are subcategorized into threshold-based, region-based, and edge-based which belong to classical methods, supervised and unsupervised machine leaning-based methods which belong to machine learning category. A growth trend of different methods and most frequently used methods in each category are meticulously analyzed. A clear explanation of the suitability of these methods for different segmentation challenges encountered on microscopic microorganism images is also enlightened.

Abstract Background Lung segmentation constitutes a critical procedure for any clinical-decision supporting system aimed to improve the early diagnosis and treatment of lung diseases. Abnormal lungs mainly include lung parenchyma with commonalities on CT images across subjects, diseases and CT scanners, and lung lesions presenting various appearances. Segmentation of lung parenchyma can help locate and analyze the neighboring lesions, but is not well studied in the framework of machine learning. Methods We proposed to segment lung parenchyma using a convolutional neural network (CNN) model. To reduce the workload of manually preparing the dataset for training the CNN, one clustering algorithm based method is proposed firstly. Specifically, after splitting CT slices into image patches, the k-means clustering algorithm with two categories is performed twice using the mean and minimum intensity of image patch, respectively. A cross-shaped verification, a volume intersection, a connected component analysis and a patch expansion are followed to generate final dataset. Secondly, we design a CNN architecture consisting of only one convolutional layer with six kernels, followed by one maximum pooling layer and two fully connected layers. Using the generated dataset, a variety of CNN models are trained and optimized, and their performances are evaluated by eightfold cross-validation. A separate validation experiment is further conducted using a dataset of 201 subjects (4.62 billion patches) with lung cancer or chronic obstructive pulmonary disease, scanned by CT or PET/CT. The segmentation results by our method are compared with those yielded by manual segmentation and some available methods. Results A total of 121,728 patches are generated to train and validate the CNN models. After the parameter optimization, our CNN model achieves an average F-score of 0.9917 and an area of curve up to 0.9991 for classification of lung parenchyma and non-lung-parenchyma. The obtain model can segment the lung parenchyma accurately for 201 subjects with heterogeneous lung diseases and CT scanners. The overlap ratio between the manual segmentation and the one by our method reaches 0.96. Conclusions The results demonstrated that the proposed clustering algorithm based method can generate the training dataset for CNN models. The obtained CNN model can segment lung parenchyma with very satisfactory performance and have the potential to locate and analyze lung lesions.

Freezing of gait (FOG) has devastating consequences for patients with Parkinson's disease (PD), but the underlying pathophysiological mechanism is unclear. This was investigated in the present study by integrated structural and functional connectivity analyses of PD patients with or without FOG (PD FOG+ and PD FOG–, respectively) and healthy control (HC) subjects. We performed resting-state functional magnetic resonance imaging (fMRI) and diffusion tensor imaging of 24 PD FOG+ patients, 37 PD FOG– patients, and 24 HCs. Tract-based spatial statistics was applied to identify white matter (WM) abnormalities across the whole brain. Fractional anisotropy (FA) and mean diffusivity (MD) of abnormal WM areas were compared among groups, and correlations between these parameters and clinical severity as determined by FOG Questionnaire (FOGQ) score were analyzed. Voxel-mirrored homotopic connectivity (VMHC) was calculated to identify brain regions with abnormal interhemispheric connectivity. Structural and functional measures were integrated by calculating correlations between VMHC and FOGQ score and between FA, MD, and VMHC. The results showed that PD FOG+ and PD FOG– patients had decreased FA in the corpus callosum (CC), cingulum (hippocampus), and superior longitudinal fasciculus and increased MD in the CC, internal capsule, corona radiata, superior longitudinal fasciculus, and thalamus. PD FOG+ patients had more WM abnormalities than PD FOG– patients. FA and MD differed significantly among the splenium, body, and genu of the CC in all three groups (P < 0.05). The decreased FA in the CC was positively correlated with FOGQ score. PD FOG+ patients showed decreased VMHC in the post-central gyrus (PCG), pre-central gyrus, and parietal inferior margin. In PD FOG+ patients, VMHC in the PCG was negatively correlated with FOGQ score but positively correlated with FA in CC. Thus, FOG is associated with impaired interhemispheric brain connectivity measured by FA, MD, and VMHC, which are related to clinical FOG severity. These results demonstrate that integrating structural and functional MRI data can provide new insight into the pathophysiological mechanism of FOG in PD.

To recognize the epidermal growth factor receptor (EGFR) gene mutation status in lung adenocarcinoma (LADC) has become a prerequisite of deciding whether EGFR-tyrosine kinase inhibitor (EGFR-TKI) medicine can be used. Polymerase chain reaction assay or gene sequencing is for measuring EGFR status, however, the tissue samples by surgery or biopsy are required. We propose to develop deep learning models to recognize EGFR status by using radiomics features extracted from non-invasive CT images. Preoperative CT images, EGFR mutation status and clinical data have been collected in a cohort of 709 patients (the primary cohort) and an independent cohort of 205 patients. After 1,037 CT-based radiomics features are extracted from each lesion region, 784 discriminative features are selected for analysis and construct a feature mapping. One Squeeze-and-Excitation (SE) Convolutional Neural Network (SE-CNN) has been designed and trained to recognize EGFR status from the radiomics feature mapping. SE-CNN model is trained and validated by using 638 patients from the primary cohort, tested by using the rest 71 patients (the internal test cohort), and further tested by using the independent 205 patients (the external test cohort). Furthermore, SE-CNN model is compared with machine learning (ML) models using radiomics features, clinical features, and both features. EGFR(-) patients show the smaller age, higher odds of female, larger lesion volumes, and lower odds of subtype of acinar predominant adenocarcinoma (APA), compared with EGFR(+). The most discriminative features are for texture (614, 78.3%) and the features of first order of intensity (158, 20.1%) and the shape features (12, 1.5%) follow. SE-CNN model can recognize EGFR mutation status with an AUC of 0.910 and 0.841 for the internal and external test cohorts, respectively. It outperforms the CNN model without SE, the fine-tuned VGG16 and VGG19, three ML models, and the state-of-art models. Utilizing radiomics feature mapping extracted from non-invasive CT images, SE-CNN can precisely recognize EGFR mutation status of LADC patients. The proposed method combining radiomics features and deep leaning is superior to ML methods and can be expanded to other medical applications. The proposed SE-CNN model may help make decision on usage of EGFR-TKI medicine.

Type 2 diabetes mellitus (T2DM) leads to a higher risk of brain damage and adversely affects cognition. The underlying neural mechanism of T2DM-induced cognitive impairment (T2DM-CI) remains unclear. This study proposes to identify a small number of dysfunctional brain connections as imaging biomarkers, distinguishing between T2DM-CI, T2DM with normal cognition (T2DM-NC), and healthy controls (HC). We have recruited 22 T2DM-CI patients, 31 T2DM-NC patients, and 39 HCs. The structural Magnetic Resonance Imaging (MRI) and resting state fMRI images are acquired, and neuropsychological tests are carried out. Amplitude of low frequency fluctuations (ALFF) is analyzed to identify impaired brain regions implicated with T2DM and T2DM-CI. The functional network is built and all connections connected to impaired brain regions are selected. Subsequently, L1-norm regularized sparse canonical correlation analysis and sparse logistic regression are used to identify discriminative connections and Support Vector Machine is trained to realize three two-category classifications. It is found that single-digit dysfunctional connections predict T2DM and T2DM-CI. For T2DM-CI versus HC, T2DM-NC versus HC, and T2DM-CI versus T2DM-NC, the number of connections is 6, 7, and 5 and the area under curve (AUC) can reach 0.912, 0.901, and 0.861, respectively. The dysfunctional connection is mainly related to Default Model Network (DMN) and long-distance links. The strength of identified connections is significantly different among groups and correlated with cognitive assessment score (p < 0.05). Via ALFF analysis and further feature selection algorithms, a small number of dysfunctional brain connections can be identified to predict T2DM and T2DM-CI. These connections might be the imaging biomarkers of T2DM-CI and targets of intervention.

Malignant cerebral edema (MCE) after an ischemic stroke results in a poor outcome or death. Early prediction of MCE helps to identify subjects that could benefit from a surgical decompressive craniectomy. Net water uptake (NWU) in an ischemic lesion is a predictor of MCE; however, CT perfusion and lesion segmentation are required. This paper proposes a new Image Patch-based Net Water Uptake (IP-NWU) procedure that only uses non-enhanced admission CT and does not need lesion segmentation. IP-NWU is calculated by comparing the density of ischemic and contralateral normal patches selected from the middle cerebral artery (MCA) area using standard reference images. We also compared IP-NWU with the Segmented Region-based NWU (SR-NWU) procedure in which segmented ischemic regions from follow-up CT images are overlaid onto admission images. Furthermore, IP-NWU and its combination with imaging features are used to construct predictive models of MCE with a radiomics approach. In total, 116 patients with an MCA infarction (39 with MCE and 77 without MCE) were included in the study. IP-NWU was significantly higher for patients with MCE than those without MCE (p < 0.05). IP-NWU can predict MCE with an AUC of 0.86. There was no significant difference between IP-NWU and SR-NWU, nor between their predictive efficacy for MCE. The inter-reader and interoperation agreement of IP-NWU was exceptional according to the Intraclass Correlation Coefficient (ICC) analysis (inter-reader: ICC = 0.92; interoperation: ICC = 0.95). By combining IP-NWU with imaging features through a random forest classifier, the radiomics model achieved the highest AUC (0.96). In summary, IP-NWU and radiomics models that combine IP-NWU with imaging features can precisely predict MCE using only admission non-enhanced CT images scanned within 24 h from onset.

Abstract Background Accurate and early prognosis of disease is essential to clinical decision making, particularly in diseases, such as HCC, that are typically diagnosed at a late stage in the course of disease and therefore carry a poor prognosis. CDCA5 is a cell cycle regulatory protein that has shown prognostic value in several cancers. Methods We retrospectively evaluated 178 patients with HCC treated with curative liver resection between September 2009 and September 2012 at Nanchong Central Hospital in Nanchong, Sichuan Province, China. Patients were screened for their CDCA5 expression levels and assigned to either the high or low expression group. Patient demographics, comorbidities, clinicopathologic data, such as tumor microvascular invasion status and size, and long-term outcomes were compared between the two groups. The effect of CDCA5 on the proliferation of liver cancer cells was analyzed using in vitro and in vivo assays. Results The present study found that increased CDCA5 expression was associated with increased tumor diameter and microvascular invasion in HCC. It was also found that CDCA5 overexpression may be associated with liver cancer cells. Additionally, this study confirmed that CDCA5 expression was increased in HCC tissue versus normal liver tissue, that CDCA5 expression was associated with decreased survival and that CDCA5 knockdown using shRNA led to cell cycle arrest in the G2/M phase. Conclusions These findings suggest that CDCA5 expression is associated with poor prognosis in patients with hepatocellular carcinoma.