TY - JOUR
T1 - Automated detection and segmentation of early gastric cancer from endoscopic images using mask R-CNN
AU - Shibata, Tomoyuki
AU - Teramoto, Atsushi
AU - Yamada, Hyuga
AU - Ohmiya, Naoki
AU - Saito, Kuniaki
AU - Fujita, Hiroshi
N1 - Publisher Copyright:
© 2020 by the authors.
PY - 2020/6/1
Y1 - 2020/6/1
N2 - Gastrointestinal endoscopy is widely conducted for the early detection of gastric cancer. However, it is often difficult to detect early gastric cancer lesions and accurately evaluate the invasive regions. Our study aimed to develop a detection and segmentation method for early gastric cancer regions from gastrointestinal endoscopic images. In this method, we first collected 1208 healthy and 533 cancer images. The gastric cancer region was detected and segmented from endoscopic images using Mask R-CNN, an instance segmentation method. An endoscopic image was provided to the Mask R-CNN, and a bounding box and a label image of the gastric cancer region were obtained. As a performance evaluation via five-fold cross-validation, sensitivity and false positives (FPs) per image were 96.0% and 0.10 FP/image, respectively. In the evaluation of segmentation of the gastric cancer region, the average Dice index was 71%. These results indicate that our proposed scheme may be useful for the detection of gastric cancer and evaluation of the invasive region in gastrointestinal endoscopy.
AB - Gastrointestinal endoscopy is widely conducted for the early detection of gastric cancer. However, it is often difficult to detect early gastric cancer lesions and accurately evaluate the invasive regions. Our study aimed to develop a detection and segmentation method for early gastric cancer regions from gastrointestinal endoscopic images. In this method, we first collected 1208 healthy and 533 cancer images. The gastric cancer region was detected and segmented from endoscopic images using Mask R-CNN, an instance segmentation method. An endoscopic image was provided to the Mask R-CNN, and a bounding box and a label image of the gastric cancer region were obtained. As a performance evaluation via five-fold cross-validation, sensitivity and false positives (FPs) per image were 96.0% and 0.10 FP/image, respectively. In the evaluation of segmentation of the gastric cancer region, the average Dice index was 71%. These results indicate that our proposed scheme may be useful for the detection of gastric cancer and evaluation of the invasive region in gastrointestinal endoscopy.
UR - http://www.scopus.com/inward/record.url?scp=85086101995&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85086101995&partnerID=8YFLogxK
U2 - 10.3390/app10113842
DO - 10.3390/app10113842
M3 - Article
AN - SCOPUS:85086101995
SN - 2076-3417
VL - 10
JO - Applied Sciences (Switzerland)
JF - Applied Sciences (Switzerland)
IS - 11
M1 - 3842
ER -