Deep Learning Method for Rapid Simultaneous Multistructure Temporal Bone Segmentation.

SummaryWe developed and compared deep learning models to detect hip osteoarthritis on clinical CT. The CT-based summation images, CT-AP, that resemble X-ray radiographs can detect radiographic hip osteoarthritis and in the absence of large training data, a reliable deep learning model can be optimized by combining CT-AP and X-ray images.IntroductionIn this study, we aimed to investigate the applicability of deep learning (DL) to assess radiographic hip osteoarthritis (rHOA) on computed tomography (CT).MethodsThe study data consisted of 94 abdominopelvic clinical CTs and 5659 hip X-ray images collected from Cohort Hip and Cohort Knee (CHECK). The CT slices were sequentially summed to create radiograph-like 2-D images named CT-AP. X-ray and CT-AP images were classified as rHOA if they had osteoarthritic changes corresponding to Kellgren-Lawrence grade 2 or higher. The study data was split into 55% training, 30% validation, and 15% test sets. A pretrained ResNet18 was optimized for a classification task of rHOA vs. no-rHOA. Five models were trained using (1) X-rays, (2) downsampled X-rays, (3) combination of CT-AP and X-ray images, (4) combination of CT-AP and downsampled X-ray images, and (5) CT-AP images.ResultsAmongst the five models, Model-3 and Model-5 performed best in detecting rHOA from the CT-AP images. Model-3 detected rHOA on the test set of CT-AP images with a balanced accuracy of 82.2% and was able to discriminate rHOA from no-rHOA with an area under the receiver operating characteristic curve (ROC AUC) of 0.93 [0.75–0.99]. Model-5 detected rHOA on the test set at a balanced accuracy of 82.2% and classified rHOA from no-rHOA with an ROC AUC of 0.89 [0.67–0.97].ConclusionCT-based summation images that resemble radiographs can be used to detect rHOA. In addition, in the absence of large training data, a reliable DL model can be optimized by combining CT-AP and X-ray images.

Background Deep learning (DL) algorithms could improve the classification of ovarian tumors assessed with multimodal US. Purpose To develop DL algorithms for the automated classification of benign versus malignant ovarian tumors assessed with US and to compare algorithm performance to Ovarian-Adnexal Reporting and Data System (O-RADS) and subjective expert assessment for malignancy. Materials and Methods This retrospective study included consecutive women with ovarian tumors undergoing gray scale and color Doppler US from January 2019 to November 2019. Histopathologic analysis was the reference standard. The data set was divided into training (70%), validation (10%), and test (20%) sets. Algorithms modified from residual network (ResNet) with two fusion strategies (feature fusion [hereafter, DLfeature] or decision fusion [hereafter, DLdecision]) were developed. DL prediction of malignancy was compared with O-RADS risk categorization and expert assessment by area under the receiver operating characteristic curve (AUC) analysis in the test set. Results A total of 422 women (mean age, 46.4 years ± 14.8 [SD]) with 304 benign and 118 malignant tumors were included; there were 337 women in the training and validation data set and 85 women in the test data set. DLfeature had an AUC of 0.93 (95% CI: 0.85, 0.97) for classifying malignant from benign ovarian tumors, comparable with O-RADS (AUC, 0.92; 95% CI: 0.85, 0.97; P = .88) and expert assessment (AUC, 0.97; 95% CI: 0.91, 0.99; P = .07), and similar to DLdecision (AUC, 0.90; 95% CI: 0.82, 0.96; P = .29). DLdecision, DLfeature, O-RADS, and expert assessment achieved sensitivities of 92%, 92%, 92%, and 96%, respectively, and specificities of 80%, 85%, 89%, and 87%, respectively, for malignancy. Conclusion Deep learning algorithms developed by using multimodal US images may distinguish malignant from benign ovarian tumors with diagnostic performance comparable to expert subjective and Ovarian-Adnexal Reporting and Data System assessment. © RSNA, 2022 Online supplemental material is available for this article.

SummaryAccurate prediction of the solubility of chemical substances in solvents remains a challenge. The sparsity of high-quality solubility data is recognized as the biggest hurdle in the development of robust data-driven methods for practical use. Nonetheless, the effects of the quality and quantity of data on aqueous solubility predictions have not yet been scrutinized. In this study, the roles of the size and the quality of data sets on the performances of the solubility prediction models are unraveled, and the concepts of actual and observed performances are introduced. In an effort to curtail the gap between actual and observed performances, a quality-oriented data selection method, which evaluates the quality of data and extracts the most accurate part of it through statistical validation, is designed. Applying this method on the largest publicly available solubility database and using a consensus machine learning approach, a top-performing solubility prediction model is achieved.

Improving the performance of machine learning algorithms to overcome the curse of dimensionality while maintaining interpretability is still a challenging issue for researchers in artificial intelligence. Patch learning (PL), based on the improved adaptive network-based fuzzy inference system (ANFIS) and continuous local optimization for the input domain, is characterized by high accuracy. However, PL can only handle low-dimensional data set regression. Based on the parallel and serial ensembles, two deep patch learning algorithms with embedded adaptive fuzzy systems (DPLFSs) are proposed in this paper. First, using the maximum information coefficient (MIC) and Pearson's correlation coefficients for feature selection, the variables with the least relationship (linear or nonlinear) are excluded. Second, principal component analysis is used to reduce the complexity further of DPLFSs. Meanwhile, fuzzy C-means clustering is used to enhance the interpretability of DPLFSs. Then, an improved PL method is put forward for the training of each sub-fuzzy system in a fashion of bottom-up layer-by-layer, and finally, the structure optimization is performed to significantly improve the interpretability of DPLFSs. Experiments on several benchmark data sets show the advantages of a DPLFS: (1) it can handle medium-scale data sets; (2) it can overcome the curse of dimensionality faced by PL; (3) its precision and generalization are greatly improved; and (4) it can overcome the poor interpretability of deep learning networks. Compared with shallow and deep learning algorithms, DPLFSs have the advantages of interpretability, self-learning, and high precision. DPLFS1 is superior for medium-scale data; DPLFS2 is more efficient and effective for high-dimensional problems, has a faster convergence, and is more interpretable.

The aim of this study is to develop a predictive model utilizing deep learning and machine learning techniques that will inform clinical decision-making by predicting the 1-year postoperative recovery of patients with lumbar disk herniation. The clinical data of 470 inpatients who underwent tubular microdiscectomy (TMD) between January 2018 and January 2021 were retrospectively analyzed as variables. The dataset was randomly divided into a training set (n = 329) and a test set (n = 141) using a 10-fold cross-validation technique. Various deep learning and machine learning algorithms including Random Forests, Extreme Gradient Boosting, Support Vector Machines, Extra Trees, K-Nearest Neighbors, Logistic Regression, Light Gradient Boosting Machine, and MLP (Artificial Neural Networks) were employed to develop predictive models for the recovery of patients with lumbar disk herniation 1 year after surgery. The cure rate score of lumbar JOA score 1 year after TMD was used as an outcome indicator. The primary evaluation metric was the area under the receiver operating characteristic curve (AUC), with additional measures including decision curve analysis (DCA), accuracy, sensitivity, specificity, and others. The heat map of the correlation matrix revealed low inter-feature correlation. The predictive model employing both machine learning and deep learning algorithms was constructed using 15 variables after feature engineering. Among the eight algorithms utilized, the MLP algorithm demonstrated the best performance. Our study findings demonstrate that the MLP algorithm provides superior predictive performance for the recovery of patients with lumbar disk herniation 1 year after surgery.

This focus issue of Physiological Measurement follows the 38th Annual International Computing in Cardiology (CinC) Conference, hosted in Hangzhou, China in September 2011 by Zhejiang University. Each year, the NIH-sponsored PhysioNet resource (http://physionet.org/) runs an open competition lasting several months, aimed at encouraging the development of solutions to an unsolved or poorly solved problem in biomedicine, in most cases making use of relevant clinical and experimental data provided freely by PhysioNet. Participants in these annual challenges discuss their diverse approaches to the Challenge problems during dedicated scientific sessions at CinC. The topics of these PhysioNet/CinC Challenges range from physiologic signal processing and analysis to forecasting and modelling clinically important events and processes.

Deep learning algorithms can be used to design systems that report data on patients and deliver warnings to medical applications or electronic health information if there are changes in the patient's health. These systems could be created using deep Learning. This helps verify that patients get the proper effective care at the proper time for each specific patient. A healthcare decision support system was presented using the Internet of Things and deep learning methods. In the proposed system, we examined the capability of integrating deep learning technology into automatic diagnosis and IoT capabilities for faster message exchange over the Internet. We have selected the suitable Neural Network structure (number of best-hidden layers and activation function classes) to construct the e-health system. In addition, the e-health system relied on data from doctors to understand the Neural Network. In the validation method, the total evaluation of the proposed healthcare system for diagnostics provides dependability under various patient conditions. Based on evaluation and simulation findings, a dual hidden layer of feed-forward NN and its neurons store the tanh function more effectively than other NN. To overcome challenges, this study will integrate artificial intelligence with IoT. This study aims to determine the NN's optimal layer counts and activation function variations.

BackgroundNasopharyngeal carcinoma (NPC), an endemic malignancy in Southeast Asia and southern China, necessitates precise delineation of the gross tumor volume (GTV) for radiotherapy to optimize patient prognosis. Positron emission tomography (PET) imaging offers valuable metabolic insights to guide radiotherapy planning but is hampered by manual GTV segmentation, which is labor-intensive and prone to inter- and intra-observer variability. Conventional segmentation methods are inherently limited, and comparative evaluations of deep learning (DL) frameworks for PET-based primary NPC lesion segmentation remain scarce. Thus, this study aimed to optimize the delineation of primary NPC radiotherapy target volumes by leveraging PET-image-based DL segmentation technology, with the goal of enhancing both the precision and efficiency of lesion delineation.MethodsResearchers retrospectively collected PET imaging data from 212 NPC patients at the Affiliated Hospital of Guangdong Medical University. The patients were randomly divided into training (170 patients) and testing (42 patients) datasets. A radiation oncologist and a nuclear medicine physician collaboratively delineated the cancer lesion boundaries through consensus. After data preprocessing, three DL models (Res-Unet, Nn-Unet, and Nn-Former) were used to automatically segment the lesions. Training was based on the training dataset. During evaluation, the models’ segmentation performance was comprehensively assessed using Dice similarity coefficient (DSC) and Hausdorff distance (HD). A visual analysis of the results was also conducted to intuitively understand the models’ segmentation capabilities.ResultsIn the training set, Nn-Unet achieved the highest DSC of 0.869, whereas in the testing set, its DSC was 0.833. The DSC for Nn-Former hovered around 0.8 in both the training and testing sets. In contrast, Res-Unet demonstrated the lowest DSC values among the three models, particularly in the testing set (DSC =0.794). Statistical analysis revealed that the DSC of Nn-Unet was significantly higher than that of both Res-Unet and Nn-Former in the training set (P<0.01 for both comparisons). Regarding the 95% HD and average surface distance (ASD) values, Nn-Unet outperformed the other two models in both the training and testing sets. However, Res-Unet exhibited a much higher HD value in the testing set compared to the training set. The Loss curves for all models gradually decreased as training progressed, indicating that the models were learning relevant features of NPC lesions. The final Loss value for Res-Unet was approximately 0.7, whereas Nn-Unet and Nn-Former had final Loss values below 0.8.ConclusionsThe PET-image-based automatic segmentation model for the primary tumor of NPC established in this study demonstrates the clinical potential of Nn-Unet in primary lesion of NPC segmentation tasks.

Objectives:Rotator cuff tears (RCT) are common injuries that increase in frequency with age. Deep learning is a subfield of artificial intelligence that uses artificial neural networks to perform a variety of tasks, including image analysis. Several previous studies have investigated the utility of deep learning for identifying fatty infiltration, muscle atrophy, and tear size of the supraspinatus muscle on shoulder magnetic resonance imaging (MRI). However, limited data exists on the use of deep learning for image analysis to determine the presence of supraspinatus pathology versus normal anatomy on shoulder MRI. RadImageNet, a recently published database consisting of 1.35 million annotated computed tomography (CT), MRI, and ultrasound (US) images from greater than 130,000 patients, contains thousands of shoulder MRI images. No research to date has investigated whether deep learning algorithms can accurately detect supraspinatus pathology on MRIs in the RadImageNet database.The objective of the present study was to determine if deep learning algorithms can accurately differentiate shoulder MRI images as those with supraspinatus pathology versus normal anatomy in the RadImageNet database.Methods:The RadImageNet database was queried for all MRI images containing supraspinatus pathology. Both supraspinatus tears (partial and full thickness) and tendinosis images are categorized under the same “supraspinatus pathology” label in the database. In the comparison cohort with normal anatomy, coronal and sagittal images capturing the supraspinatus muscle were included. Although the supraspinatus was still visualized, all sagittal images medial to the glenoid were excluded to better represent the supraspinatus pathology images. The training/validation/test datasets were created using a random 80/10/10 split of the entire cohort. Data were pre-processed using standard data augmentation, including random cropping, rotation, and translation of images. ConvNeXt, a pre-trained deep learning model for the purposes of image analysis, was chosen as the base architecture for transfer learning to optimize both accuracy and computing speed. The ConvNeXt model was trained using training (N=4,937 images) and validation (N=619 images) sets for 15 epochs. Algorithm performance was assessed on an independent test cohort (N=619 images) not used during model training. Performance metrics included classification accuracy, sensitivity, specificity, and positive and negative predictive values. Model training was performed in PyTorch on an 8-gigabyte NIVIDIA Quadro M4000 Cloud Graphics Processing Unit.Results:A total of 5,241 shoulder MRIs with supraspinatus pathology and 932 without any pathology were obtained for comparison. The overall accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of the classifier on the independent test set was 98.9% (95% confidence interval: 97.7% – 99.5%), 98.7%, 100.0%, 100.0%, and 93.1%, respectively. A confusion matrix for model predictions on the test set is displayed in Figure 1. Interpretation plots displaying six examples of incorrect model predictions are shown in Figure 2. Class 1 and 2 designate images without pathology and those with supraspinatus pathology, respectively. All six images were cases where the model predicted “normal” when the ground truth label of the image was supraspinatus pathology. Figure 3 demonstrates an example of class activation mapping, which visually indicates the areas on an image that influenced the model prediction the most. Bright yellow coloration indicates highly influential regions whereas purple coloration corresponds to regions that were less influential. In Figure 3, which is an example image of supraspinatus pathology, one of the most influential regions appears to localize to the supraspinatus tendon.Conclusions:Deep learning is a viable method for differentiating supraspinatus pathology from normal anatomy on shoulder MRIs. The ConvNeXt model demonstrated excellent performance in predicting images with supraspinatus pathology on shoulder MRIs in the RadImageNet database. Future research using deep learning techniques to classify different rotator cuff tear types and sizes is warranted.

Accurate segmentation of the hippocampus head and body from MR images is routinely performed to examine the link between the hippocampus deformation and neurological diseases, such as Alzheimer's and epilepsy. State-of-the-art seminal segmentation methods (including hippocampus segmentation) are based on deep learning algorithms. Most studies focused on developing robust deep learning algorithms to achieve satisfactory performance in hippocampus body and head segmentation. A critical aspect that has been overlooked in these studies is the strategy adopted to train deep learning algorithms when there are two or more target structures. In this work, we examine which deep learning training strategies would be more effective. These strategies include simultaneous (parallel segmentation of the head and body), serial (first head and then body), independent, and attention-based training and segmentation of the target structures. To this end, the hippocampus dataset from the Decathlon challenge and a residual neural network (Resnet) were employed to compare the above-mentioned strategies for hippocampus head and body segmentation. The Dice similarity coefficient and Hausdorff distance were calculated for the outcome of each strategy versus the manually defined hippocampus head and body masks. The quantitative analysis of the outcomes of different training frameworks demonstrated the superior performance of the attention-based training framework with Dice index of 0.89±0.03 (body) and 0.88±0.04 (head) compared to simultaneous, serial, and independent training frameworks with Dice indices of 0.88±0.04 (body) and 0.87±0.04 (head), 0.88±0.04 (body) and 0.87±0.04 (head), and 0.88±0.04 (body) and 0.86±0.04 (head), respectively. The statistical analysis demonstrated the significantly superior performance of the attention-based training framework (p-value<0.0001). In conclusion, the attention-based training framework is recommended for multi-structure seminal segmentation.

ObjectiveTo develop and test a deep learning algorithm to automatically detect cortical tubers in magnetic resonance imaging (MRI), to explore the utility of deep learning in rare disorders with limited data, and to generate an open-access deep learning standalone application.MethodsT2 and FLAIR axial images with and without tubers were extracted from MRIs of patients with tuberous sclerosis complex (TSC) and controls, respectively. We trained three different convolutional neural network (CNN) architectures on a training dataset and selected the one with the lowest binary cross-entropy loss in the validation dataset, which was evaluated on the testing dataset. We visualized image regions most relevant for classification with gradient-weighted class activation maps (Grad-CAM) and saliency maps.Results114 patients with TSC and 114 controls were divided into a training set, a validation set, and a testing set. The InceptionV3 CNN architecture performed best in the validation set and was evaluated in the testing set with the following results: sensitivity: 0.95, specificity: 0.95, positive predictive value: 0.94, negative predictive value: 0.95, F1-score: 0.95, accuracy: 0.95, and area under the curve: 0.99. Grad-CAM and saliency maps showed that tubers resided in regions most relevant for image classification within each image. A stand-alone trained deep learning App was able to classify images using local computers with various operating systems.ConclusionThis study shows that deep learning algorithms are able to detect tubers in selected MRI images, and deep learning can be prudently applied clinically to manually selected data in a rare neurological disorder.

Background Machine learning (ML) algorithm support vector machine (SVM) performed better than Thrombolysis in Myocardial Infarction (TIMI) score for ASIAN STEMI patients. However, Deep Learning (DL) effectiveness in the multiethnic ASIAN population has yet to be determined. DL has automatic learning of the feature from a given dataset without the need to conduct feature selection. However, the selected features by the algorithm is black box. Identifying features associated with mortality is essential to recognize characteristics of patients with high risk for better patient management. Purpose To develop a DL algorithm for in-hospital mortality in multiethnic STEMI patients using predictors identified from the SVM algorithm. To investigate DL performance constructed using predictors from SVM feature extraction and expert-recommended predictors. Methods We constructed four algorithms; a) DL and SVM algorithms with predictors identified from the SVM variable importance b) DL and SVM using predictors based on expert recommendation. We used registry data from the National Cardiovascular Disease Database of 11397 patient's. Fifty parameters including demographics, cardiovascular risk, medications and clinical variables were considered. The Area under the curve (AUC) is the performance evaluation metric. Algorithms were validated against the TIMI and tested using the same validation data. SVM variable importance with backward elimination was used to select and rank important variables. Results DL algorithms outperform SVM and TIMI on the validation dataset; i) DL with SVM selected predictors (15 predictors, AUC = 0.97), ii) DL with expert-recommended predictors (16 predictors, AUC = 0.96), iii) SVM with selected predictors (15 predictors, AUC = 0.92), iv) SVM with expert-recommended predictors (AUC = 0.89) and TIMI (AUC = 0.82). Common predictors across SVM feature selection, expert-recommendation and TIMI are: age, heart rate, Killip class, fasting blood glucose, systolic blood pressure, comorbid diseases and ST-elevation. SVM feature selection also identified diuretics, PCI and pharmacotherapy drugs as predictors that improve mortality prediction in STEMI patients. Our findings suggest that the TIMI score underestimates patients risk of mortality. DL algorithm using selected predictors classified 35% of nonsurvival patients as high risk (risk probabilities &amp;gt;50%) compared to only 12.7% nonsurvival patients by TIMI (score &amp;gt;5) (Figure below). Conclusions In the ASIAN population, patients with STEMI can be better classified using the DL algorithm compared to the ML and TIMI score. Combining ML feature selection with DL allows the identification of distinct factors in a unique ASIAN population for better mortality prediction than relying solely on an expert recommendation as it is a very subjective approach. Continuous validation on population-specific algorithms using DL and ML is needed before implementing in a real clinical setting. Funding Acknowledgement Type of funding sources: Public grant(s) – National budget only. Main funding source(s): Technology Development Fund 1 TIMI performance on validation setDL performance on validation set

Deep learning has gained immense popularity in scientific computing, and its algorithms are widely used in complex problem-solving industries. Every deep learning algorithm use different types of neural networks to perform indented tasks. Deep learning (DL) algorithms have emerged from different machine learning and soft computing methodologies. Since then, a number of deep learning (DL) algorithms have been recently introduced in the scientific community and applied in various application fields. Today, the use of DLs has become indispensable due to their intelligence, effective learning, accuracy and reliability in model creation. However, a comprehensive list of DL algorithms has not yet been presented in the scientific literature. This article lists the most popular DL algorithms and their application areas. Deep learning uses ANN artificial neural networks to perform convoluted calculations on huge amounts of data. It is a type of machine learning based on the structure and function of the human brain. Deep learning algorithms train machines by learning from examples. Industries such as healthcare, e-commerce, entertainment and advertising often use deep learning.

BackgroundNailfold capillary microscopy is used for diagnostic purposes in rheumatology since many years. Abnormal nailfold capillaries are also listed in the 2013 ACR/EULAR classification criteria for systemic sclerosis (SSc) [1]....

Lattice degeneration and/or retinal breaks, defined as notable peripheral retinal lesions (NPRLs), are prone to evolving into rhegmatogenous retinal detachment which can cause severe visual loss. However, screening NPRLs is time-consuming and labor-intensive. Therefore, we aimed to develop and evaluate a deep learning (DL) system for automated identifying NPRLs based on ultra-widefield fundus (UWF) images. A total of 5,606 UWF images from 2,566 participants were used to train and verify a DL system. All images were classified by 3 experienced ophthalmologists. The reference standard was determined when an agreement was achieved among all 3 ophthalmologists, or adjudicated by another retinal specialist if disagreements existed. An independent test set of 750 images was applied to verify the performance of 12 DL models trained using 4 different DL algorithms (InceptionResNetV2, InceptionV3, ResNet50, and VGG16) with 3 preprocessing techniques (original, augmented, and histogram-equalized images). Heatmaps were generated to visualize the process of the best DL system in the identification of NPRLs. In the test set, the best DL system for identifying NPRLs achieved an area under the curve (AUC) of 0.999 with a sensitivity and specificity of 98.7% and 99.2%, respectively. The best preprocessing method in each algorithm was the application of original image augmentation (average AUC =0.996). The best algorithm in each preprocessing method was InceptionResNetV2 (average AUC =0.996). In the test set, 150 of 154 true-positive cases (97.4%) displayed heatmap visualization in the NPRL regions. A DL system has high accuracy in identifying NPRLs based on UWF images. This system may help to prevent the development of rhegmatogenous retinal detachment by early detection of NPRLs.