Towards Interpretable Skin Lesion Classification with Deep Learning Models.
Ontology highlight
ABSTRACT:
SUBMITTER: Xiang A
PROVIDER: S-EPMC7153112 | biostudies-literature | 2019
REPOSITORIES: biostudies-literature
Publications
Towards Interpretable Skin Lesion Classification with Deep Learning Models.
AMIA ... Annual Symposium proceedings. AMIA Symposium 20190101
Skin disease is a prevalent condition all over the world. Computer vision-based technology for automatic skin lesion classification holds great promise as an effective screening tool for early diagnosis. In this paper, we propose an accurate and interpretable deep learning pipeline to achieve such a goal. Comparing with existing research, we would like to highlight the following aspects of our model. 1) Rather than a single model, our approach ensembles a set of deep learning architectures to ac ...[more]
Similar Datasets
Project description:Background: Diagnosis of skin diseases is often challenging and computer-aided diagnostic tools are urgently needed to underpin decision making. Objective: To develop a convolutional neural network model to classify clinically relevant selected multiple-lesion skin diseases, this in accordance to the STARD guidelines. Methods: This was an image-based retrospective study using multi-task learning for binary classification. A VGG-16 model was trained on 16,543 non-standardized images. Image data was distributed in training set (80%), validation set (10%), and test set (10%). All images were collected from a clinical database of a Danish population attending one dermatological department. Included was patients categorized with ICD-10 codes related to acne, rosacea, psoriasis, eczema, and cutaneous t-cell lymphoma. Results: Acne was distinguished from rosacea with a sensitivity of 85.42% CI 72.24-93.93% and a specificity of 89.53% CI 83.97-93.68%, cutaneous t-cell lymphoma was distinguished from eczema with a sensitivity of 74.29% CI 67.82-80.05% and a specificity of 84.09% CI 80.83-86.99%, and psoriasis from eczema with a sensitivity of 81.79% CI 78.51-84.76% and a specificity of 73.57% CI 69.76-77.13%. All results were based on the test set. Conclusion: The performance rates reported were equal or superior to those reported for general practitioners with dermatological training, indicating that computer-aided diagnostic models based on convolutional neural network may potentially be employed for diagnosing multiple-lesion skin diseases.
| S-EPMC7536339 | biostudies-literature
Project description:Alzheimer's disease is the primary cause of dementia worldwide, with an increasing morbidity burden that may outstrip diagnosis and management capacity as the population ages. Current methods integrate patient history, neuropsychological testing and MRI to identify likely cases, yet effective practices remain variably applied and lacking in sensitivity and specificity. Here we report an interpretable deep learning strategy that delineates unique Alzheimer's disease signatures from multimodal inputs of MRI, age, gender, and Mini-Mental State Examination score. Our framework linked a fully convolutional network, which constructs high resolution maps of disease probability from local brain structure to a multilayer perceptron and generates precise, intuitive visualization of individual Alzheimer's disease risk en route to accurate diagnosis. The model was trained using clinically diagnosed Alzheimer's disease and cognitively normal subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset (n?=?417) and validated on three independent cohorts: the Australian Imaging, Biomarker and Lifestyle Flagship Study of Ageing (AIBL) (n?=?382), the Framingham Heart Study (n?=?102), and the National Alzheimer's Coordinating Center (NACC) (n?=?582). Performance of the model that used the multimodal inputs was consistent across datasets, with mean area under curve values of 0.996, 0.974, 0.876 and 0.954 for the ADNI study, AIBL, Framingham Heart Study and NACC datasets, respectively. Moreover, our approach exceeded the diagnostic performance of a multi-institutional team of practicing neurologists (n?=?11), and high-risk cerebral regions predicted by the model closely tracked post-mortem histopathological findings. This framework provides a clinically adaptable strategy for using routinely available imaging techniques such as MRI to generate nuanced neuroimaging signatures for Alzheimer's disease diagnosis, as well as a generalizable approach for linking deep learning to pathophysiological processes in human disease.
| S-EPMC7296847 | biostudies-literature
Project description:The lack of explainability is one of the most prominent disadvantages of deep learning applications in omics. This 'black box' problem can undermine the credibility and limit the practical implementation of biomedical deep learning models. Here we present XOmiVAE, a variational autoencoder (VAE)-based interpretable deep learning model for cancer classification using high-dimensional omics data. XOmiVAE is capable of revealing the contribution of each gene and latent dimension for each classification prediction and the correlation between each gene and each latent dimension. It is also demonstrated that XOmiVAE can explain not only the supervised classification but also the unsupervised clustering results from the deep learning network. To the best of our knowledge, XOmiVAE is one of the first activation level-based interpretable deep learning models explaining novel clusters generated by VAE. The explainable results generated by XOmiVAE were validated by both the performance of downstream tasks and the biomedical knowledge. In our experiments, XOmiVAE explanations of deep learning-based cancer classification and clustering aligned with current domain knowledge including biological annotation and academic literature, which shows great potential for novel biomedical knowledge discovery from deep learning models.
| S-EPMC8575033 | biostudies-literature
Project description:BACKGROUND:Adverse drug reactions (ADRs) are unintended and harmful reactions caused by normal uses of drugs. Predicting and preventing ADRs in the early stage of the drug development pipeline can help to enhance drug safety and reduce financial costs. METHODS:In this paper, we developed machine learning models including a deep learning framework which can simultaneously predict ADRs and identify the molecular substructures associated with those ADRs without defining the substructures a-priori. RESULTS:We evaluated the performance of our model with ten different state-of-the-art fingerprint models and found that neural fingerprints from the deep learning model outperformed all other methods in predicting ADRs. Via feature analysis on drug structures, we identified important molecular substructures that are associated with specific ADRs and assessed their associations via statistical analysis. CONCLUSIONS:The deep learning model with feature analysis, substructure identification, and statistical assessment provides a promising solution for identifying risky components within molecular structures and can potentially help to improve drug safety evaluation.
| S-EPMC6300887 | biostudies-other
Project description:High-throughput technologies have led to large collections of different types of biological data that provide unprecedented opportunities to unravel molecular heterogeneity of biological processes. Nevertheless, how to jointly explore data from multiple sources into a holistic, biologically meaningful interpretation remains challenging. In this work, we propose a scalable and tuning-free preprocessing framework, Heterogeneity Rescaling Pursuit (Hetero-RP), which weighs important features more highly than less important ones in accord with implicitly existing auxiliary knowledge. Finally, we demonstrate effectiveness of Hetero-RP in diverse clustering and classification applications. More importantly, Hetero-RP offers an interpretation of feature importance, shedding light on the driving forces of the underlying biology. In metagenomic contig binning, Hetero-RP automatically weighs abundance and composition profiles according to the varying number of samples, resulting in markedly improved performance of contig binning. In RNA-binding protein (RBP) binding site prediction, Hetero-RP not only improves the prediction performance measured by the area under the receiver operating characteristic curves (AUC), but also uncovers the evidence supported by independent studies, including the distribution of the binding sites of IGF2BP and PUM2, the binding competition between hnRNPC and U2AF2, and the intron-exon boundary of U2AF2 [availability: https://github.com/younglululu/Hetero-RP].
| S-EPMC5714251 | biostudies-literature
Project description:Recent studies have shown that deep learning is capable of classifying dermatoscopic images at least as well as dermatologists. However, many studies in skin cancer classification utilize non-biopsy-verified training images. This imperfect ground truth introduces a systematic error, but the effects on classifier performance are currently unknown. Here, we systematically examine the effects of label noise by training and evaluating convolutional neural networks (CNN) with 804 images of melanoma and nevi labeled either by dermatologists or by biopsy. The CNNs are evaluated on a test set of 384 images by means of 4-fold cross validation comparing the outputs with either the corresponding dermatological or the biopsy-verified diagnosis. With identical ground truths of training and test labels, high accuracies with 75.03% (95% CI: 74.39-75.66%) for dermatological and 73.80% (95% CI: 73.10-74.51%) for biopsy-verified labels can be achieved. However, if the CNN is trained and tested with different ground truths, accuracy drops significantly to 64.53% (95% CI: 63.12-65.94%, p < 0.01) on a non-biopsy-verified and to 64.24% (95% CI: 62.66-65.83%, p < 0.01) on a biopsy-verified test set. In conclusion, deep learning methods for skin cancer classification are highly sensitive to label noise and future work should use biopsy-verified training images to mitigate this problem.
| S-EPMC7218064 | biostudies-literature
Project description:BackgroundAn open challenge in translational bioinformatics is the analysis of sequenced metagenomes from various environmental samples. Of course, several studies demonstrated the 16S ribosomal RNA could be considered as a barcode for bacteria classification at the genus level, but till now it is hard to identify the correct composition of metagenomic data from RNA-seq short-read data. 16S short-read data are generated using two next generation sequencing technologies, i.e. whole genome shotgun (WGS) and amplicon (AMP); typically, the former is filtered to obtain short-reads belonging to a 16S shotgun (SG), whereas the latter take into account only some specific 16S hypervariable regions. The above mentioned two sequencing technologies, SG and AMP, are used alternatively, for this reason in this work we propose a deep learning approach for taxonomic classification of metagenomic data, that can be employed for both of them.ResultsTo test the proposed pipeline, we simulated both SG and AMP short-reads, from 1000 16S full-length sequences. Then, we adopted a k-mer representation to map sequences as vectors into a numerical space. Finally, we trained two different deep learning architecture, i.e., convolutional neural network (CNN) and deep belief network (DBN), obtaining a trained model for each taxon. We tested our proposed methodology to find the best parameters configuration, and we compared our results against the classification performances provided by a reference classifier for bacteria identification, known as RDP classifier. We outperformed the RDP classifier at each taxonomic level with both architectures. For instance, at the genus level, both CNN and DBN reached 91.3% of accuracy with AMP short-reads, whereas RDP classifier obtained 83.8% with the same data.ConclusionsIn this work, we proposed a 16S short-read sequences classification technique based on k-mer representation and deep learning architecture, in which each taxon (from phylum to genus) generates a classification model. Experimental results confirm the proposed pipeline as a valid approach for classifying bacteria sequences; for this reason, our approach could be integrated into the most common tools for metagenomic analysis. According to obtained results, it can be successfully used for classifying both SG and AMP data.
| S-EPMC6069770 | biostudies-literature
Project description:Recent studies have demonstrated the usefulness of convolutional neural networks (CNNs) to classify images of melanoma, with accuracies comparable to those achieved by dermatologists. However, the performance of a CNN trained with only clinical images of a pigmented skin lesion in a clinical image classification task, in competition with dermatologists, has not been reported to date. In this study, we extracted 5846 clinical images of pigmented skin lesions from 3551 patients. Pigmented skin lesions included malignant tumors (malignant melanoma and basal cell carcinoma) and benign tumors (nevus, seborrhoeic keratosis, senile lentigo, and hematoma/hemangioma). We created the test dataset by randomly selecting 666 patients out of them and picking one image per patient, and created the training dataset by giving bounding-box annotations to the rest of the images (4732 images, 2885 patients). Subsequently, we trained a faster, region-based CNN (FRCNN) with the training dataset and checked the performance of the model on the test dataset. In addition, ten board-certified dermatologists (BCDs) and ten dermatologic trainees (TRNs) took the same tests, and we compared their diagnostic accuracy with FRCNN. For six-class classification, the accuracy of FRCNN was 86.2%, and that of the BCDs and TRNs was 79.5% (p = 0.0081) and 75.1% (p < 0.00001), respectively. For two-class classification (benign or malignant), the accuracy, sensitivity, and specificity were 91.5%, 83.3%, and 94.5% by FRCNN; 86.6%, 86.3%, and 86.6% by BCD; and 85.3%, 83.5%, and 85.9% by TRN, respectively. False positive rates and positive predictive values were 5.5% and 84.7% by FRCNN, 13.4% and 70.5% by BCD, and 14.1% and 68.5% by TRN, respectively. We compared the classification performance of FRCNN with 20 dermatologists. As a result, the classification accuracy of FRCNN was better than that of the dermatologists. In the future, we plan to implement this system in society and have it used by the general public, in order to improve the prognosis of skin cancer.
| S-EPMC7465007 | biostudies-literature
Project description:MotivationCancer dependencies provide potential drug targets. Unfortunately, dependencies differ among cancers and even individuals. To this end, visible neural networks (VNNs) are promising due to robust performance and the interpretability required for the biomedical field.ResultsWe design Biological VNN (BioVNN) using pathway knowledge to predict cancer dependencies. Despite having fewer parameters, BioVNN marginally outperforms traditional neural networks and converges faster. BioVNN also outperforms a neural network based on randomized pathways. More importantly, dependency predictions can be explained by correlating with the neuron output states of relevant pathways, which suggest dependency mechanisms. In feature importance analysis, BioVNN recapitulates known reaction partners and proposes new ones. Such robust and interpretable VNNs may facilitate the understanding of cancer dependency and the development of targeted therapies.Availability and implementationCode and data are available at http://static.lichtargelab.org/BioVNN/.Supplementary informationSee Bioinformatics online.
| S-EPMC8428607 | biostudies-literature
Project description:Simple Summary According to skin disease reports by healthcare organizations, the number of cases of skin disease is growing gradually over the years globally. In skin disease diagnosis, dermatologists examine skin cells by using a dermatoscope. Due to the global shortage of expert dermatologists, mainly in developing countries, an accurate early skin disease diagnosis is not possible. To automate the examination of skin disease images, computer-aided diagnosis-based tools are used in healthcare and medical environments. Computer-aided diagnosis employs machine learning including deep learning models on skin disease images to detect and classify skin diseases. The present work proposes a deep learning-based model to accurately detect skin diseases and classify them into a family of skin diseases using skin disease images. The proposed system demonstrated a performance improvement of 4% accuracy for skin disease detection and 9% accuracy for skin disease classification compared to the existing deep learning-based models. The proposed computer-aided tool can be used as an early skin diagnosis tool to assist dermatologists in healthcare and medical environments. Abstract Deep learning-based models have been employed for the detection and classification of skin diseases through medical imaging. However, deep learning-based models are not effective for rare skin disease detection and classification. This is mainly due to the reason that rare skin disease has very a smaller number of data samples. Thus, the dataset will be highly imbalanced, and due to the bias in learning, most of the models give better performances. The deep learning models are not effective in detecting the affected tiny portions of skin disease in the overall regions of the image. This paper presents an attention-cost-sensitive deep learning-based feature fusion ensemble meta-classifier approach for skin cancer detection and classification. Cost weights are included in the deep learning models to handle the data imbalance during training. To effectively learn the optimal features from the affected tiny portions of skin image samples, attention is integrated into the deep learning models. The features from the finetuned models are extracted and the dimensionality of the features was further reduced by using a kernel-based principal component (KPCA) analysis. The reduced features of the deep learning-based finetuned models are fused and passed into ensemble meta-classifiers for skin disease detection and classification. The ensemble meta-classifier is a two-stage model. The first stage performs the prediction of skin disease and the second stage performs the classification by considering the prediction of the first stage as features. Detailed analysis of the proposed approach is demonstrated for both skin disease detection and skin disease classification. The proposed approach demonstrated an accuracy of 99% on skin disease detection and 99% on skin disease classification. In all the experimental settings, the proposed approach outperformed the existing methods and demonstrated a performance improvement of 4% accuracy for skin disease detection and 9% accuracy for skin disease classification. The proposed approach can be used as a computer-aided diagnosis (CAD) tool for the early diagnosis of skin cancer detection and classification in healthcare and medical environments. The tool can accurately detect skin diseases and classify the skin disease into their skin disease family.
| S-EPMC9735681 | biostudies-literature