2018/01/23 by Korsuk Sirinukunwattana, David Snead, Sirinukunwattana, Korsuk +15
Computer Science · Medicine · #AI in cancer detection #Colorectal Cancer Surgical Treatments #Computer Vision and Pattern Recognition (cs.CV) #FOS: Biological sciences #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #Radiomics and Machine Learning in Medical Imaging #Tissues and Organs (q-bio.TO) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.1801.07451
openalex publication_date 2018/01/23 · openalex created_date 2022/09/10 · openalex updated_date 2026/07/28
Distant metastasis is the major cause of death in colorectal cancer (CRC).\nPatients at high risk of developing distant metastasis could benefit from\nappropriate adjuvant and follow-up treatments if stratified accurately at an\nearly stage of the disease. Studies have increasingly recognized the role of\ndiverse cellular components within the tumor microenvironment in the\ndevelopment and progression of CRC tumors. In this paper, we show that a new\nmethod of automated analysis of digitized images from colorectal cancer tissue\nslides can provide important estimates of distant metastasis-free survival\n(DMFS, the time before metastasis is first observed) on the basis of details of\nthe microenvironment. Specifically, we determine what cell types are found in\nthe vicinity of other cell types, and in what numbers, rather than\nconcentrating exclusively on the cancerous cells. We then extract novel tissue\nphenotypic signatures using statistical measurements about tissue composition.\nSuch signatures can underpin clinical decisions about the advisability of\nvarious types of adjuvant therapy.\n