Search

Structural docking between the adaptive immune receptors (AIRs), including T cell receptors (TCRs) and B cell receptors (BCRs), and their cognate antigens are one of the most fundamental processes in adaptive immunity. However, current methods for predicting AIR-antigen binding largely rely on sequence-derived features of AIRs, omitting the structure features that are essential for binding affinity. In this study, we present a deep learning framework, termed DeepAIR, for the accurate prediction of AIR-antigen binding by integrating both sequence and structure features of AIRs. DeepAIR achieves a Pearson's correlation of 0.813 in predicting the binding affinity of TCR, and a median area under the receiver-operating characteristic curve (AUC) of 0.904 and 0.942 in predicting the binding reactivity of TCR and BCR, respectively. Meanwhile, using TCR and BCR repertoire, DeepAIR correctly identifies every patient with nasopharyngeal carcinoma and inflammatory bowel disease in test data. Thus, DeepAIR improves the AIR-antigen binding prediction that facilitates the study of adaptive immunity.

Antimicrobial peptides (AMPs) are short peptides that play crucial roles in diverse biological processes and have various functional activities against target organisms. Due to the abuse of chemical antibiotics and microbial pathogens' increasing resistance to antibiotics, AMPs have the potential to be alternatives to antibiotics. As such, the identification of AMPs has become a widely discussed topic. A variety of computational approaches have been developed to identify AMPs based on machine learning algorithms. However, most of them are not capable of predicting the functional activities of AMPs, and those predictors that can specify activities only focus on a few of them. In this study, we first surveyed 10 predictors that can identify AMPs and their functional activities in terms of the features they employed and the algorithms they utilized. Then, we constructed comprehensive AMP datasets and proposed a new deep learning-based framework, iAMPCN (identification of AMPs based on CNNs), to identify AMPs and their related 22 functional activities. Our experiments demonstrate that iAMPCN significantly improved the prediction performance of AMPs and their corresponding functional activities based on four types of sequence features. Benchmarking experiments on the independent test datasets showed that iAMPCN outperformed a number of state-of-the-art approaches for predicting AMPs and their functional activities. Furthermore, we analyzed the amino acid preferences of different AMP activities and evaluated the model on datasets of varying sequence redundancy thresholds. To facilitate the community-wide identification of AMPs and their corresponding functional types, we have made the source codes of iAMPCN publicly available at https://github.com/joy50706/iAMPCN/tree/master. We anticipate that iAMPCN can be explored as a valuable tool for identifying potential AMPs with specific functional activities for further experimental validation., (© The Author(s) 2023. Published by Oxford University Press. All rights reserved. For Permissions, please email: journals.permissions@oup.com.)

Introduction: Microvascular invasion (MVI) is a known risk factor for prognosis after R0 liver resection for hepatocellular carcinoma (HCC). The aim of this study was to develop a deep learning prognostic prediction model by incorporating a new factor of MVI area to the other independent risk factors., Methods: Consecutive patients with HCC who underwent R0 liver resection from January to December 2016 at the Eastern Hepatobiliary Surgery Hospital were included in this retrospective study. For patients with MVI detected on resected specimens, they were divided into two groups according to the size of the maximal MVI area: the small-MVI group and the large-MVI group., Results: Of 193 patients who had MVI in the 337 HCC patients, 130 patients formed the training cohort and 63 patients formed the validation cohort. The large-MVI group of patients had worse overall survival (OS) when compared with the small-MVI group (p = 0.009). A deep learning model was developed based on the following independent risk factors found in this study: MVI stage, maximal MVI area, presence/absence of cirrhosis, and maximal tumor diameter. The areas under the receiver operating characteristic of the deep learning model for the 1-, 3-, and 5-year predictions of OS were 80.65, 74.04, and 79.44, respectively, which outperformed the traditional COX proportional hazards model., Conclusion: The deep learning model, by incorporating the maximal MVI area as an additional prognostic factor to the other previously known independent risk factors, predicted more accurately postoperative long-term OS for HCC patients with MVI after R0 liver resection., (© 2022. Asian Pacific Association for the Study of the Liver.)

Objective: The aim of this study was to build a SVM classifier using ResNet-3D algorithm by artificial intelligence for prediction of synchronous PC., Background: Adequate detection and staging of PC from CRC remain difficult., Methods: The primary tumors in synchronous PC were delineated on preoperative contrast-enhanced computed tomography (CT) images. The features of adjacent peritoneum were extracted to build a ResNet3D + SVM classifier. The performance of ResNet3D + SVM classifier was evaluated in the test set and was compared to routine CT which was evaluated by radiologists., Results: The training set consisted of 19,814 images from 54 patients with PC and 76 patients without PC. The test set consisted of 7837 images from 40 test patients. The ResNet-3D spent only 34 seconds to analyze the test images. To increase the accuracy of PC detection, we have built a SVM classifier by integrating ResNet-3D features with twelve PC-specific features (P < 0.05). The ResNet3D + SVM classifier showed accuracy of 94.11% with AUC of 0.922 (0.912-0.944), sensitivity of 93.75%, specificity of 94.44%, positive predictive value (PPV) of 93.75%, and negative predictive value (NPV) of 94.44% in the test set. The performance was superior to routine contrast-enhanced CT (AUC: 0.791)., Conclusions: The ResNet3D + SVM classifier based on deep learning algorithm using ResNet-3D framework has shown great potential in prediction of synchronous PC in CRC., Competing Interests: The authors declare no conflicts of interest., (Copyright © 2020 Wolters Kluwer Health, Inc. All rights reserved.)

The sudden deterioration of patients with novel coronavirus disease 2019 (COVID-19) into critical illness is of major concern. It is imperative to identify these patients early. We show that a deep learning-based survival model can predict the risk of COVID-19 patients developing critical illness based on clinical characteristics at admission. We develop this model using a cohort of 1590 patients from 575 medical centers, with internal validation performance of concordance index 0.894 We further validate the model on three separate cohorts from Wuhan, Hubei and Guangdong provinces consisting of 1393 patients with concordance indexes of 0.890, 0.852 and 0.967 respectively. This model is used to create an online calculation tool designed for patient triage at admission to identify patients at risk of severe illness, ensuring that patients at greatest risk of severe illness receive appropriate care as early as possible and allow for effective allocation of health resources.

Purpose: Accurate pancreas segmentation has application in surgical planning, assessment of diabetes, and detection and analysis of pancreatic tumors. Factors that affect pancreas segmentation accuracy have not been previously reported. The purpose of this study is to identify technical and clinical factors that adversely affect the accuracy of pancreas segmentation on CT., Method and Materials: In this IRB and HIPAA compliant study, a deep convolutional neural network was used for pancreas segmentation in a publicly available archive of 82 portal-venous phase abdominal CT scans of 53 men and 29 women. The accuracies of the segmentations were evaluated by the Dice similarity coefficient (DSC). The DSC was then correlated with demographic and clinical data (age, gender, height, weight, body mass index), CT technical factors (image pixel size, slice thickness, presence or absence of oral contrast), and CT imaging findings (volume and attenuation of pancreas, visceral abdominal fat, and CT attenuation of the structures within a 5 mm neighborhood of the pancreas)., Results: The average DSC was 78% ± 8%. Factors that were statistically significantly correlated with DSC included body mass index (r = 0.34, p < 0.01), visceral abdominal fat (r = 0.51, p < 0.0001), volume of the pancreas (r = 0.41, p = 0.001), standard deviation of CT attenuation within the pancreas (r = 0.30, p = 0.01), and median and average CT attenuation in the immediate neighborhood of the pancreas (r = -0.53, p < 0.0001 and r = -0.52, p < 0.0001). There were no significant correlations between the DSC and the height, gender, or mean CT attenuation of the pancreas., Conclusion: Increased visceral abdominal fat and accumulation of fat within or around the pancreas are major factors associated with more accurate segmentation of the pancreas. Potential applications of our findings include assessment of pancreas segmentation difficulty of a particular scan or dataset and identification of methods that work better for more challenging pancreas segmentations., (Copyright © 2019. Published by Elsevier Inc.)

Objective: To investigate a fully automated abdominal CT-based muscle tool in a large adult screening population., Methods: A fully automated validated muscle segmentation algorithm was applied to 9310 non-contrast CT scans, including a primary screening cohort of 8037 consecutive asymptomatic adults (mean age, 57.1±7.8 years; 3555M/4482F). Sequential follow-up scans were available in a subset of 1171 individuals (mean interval, 5.1 years). Muscle tissue cross-sectional area and attenuation (Hounsfield unit, HU) at the L3 level were assessed, including change over time., Results: Mean values were significantly higher in males for both muscle area (190.6±33.6 vs 133.3±24.1 cm 2 , p <0.001) and density (34.3±11.1 HU vs 27.3±11.7 HU, p <0.001). Age-related losses were observed, with mean muscle area reduction of -1.5 cm 2 /year and attenuation reduction of -1.5 HU/year. Overall age-related muscle density (attenuation) loss was steeper than for muscle area for both sexes up to the age of 70 years. Between ages 50 and 70, relative muscle attenuation decreased significantly more in females (-30.6% vs -18.0%, p <0.001), whereas relative rates of muscle area loss were similar (-8%). Between ages 70 and 90, males lost more density (-22.4% vs -7.5%) and area (-13.4% vs -6.9%, p <0.001). Of the 1171 patients with longitudinal follow-up, 1013 (86.5%) showed a decrease in muscle attenuation, 739 (63.1%) showed a decrease in area, and 1119 (95.6%) showed a decrease in at least one of these measures., Conclusion: This fully automated CT muscle tool allows for both individualized and population-based assessment. Such data could be automatically derived at abdominal CT regardless of study indication, allowing for opportunistic sarcopenia detection., Advances in Knowledge: This fully automated tool can be applied to routine abdominal CT scans for prospective or retrospective opportunistic sarcopenia assessment, regardless of the original clinical indication. Mean values were significantly higher in males for both muscle area and muscle density. Overall age-related muscle density (attenuation) loss was steeper than for muscle area for both sexes, and therefore may be a more valuable predictor of adverse outcomes.

Injuries of the spine, and its posterior elements in particular, are a common occurrence in trauma patients, with potentially devastating consequences. Computer-aided detection (CADe) could assist in the detection and classification of spine fractures. Furthermore, CAD could help assess the stability and chronicity of fractures, as well as facilitate research into optimization of treatment paradigms. In this work, we apply deep convolutional networks (ConvNets) for the automated detection of posterior element fractures of the spine. First, the vertebra bodies of the spine with its posterior elements are segmented in spine CT using multi-atlas label fusion. Then, edge maps of the posterior elements are computed. These edge maps serve as candidate regions for predicting a set of probabilities for fractures along the image edges using ConvNets in a 2.5D fashion (three orthogonal patches in axial, coronal and sagittal planes). We explore three different methods for training the ConvNet using 2.5D patches along the edge maps of 'positive', i.e. fractured posterior-elements and 'negative', i.e. non-fractured elements. An experienced radiologist retrospectively marked the location of 55 displaced posterior-element fractures in 18 trauma patients. We randomly split the data into training and testing cases. In testing, we achieve an area-under-the-curve of 0.857. This corresponds to 71% or 81% sensitivities at 5 or 10 false-positives per patient, respectively. Analysis of our set of trauma patients demonstrates the feasibility of detecting posterior-element fractures in spine CT images using computer vision techniques such as deep convolutional networks.

Accurately predicting the antigen-binding specificity of adaptive immune receptors (AIRs), such as T-cell receptors (TCRs) and B-cell receptors (BCRs), is essential for discovering new immune therapies. However, the diversity of AIR chain sequences limits the accuracy of current prediction methods. This study introduces SC-AIR-BERT, a pre-trained model that learns comprehensive sequence representations of paired AIR chains to improve binding specificity prediction. SC-AIR-BERT first learns the 'language' of AIR sequences through self-supervised pre-training on a large cohort of paired AIR chains from multiple single-cell resources. The model is then fine-tuned with a multilayer perceptron head for binding specificity prediction, employing the K-mer strategy to enhance sequence representation learning. Extensive experiments demonstrate the superior AUC performance of SC-AIR-BERT compared with current methods for TCR- and BCR-binding specificity prediction. [ABSTRACT FROM AUTHOR]

Objective: This study aimed to develop an artificial intelligence model for predicting the pathological complete response (pCR) to neoadjuvant chemoradiotherapy (nCRT) of locally advanced rectal cancer (LARC) using digital pathological images. Background: nCRT followed by total mesorectal excision (TME) is a standard treatment strategy for patients with LARC. Predicting the PCR to nCRT of LARC remine difficulty. Methods: 842 LARC patients treated with standard nCRT from three medical centers were retrospectively recruited and subgrouped into the training, testing and external validation sets. Treatment response was classified as pCR and non-pCR based on the pathological diagnosis after surgery as the ground truth. The hematoxylin & eosin (H&E)-stained biopsy slides were manually annotated and used to develop a deep pathological complete response (DeepPCR) prediction model by deep learning. Results: The proposed DeepPCR model achieved an AUC-ROC of 0.710 (95% CI: 0.595, 0.808) in the testing cohort. Similarly, in the external validation cohort, the DeepPCR model achieved an AUC-ROC of 0.723 (95% CI: 0.591, 0.844). The sensitivity and specificity of the DeepPCR model were 72.6% and 46.9% in the testing set and 72.5% and 62.7% in the external validation cohort, respectively. Multivariate logistic regression analysis showed that the DeepPCR model was an independent predictive factor of nCRT (P =0.008 and P =0.004 for the testing set and external validation set, respectively). Conclusions: The DeepPCR model showed high accuracy in predicting pCR and served as an independent predictive factor for pCR. The model can be used to assist in clinical treatment decision making before surgery. [ABSTRACT FROM AUTHOR]

We attempt to generate a definition of delayed perihematomal edema expansion (DPE) and analyze its time course, risk factors, and clinical outcomes. A multi-cohort data was derived from the Chinese Intracranial Hemorrhage Image Database (CICHID). A non-contrast computed tomography (NCCT) -based deep learning model was constructed for fully automated segmentation hematoma and perihematomal edema (PHE). Time course of hematoma and PHE evolution correlated to initial hematoma volume was volumetrically assessed. Predictive values for DPE were calculated through receiver operating characteristic curve analysis and were tested in an independent cohort. Logistic regression analysis was utilized to identify risk factors for DPE formation and poor outcomes. The test cohort's Dice scores of lesion segmentation were 0.877 and 0.642 for hematoma and PHE, respectively. Overall, 1201 patients were enrolled for time-course analysis of ICH evolution. A total of 312 patients were further selected for DPE analysis. Time course analysis showed the growth peak of PHE approximately concentrates in 14 days after onset. The best cutoff for DPE to predict poor outcome was 3.34 mL of absolute PHE expansion from 4-7 days to 8-14 days (AUC=0.784, sensitivity=72.2%, specificity=81.2%), and 3.78 mL of absolute PHE expansion from 8-14 days to 15-21 days (AUC=0.682, sensitivity=59.3%, specificity=92.1%) in the derivation sample. Patients with DPE was associated with worse outcome (OR: 12.340, 95%CI: 6.378-23.873, P<0.01), and the larger initial hematoma volume (OR: 1.021, 95%CI: 1.000-1.043, P=0.049) was the significant risk factor for DPE formation. This study constructed a well-performance deep learning model for automatic segmentations of hematoma and PHE. A new definition of DPE was generated and is confirmed to be related to poor outcomes in ICH. Patients with larger initial hematoma volume have a higher risk of developing DPE formation. [ABSTRACT FROM AUTHOR]

Motivation Advanced deep learning techniques have been widely applied in disease diagnosis and prognosis with clinical omics, especially gene expression data. In the regulation of biological processes and disease progression, genes often work interactively rather than individually. Therefore, investigating gene association information and co-functional gene modules can facilitate disease state prediction. Results To explore the gene modules and inter-gene relational information contained in the omics data, we propose a novel multi-level attention graph neural network (MLA-GNN) for disease diagnosis and prognosis. Specifically, we format omics data into co-expression graphs via weighted correlation network analysis, and then construct multi-level graph features, finally fuse them through a well-designed multi-level graph feature fully fusion module to conduct predictions. For model interpretation, a novel full-gradient graph saliency mechanism is developed to identify the disease-relevant genes. MLA-GNN achieves state-of-the-art performance on transcriptomic data from TCGA-LGG/TCGA-GBM and proteomic data from coronavirus disease 2019 (COVID-19)/non-COVID-19 patient sera. More importantly, the relevant genes selected by our model are interpretable and are consistent with the clinical understanding. Availabilityand implementation The codes are available at https://github.com/TencentAILabHealthcare/MLA-GNN. [ABSTRACT FROM AUTHOR]

Untreated colorectal polyps can develop into colorectal cancer, which is a leading cause of cancer-related deaths. Colonoscopy is a commonly-used method for colorectal polyp scanning, but limited to the experience and subjectivity of clinicians, one out of four polyps cannot be correctly recognized. In this article, we propose an automatic colorectal polyp segmentation system based on the deep convolutional neural network, aiming to improve the accuracy of colorectal polyp scanning. The proposed ABC-Net is comprised of a shared encoder and two novel mutually-constrained decoders for simultaneous polyp area and boundary segmentation. To sufficiently exploit multi-scale image information, the selective feature modules are embedded into the network and used for dynamically learning and fusing multi-scale feature representations. Furthermore, a new boundary-sensitive loss is proposed to model the interdependencies between the area and boundary branches, the information of the two branches are reciprocally propagated and constrained, yielding a significant improvement in segmentation accuracy. Extensive experiments are conducted on three public colorectal polyp datasets, and the results, e.g., F1 scores are 0.866, 0.915, 0.874 in EndoScene, Kvasir-SEG, and ETIS-Larib datasets, demonstrate the advantages of the proposed method. [ABSTRACT FROM AUTHOR]

Many medical image datasets have been collected without proper annotations for deep learning training. In this paper, we propose a novel unsupervised domain adaptation framework with adversarial learning to minimize the annotation efforts. Our framework employs a task specific network, i.e. , fully convolutional network (FCN), for spatial density prediction. Moreover, we employ a domain discriminator, in which adversarial learning is adopted to align the less-annotated target domain features with the well-annotated source domain features in the feature space. We further propose a novel training strategy for the adversarial learning by coupling data from source and target domains and alternating the subnet updates. We employ the public CBIS-DDSM dataset as the source domain, and perform two sets of experiments on two target domains (i.e. , the public INbreast dataset and a self-collected dataset), respectively. Experimental results suggest consistent and comparable performance improvement over the state-of-the-art methods. Our proposed training strategy is also proved to converge much faster. [ABSTRACT FROM AUTHOR]

Prognostic tumor growth modeling via volumetric medical imaging observations can potentially lead to better outcomes of tumor treatment management and surgical planning. Recent advances of convolutional networks (ConvNets) have demonstrated higher accuracy than traditional mathematical models can be achieved in predicting future tumor volumes. This indicates that deep learning based data-driven techniques may have great potentials on addressing such problem. However, current 2D image patch based modeling approaches can not make full use of the spatio-temporal imaging context of the tumor’s longitudinal 4D (3D + time) patient data. Moreover, they are incapable to predict clinically-relevant tumor properties, other than the tumor volumes. In this paper, we exploit to formulate the tumor growth process through convolutional Long Short-Term Memory (ConvLSTM) that extract tumor’s static imaging appearances and simultaneously capture its temporal dynamic changes within a single network. We extend ConvLSTM into the spatio-temporal domain (ST-ConvLSTM) by jointly learning the inter-slice 3D contexts and the longitudinal or temporal dynamics from multiple patient studies. Our approach can incorporate other non-imaging patient information in an end-to-end trainable manner. Experiments are conducted on the largest 4D longitudinal tumor dataset of 33 patients to date. Results validate that the proposed ST-ConvLSTM model produces a Dice score of 83.2%±5.1% and a RVD of 11.2%±10.8%, both statistically significantly outperforming (p < 0.05) other compared methods of traditional linear model, ConvLSTM, and generative adversarial network (GAN) under the metric of predicting future tumor volumes. Additionally, our new method enables the prediction of both cell density and CT intensity numbers. Last, we demonstrate the generalizability of ST-ConvLSTM by employing it in 4D medical image segmentation task, which achieves an averaged Dice score of 86.3%±1.2% for left-ventricle segmentation in 4D ultrasound with 3 seconds per patient case. [ABSTRACT FROM AUTHOR]

Tumor growth is associated with cell invasion and mass-effect, which are traditionally formulated by mathematical models, namely reaction-diffusion equations and biomechanics. Such models can be personalized based on clinical measurements to build the predictive models for tumor growth. In this paper, we investigate the possibility of using deep convolutional neural networks to directly represent and learn the cell invasion and mass-effect, and to predict the subsequent involvement regions of a tumor. The invasion network learns the cell invasion from information related to metabolic rate, cell density, and tumor boundary derived from multimodal imaging data. The expansion network models the mass-effect from the growing motion of tumor mass. We also study different architectures that fuse the invasion and expansion networks, in order to exploit the inherent correlations among them. Our network can easily be trained on population data and personalized to a target patient, unlike most previous mathematical modeling methods that fail to incorporate population data. Quantitative experiments on a pancreatic tumor data set show that the proposed method substantially outperforms a state-of-the-art mathematical model-based approach in both accuracy and efficiency, and that the information captured by each of the two subnetworks is complementary. [ABSTRACT FROM PUBLISHER]

The prognosis following a hemorrhagic stroke is usually extremely poor. Rating scales have been developed to predict the outcomes of patients with intracerebral hemorrhage (ICH). To date, however, the prognostic prediction models have not included the full range of relevant imaging features. We constructed a clinic-imaging fusion model based on convolutional neural networks (CNN) to predict the short-term prognosis of ICH patients. This was a multi-center retrospective study, which included 1990 patients with ICH. Two CNN-based deep learning models were constructed to predict the neurofunctional outcomes at discharge; these were validated using a nested 5-fold cross-validation approach. The models' predictive efficiency was compared with the original ICH scale and the ICH grading scale. Poor neurological outcome was defined as a Glasgow Outcome Scale (GOS) score of 1–3. The training and test sets included 1599 and 391 patients, respectively. For the test set, the clinic-imaging fusion model had the highest area under the curve (AUC = 0.903), followed by the imaging-based model (AUC = 0.886), the ICH scale (AUC = 0.777), and finally the ICH grading scale (AUC = 0.747). The CNN prognostic prediction model based on neuroimaging features was more effective than the ICH scales in predicting the neurological outcomes of ICH patients at discharge. The CNN model's predictive efficiency slightly improved when clinical data were included. [ABSTRACT FROM AUTHOR]

Background: Deep convolutional neural networks (CNNs) have yielded promising results in automatic whole slide images (WSIs) processing for digital pathology in recent years. Training supervised CNNs usually requires a large amount of annotated samples. However, manual annotation of gigapixel WSIs is labor-intensive and error-prone, i.e., the shortage of annotations has become the major bottleneck of WSI diagnosis model development. In this work, we aim to develop a deep learning based self-supervised histopathology image analysis workflow that can classify tissues without any annotation. Methods: Inspired by the contrastive learning methods that have achieved state-of-the-art results on unsupervised representation learning for natural images, we adopt the self-supervised training scheme to generate discriminative embeddings from annotation-free WSI patches and simultaneously obtain initial clusters, which are further refined by a silhouette coefficient based recursive scheme to divide tissue mixture clusters. A multi-scale encoder network is specifically designed to extract pathology-specific contextual features. A tissue dictionary composed by the tissue clusters is then built for cancer diagnosis. Results: Experiments show that our method can identify different tissues in annotation-free conditions with competitive results (achieving the accuracy of 0.9364/0.9325 in human colorectal/sentinel lymph WSIs) as the supervised methods (with the corresponding accuracy of 0.9806/0.9494) and surpass other unsupervised baselines. Our method is also evaluated in a cohort of 20 clinical patients and get an AUC score of 0.99 to distinguish benign/malignant polyps. Conclusion: Our proposed deep contrastive learning based tissue clustering method can learn from raw WSIs without annotation to distinguish different tissues. The method are tested in three different datasets and show the potential to help pathologists diagnosing diseases as a quantitative and qualitative tool. • A deep clustering method is introduced to learn from annotation-free WSIs and obtain initial clusters. • A parameter-free recursive cluster refinement method is proposed to refine initial clusters. • A multi-scale encoder network is designed to better extract pathology-specific features. • A tissue dictionary is built based on refined clusters and evaluated in a colon polyp dataset for cancer diagnosis [ABSTRACT FROM AUTHOR]