A hierarchical deep learning approach with transparency and interpretability based on small samples for glaucoma diagnosis.
Ontology highlight
ABSTRACT:
SUBMITTER: Xu Y
PROVIDER: S-EPMC7952384 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Enzymes are critical proteins in every organism. They speed up essential chemical reactions, help fight diseases, and have a wide use in the pharmaceutical and manufacturing industries. Wet lab experiments to figure out an enzyme's function are time consuming and expensive. Therefore, the need for computational approaches to address this problem are becoming necessary. Usually, an enzyme is extremely specific in performing its function. However, there exist enzymes that can perform multiple functions. A multi-functional enzyme has vast potential as it reduces the need to discover/use different enzymes for different functions. We propose an approach to predict a multi-functional enzyme's function up to the most specific fourth level of the hierarchy of the Enzyme Commission (EC) number. Previous studies can only predict the function of the enzyme till level 1. Using a dataset of 2,583 multi-functional enzymes, we achieved a hierarchical subset accuracy of 71.4% and a Macro F1 Score of 96.1% at the fourth level. The robustness of the network was further tested on a multi-functional isoforms dataset. Our method is broadly applicable and may be used to discover better enzymes. The web-server can be freely accessed at http://hecnet.cbrlab.org/.
| S-EPMC8376422 | biostudies-literature
Project description:PurposeTo investigate the suitability of multi-scale spatial information in 30o visual fields (VF), computed from a Convolutional Neural Network (CNN) classifier, for early-glaucoma vs. control discrimination.MethodTwo data sets of VFs acquired with the OCTOPUS 101 G1 program and the Humphrey Field Analyzer 24-2 pattern were subdivided into control and early-glaucomatous groups, and converted into a new image using a novel voronoi representation to train a custom-designed CNN so to discriminate between control and early-glaucomatous eyes. Saliency maps that highlight what regions of the VF are contributing maximally to the classification decision were computed to provide classification justification. Model fitting was cross-validated and average precision (AP) score performances were computed for our method, Mean Defect (MD), square-root of Loss Variance (sLV), their combination (MD+sLV), and a Neural Network (NN) that does not use convolutional features.ResultsCNN achieved the best AP score (0.874±0.095) across all test folds for one data set compared to others (MD = 0.869±0.064, sLV = 0.775±0.137, MD+sLV = 0.839±0.085, NN = 0.843±0.089) and the third best AP score (0.986 ±0.019) on the other one with slight difference from the other methods (MD = 0.986±0.023, sLV = 0.992±0.016, MD+sLV = 0.987±0.017, NN = 0.985±0.017). In general, CNN consistently led to high AP across different data sets. Qualitatively, computed saliency maps appeared to provide clinically relevant information on the CNN decision for individual VFs.ConclusionThe proposed CNN offers high classification performance for the discrimination of control and early-glaucoma VFs when compared with standard clinical decision measures. The CNN classification, aided by saliency visualization, may support clinicians in the automatic discrimination of early-glaucomatous and normal VFs.
| S-EPMC6261540 | biostudies-literature
Project description:Peptide-based therapeutics are here to stay and will prosper in the future. A key step in identifying novel peptide-drugs is the determination of their bioactivities. Recent advances in peptidomics screening approaches hold promise as a strategy for identifying novel drug targets. However, these screenings typically generate an immense number of peptides and tools for ranking these peptides prior to planning functional studies are warranted. Whereas a couple of tools in the literature predict multiple classes, these are constructed using multiple binary classifiers. We here aimed to use an innovative deep learning approach to generate an improved peptide bioactivity classifier with capacity of distinguishing between multiple classes. We present MultiPep: a deep learning multi-label classifier that assigns peptides to zero or more of 20 bioactivity classes. We train and test MultiPep on data from several publically available databases. The same data are used for a hierarchical clustering, whose dendrogram shapes the architecture of MultiPep. We test a new loss function that combines a customized version of Matthews correlation coefficient with binary cross entropy (BCE), and show that this is better than using class-weighted BCE as loss function. Further, we show that MultiPep surpasses state-of-the-art peptide bioactivity classifiers and that it predicts known and novel bioactivities of FDA-approved therapeutic peptides. In conclusion, we present innovative machine learning techniques used to produce a peptide prediction tool to aid peptide-based therapy development and hypothesis generation.
| S-EPMC8665375 | biostudies-literature
Project description:In this study, series networks (AlexNet and VGG-19) and directed acyclic graph (DAG) networks (ResNet-18, ResNet-50, and ResNet-101) with transfer learning were employed to identify and classify 13 classes of apples from 7439 images. Two training datasets, model evaluation metrics, and three visualization methods were used to objectively assess, compare, and interpret five Convolutional Neural Network (CNN)-based models. The results show that the dataset configuration had a significant impact on the classification results, as all models achieved over 96.1% accuracy on dataset A (training-to-testing = 2.4:1.0) compared to 89.4-93.9% accuracy on dataset B (training-to-testing = 1.0:3.7). VGG-19 achieved the highest accuracy of 100.0% on dataset A and 93.9% on dataset B. Moreover, for networks of the same framework, the model size, accuracy, and training and testing times increased as the model depth (number of layers) increased. Furthermore, feature visualization, strongest activations, and local interpretable model-agnostic explanations techniques were used to show the understanding of apple images by different trained models, as well as to reveal how and why the models make classification decisions. These results improve the interpretability and credibility of CNN-based models, which provides guidance for future applications of deep learning methods in agriculture.
| S-EPMC9956933 | biostudies-literature
Project description:BackgroundAccurate diagnosis of unexplained cervical lymphadenopathy (CLA) using medical images heavily relies on the experience of radiologists, which is even worse for CLA patients in underdeveloped countries and regions, because of lack of expertise and reliable medical history. This study aimed to develop a deep learning (DL) radiomics model based on B-mode and color Doppler ultrasound images for assisting radiologists to improve their diagnoses of the etiology of unexplained CLA.MethodsPatients with unexplained CLA who received ultrasound examinations from three hospitals located in underdeveloped areas of China were retrospectively enrolled. They were all pathologically confirmed with reactive hyperplasia, tuberculous lymphadenitis, lymphoma, or metastatic carcinoma. By mimicking the diagnosis logic of radiologists, three DL sub-models were developed to achieve the primary diagnosis of benign and malignant, the secondary diagnosis of reactive hyperplasia and tuberculous lymphadenitis in benign candidates, and of lymphoma and metastatic carcinoma in malignant candidates, respectively. Then, a CLA hierarchical diagnostic model (CLA-HDM) integrating all sub-models was proposed to classify the specific etiology of each unexplained CLA. The assistant effectiveness of CLA-HDM was assessed by comparing six radiologists between without and with using the DL-based classification and heatmap guidance.ResultsA total of 763 patients with unexplained CLA were enrolled and were split into the training cohort (n=395), internal testing cohort (n=171), and external testing cohorts 1 (n=105) and 2 (n=92). The CLA-HDM for diagnosing four common etiologies of unexplained CLA achieved AUCs of 0.873 (95% CI: 0.838-0.908), 0.837 (95% CI: 0.789-0.889), and 0.840 (95% CI: 0.789-0.898) in the three testing cohorts, respectively, which was systematically more accurate than all the participating radiologists. With its assistance, the accuracy, sensitivity, and specificity of six radiologists with different levels of experience were generally improved, reducing the false-negative rate of 2.2-10% and the false-positive rate of 0.7-3.1%.ConclusionsMulti-cohort testing demonstrated our DL model integrating dual-modality ultrasound images achieved accurate diagnosis of unexplained CLA. With its assistance, the gap between radiologists with different levels of experience was narrowed, which is potentially of great significance for benefiting CLA patients in underdeveloped countries and regions worldwide.
| S-EPMC9410737 | biostudies-literature
Project description:Engineered RNA elements are programmable tools capable of detecting small molecules, proteins, and nucleic acids. Predicting the behavior of these tools remains a challenge, a situation that could be addressed through enhanced pattern recognition from deep learning. Thus, we investigate Deep Neural Networks (DNN) to predict toehold switch function as a canonical riboswitch model in synthetic biology. To facilitate DNN training, we synthesized and characterized in vivo a dataset of 91,534 toehold switches spanning 23 viral genomes and 906 human transcription factors. DNNs trained on nucleotide sequences outperformed (R2=0.43-0.70) previous state-of-the-art thermodynamic and kinetic models (R2=0.04-0.15) and allowed for human-understandable attention-visualizations (VIS4Map) to identify success and failure modes. This deep learning approach constitutes a major step forward in engineering and understanding of RNA synthetic biology.
2020-08-12 | GSE149225 | GEO
Project description:Background: Radiofrequency catheter ablation (RFCA) therapy is the first-line treatment for atrial fibrillation (AF), the most common type of cardiac arrhythmia globally. However, the procedure currently has low success rates in dealing with persistent AF, with a reoccurrence rate of ∼50% post-ablation. Therefore, deep learning (DL) has increasingly been applied to improve RFCA treatment for AF. However, for a clinician to trust the prediction of a DL model, its decision process needs to be interpretable and have biomedical relevance. Aim: This study explores interpretability in DL prediction of successful RFCA therapy for AF and evaluates if pro-arrhythmogenic regions in the left atrium (LA) were used in its decision process. Methods: AF and its termination by RFCA have been simulated in MRI-derived 2D LA tissue models with segmented fibrotic regions (n = 187). Three ablation strategies were applied for each LA model: pulmonary vein isolation (PVI), fibrosis-based ablation (FIBRO) and a rotor-based ablation (ROTOR). The DL model was trained to predict the success of each RFCA strategy for each LA model. Three feature attribution (FA) map methods were then used to investigate interpretability of the DL model: GradCAM, Occlusions and LIME. Results: The developed DL model had an AUC (area under the receiver operating characteristic curve) of 0.78 ± 0.04 for predicting the success of the PVI strategy, 0.92 ± 0.02 for FIBRO and 0.77 ± 0.02 for ROTOR. GradCAM had the highest percentage of informative regions in the FA maps (62% for FIBRO and 71% for ROTOR) that coincided with the successful RFCA lesions known from the 2D LA simulations, but unseen by the DL model. Moreover, GradCAM had the smallest coincidence of informative regions of the FA maps with non-arrhythmogenic regions (25% for FIBRO and 27% for ROTOR). Conclusion: The most informative regions of the FA maps coincided with pro-arrhythmogenic regions, suggesting that the DL model leveraged structural features of MRI images to identify such regions and make its prediction. In the future, this technique could provide a clinician with a trustworthy decision support tool.
| S-EPMC10043207 | biostudies-literature
Project description:Knee osteoarthritis (OA) is the most common musculoskeletal disorder. OA diagnosis is currently conducted by assessing symptoms and evaluating plain radiographs, but this process suffers from subjectivity. In this study, we present a new transparent computer-aided diagnosis method based on the Deep Siamese Convolutional Neural Network to automatically score knee OA severity according to the Kellgren-Lawrence grading scale. We trained our method using the data solely from the Multicenter Osteoarthritis Study and validated it on randomly selected 3,000 subjects (5,960 knees) from Osteoarthritis Initiative dataset. Our method yielded a quadratic Kappa coefficient of 0.83 and average multiclass accuracy of 66.71% compared to the annotations given by a committee of clinical experts. Here, we also report a radiological OA diagnosis area under the ROC curve of 0.93. Besides this, we present attention maps highlighting the radiological features affecting the network decision. Such information makes the decision process transparent for the practitioner, which builds better trust toward automatic methods. We believe that our model is useful for clinical decision making and for OA research; therefore, we openly release our training codes and the data set created in this study.
| S-EPMC5789045 | biostudies-literature
Project description:Alzheimer’s disease (AD) is a multifactorial disease which is caused by inherited autosomal recessive as familial and late-onset as non-familial changes. However, the genetics of AD underlining variation or mutation are not well understood. Exon skipping through the occurrence of the unpredicted genetic events leads to variation of translation, but the event does not can be exploited for AD diagnosis. We identified a gene as phospholipase c gamma-1 (PLCγ1) with severe genetic modification in AD through deep-learning based high throughput screening which showed single nucleotide variants (SNVs). Genome-wide association study (GWAS) data from AD mouse model demonstrated that AD specific novel SNVs are preferentially occurred H3K27ac accumulated region at PLCγ1 gene body during the brain development. Moreover, exon skipping in mature mRNA was caused by single nucleotide insertion at 27th exon of PLCγ1 gene. In addition, we show mutation site was evolutionally conserved in various species included human which means important region for homeostasis. Collectively, our findings suggest the genetic variation and possibility of diagnosis potent of PLCγ1 for AD.
2021-01-12 | GSE151270 | GEO
Project description:Deep learning is being employed in disease detection and classification based on medical images for clinical decision making. It typically requires large amounts of labelled data; however, the sample size of such medical image datasets is generally small. This study proposes a novel training framework for building deep learning models of disease detection and classification with small datasets. Our approach is based on a hierarchical classification method where the healthy/disease information from the first model is effectively utilized to build subsequent models for classifying the disease into its sub-types via a transfer learning method. To improve accuracy, multiple input datasets were used, and a stacking ensembled method was employed for final classification. To demonstrate the method's performance, a labelled dataset extracted from volumetric ophthalmic optical coherence tomography data for 156 healthy and 798 glaucoma eyes was used, in which glaucoma eyes were further labelled into four sub-types. The average weighted accuracy and Cohen's kappa for three randomized test datasets were 0.839 and 0.809, respectively. Our approach outperformed the flat classification method by 9.7% using smaller training datasets. The results suggest that the framework can perform accurate classification with a small number of medical images.
| S-EPMC7921640 | biostudies-literature