{"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/liver-lesion-detection-from-weakly-labeled","title":"Liver Lesion Detection from Weakly-labeled Multi-phase CT Volumes with a Grouped Single Shot MultiBox Detector","arxiv_id":"1807.00436","date":"2018-07-02","proceeding":null,"authors":["Sang-gil Lee","Jae Seok Bae","Hyunjae Kim","Jung Hoon Kim","Sungroh Yoon"],"abstract":"We present a focal liver lesion detection model leveraged by custom-designed\nmulti-phase computed tomography (CT) volumes, which reflects real-world\nclinical lesion detection practice using a Single Shot MultiBox Detector (SSD).\nWe show that grouped convolutions effectively harness richer information of the\nmulti-phase data for the object detection model, while a naive application of\nSSD suffers from a generalization gap. We trained and evaluated the modified\nSSD model and recently proposed variants with our CT dataset of 64 subjects by\nfive-fold cross validation. Our model achieved a 53.3% average precision score\nand ran in under three seconds per volume, outperforming the original model and\nstate-of-the-art variants. Results show that the one-stage object detection\nmodel is a practical solution, which runs in near real-time and can learn an\nunbiased feature representation from a large-volume real-world detection\ndataset, which requires less tedious and time consuming construction of the\nweak phase-level bounding box labels.","url_abs":"http://arxiv.org/abs/1807.00436v1","url_pdf":"http://arxiv.org/pdf/1807.00436v1.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":"liver-lesion-detection-from-weakly-labeled","repo_url":"https://github.com/L0SG/grouped-ssd-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"computed-tomography-ct","task_name":"Computed Tomography (CT)"},{"task_slug":"lesion-detection","task_name":"Lesion Detection"},{"task_slug":"lesion-segmentation","task_name":"Lesion Segmentation"},{"task_slug":"medical-object-detection","task_name":"Medical Object Detection"},{"task_slug":"object-detection","task_name":"Object Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}