2019/12/22 by Xavier Rafael-Palou, Rafael-Palou, Xavier, Anton Aubanell +11
Computer Science · Medicine · #AI in cancer detection #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #Lung Cancer Diagnosis and Treatment #Radiomics and Machine Learning in Medical Imaging #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.1912.10525
openalex publication_date 2019/12/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Lung cancer follow-up is a complex, error prone, and time consuming task for\nclinical radiologists. Several lung CT scan images taken at different time\npoints of a given patient need to be individually inspected, looking for\npossible cancerogenous nodules. Radiologists mainly focus their attention in\nnodule size, density, and growth to assess the existence of malignancy. In this\nstudy, we present a novel method based on a 3D siamese neural network, for the\nre-identification of nodules in a pair of CT scans of the same patient without\nthe need for image registration. The network was integrated into a two-stage\nautomatic pipeline to detect, match, and predict nodule growth given pairs of\nCT scans. Results on an independent test set reported a nodule detection\nsensitivity of 94.7%, an accuracy for temporal nodule matching of 88.8%, and a\nsensitivity of 92.0% with a precision of 88.4% for nodule growth detection.\n