{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/chest-x-rays-image-inpainting-with-context","title":"Context Encoding Chest X-rays","arxiv_id":"1812.00964","date":"2018-12-03","proceeding":null,"authors":["Davide Belli","Shi Hu","Ecem Sogancioglu","Bram van Ginneken"],"abstract":"Chest X-rays are one of the most commonly used technologies for medical\ndiagnosis. Many deep learning models have been proposed to improve and automate\nthe abnormality detection task on this type of data. In this paper, we propose\na different approach based on image inpainting under adversarial training first\nintroduced by Goodfellow et al. We configure the context encoder model for this\ntask and train it over 1.1M 128x128 images from healthy X-rays. The goal of our\nmodel is to reconstruct the missing central 64x64 patch. Once the model has\nlearned how to inpaint healthy tissue, we test its performance on images with\nand without abnormalities. We discuss and motivate our results considering\nPSNR, MSE and SSIM scores as evaluation metrics. In addition, we conduct a 2AFC\nobserver study showing that in half of the times an expert is unable to\ndistinguish real images from the ones reconstructed using our model. By\ncomputing and visualizing the pixel-wise difference between the source and the\nreconstructed images, we can highlight abnormalities to simplify further\ndetection and classification tasks.","url_abs":"http://arxiv.org/abs/1812.00964v2","url_pdf":"http://arxiv.org/pdf/1812.00964v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"chest-x-rays-image-inpainting-with-context","repo_url":"https://github.com/davide-belli/context-encoding-chest-xrays","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"anomaly-detection","task_name":"Anomaly Detection"},{"task_slug":"image-inpainting","task_name":"Image Inpainting"},{"task_slug":"medical-diagnosis","task_name":"Medical Diagnosis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}