2016/06/20 by Mitko Veta, P. J. van Diest, Veta, Mitko +3 · 2 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · Medicine · #AI in cancer detection #Breast Cancer Treatment Studies #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Medical Image Segmentation Techniques #Radiomics and Machine Learning in Medical Imaging
paper · pdf · doi:10.48550/arxiv.1606.06127
openalex publication_date 2016/06/20 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
The size of nuclei in histological preparations from excised breast tumors is\npredictive of patient outcome (large nuclei indicate poor outcome).\nPathologists take into account nuclear size when performing breast cancer\ngrading. In addition, the mean nuclear area (MNA) has been shown to have\nindependent prognostic value. The straightforward approach to measuring nuclear\nsize is by performing nuclei segmentation. We hypothesize that given an image\nof a tumor region with known nuclei locations, the area of the individual\nnuclei and region statistics such as the MNA can be reliably computed directly\nfrom the image data by employing a machine learning model, without the\nintermediate step of nuclei segmentation. Towards this goal, we train a deep\nconvolutional neural network model that is applied locally at each nucleus\nlocation, and can reliably measure the area of the individual nuclei and the\nMNA. Furthermore, we show how such an approach can be extended to perform\ncombined nuclei detection and measurement, which is reminiscent of\ngranulometry.\n