Expert-level detection of pathologies from unannotated chest X-ray images via self-supervised learning.
Ontology highlight
ABSTRACT:
SUBMITTER: Tiu E
PROVIDER: S-EPMC9792370 | biostudies-literature | 2022 Dec
REPOSITORIES: biostudies-literature
Publications
Expert-level detection of pathologies from unannotated chest X-ray images via self-supervised learning.
Tiu Ekin E Talius Ellie E Patel Pujan P Langlotz Curtis P CP Ng Andrew Y AY Rajpurkar Pranav P
Nature biomedical engineering 20220915 12
In tasks involving the interpretation of medical images, suitably trained machine-learning models often exceed the performance of medical experts. Yet such a high-level of performance typically requires that the models be trained with relevant datasets that have been painstakingly annotated by experts. Here we show that a self-supervised model trained on chest X-ray images that lack explicit annotations performs pathology-classification tasks with accuracies comparable to those of radiologists. ...[more]
Similar Datasets
Project description:Training deep learning models on medical images heavily depends on experts' expensive and laborious manual labels. In addition, these images, labels, and even models themselves are not widely publicly accessible and suffer from various kinds of bias and imbalances. In this paper, chest X-ray pre-trained model via self-supervised contrastive learning (CheSS) was proposed to learn models with various representations in chest radiographs (CXRs). Our contribution is a publicly accessible pretrained model trained with a 4.8-M CXR dataset using self-supervised learning with a contrastive learning and its validation with various kinds of downstream tasks including classification on the 6-class diseases in internal dataset, diseases classification in CheXpert, bone suppression, and nodule generation. When compared to a scratch model, on the 6-class classification test dataset, we achieved 28.5% increase in accuracy. On the CheXpert dataset, we achieved 1.3% increase in mean area under the receiver operating characteristic curve on the full dataset and 11.4% increase only using 1% data in stress test manner. On bone suppression with perceptual loss, we achieved improvement in peak signal to noise ratio from 34.99 to 37.77, structural similarity index measure from 0.976 to 0.977, and root-square-mean error from 4.410 to 3.301 when compared to ImageNet pretrained model. Finally, on nodule generation, we achieved improvement in Fréchet inception distance from 24.06 to 17.07. Our study showed the decent transferability of CheSS weights. CheSS weights can help researchers overcome data imbalance, data shortage, and inaccessibility of medical image datasets. CheSS weight is available at https://github.com/mi2rl/CheSS .
| S-EPMC10287612 | biostudies-literature
Project description:Backgrounds & Aims: Transcriptomic classification of intrahepatic cholangiocarcinoma (iCCA) has been recently improved from two classes to five classes, associated with pathological features, targetable genetic alterations and survival. Despite its prognostic and therapeutic value, the classification is not routinely performed due to technical limits such as insufficient material or the cost of molecular analyses. Our aim was to predict iCCA transcriptomic classes on whole-slide digital histological images (WSI) using a self-supervised learning (SSL) model. Methods: Gene expression was investigated using RNA sequencing to class samples in the five transcriptomic classes. We then used a SSL method called GigaSSL. We first trained our model on a discovery set of 769 slides (biopsy and surgical samples, 246 patients) in a 5-fold cross-validation scheme. We then validated the model in a TCGA (n= 29) and a French external validation set (n=32). Results: Our model showed good performance for predicting each transcriptomic class in the discovery set (Area under the curve, AUC: 0.55-0.81), particularly for the Hepatic stem-like class (most frequent group, 37% of cases), with AUC 0.81. The model generalised well for the prediction of four on five of the transcriptomic classes into the two validation sets with AUCs ranging from 0.76 to 0.80 in the TCGA set and from 0.62 to 0.92 in the French external set. Conclusion: We have developed and validated a SSL based model able to predict iCCA transcriptomic classes on routine histological slides (biopsy and surgical samples), which could have an impact on the management of patients.
2023-11-01 | GSE244807 | GEO
Project description:Cancer diagnosis and management depend upon the extraction of complex information from microscopy images by pathologists, which requires time-consuming expert interpretation prone to human bias. Supervised deep learning approaches have proven powerful, but are inherently limited by the cost and quality of annotations used for training. Therefore, we present Histomorphological Phenotype Learning, a self-supervised methodology requiring no labels and operating via the automatic discovery of discriminatory features in image tiles. Tiles are grouped into morphologically similar clusters which constitute an atlas of histomorphological phenotypes (HP-Atlas), revealing trajectories from benign to malignant tissue via inflammatory and reactive phenotypes. These clusters have distinct features which can be identified using orthogonal methods, linking histologic, molecular and clinical phenotypes. Applied to lung cancer, we show that they align closely with patient survival, with histopathologically recognised tumor types and growth patterns, and with transcriptomic measures of immunophenotype. These properties are maintained in a multi-cancer study.
| S-EPMC11525555 | biostudies-literature
Project description:MotivationAdvances in bioimaging now permit in situ proteomic characterization of cell-cell interactions in complex tissues, with important applications across a spectrum of biological problems from development to disease. These methods depend on selection of antibodies targeting proteins that are expressed specifically in particular cell types. Candidate marker proteins are often identified from single-cell transcriptomic data, with variable rates of success, in part due to divergence between expression levels of proteins and the genes that encode them. In principle, marker identification could be improved by using existing databases of immunohistochemistry for thousands of antibodies in human tissue, such as the Human Protein Atlas. However, these data lack detailed annotations of the types of cells in each image.ResultsWe develop a method to predict cell type specificity of protein markers from unlabeled images. We train a convolutional neural network with a self-supervised objective to generate embeddings of the images. Using non-linear dimensionality reduction, we observe that the model clusters images according to cell types and anatomical regions for which the stained proteins are specific. We then use estimates of cell type specificity derived from an independent single-cell transcriptomics dataset to train an image classifier, without requiring any human labelling of images. Our scheme demonstrates superior classification of known proteomic markers in kidney compared to selection via single-cell transcriptomics.Availability and implementationCode and trained model are available at www.github.com/murphy17/HPA-SimCLR.Supplementary informationSupplementary data are available at Bioinformatics online.
| S-EPMC9235491 | biostudies-literature
Project description:Chest X-ray (CXR) is widely used to diagnose conditions affecting the chest, its contents, and its nearby structures. In this study, we used a private data set containing 1630 CXR images with disease labels; most of the images were disease-free, but the others contained multiple sites of abnormalities. Here, we used deep convolutional neural network (CNN) models to extract feature representations and to identify possible diseases in these images. We also used transfer learning combined with large open-source image data sets to resolve the problems of insufficient training data and optimize the classification model. The effects of different approaches of reusing pretrained weights (model finetuning and layer transfer), source data sets of different sizes and similarity levels to the target data (ImageNet, ChestX-ray, and CheXpert), methods integrating source data sets into transfer learning (initiating, concatenating, and co-training), and backbone CNN models (ResNet50 and DenseNet121) on transfer learning were also assessed. The results demonstrated that transfer learning applied with the model finetuning approach typically afforded better prediction models. When only one source data set was adopted, ChestX-ray performed better than CheXpert; however, after ImageNet initials were attached, CheXpert performed better. ResNet50 performed better in initiating transfer learning, whereas DenseNet121 performed better in concatenating and co-training transfer learning. Transfer learning with multiple source data sets was preferable to that with a source data set. Overall, transfer learning can further enhance prediction capabilities and reduce computing costs for CXR images.
| S-EPMC9222116 | biostudies-literature
Project description:Background and Aims Chest X-ray (CXR) is indispensable to the assessment of severity, diagnosis, and management of pneumonia. Deep learning is an artificial intelligence (AI) technology that has been applied to the interpretation of medical images. This study investigated the feasibility of classifying fatal pneumonia based on CXR images using deep learning models on publicly available platforms. Methods CXR images of patients with pneumonia at diagnosis were labeled as fatal or nonfatal based on medical records. We applied CXR images from 1031 patients with nonfatal pneumonia and 243 patients with fatal pneumonia for training and self-evaluation of the deep learning models. All labeled CXR images were randomly allocated to the training, validation, and test datasets of deep learning models. Data augmentation techniques were not used in this study. We created two deep learning models using two publicly available platforms. Results The first model showed an area under the precision-recall curve of 0.929 with a sensitivity of 50.0% and a specificity of 92.4% for classifying fatal pneumonia. We evaluated the performance of our deep learning models using sensitivity, specificity, PPV, negative predictive value (NPV), accuracy, and F1 score. Using the external validation test dataset of 100 CXR images, the sensitivity, specificity, accuracy, and F1 score were 68.0%, 86.0%, 77.0%, and 74.7%, respectively. In the original dataset, the performance of the second model showed a sensitivity, specificity, and accuracy of 39.6%, 92.8%, and 82.7%, respectively, while external validation showed values of 38.0%, 92.0%, and 65.0%, respectively. The F1 score was 52.1%. These results were comparable to those obtained by respiratory physicians and residents. Conclusions The deep learning models yielded good accuracy in classifying fatal pneumonia. By further improving the performance, AI could assist physicians in the severity assessment of patients with pneumonia.
| S-EPMC9715345 | biostudies-literature
Project description:Supervised learning method requires a large volume of annotated datasets. Collecting such datasets is time-consuming and expensive. Until now, very few annotated COVID-19 imaging datasets are available. Although self-supervised learning enables us to bootstrap the training by exploiting unlabeled data, the generic self-supervised methods for natural images do not sufficiently incorporate the context. For medical images, a desirable method should be sensitive enough to detect deviation from normal-appearing tissue of each anatomical region; here, anatomy is the context. We introduce a novel approach with two levels of self-supervised representation learning objectives: one on the regional anatomical level and another on the patient-level. We use graph neural networks to incorporate the relationship between different anatomical regions. The structure of the graph is informed by anatomical correspondences between each patient and an anatomical atlas. In addition, the graph representation has the advantage of handling any arbitrarily sized image in full resolution. Experiments on large-scale Computer Tomography (CT) datasets of lung images show that our approach compares favorably to baseline methods that do not account for the context. We use the learnt embedding to quantify the clinical progression of COVID-19 and show that our method generalizes well to COVID-19 patients from different hospitals. Qualitative results suggest that our model can identify clinically relevant regions in the images.
| S-EPMC8513790 | biostudies-literature
Project description:BackgroundNowadays doctors and radiologists are overwhelmed with a huge amount of work. This led to the effort to design different Computer-Aided Diagnosis systems (CAD system), with the aim of accomplishing a faster and more accurate diagnosis. The current development of deep learning is a big opportunity for the development of new CADs. In this paper, we propose a novel architecture for a convolutional neural network (CNN) ensemble for classifying chest X-ray (CRX) images into four classes: viral Pneumonia, Tuberculosis, COVID-19, and Healthy. Although Computed tomography (CT) is the best way to detect and diagnoses pulmonary issues, CT is more expensive than CRX. Furthermore, CRX is commonly the first step in the diagnosis, so it's very important to be accurate in the early stages of diagnosis and treatment.ResultsWe applied the transfer learning technique and data augmentation to all CNNs for obtaining better performance. We have designed and evaluated two different CNN-ensembles: Stacking and Voting. This system is ready to be applied in a CAD system to automated diagnosis such a second or previous opinion before the doctors or radiology's. Our results show a great improvement, 99% accuracy of the Stacking Ensemble and 98% of accuracy for the the Voting Ensemble.ConclusionsTo minimize missclassifications, we included six different base CNN models in our architecture (VGG16, VGG19, InceptionV3, ResNet101V2, DenseNet121 and CheXnet) and it could be extended to any number as well as we expect extend the number of diseases to detected. The proposed method has been validated using a large dataset created by mixing several public datasets with different image sizes and quality. As we demonstrate in the evaluation carried out, we reach better results and generalization compared with previous works. In addition, we make a first approach to explainable deep learning with the objective of providing professionals more information that may be valuable when evaluating CRXs.
| S-EPMC9568999 | biostudies-literature
Project description:The ongoing pandemic due to coronavirus disease, commonly abbreviated as COVID-19, has unleashed a major health crisis across the world. Although multiple vaccines have emerged, large scale vaccination have proven to be a major challenge, especially in developing nations. As a result, early detection still remains a crucial aspect of containing the spread of the virus. The popularly used test for COVID-19 is limited by the availability of test kits and is time-consuming. This has prompted researchers to use chest x-ray (CXR) and chest tomography (CT) scan images of subjects to predict COVID. Many COVID-19 patients also suffer from viral Pneumonia caused by SARS-CoV2 virus. Hence, distinguishing between bacterial and non-COVID Pneumonia is of paramount importance for proper diagnosis of the patients. To this end, in the present work, we have developed a bi-level prediction model of the subjects into normal, Pneumonia and COVID-19 patients by using a shallow learner based classifier on features extracted by VGG19 from the CXR images. The model is used on 3168 images distributed among normal, Pneumonia and COVID classes. We have created a dataset by collating CXR images from various sources like SIRM COVID-19 Database, Chest Imaging (Twitter), COVID-chestxray-dataset and Chest X-Ray Images. The experimental results confirm the superiority of the proposed model (99.26% accuracy) over the best performing single-level classification method (96.74% accuracy). This result is also at par with the many state-of-the-art methods mentioned in literature. The source code is available in the link https://github.com/sdrxc/Bi-level-Prediction-Model-for-Screening-COVID-19-from-Chest-X-ray-Images.
| S-EPMC8084620 | biostudies-literature
Project description:Deep learning has shown potential in domains with large-scale annotated datasets. However, manual annotation is expensive, time-consuming, and tedious. Pixel-level annotations are particularly costly for semantic segmentation in images with dense irregular patterns of object instances, such as in plant images. In this work, we propose a method for developing high-performing deep learning models for semantic segmentation of such images utilizing little manual annotation. As a use case, we focus on wheat head segmentation. We synthesize a computationally annotated dataset-using a few annotated images, a short unannotated video clip of a wheat field, and several video clips with no wheat-to train a customized U-Net model. Considering the distribution shift between the synthesized and real images, we apply three domain adaptation steps to gradually bridge the domain gap. Only using two annotated images, we achieved a Dice score of 0.89 on the internal test set. When further evaluated on a diverse external dataset collected from 18 different domains across five countries, this model achieved a Dice score of 0.73. To expose the model to images from different growth stages and environmental conditions, we incorporated two annotated images from each of the 18 domains to further fine-tune the model. This increased the Dice score to 0.91. The result highlights the utility of the proposed approach in the absence of large-annotated datasets. Although our use case is wheat head segmentation, the proposed approach can be extended to other segmentation tasks with similar characteristics of irregularly repeating patterns of object instances.
| S-EPMC10013790 | biostudies-literature