To evaluate the generalizability of the system to new patient populations and in the presence of diseases not seen in the training set, we used four de-identified datasets from three countries, including two publicly available tuberculosis datasets and two COVID-19 datasets from Northwestern Medicine. Though the evaluations on DS-1 and CXR-14 contained a wide range of abnormalities, a possible use-case would be to utilize such an abnormality detector in novel or unforeseen settings with diseases that it had not encountered before. The system achieved areas under the receiver operating characteristic curve ( AUROC) of 0.87 on DS-1 and 0.94 on CXR-14 (higher is better). The labels for these two test sets were annotated for the purposes of this project by a group of US board-certified radiologists. To evaluate how well the system generalizes to new patient populations, we compared its performance on two datasets consisting of a wide spectrum of abnormalities: the test split from the Apollo Hospitals dataset (DS-1), and the publicly available ChestX-ray14 (CXR-14). Each CXR was assigned a label of either “normal” or “abnormal” using a regular expression–based natural language processing approach on the associated radiology reports. We trained the model using over 200,000 de-identified CXRs from the Apollo Hospitals in India. The deep learning system we used is based on the EfficientNet-B7 architecture, pre-trained on ImageNet. We are also releasing our set of radiologists’ labels 1 for the test set used in this study for the publicly available ChestX-ray14 dataset.Ī Deep Learning System for Detecting Abnormal Chest X-rays We find that the model performs well on general abnormalities, as well as unseen examples of tuberculosis and COVID-19. In “ Deep Learning for Distinguishing Normal versus Abnormal Chest Radiographs and Generalization to Two Unseen Diseases Tuberculosis and COVID-19”, published in Scientific Reports, we present a model that can distinguish between normal and abnormal CXRs across multiple de-identified datasets and settings. However, developing a classifier to do this is challenging due to the wide variety of abnormal findings that present on CXRs. Since an initial triaging step is to determine whether a CXR contains concerning abnormalities, a general-purpose algorithm that identifies X-rays containing any sort of abnormality could significantly facilitate the workflow. For example, a pneumothorax detector is not expected to highlight nodules suggestive of cancer, and a tuberculosis detector may not identify findings specific to pneumonia. By virtue of being trained to detect a specific disease, however, the utility of these algorithms may be limited in a general clinical setting, where a wide variety of abnormalities could surface. Indeed, a plethora of algorithms have already been developed to detect specific conditions, such as lung cancer, tuberculosis and pneumothorax. The adoption of machine learning (ML) for medical imaging applications presents an exciting opportunity to improve the availability, latency, accuracy, and consistency of chest X-ray (CXR) image interpretation. Chest xray normal vs abnormal software#Posted by Zaid Nabulsi, Software Engineer and Po-Hsuan Cameron Chen, Software Engineer, Google Health
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |