Search

Breast cancer (BC) is the leading cause of death among women worldwide. It affects in general women older than 40 years old. Medical images analysis is one of the most promising research areas since it provides facilities for diagnosis and decision-making of several diseases such as BC. This paper conducts a Structured Literature Review (SLR) of the use of Machine Learning (ML) and Image Processing (IP) techniques to deal with BC imaging. A set of 530 papers published between 2000 and August 2019 were selected and analyzed according to ten criteria: year and publication channel, empirical type, research type, medical task, machine learning techniques, datasets used, validation methods, performance measures and image processing techniques which include image pre-processing, segmentation, feature extraction and feature selection. Results showed that diagnosis was the most used medical task and that Deep Learning techniques (DL) were largely used to perform classification. Furthermore, we found out that classification was the most ML objective investigated followed by prediction and clustering. Most of the selected studies used Mammograms as imaging modalities rather than Ultrasound or Magnetic Resonance Imaging with the use of public or private datasets with MIAS as the most frequently investigated public dataset. As for image processing techniques, the majority of the selected studies pre-process their input images by reducing the noise and normalizing the colors, and some of them use segmentation to extract the region of interest with the thresholding method. For feature extraction, we note that researchers extracted the relevant features using classical feature extraction techniques (e.g. Texture features, Shape features, etc.) or DL techniques (e. g. VGG16, VGG19, ResNet, etc.), and finally few papers used feature selection techniques in particular the filter methods. [ABSTRACT FROM AUTHOR]

Fungal keratitis (FK) is a common and severe corneal disease, which is widely spread in tropical and subtropical areas. Early diagnosis and treatment are vital for patients, with confocal microscopy cornea imaging being one of the most effective methods for the diagnosis of FK. However, most cases are currently diagnosed by the subjective judgment of ophthalmologists, which is time-consuming and heavily depends on the experience of the ophthalmologists. In this paper, we introduce a novel structure-aware automatic diagnosis algorithm based on deep convolutional neural networks for the accurate diagnosis of FK. Specifically, a two-stream convolutional network is deployed, combining GoogLeNet and VGGNet, which are two commonly used networks in computer vision architectures. The main stream is used for feature extraction of the input image, while the auxiliary stream is used for feature discrimination and enhancement of the hyphae structure. Then, the features are combined by concatenating the channel dimension to obtain the final output, i.e., normal or abnormal. The results showed that the proposed method achieved accuracy, sensitivity, and specificity of 97.73%, 97.02%, and 98.54%, respectively. These results suggest that the proposed neural network could be a promising computer-aided FK diagnosis solution. [ABSTRACT FROM AUTHOR]

In the lung computer-aided detection (Lung CAD) system, the region of interest (ROI) of lung nodules has more false positives, making the imbalance between positive and negative (true positive and false positive) samples more likely to lead to misclassification of true positive nodules, a cost-sensitive multikernel learning support vector machine (CS-MKL-SVM) algorithm is proposed. Different penalty coefficients are assigned to positive and negative samples, so that the model can better learn the features of true positive nodules and improve the classification effect. To further improve the detection rate of pulmonary nodules and overall recognition accuracy, a score function named F-new based on the harmonic mean of accuracy (ACC) and sensitivity (SEN) is proposed as a fitness function for subsequent particle swarm optimization (PSO) parameter optimization, and a feasibility analysis of this function is performed. Compared with the fitness function that considers only accuracy or sensitivity, both the detection rate and the recognition accuracy of pulmonary nodules can be improved by this new algorithm. Compared with the grid search algorithm, using PSO for parameter search can reduce the model training time by nearly 20 times and achieve rapid parameter optimization. The maximum F-new obtained on the test set is 0.9357 for the proposed algorithm. When the maximum value of F-new is achieved, the corresponding recognition ACC is 91%, and SEN is 96.3%. Compared with the radial basis function in the single kernel, the F-new of the algorithm in this paper is 2.16% higher, ACC is 1.00% higher and SEN is equal. Compared with the polynomial kernel function in the single kernel, the F-new of the algorithm is 3.64% higher, ACC is 1.00% higher and SEN is 7.41% higher. The experimental results show that the F-new, ACC and SEN of the proposed algorithm is the best among them, and the results obtained by using multikernel function combined with F-new index are better than the single kernel function. Compared with the MKL-SVM algorithm of grid search, the ACC of the algorithm in this paper is reduced by 1%, and the results are equal to those of the MKL-SVM algorithm based on PSO only. Compared with the above two algorithms, SEN is increased by 3.71% and 7.41%, respectively. Therefore, it can be seen that the cost sensitive method can effectively reduce the missed detection of nodules, and the availability of the new algorithm can be further verified. [ABSTRACT FROM AUTHOR]

Rib segmentation based on chest X-ray images is essential in the computer-aided diagnosis systems of lung cancer, which serves as an important step in the quantitative analysis of various types of lung diseases. However, the traditional methods are unable to segment ribs effectively due to the unclear edges and overlapping regions in X-ray images. A novel rib segmentation framework based on Unpaired Sample Augmentation and Multi-Scale Network is presented in this paper, aiming to improve the accuracy of ribs segmentation with limited labeled samples. First, the algorithm learns pneumonia-related texture changes via unpaired chest x-ray images and generates various augmented samples. Then, a multi-scale network attempts to learn hierarchical features using global supervision. Finally, the refined segmentation result of each organ is achieved by using a deep separation module and a comprehensive loss function. Specifically, the hierarchical features can greatly improve the robustness of multi-organ segmentation networks. The complex multi-organ segmentation task with limited labeled data is simplified with the designed deep separation module. We justify the proposed framework through extensive experiments. It achieves good performance with DSC, Precision, Recall, and Jaccard of 88.03, 88.25, 88.36, and 79.02%, respectively. The DSC value increases nearly by 3% compared to other popular methods. The experimental results show that our algorithm presents better segmentation performance for the overlapping region and fuzzy region of multiple organs, which holds research value and prospects for application. [ABSTRACT FROM AUTHOR]

An automated diagnosis system is crucial for helping radiologists identify brain abnormalities efficiently. The convolutional neural network (CNN) algorithm of deep learning has the advantage of automated feature extraction beneficial for an automated diagnosis system. However, several challenges in the CNN-based classifiers of medical images, such as a lack of labeled data and class imbalance problems, can significantly hinder the performance. Meanwhile, the expertise of multiple clinicians may be required to achieve accurate diagnoses, which can be reflected in the use of multiple algorithms. In this paper, we present Deep-Stacked CNN, a deep heterogeneous model based on stacked generalization to harness the advantages of different CNN-based classifiers. The model aims to improve robustness in the task of multi-class brain disease classification when we have no opportunity to train single CNNs on sufficient data. We propose two levels of learning processes to obtain the desired model. At the first level, different pre-trained CNNs fine-tuned via transfer learning will be selected as the base classifiers through several procedures. Each base classifier has a unique expert-like character, which provides diversity to the diagnosis outcomes. At the second level, the base classifiers are stacked together through neural network, representing the meta-learner that best combines their outputs and generates the final prediction. The proposed Deep-Stacked CNN obtained an accuracy of 99.14% when evaluated on the untouched dataset. This model shows its superiority over existing methods in the same domain. It also requires fewer parameters and computations while maintaining outstanding performance. [ABSTRACT FROM AUTHOR]

Breast cancer is the second most common cancer among women worldwide, and the diagnosis by pathologists is a time-consuming procedure and subjective. Computer-aided diagnosis frameworks are utilized to relieve pathologist workload by classifying the data automatically, in which deep convolutional neural networks (CNNs) are effective solutions. The features extracted from the activation layer of pre-trained CNNs are called deep convolutional activation features (DeCAF). In this paper, we have analyzed that all DeCAF features are not necessarily led to higher accuracy in the classification task and dimension reduction plays an important role. We have proposed reduced DeCAF (R-DeCAF) for this purpose, and different dimension reduction methods are applied to achieve an effective combination of features by capturing the essence of DeCAF features. This framework uses pre-trained CNNs such as AlexNet, VGG-16, and VGG-19 as feature extractors in transfer learning mode. The DeCAF features are extracted from the first fully connected layer of the mentioned CNNs, and a support vector machine is used for classification. Among linear and nonlinear dimensionality reduction algorithms, linear approaches such as principal component analysis (PCA) represent a better combination among deep features and lead to higher accuracy in the classification task using a small number of features considering a specific amount of cumulative explained variance (CEV) of features. The proposed method is validated using experimental BreakHis and ICIAR datasets. Comprehensive results show improvement in the classification accuracy up to 4.3% with a feature vector size (FVS) of 23 and CEV equal to 0.15. [ABSTRACT FROM AUTHOR]

Preoperative planning for liver surgical treatments is an essential planning tool that aids in reducing the risks of surgical resection. Based on the computed tomography (CT) images, the resection can be planned before the actual tumour resection surgery. The computer-aided system provides an overview of the spatial relationships of the liver organ and its internal structures, tumours, and vasculature. It also allows for an accurate calculation of the remaining liver volume after resection. The aim of this paper was to review the main stages of the computer-aided system that helps to evaluate the risk of resection during liver cancer surgical treatments. The computer-aided system assists with surgical planning by enabling physicians to get volumetric measurements and visualise the liver, tumours, and surrounding vasculature. In this paper, it is concluded that for accurate planning of tumour resections, the liver organ and its internal structures should be segmented to understand the clear spatial relationship between them, thus allowing for a safer resection. This paper presents the main proposed segmentation techniques for each stage in the computer-aided system, namely the liver organ, tumours, and vessels. From the reviewed methods, it has been found that instead of relying on a single specific technique, a combination of a group of techniques would give more accurate segmentation results. The extracted masks from the segmentation algorithms are fused together to give the surgeons the 3D visualisation tool to study the spatial relationships of the liver and to calculate the required resection planning parameters. [ABSTRACT FROM AUTHOR]

Federated learning (FL), a relatively new area of research in medical image analysis, enables collaborative learning of a federated deep learning model without sharing the data of participating clients. In this paper, we propose FedDropoutAvg, a new federated learning approach for detection of tumor in images of colon tissue slides. The proposed method leverages the power of dropout, a commonly employed scheme to avoid overfitting in neural networks, in both client selection and federated averaging processes. We examine FedDropoutAvg against other FL benchmark algorithms for two different image classification tasks using a publicly available multi-site histopathology image dataset. We train and test the proposed model on a large dataset consisting of 1.2 million image tiles from 21 different sites. For testing the generalization of all models, we select held-out test sets from sites that were not used during training. We show that the proposed approach outperforms other FL methods and reduces the performance gap (to less than 3% in terms of AUC on independent test sites) between FL and a central deep learning model that requires all data to be shared for centralized training, demonstrating the potential of the proposed FedDropoutAvg model to be more generalizable than other state-of-the-art federated models. To the best of our knowledge, ours is the first study to effectively utilize the dropout strategy in a federated setting for tumor detection in histology images. [ABSTRACT FROM AUTHOR]

Computer-aided diagnosis system is becoming a more and more important tool in clinical treatment, which can provide a verification of the doctors' decisions. In this paper, we proposed a novel abnormal brain detection method for magnetic resonance image. Firstly, a pre-trained AlexNet was modified with batch normalization layers and trained on our brain images. Then, the last several layers were replaced with an extreme learning machine. A searching method was proposed to find the best number of layers to be replaced. Finally, the extreme learning machine was optimized by chaotic bat algorithm to obtain better classification performance. Experiment results based on 5 × hold-out validation revealed that our method achieved state-of-the-art performance. [ABSTRACT FROM AUTHOR]

Epileptic seizure detection and classification in clinical electroencephalogram data still is a challenge, and only low sensitivity with a high rate of false positives has been achieved with commercially available seizure detection tools, which usually are patient non-specific. Epilepsy patients suffer from severe detrimental effects like physical injury or depression due to unpredictable seizures. However, even in hospitals due to the high rate of false positives, the seizure alert systems are of poor help for patients as tools of seizure detection are mostly trained on unrealistically clean data, containing little noise and obtained under controlled laboratory conditions, where patient groups are homogeneous, e.g. in terms of age or type of seizures. In this study authors present the approach for detection and classification of a seizure using clinical data of electroencephalograms and a convolutional neural network trained on features of brain synchronisation and power spectrum. Various deep learning methods were applied, and the network was trained on a very heterogeneous clinical electroencephalogram dataset. In total, eight different types of seizures were considered, and the patients were of various ages, health conditions and they were observed under clinical conditions. Despite this, the classifier presented in this paper achieved sensitivity and specificity equal to 0.68 and 0.67, accordingly, which is a significant improvement as compared to the known results for clinical data. Graphical abstract. [ABSTRACT FROM AUTHOR]

The classification of leukocytes in peripheral blood images is an important milestone to be achieved because it can greatly assist pathologists to diagnose diseases such as leukemia, anemia, and other blood disorders. To a certain extent, a good segmentation method for identifying leukocytes from their background is the first step to the efficient functioning of the leukocytes classification system. However, the morphological structure of leukocytes, poor contrast, and the variations in their shape and size lead to the degradation of the segmentation accuracy. In this paper, we propose a new leukocyte segmentation framework that first locates and then segments leukocytes from peripheral blood images. Here, the locations of the leukocytes are first identified using a novel edge strength cue (ESc), and later, the Grabcut model is deployed to obtain the segmentation of the leukocytes. The novelty lies in the way the location of the leukocytes is detected, and this improves the leukocyte segmentation accuracy. The experimental evaluation is performed on ALL-IDB1, Cellavision, and LISC datasets for leukocyte segmentation based on the detection of the ESc location. Experimental results are evaluated using precision, recall, and F-score measures. The proposed method outperforms the state-of-the-art techniques. Additionally, the computation time of the proposed method is analyzed and presented in the study. Graphical Abstract Leukocytes Location Detection and Segmentation. [ABSTRACT FROM AUTHOR]

Considering that the traditional lung segmentation algorithms are not adaptive for the situations that most of the juxtapleural nodules, which are excluded as fat, and lung are not segmented perfectly. In this paper, several methods are comprehensively utilized including optimal iterative threshold, three-dimensional connectivity labeling, three-dimensional region growing for the initial segmentation of the lung parenchyma, based on improved chain code, and Bresenham algorithms to repair the lung parenchyma. The paper thus proposes a fully automatic method for lung parenchyma segmentation and repairing. Ninety-seven lung nodule thoracic computed tomography scans and 25 juxtapleural nodule scans are used to test the proposed method and compare with the most-cited rolling-ball method. Experimental results show that the algorithm can segment lung parenchyma region automatically and accurately. The sensitivity of juxtapleural nodule inclusion is 100 %, the segmentation accuracy of juxtapleural nodule regions is 98.6 %, segmentation accuracy of lung parenchyma is more than 95.2 %, and the average segmentation time is 0.67 s/frame. The algorithm can achieve good results for lung parenchyma segmentation and repairing in various cases that nodules/tumors adhere to lung wall. [ABSTRACT FROM AUTHOR]

Red blood cell (RBC) deformation is the consequence of several diseases, including sickle cell anemia, which causes recurring episodes of pain and severe pronounced anemia. Monitoring patients with these diseases involves the observation of peripheral blood samples under a microscope, a time-consuming procedure. Moreover, a specialist is required to perform this technique, and owing to the subjective nature of the observation of isolated RBCs, the error rate is high. In this paper, we propose an automated method for differentially enumerating RBCs that uses peripheral blood smear image analysis. In this method, the objects of interest in the image are segmented using a Chan-Vese active contour model. An analysis is then performed to classify the RBCs, also called erythrocytes, as normal or elongated or having other deformations, using the basic shape analysis descriptors: circular shape factor (CSF) and elliptical shape factor (ESF). To analyze cells that become partially occluded in a cluster during sample preparation, an elliptical adjustment is performed to allow the analysis of erythrocytes with discoidal and elongated shapes. The images of patient blood samples used in the study were acquired by a clinical laboratory specialist in the Special Hematology Department of the "Dr. Juan Bruno Zayas" General Hospital in Santiago de Cuba. A comparison of the results obtained by the proposed method in our experiments with those obtained by some state-of-the-art methods showed that the proposed method is superior for the diagnosis of sickle cell anemia. This superiority is achieved for evidenced by the obtained F-measure value (0.97 for normal cells and 0.95 for elongated ones) and several overall multiclass performance measures. The results achieved by the proposed method are suitable for the purpose of clinical treatment and diagnostic support of sickle cell anemia. We present a new method to obtain erythrocyte shape classification using peripheral blood smear sample images. The aim of the method is to segment the cells, to separate clusters and classify cells (circulars, elongated and others). We compared our method with state-of the-art. Results showed that our method with is superior for the diagnosis support of sickle cell anemia. [ABSTRACT FROM AUTHOR]

Lung cancer is considered one of the deadliest diseases in the world. An early and accurate diagnosis aims to promote the detection and characterization of pulmonary nodules, which is of vital importance to increase the patients' survival rates. The mentioned characterization is done through a segmentation process, facing several challenges due to the diversity in nodular shape, size, and texture, as well as the presence of adjacent structures. This paper tackles pulmonary nodule segmentation in computed tomography scans proposing three distinct methodologies. First, a conventional approach which applies the Sliding Band Filter (SBF) to estimate the filter's support points, matching the border coordinates. The remaining approaches are Deep Learning based, using the U-Net and a novel network called SegU-Net to achieve the same goal. Their performance is compared, as this work aims to identify the most promising tool to improve nodule characterization. All methodologies used 2653 nodules from the LIDC database, achieving a Dice score of 0.663, 0.830, and 0.823 for the SBF, U-Net and SegU-Net respectively. This way, the U-Net based models yield more identical results to the ground truth reference annotated by specialists, thus being a more reliable approach for the proposed exercise. The novel network revealed similar scores to the U-Net, while at the same time reducing computational cost and improving memory efficiency. Consequently, such study may contribute to the possible implementation of this model in a decision support system, assisting the physicians in establishing a reliable diagnosis of lung pathologies based on this segmentation task. [ABSTRACT FROM AUTHOR]

This paper addresses the task of nuclei segmentation in high-resolution histopathology images. We propose an automatic end-to-end deep neural network algorithm for segmentation of individual nuclei. A nucleus-boundary model is introduced to predict nuclei and their boundaries simultaneously using a fully convolutional neural network. Given a color-normalized image, the model directly outputs an estimated nuclei map and a boundary map. A simple, fast, and parameter-free post-processing procedure is performed on the estimated nuclei map to produce the final segmented nuclei. An overlapped patch extraction and assembling method is also designed for seamless prediction of nuclei in large whole-slide images. We also show the effectiveness of data augmentation methods for nuclei segmentation task. Our experiments showed our method outperforms prior state-of-the-art methods. Moreover, it is efficient that one 1000×1000 image can be segmented in less than 5 s. This makes it possible to precisely segment the whole-slide image in acceptable time. The source code is available at https://github.com/easycui/nuclei_segmentation . Graphical Abstract The neural network for nuclei segmentation. [ABSTRACT FROM AUTHOR]

Dermoscopy is a technique used to capture the images of skin, and these images are useful to analyze the different types of skin diseases. Malignant melanoma is a kind of skin cancer whose severity even leads to death. Earlier detection of melanoma prevents death and the clinicians can treat the patients to increase the chances of survival. Only few machine learning algorithms are developed to detect the melanoma using its features. This paper proposes a Computer Aided Diagnosis (CAD) system which equips efficient algorithms to classify and predict the melanoma. Enhancement of the images are done using Contrast Limited Adaptive Histogram Equalization technique (CLAHE) and median filter. A new segmentation algorithm called Normalized Otsu's Segmentation (NOS) is implemented to segment the affected skin lesion from the normal skin, which overcomes the problem of variable illumination. Fifteen features are derived and extracted from the segmented images are fed into the proposed classification techniques like Deep Learning based Neural Networks and Hybrid Adaboost-Support Vector Machine (SVM) algorithms. The proposed system is tested and validated with nearly 992 images (malignant & benign lesions) and it provides a high classification accuracy of 93 %. The proposed CAD system can assist the dermatologists to confirm the decision of the diagnosis and to avoid excisional biopsies. [ABSTRACT FROM AUTHOR]

Retinal blood vessels are the source to provide oxygen and nutrition to retina and any change in the normal structure may lead to different retinal abnormalities. Automated detection of vascular structure is very important while designing a computer aided diagnostic system for retinal diseases. Most popular methods for vessel segmentation are based on matched filters and Gabor wavelets which give good response against blood vessels. One major drawback in these techniques is that they also give strong response for lesion (exudates, hemorrhages) boundaries which give rise to false vessels. These false vessels may lead to incorrect detection of vascular changes. In this paper, we propose a new hybrid feature set along with new classification technique for accurate detection of blood vessels. The main motivation is to lower the false positives especially from retinal images with severe disease level. A novel region based hybrid feature set is presented for proper discrimination between true and false vessels. A new modified m-mediods based classification is also presented which uses most discriminating features to categorize vessel regions into true and false vessels. The evaluation of proposed system is done thoroughly on publicly available databases along with a locally gathered database with images of advanced level of retinal diseases. The results demonstrate the validity of the proposed system as compared to existing state of the art techniques. [ABSTRACT FROM AUTHOR]

Scientific research of artificial intelligence (AI) in dermatology has increased exponentially. The objective of this study was to perform a systematic review and meta-analysis to evaluate the performance of AI algorithms for skin cancer classification in comparison to clinicians with different levels of expertise. Based on PRISMA guidelines, 3 electronic databases (PubMed, Embase, and Cochrane Library) were screened for relevant articles up to August 2022. The quality of the studies was assessed using QUADAS-2. A meta-analysis of sensitivity and specificity was performed for the accuracy of AI and clinicians. Fifty-three studies were included in the systematic review, and 19 met the inclusion criteria for the meta-analysis. Considering all studies and all subgroups of clinicians, we found a sensitivity (Sn) and specificity (Sp) of 87.0% and 77.1% for AI algorithms, respectively, and a Sn of 79.78% and Sp of 73.6% for all clinicians (overall); differences were statistically significant for both Sn and Sp. The difference between AI performance (Sn 92.5%, Sp 66.5%) vs. generalists (Sn 64.6%, Sp 72.8%), was greater, when compared with expert clinicians. Performance between AI algorithms (Sn 86.3%, Sp 78.4%) vs expert dermatologists (Sn 84.2%, Sp 74.4%) was clinically comparable. Limitations of AI algorithms in clinical practice should be considered, and future studies should focus on real-world settings, and towards AI-assistance. [ABSTRACT FROM AUTHOR]

Distribution shifts remain a problem for the safe application of regulated medical AI systems, and may impact their real-world performance if undetected. Postmarket shifts can occur for example if algorithms developed on data from various acquisition settings and a heterogeneous population are predominantly applied in hospitals with lower quality data acquisition or other centre-specific acquisition factors, or where some ethnicities are over-represented. Therefore, distribution shift detection could be important for monitoring AI-based medical products during postmarket surveillance. We implemented and evaluated three deep-learning based shift detection techniques (classifier-based, deep kernel, and multiple univariate kolmogorov-smirnov tests) on simulated shifts in a dataset of 130'486 retinal images. We trained a deep learning classifier for diabetic retinopathy grading. We then simulated population shifts by changing the prevalence of patients' sex, ethnicity, and co-morbidities, and example acquisition shifts by changes in image quality. We observed classification subgroup performance disparities w.r.t. image quality, patient sex, ethnicity and co-morbidity presence. The sensitivity at detecting referable diabetic retinopathy ranged from 0.50 to 0.79 for different ethnicities. This motivates the need for detecting shifts after deployment. Classifier-based tests performed best overall, with perfect detection rates for quality and co-morbidity subgroup shifts at a sample size of 1000. It was the only method to detect shifts in patient sex, but required large sample sizes ( > 3 0 ′ 000 ). All methods identified easier-to-detect out-of-distribution shifts with small (≤300) sample sizes. We conclude that effective tools exist for detecting clinically relevant distribution shifts. In particular classifier-based tests can be easily implemented components in the post-market surveillance strategy of medical device manufacturers. [ABSTRACT FROM AUTHOR]

Exoskeletons offer great facilities to the elderly and disabled people with respect to extending their moving ranges and reacting to certain physical activities. Electromyogram (EMG) signals, which are derived from the neuromuscular system, provide an important access to the human-robot interface. On one hand, EMG signals can be used for real-time estimation of the motion intention of human body, e.g., the current joint angle status. On the other hand, however, the process of the mass EMG data, which are captured instantaneously from skin surface, challenges the state-of-the-art technology. Because its non-stationary and randomness, it is difficult to extract the valuable and stable features from the raw EMG signals. This paper investigates into the learning process of high dimensional EMG signals with a hierarchical mechanism that projects the original data into a lower feature space to achieve a local refined mapping from the EMG signals to the motion states of the human body. This hierarchically projected regression algorithm constructs incrementally a tree-based knowledge library, whose components represent local regression models. The components will be retrieved online efficiently and contribute to the estimation of the motion states. A great number of experiments are carried out to evaluate the accuracy of this novel algorithm. [ABSTRACT FROM AUTHOR]

Similarity measurement of lung nodules is a critical component in content-based image retrieval (CBIR), which can be useful in differentiating between benign and malignant lung nodules on computer tomography (CT). This paper proposes a new two-step CBIR scheme (TSCBIR) for computer-aided diagnosis of lung nodules. Two similarity metrics, semantic relevance and visual similarity, are introduced to measure the similarity of different nodules. The first step is to search for K most similar reference ROIs for each queried ROI with the semantic relevance metric. The second step is to weight each retrieved ROI based on its visual similarity to the queried ROI. The probability is computed to predict the likelihood of the queried ROI depicting a malignant lesion. In order to verify the feasibility of the proposed algorithm, a lung nodule dataset including 366 nodule regions of interest (ROIs) is assembled from LIDC-IDRI lung images on CT scans. Three groups of texture features are implemented to represent a nodule ROI. Our experimental results on the assembled lung nodule dataset show good performance improvement over existing popular classifiers. [ABSTRACT FROM AUTHOR]

Powerful non-invasive imaging technologies like computed tomography (CT), ultrasound, and magnetic resonance imaging (MRI) are used daily by medical professionals to diagnose and treat patients. While 2D slice viewers have long been the standard, many tools allowing 3D representations of digital medical data are now available. The newest imaging advancement, functional MRI (fMRI) technology, has changed medical imaging from viewing static to dynamic physiology (4D) over time, particularly to study brain activity. Add this to the rapid adoption of mobile devices for everyday work and the need to visualize fMRI data on tablets or smartphones arises. However, there are few mobile tools available to visualize 3D MRI data, let alone 4D fMRI data. Building volume rendering tools on mobile devices to visualize 3D and 4D medical data is challenging given the limited computational power of the devices. This paper describes research that explored the feasibility of performing real-time 3D and 4D volume raycasting on a tablet device. The prototype application was tested on a 9.7' iPad Pro using two different fMRI datasets of brain activity. The results show that mobile raycasting is able to achieve between 20 and 40 frames per second for traditional 3D datasets, depending on the sampling interval, and up to 9 frames per second for 4D data. While the prototype application did not always achieve true real-time interaction, these results clearly demonstrated that visualizing 3D and 4D digital medical data is feasible with a properly constructed software framework. [ABSTRACT FROM AUTHOR]

Epilepsy is a serious chronic neurological disorder, which affects more than 50 million people worldwide, and automatic seizure detection on EEG recordings is extremely required in the diagnosis and monitoring of epilepsy. This paper presents a novel seizure detection method using sparse representation-based Earth Mover's Distance (SR-EMD). In the proposed algorithm, wavelet decomposition is executed on the original EEG recordings with five scales, and the scales 3, 4 and 5 are selected to structure the distributions of EEG signals. Then, the Gaussian mixture models (GMMs) of EEG signals are estimated and the distances between GMMs are computed using SR-EMD as EEG features. After that, EEG features are sent to Bayesian linear discriminant analysis classifier for classification. To improve the detection accuracy, the post-processing procedure is employed finally. The long-term intracranial EEG dataset with 21 patients is used to evaluate the performance of the method, and the satisfactory sensitivity of 93.54 %, specificity of 97.57 % and false detection rate of 0.223/h are achieved. The results indicate that SR-EMD is more effective and efficient than the conventional Earth Mover's Distance (EMD). Moreover, the good performance and fast speed of this algorithm make it suitable for the real-time seizure monitoring application. [ABSTRACT FROM AUTHOR]

Meniscal tear is one of the prevalent knee disorders among young athletes and the aging population, and requires correct diagnosis and surgical intervention, if necessary. Not only the errors followed by human intervention but also the obstacles of manual meniscal tear detection highlight the need for automatic detection techniques. This paper presents a type-2 fuzzy expert system for meniscal tear diagnosis using PD magnetic resonance images (MRI). The scheme of the proposed type-2 fuzzy image processing model is composed of three distinct modules: Pre-processing, Segmentation, and Classification. λ-nhancement algorithm is used to perform the pre-processing step. For the segmentation step, first, Interval Type-2 Fuzzy C-Means (IT2FCM) is applied to the images, outputs of which are then employed by Interval Type-2 Possibilistic C-Means (IT2PCM) to perform post-processes. Second stage concludes with re-estimation of ' η' value to enhance IT2PCM. Finally, a Perceptron neural network with two hidden layers is used for Classification stage. The results of the proposed type-2 expert system have been compared with a well-known segmentation algorithm, approving the superiority of the proposed system in meniscal tear recognition. [ABSTRACT FROM AUTHOR]

Breast cancer is one of the leading causes of mortality in the world and it occurs in high frequency among women that carries away many lives. To detect cancer, extraction or segmentation of lesions/tumors is required. Segmentation process is very crucial if the mammogram images are blurred or low contrast. This paper suggests a novel clustering approach for segmenting lesions/tumors in the mammogram images using Atanassov's intuitionistic fuzzy set theory. The algorithm initially converts an image to an intuitionistic fuzzy image using a novel intuitionistic fuzzy generator. From the intuitionistic fuzzy image, two membership intervals are computed. Then, using Zadeh's min t-conorm, a new membership function is computed. Using the new membership function, an interval type 2 fuzzy image is constructed. Two types of distance functions are used in clustering—intuitionistic fuzzy divergence and a fuzzy exponential type distance function. Further, in each iteration, membership matrix is updated using a hesitation degree and a clustered image is obtained. Tumors/lesions are then segmented from the clustered image. The proposed method is compared with existing methods both quantitatively and qualitatively and it is observed that the proposed method performs better than the existing methods. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI)-assisted PET imaging is emerging as a promising tool for the diagnosis of Parkinson's disease (PD). We aim to systematically review the diagnostic accuracy of AI-assisted PET in detecting PD. The Ovid MEDLINE, Ovid Embase, Web of Science, and IEEE Xplore databases were systematically searched for related studies that developed an AI algorithm in PET imaging for diagnostic performance from PD and were published by August 17, 2023. Binary diagnostic accuracy data were extracted for meta-analysis to derive outcomes of interest: area under the curve (AUC). 23 eligible studies provided sufficient data to construct contingency tables that allowed the calculation of diagnostic accuracy. Specifically, 11 studies were identified that distinguished PD from normal control, with a pooled AUC of 0.96 (95% CI: 0.94–0.97) for presynaptic dopamine (DA) and 0.90 (95% CI: 0.87–0.93) for glucose metabolism (18F-FDG). 13 studies were identified that distinguished PD from the atypical parkinsonism (AP), with a pooled AUC of 0.93 (95% CI: 0.91 − 0.95) for presynaptic DA, 0.79 (95% CI: 0.75–0.82) for postsynaptic DA, and 0.97 (95% CI: 0.96–0.99) for 18F-FDG. Acceptable diagnostic performance of PD with AI algorithms-assisted PET imaging was highlighted across the subgroups. More rigorous reporting standards that take into account the unique challenges of AI research could improve future studies. [ABSTRACT FROM AUTHOR]

The main objective of the paper is to implement Savitzky Golay Smoothing Filter (SGSF) so as to apply in pre-processing of real time smart medical diagnostic systems. As very important information of EEG and ECG waveforms lies in the peak of the signal, hence it becomes absolutely necessary to filter noise and artifacts from the signal. The implemented filter should be able to reject the noise efficiently along with the least distortion from the original signal. The shape preserving characteristics of the filter are determined by introducing different noise levels in the signal. The designed filter is tested on synthetic signals of EEG and ECG by adding different types of noise and the performance is analysed on various parameters, i.e., SNR, SSNR, SNRI, MSE, COR and signal distortion of the final output. The smoothing performance comparison of SGSF with the most commonly used Moving Average Filter (MAF) proves that SGSF is more efficient. Hence it is suggested that MAF can be replaced by SGSF. For real time issues, it is further implemented on reconfigurable architectures so as to achieve high speed, low cost, low power consumption and less area. Therefore SGSF is realized on FPGA platform to combine the advantages of both. Real time EEG and ECG signals are also considered for experimentation. The experimental results show that the proposed methodology (FPGA-SGSF) significantly reduces the processing time and preserves the actual features of the signal. [ABSTRACT FROM AUTHOR]

Content-based medical image retrieval (CBMIR) is a powerful resource to improve differential computer-aided diagnosis. The major problem with CBMIR applications is the semantic gap, a situation in which the system does not follow the users' sense of similarity. This gap can be bridged by the adequate modeling of similarity queries, which ultimately depends on the combination of feature extractor methods and distance functions. In this study, such combinations are referred to as perceptual parameters, as they impact on how images are compared. In a CBMIR, the perceptual parameters must be manually set by the users, which imposes a heavy burden on the specialists; otherwise, the system will follow a predefined sense of similarity. This paper presents a novel approach to endow a CBMIR with a proper sense of similarity, in which the system defines the perceptual parameter depending on the query element. The method employs ensemble strategy, where an extreme learning machine acts as a meta-learner and identifies the most suitable perceptual parameter according to a given query image. This parameter defines the search space for the similarity query that retrieves the most similar images. An instance-based learning classifier labels the query image following the query result set. As the concept implementation, we integrated the approach into a mammogram CBMIR. For each query image, the resulting tool provided a complete second opinion, including lesion class, system certainty degree, and set of most similar images. Extensive experiments on a large mammogram dataset showed that our proposal achieved a hit ratio up to 10% higher than the traditional CBMIR approach without requiring external parameters from the users. Our database-driven solution was also up to 25% faster than content retrieval traditional approaches. [ABSTRACT FROM AUTHOR]

Early and accurate diagnosis of Parkinson's disease (PD) remains challenging. Neuropathological studies using brain bank specimens have estimated that a large percentages of clinical diagnoses of PD may be incorrect especially in the early stages. In this paper, a comprehensive computer model is presented for the diagnosis of PD based on motor, non-motor, and neuroimaging features using the recently-developed enhanced probabilistic neural network (EPNN). The model is tested for differentiating PD patients from those with scans without evidence of dopaminergic deficit (SWEDDs) using the Parkinson's Progression Markers Initiative (PPMI) database, an observational, multi-center study designed to identify PD biomarkers for diagnosis and disease progression. The results are compared to four other commonly-used machine learning algorithms: the probabilistic neural network (PNN), support vector machine (SVM), k-nearest neighbors (k-NN) algorithm, and classification tree (CT). The EPNN had the highest classification accuracy at 92.5 % followed by the PNN (91.6 %), k-NN (90.8 %) and CT (90.2 %). The EPNN exhibited an accuracy of 98.6 % when classifying healthy control (HC) versus PD, higher than any previous studies. [ABSTRACT FROM AUTHOR]

Breast cancer is becoming a leading death of women all over the world; clinical experiments demonstrate that early detection and accurate diagnosis can increase the potential of treatment. In order to improve the breast cancer diagnosis precision, this paper presents a novel automated segmentation and classification method for mammograms. We conduct the experiment on both DDSM database and MIAS database, firstly extract the region of interests (ROIs) with chain codes and using the rough set (RS) method to enhance the ROIs, secondly segment the mass region from the location ROIs with an improved vector field convolution (VFC) snake and following extract features from the mass region and its surroundings, and then establish features database with 32 dimensions; finally, these features are used as input to several classification techniques. In our work, the random forest is used and compared with support vector machine (SVM), genetic algorithm support vector machine (GA-SVM), particle swarm optimization support vector machine (PSO-SVM), and decision tree. The effectiveness of our method is evaluated by a comprehensive and objective evaluation system; also, Matthew's correlation coefficient (MCC) indicator is used. Among the state-of-the-art classifiers, our method achieves the best performance with best accuracy of 97.73 %, and the MCC value reaches 0.8668 and 0.8652 in unique DDSM database and both two databases, respectively. Experimental results prove that the proposed method outperforms the other methods; it could consider applying in CAD systems to assist the physicians for breast cancer diagnosis. [ABSTRACT FROM AUTHOR]

In the medical literature, promising results regarding accuracy of medical AI are presented as claims for its potential to increase efficiency. This elision of concepts is misleading and incorrect. First, the promise that AI will reduce human workload rests on a too narrow assessment of what constitutes workload in the first place. Human operators need new skills and deal with new responsibilities, these systems need an elaborate infrastructure and support system that all contribute to an increased amount of human work and short-term efficiency wins may become sources of long-term inefficiency. Second, for the realization of increased efficiency, the human-side of technology implementation is determinate. Human knowledge, competencies and trust can foster or undermine efficiency. We conclude that is important to remain conscious and critical about how we talk about expected benefits of AI, especially when referring to systemic changes based on single studies. [ABSTRACT FROM AUTHOR]

Machine learning has immense potential to enhance diagnostic and intervention research in the behavioral sciences, and may be especially useful in investigations involving the highly prevalent and heterogeneous syndrome of autism spectrum disorder. However, use of machine learning in the absence of clinical domain expertise can be tenuous and lead to misinformed conclusions. To illustrate this concern, the current paper critically evaluates and attempts to reproduce results from two studies (Wall et al. in Transl Psychiatry 2(4):e100, ; PloS One 7(8), ) that claim to drastically reduce time to diagnose autism using machine learning. Our failure to generate comparable findings to those reported by Wall and colleagues using larger and more balanced data underscores several conceptual and methodological problems associated with these studies. We conclude with proposed best-practices when using machine learning in autism research, and highlight some especially promising areas for collaborative work at the intersection of computational and behavioral science. [ABSTRACT FROM AUTHOR]

The article presents a study which described the use of modified convolutional neural network DenseNet to improve accuracy of pneumonia classification. Topics include improvements made to DenseNet, performance of different improvements in DenseNet121, and comparison of the performance of different models.

We present a novel algorithm that is able to generate deep synthetic COVID-19 pneumonia CT scan slices using a very small sample of positive training images in tandem with a larger number of normal images. This generative algorithm produces images of sufficient accuracy to enable a DNN classifier to achieve high classification accuracy using as few as 10 positive training slices (from 10 positive cases), which to the best of our knowledge is one order of magnitude fewer than the next closest published work at the time of writing. Deep learning with extremely small positive training volumes is a very difficult problem and has been an important topic during the COVID-19 pandemic, because for quite some time it was difficult to obtain large volumes of COVID-19-positive images for training. Algorithms that can learn to screen for diseases using few examples are an important area of research. Furthermore, algorithms to produce deep synthetic images with smaller data volumes have the added benefit of reducing the barriers of data sharing between healthcare institutions. We present the cycle-consistent segmentation-generative adversarial network (CCS-GAN). CCS-GAN combines style transfer with pulmonary segmentation and relevant transfer learning from negative images in order to create a larger volume of synthetic positive images for the purposes of improving diagnostic classification performance. The performance of a VGG-19 classifier plus CCS-GAN was trained using a small sample of positive image slices ranging from at most 50 down to as few as 10 COVID-19-positive CT scan images. CCS-GAN achieves high accuracy with few positive images and thereby greatly reduces the barrier of acquiring large training volumes in order to train a diagnostic classifier for COVID-19. [ABSTRACT FROM AUTHOR]

Chest radiography is the modality of choice for the identification of rib fractures in young children and there is value for the development of computer-aided rib fracture detection in this age group. However, the automated identification of rib fractures on chest radiographs can be challenging due to the need for high spatial resolution in deep learning frameworks. A patch-based deep learning algorithm was developed to automatically detect rib fractures on frontal chest radiographs in children under 2 years old. A total of 845 chest radiographs of children 0–2 years old (median: 4 months old) were manually segmented for rib fractures by radiologists and served as the ground-truth labels. Image analysis utilized a patch-based sliding-window technique, to meet the high-resolution requirements for fracture detection. Standard transfer learning techniques used ResNet-50 and ResNet-18 architectures. Area-under-curve for precision-recall (AUC-PR) and receiver-operating-characteristic (AUC-ROC), along with patch and whole-image classification metrics, were reported. On the test patches, the ResNet-50 model showed AUC-PR and AUC-ROC of 0.25 and 0.77, respectively, and the ResNet-18 showed an AUC-PR of 0.32 and AUC-ROC of 0.76. On the whole-radiograph level, the ResNet-50 had an AUC-ROC of 0.74 with 88% sensitivity and 43% specificity in identifying rib fractures, and the ResNet-18 had an AUC-ROC of 0.75 with 75% sensitivity and 60% specificity in identifying rib fractures. This work demonstrates the utility of patch-based analysis for detection of rib fractures in children under 2 years old. Future work with large cohorts of multi-institutional data will improve the generalizability of these findings to patients with suspicion of child abuse. [ABSTRACT FROM AUTHOR]

In this paper, an automatic computer-aided detection system for breast magnetic resonance imaging (MRI) tumour segmentation will be presented. The study is focused on tumour segmentation using the modified automatic seeded region growing algorithm with a variation of the automated initial seed and threshold selection methodologies. Prior to that, some pre-processing methodologies are involved. Breast skin is detected and deleted using the integration of two algorithms, namely the level set active contour and morphological thinning. The system is applied and tested on 40 test images from the RIDER breast MRI dataset, the results are evaluated and presented in comparison to the ground truths of the dataset. The analysis of variance (ANOVA) test shows that there is a statistically significance in the performance compared to the previous segmentation approaches that have been tested on the same dataset where ANOVA p values for the evaluation measures' results are less than 0.05, such as: relative overlap ( p = 0.0002), misclassification rate ( p = 0.045), true negative fraction ( p = 0.0001) and sum of true volume fraction ( p = 0.0001). [ABSTRACT FROM AUTHOR]

In clinical diagnosis of nasopharyngeal carcinoma (NPC) lesion, clinicians are often required to delineate boundaries of NPC on a number of tumor-bearing magnetic resonance images, which is a tedious and time-consuming procedure highly depending on expertise and experience of clinicians. Computer-aided tumor segmentation methods (either contour-based or region-based) are necessary to alleviate clinicians' workload. For contour-based methods, a minimal user interaction to draw an initial contour inside or outside the tumor lesion for further curve evolution to match the tumor boundary is preferred, but parameters within most of these methods require manual adjustment, which is technically burdensome for clinicians without specific knowledge. Therefore, segmentation methods with a minimal user interaction as well as automatic parameters adjustment are often favored in clinical practice. In this paper, two region-based methods with parameters learning are introduced for NPC segmentation. Two hundred fifty-three MRI slices containing NPC lesion are utilized for evaluating the performance of the two methods, as well as being compared with other similar region-based tumor segmentation methods. Experimental results demonstrate the superiority of adopting learning in the two introduced methods. Also, they achieve comparable segmentation performance from a statistical point of view. [ABSTRACT FROM AUTHOR]

Medical image registration is an important component of computer-aided diagnosis system in diagnostics, therapy planning, and guidance of surgery. Because of its low signal/noise ratio (SNR), ultrasound (US) image registration is a difficult task. In this paper, a fully automatic non-rigid image registration algorithm based on demons algorithm is proposed for registration of ultrasound images. In the proposed method, an 'inertia force' derived from the local motion trend of pixels in a Moore neighborhood system is produced and integrated into optical flow equation to estimate the demons force, which is helpful to handle the speckle noise and preserve the geometric continuity of US images. In the experiment, a series of US images and several similarity measure metrics are utilized for evaluating the performance. The experimental results demonstrate that the proposed method can register ultrasound images efficiently, robust to noise, quickly and automatically. [ABSTRACT FROM AUTHOR]

Mammography is the most efficient technique for detecting and diagnosing breast cancer. Clusters of microcalcifications have been mainly targeted as a reliable early sign of breast cancer and their earliest detection is essential to reduce the probability of mortality rate. Since the size of microcalcifications is very tiny and may be overlooked by the observing radiologist, we have developed a Computer Aided Diagnosis system for automatic and accurate cluster detection. A three-phased novel approach is presented in this paper. Firstly, regions of interest that corresponds to microcalcifications are identified. This can be achieved by analyzing the bandpass coefficients of the mammogram image. The suspicious regions are passed to the second phase, in which the nodular structured microcalcifications are detected based on eigenvalues of second order partial derivatives of the image and microcalcification pixels are segmented out by exploiting the foveal segmentation in multiscale analysis. Finally, by combining the responses coming out from the second order partial derivatives and the foveal method, potential microcalcifications are detected. The detection performance of the proposed method has been evaluated by using 370 mammograms. The detection method has a TP ratio of 97.76 % with 0.68 false positives per image. We have examined the performance of our computerized scheme using free-response operating characteristics curve. [ABSTRACT FROM AUTHOR]

Due to the complex topological structure of the coronary artery and the uneven distribution of the contrast agent, the angiography images are inevitably blurred and has low contrast, which causes great difficulty in process of segmentation. For this problem, a two-steps segmentation algorithm based on Hessian matrix and level set is proposed in this paper. Firstly, potential blood vessels of coronary images are preliminary extracted via Hessian matrix eigenvalues feature vectors of the geometric features and the response function. Then a novel regularization and area constraint is introduced into the local data energy fitting functional. Finally, the precision of Coronary Artery image is obtained in the evolution of the level set function. Experiments show that our proposed algorithm has better performance to these comparison segmentation algorithms. [ABSTRACT FROM AUTHOR]

Aiming at the problem of low accuracy of classification learning algorithm caused by serious imbalance of sample set in medical diagnostic application, this paper proposes a distribution-sensitive oversampling algorithm for imbalanced data. The algorithm accurately divides the minority samples into noise samples, unstable samples, boundary samples and stable samples according to the location of the minority samples. Different samples are processed differently to select the most suitable sample for the synthesis of new samples. In the case of sample synthesis, a distribution-sensitive sample synthesis method is adopted. Different sample synthesis methods are selected according to their different distance from the surrounding minority samples, so as to ensure that the newly synthesized samples have the same characteristics with the original minority samples. The real medical diagnostic data test shows that this algorithm improves the accuracy rate of classification learning algorithm compared with the existing sampling algorithms, especially for the accuracy rate and recall rate of minority classes. [ABSTRACT FROM AUTHOR]

Cholangiocarcinoma, cancer of the bile ducts, is often diagnosed via magnetic resonance cholangiopancreatography (MRCP). Due to low resolution, noise and difficulty is actually seeing the tumor in the images, especially by examining only a single image, there has been very little development of automated systems for cholangiocarcinoma diagnosis. This paper presents a computer-aided diagnosis (CAD) system for the automated preliminary detection of the tumor using a single MRCP image. The multi-stage system employs algorithms and techniques that correspond to the radiological diagnosis characteristics employed by doctors. A popular artificial neural network, the multi-layer perceptron (MLP), is used for decision making to differentiate images with cholangiocarcinoma from those without. The test results achieved was 94% when differentiating only healthy and tumor images, and 88% in a robust multi-disease test where the system had to identify the tumor images from a large set of images containing common biliary diseases. [ABSTRACT FROM AUTHOR]

A new application, Fusion Viewer, available for free, has been designed and implemented with a modular object-oriented design. The viewer provides both traditional and novel tools to fuse 3D data sets such as CT (computed tomography), MRI (magnetic resonance imaging), PET (positron emission tomography), and SPECT (single photon emission tomography) of the same subject, to create maximum intensity projections (MIP) and to adjust dynamic range. In many situations, it is desirable and advantageous to acquire biomedical images in more than one modality. For example, PET can be used to acquire functional data, whereas MRI can be used to acquire morphological data. In some situations, a side-by-side comparison of the images provides enough information, but in most of the cases it may be necessary to have the exact spatial relationship between the modalities presented to the observer. To accomplish this task, the images need to first be registered and then combined (fused) to create a single image. In this paper, we discuss the options for performing such fusion in the context of multimodal breast imaging. Additionally, a novel spline-based dynamic range technique is presented in detail. It has the advantage of obtaining a high level of contrast in the intensity range of interest without discarding the intensity information outside of this range while maintaining a user interface similar to the standard window/level windowing procedure. [ABSTRACT FROM AUTHOR]

This paper proposes a detection scheme for identifying stones in the biliary tract of the body, which is examined using magnetic resonance cholangiopancreatography (MRCP), a sequence of magnetic resonance imaging targeted at the pancreatobiliary region of the abdomen. The scheme enhances the raw 2D thick slab MRCP images and extracts the biliary structure in the images using a segment-based region-growing approach. Detection of stones is scoped within this extracted structure, by highlighting possible stones. A trained feedforward artificial neural network uses selected features of size and average segment intensity as its input to detect possible stones in MRCP images and eliminate false stone-like objects. The proposed scheme achieved satisfactory results in tests of clinical MRCP thick slab images, indicating potential for implementation in computer-aided diagnosis systems for the liver. [ABSTRACT FROM AUTHOR]

Tremor is a clinical feature characterized by oscillations of a part of the body. The detection and study of tremor is an important step in investigations seeking to explain underlying control strategies of the central nervous system under natural (or physiological) and pathological conditions. It is well established that tremorous activity is composed of deterministic and stochastic components. For this reason, the use of digital signal processing techniques (DSP) which take into account the nonlinearity and nonstationarity of such signals may bring new information into the signal analysis which is often obscured by traditional linear techniques (e.g. Fourier analysis). In this context, this paper introduces the application of the empirical mode decomposition (EMD) and Hilbert spectrum (HS), which are relatively new DSP techniques for the analysis of nonlinear and nonstationary time-series, for the study of tremor. Our results, obtained from the analysis of experimental signals collected from 31 patients with different neurological conditions, showed that the EMD could automatically decompose acquired signals into basic components, called intrinsic mode functions (IMFs), representing tremorous and voluntary activity. The identification of a physical meaning for IMFs in the context of tremor analysis suggests an alternative and new way of detecting tremorous activity. These results may be relevant for those applications requiring automatic detection of tremor. Furthermore, the energy of IMFs was visualized as a function of time and frequency by means of the HS. This analysis showed that the variation of energy of tremorous and voluntary activity could be distinguished and characterized on the HS. Such results may be relevant for those applications aiming to identify neurological disorders. In general, both the HS and EMD demonstrated to be very useful to perform objective analysis of any kind of tremor and can therefore be potentially used to perform functional assessment. [ABSTRACT FROM AUTHOR]

The use of artificial intelligence (AI) has the potential to improve the assessment of lesions suspicious of melanoma, but few clinical studies have been conducted. We validated the accuracy of an open-source, non-commercial AI algorithm for melanoma diagnosis and assessed its potential impact on dermatologist decision-making. We conducted a prospective, observational clinical study to assess the diagnostic accuracy of the AI algorithm (ADAE) in predicting melanoma from dermoscopy skin lesion images. The primary aim was to assess the reliability of ADAE's sensitivity at a predefined threshold of 95%. Patients who had consented for a skin biopsy to exclude melanoma were eligible. Dermatologists also estimated the probability of melanoma and indicated management choices before and after real-time exposure to ADAE scores. All lesions underwent biopsy. Four hundred thirty-five participants were enrolled and contributed 603 lesions (95 melanomas). Participants had a mean age of 59 years, 54% were female, and 96% were White individuals. At the predetermined 95% sensitivity threshold, ADAE had a sensitivity of 96.8% (95% CI: 91.1–98.9%) and specificity of 37.4% (95% CI: 33.3–41.7%). The dermatologists' ability to assess melanoma risk significantly improved after ADAE exposure (AUC 0.7798 vs. 0.8161, p = 0.042). Post-ADAE dermatologist decisions also had equivalent or higher net benefit compared to biopsying all lesions. We validated the accuracy of an open-source melanoma AI algorithm and showed its theoretical potential for improving dermatology experts' ability to evaluate lesions suspicious of melanoma. Larger randomized trials are needed to fully evaluate the potential of adopting this AI algorithm into clinical workflows. [ABSTRACT FROM AUTHOR]

The assessment of bone age is important for evaluating child development, optimizing the treatment for endocrine diseases, etc. And the well-known Tanner-Whitehouse (TW) clinical method improves the quantitative description of skeletal development based on setting up a series of distinguishable stages for each bone individually. However, the assessment is affected by rater variability, which makes the assessment result not reliable enough in clinical practice. The main goal of this work is to achieve a reliable and accurate skeletal maturity determination by proposing an automated bone age assessment method called PEARLS, which is based on the TW3-RUS system (analysis of the radius, ulna, phalanges, and metacarpal bones). The proposed method comprises the point estimation of anchor (PEA) module for accurately localizing specific bones, the ranking learning (RL) module for producing a continuous stage representation of each bone by encoding the ordinal relationship between stage labels into the learning process, and the scoring (S) module for outputting the bone age directly based on two standard transform curves. The development of each module in PEARLS is based on different datasets. Finally, corresponding results are presented to evaluate the system performance in localizing specific bones, determining the skeletal maturity stage, and assessing the bone age. The mean average precision of point estimation is 86.29%, the average stage determination precision is 97.33% overall bones, and the average bone age assessment accuracy is 96.8% within 1 year for the female and male cohorts. [ABSTRACT FROM AUTHOR]

The paper investigates quantitative differences in the signal characteristics of ventricular fibrillation (VF) and other cardiac arrhythmias. The analysis procedure comprises two steps: calculation of a short-term autocorrelation function (ACF) followed by a regression test on a plot of peak magnitudes of the ACF against lag values (the ACF/lag plot). We detect VF by testing the hypothesis that the ACF/lag plot of VF does not pass a linear regression test. Analysis of 31 separate episodes (of VF and other ventricular arrhythmias), each comprising three successive segments of 1·5s each produced the following results: (1) 100 per cent sensitivity (Se), 62 per cent specificity (Sp) and 74 per cent test efficiency (TE) after analysis of the first segment; (2) 100 per cent Se, 86 per cent Sp and 90 per cent TE after the second segment; and (3) 100 per cent Se, 100 per cent Sp and 100 per cent TE after the third segment. This method quantifies the notion that VF signals are nonperiodic with a random amplitude distribution, whereas ventricular tachycardia (VT) signals are usually periodic with more uniform amplitude distributions. Accurate discrimination and identification of VF can be very important in intensive-care settings, as well as in the design of automatic cardioverters and defibrillators. [ABSTRACT FROM AUTHOR]

Diabetic retinopathy is the predominant cause of visual impairment in diabetes patients. The early detection process can prevent diabetes patients from severe situations. The progression of diabetic retinopathy is determined by analyzing the fundus images, thus determining whether they are affected by exudates or not. The manual detection process is laborious and requires more time and there is a possibility of wrong predictions. Therefore, this research focuses on developing an automated decision-making system. To predict the existence of exudates in fundus images, we developed a novel technique named a hybrid convolutional neural network-recurrent neural network along with the artificial humming bird optimization (HCNNRNN-AHB) approach. The proposed HCNNRNN-AHB technique effectively detects and classifies the fundus image into two categories namely exudates and non-exudates. Before the classification process, the optic discs are removed to prevent false alarms using Hough transform. Then, to differentiate the exudates and non-exudates, color and texture features are extracted from the fundus images. The classification process is then performed using the HCNNRNN-AHB approach which is the combination of CNN and RNN frameworks along with the AHB optimization algorithm. The AHB algorithm is introduced with this framework to optimize the parameters of CNN and RNN thereby enhancing the prediction accuracy of the model. Finally, the simulation results are performed to analyze the effectiveness of the proposed method using different performance metrics such as accuracy, sensitivity, specificity, F-score, and area under curve score. The analytic result reveals that the proposed HCNNRNN-AHB approach achieves a greater prediction and classification accuracy of about 97.4%. [ABSTRACT FROM AUTHOR]

In large clinical centers a small subset of patients present with hydrocephalus that requires surgical treatment. We aimed to develop a screening tool to detect such cases from the head MRI with performance comparable to neuroradiologists. We leveraged 496 clinical MRI exams collected retrospectively at a single clinical site from patients referred for any reason. This diagnostic dataset was enriched to have 259 hydrocephalus cases. A 3D convolutional neural network was trained on 16 manually segmented exams (ten hydrocephalus) and subsequently used to automatically segment the remaining 480 exams and extract volumetric anatomical features. A linear classifier of these features was trained on 240 exams to detect cases of hydrocephalus that required treatment with surgical intervention. Performance was compared to four neuroradiologists on the remaining 240 exams. Performance was also evaluated on a separate screening dataset of 451 exams collected from a routine clinical population to predict the consensus reading from four neuroradiologists using images alone. The pipeline was also tested on an external dataset of 31 exams from a 2nd clinical site. The most discriminant features were the Magnetic Resonance Hydrocephalic Index (MRHI), ventricle volume, and the ratio between ventricle and brain volume. At matching sensitivity, the specificity of the machine and the neuroradiologists did not show significant differences for detection of hydrocephalus on either dataset (proportions test, p > 0.05). ROC performance compared favorably with the state-of-the-art (AUC 0.90–0.96), and replicated in the external validation. Hydrocephalus cases requiring treatment can be detected automatically from MRI in a heterogeneous patient population based on quantitative characterization of brain anatomy with performance comparable to that of neuroradiologists. [ABSTRACT FROM AUTHOR]