CheX-Nomaly: Segmenting Lung Abnormalities from Chest Radiographs using Machine Learning
This addresses the challenge of reducing perceptual errors in chest disease diagnosis for healthcare providers, though it is incremental as it builds on existing segmentation models with novel techniques.
The paper tackles the problem of misdiagnosing chest radiograph abnormalities due to perceptual errors by developing CheX-Nomaly, a binary localization U-net model that achieves generalizability across 14 diseases and unseen ones, improving abnormality segmentation precision.
The global challenge in chest radiograph X-ray (CXR) abnormalities often being misdiagnosed is primarily associated with perceptual errors, where healthcare providers struggle to accurately identify the location of abnormalities, rather than misclassification errors. We currently address this problem through disease-specific segmentation models. Unfortunately, these models cannot be released in the field due to their lack of generalizability across all thoracic diseases. A binary model tends to perform poorly when it encounters a disease that isn't represented in the dataset. We present CheX-nomaly: a binary localization U-net model that leverages transfer learning techniques with the incorporation of an innovative contrastive learning approach. Trained on the VinDr-CXR dataset, which encompasses 14 distinct diseases in addition to 'no finding' cases, my model achieves generalizability across these 14 diseases and others it has not seen before. We show that we can significantly improve the generalizability of an abnormality localization model by incorporating a contrastive learning method and dissociating the bounding boxes with its disease class. We also introduce a new loss technique to apply to enhance the U-nets performance on bounding box segmentation. By introducing CheX-nomaly, we offer a promising solution to enhance the precision of chest disease diagnosis, with a specific focus on reducing the significant number of perceptual errors in healthcare.