{"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/survivalnet-predicting-patient-survival-from","title":"SurvivalNet: Predicting patient survival from diffusion weighted magnetic resonance images using cascaded fully convolutional and 3D convolutional neural networks","arxiv_id":"1702.05941","date":"2017-02-20","proceeding":null,"authors":["Patrick Ferdinand Christ","Florian Ettlinger","Georgios Kaissis","Sebastian Schlecht","Freba Ahmaddy","Felix Grün","Alexander Valentinitsch","Seyed-Ahmad Ahmadi","Rickmer Braren","Bjoern Menze"],"abstract":"Automatic non-invasive assessment of hepatocellular carcinoma (HCC)\nmalignancy has the potential to substantially enhance tumor treatment\nstrategies for HCC patients. In this work we present a novel framework to\nautomatically characterize the malignancy of HCC lesions from DWI images. We\npredict HCC malignancy in two steps: As a first step we automatically segment\nHCC tumor lesions using cascaded fully convolutional neural networks (CFCN). A\n3D neural network (SurvivalNet) then predicts the HCC lesions' malignancy from\nthe HCC tumor segmentation. We formulate this task as a classification problem\nwith classes being \"low risk\" and \"high risk\" represented by longer or shorter\nsurvival times than the median survival. We evaluated our method on DWI of 31\nHCC patients. Our proposed framework achieves an end-to-end accuracy of 65%\nwith a Dice score for the automatic lesion segmentation of 69% and an accuracy\nof 68% for tumor malignancy classification based on expert annotations. We\ncompared the SurvivalNet to classical handcrafted features such as Histogram\nand Haralick and show experimentally that SurvivalNet outperforms the\nhandcrafted features in HCC malignancy classification. End-to-end assessment of\ntumor malignancy based on our proposed fully automatic framework corresponds to\nassessment based on expert annotations with high significance (p>0.95).","url_abs":"http://arxiv.org/abs/1702.05941v1","url_pdf":"http://arxiv.org/pdf/1702.05941v1.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":"survivalnet-predicting-patient-survival-from","repo_url":"https://github.com/FelixGruen/tensorflow-u-net","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"lesion-segmentation","task_name":"Lesion Segmentation"},{"task_slug":"tumor-segmentation","task_name":"Tumor Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}