An Automatic Detection Approach of Traumatic Bleeding Based on 3D CNN Networks

Lei YANG  Tingxiao YANG  Hiroki KIMURA  Yuichiro YOSHIMURA  Kumiko ARAI  Taka-aki NAKADA  Huiqin JIANG  Toshiya NAKAGUCHI  

Publication
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences   Vol.E104-A   No.6   pp.887-896
Publication Date: 2021/06/01
Publicized: 2021/01/18
Online ISSN: 1745-1337
DOI: 10.1587/transfun.2020IMP0014
Type of Manuscript: Special Section PAPER (Special Section on Image Media Quality)
Category: 
Keyword: 
CT,  CNN,  traumatic bleeding,  segmentation,  classification,  

Full Text: PDF>>
Buy this Article




Summary: 
In medical fields, detecting traumatic bleedings has always been a difficult task due to the small size, low contrast of targets and large number of images. In this work we propose an automatic traumatic bleeding detection approach from contrast enhanced CT images via deep CNN networks, containing segmentation process and classification process. CT values of DICOM images are extracted and processed via three different window settings first. Small 3D patches are cropped from processed images and segmented by a 3D CNN network. Then segmentation results are converted to point cloud data format and classified by a classifier. The proposed pre-processing approach makes the segmentation network be able to detect small and low contrast targets and achieve a high sensitivity. The additional classification network solves the boundary problem and short-sighted problem generated during the segmentation process to further decrease false positives. The proposed approach is tested with 3 CT cases containing 37 bleeding regions. As a result, a total of 34 bleeding regions are correctly detected, the sensitivity reaches 91.89%. The average false positive number of test cases is 1678. 46.1% of false positive predictions are decreased after being classified. The proposed method is proved to be able to achieve a high sensitivity and be a reference of medical doctors.