Automated Detection and Segmentation of Early Gastric Cancer from Endoscopic Images Using Mask R-CNN
Source abstract
Abstract
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.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Gastric Cancer Management and Outcomes · Colorectal Cancer Screening and Detection · Gastrointestinal Bleeding Diagnosis and Treatment
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Medicine, Fujita Health University, Toyoake, Aichi 470-1192, Japan
Graduate School of Health Sciences, Fujita Health University, Toyoake, Aichi 470-1192, Japan
Faculty of Engineering, Gifu University, Gifu, Gifu 501-1194, Japan
References (28)
Show source-provided references
1. Global, regional, and national cancer incidence, mortality, years of life lost, years lived with disability, and disability-adjusted life-years for 29 cancer groups, 1990 to 2016: A systematic analysis for the global burden of disease study global burden of disease cancer collaboration10.1001/jamaoncol.2018.2706 ↗
2. Karger Publishers (2020, April 30). GLOBOCAN 2012: Estimated Cancer Incidence, Mortality, and Prevalence Worldwide in 2012. Available online: http://globocan.iarc.fr/Pages/fact_sheets_cancer.aspx.
3. Increases in United States life expectancy through reductions in injury-related death10.1186/s12963-017-0150-4 ↗
4. Comparing mass screening techniques for gastric cancer in Japan
5. Ultrathin endoscopy versus high-resolution endoscopy for diagnosing superficial gastric neoplasia10.1016/j.gie.2008.10.064 ↗
6. How commonly is upper gastrointestinal cancer missed at endoscopy? A meta-analysis10.1055/s-0034-1365524 ↗
7. Evaluation of the diagnostic accuracy of gastroscopy to detect gastric tumours: Clinicopathological features and prognosis of patients with gastric cancer missed on endoscopy10.1097/00042737-200512000-00013 ↗
8. Difference in accuracy between gastroscopy and colonoscopy for detection of cancer
9. Missed diagnoses in patients with upper gastrointestinal cancers10.1055/s-2004-825853 ↗
10. Deep learning of the sectional appearances of 3D CT images for anatomical structure segmentation based on an FCN voting method10.1002/mp.12480 ↗
11. A computer-aided diagnostic system to characterize CT focal liver lesions: Design and optimization of a neural network classifier10.1109/TITB.2003.813793 ↗
12. Teramoto, A., Tsukamoto, T., Yamada, A., Kiriyama, Y., Imaizumi, K., Saito, K., and Fujita, H. (2020). Deep learning approach to classification of lung cytological images: Two-step training using actual and synthesized images by progressive growing of generative adversarial networks. PLoS ONE, 15.10.1371/journal.pone.0229951 ↗
13. Cerebral micro-bleeding identification based on a nine-layer convolutional neural network with stochastic pooling10.1002/cpe.5130 ↗
14. Alcoholism identification via convolutional neural network based on parametric ReLU, dropout, and batch normalization10.1007/s00521-018-3924-0 ↗
15. Jia, X., and Meng, M.Q. (2016, January 16–20). A deep convolutional neural network for bleeding detection in wireless capsule endoscopy images. Proceedings of the 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Orlando, FL, USA.10.1109/EMBC.2016.7590783 ↗
16. Sakai, Y., Takemoto, S., Hori, K., Nishimura, M., Ikematsu, H., Yano, T., and Yokota, H. (2018, January 17–21). Automatic detection of early gastric cancer in endoscopic images using a transferring convolutional neural network. Proceedings of the 40th International Conference of the IEEE Engineering in Medicine and Biology Society, Honolulu, HI, USA.10.1109/EMBC.2018.8513274 ↗
17. Yoon, H.J., Kim, S., Kim, J.-H., Keum, J.-S., Oh, S.-I., Jo, J., Chun, J., Youn, Y.H., Park, H., and Kwon, I.G. (2019). A lesion-based convolutional neural network improves endoscopic detection and depth prediction of early gastric cancer. J. Clin. Med., 8.10.3390/jcm8091310 ↗
18. Application of artificial intelligence using a convolutional neural network for detecting gastric cancer in endoscopic images10.1007/s10120-018-0793-2 ↗
19. Long, J., Shelhamer, E., and Darrell, T. (2015, January 7–12). Fully convolutional networks for semantic segmentation. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA.10.1109/CVPR.2015.7298965 ↗
20. U-Net: Convolutional networks for biomedical image segmentation10.1007/978-3-319-24574-4_28 ↗
21. Mask R-CNN10.1109/TPAMI.2018.2844175 ↗
22. Japanese Gastric Cancer Association (2011). Japanese classification of gastric carcinoma: 3rd English edition. Gastric Cancer, 14, 101–112.10.1007/s10120-011-0041-5 ↗
23. Characteristic endoscopic and magnified endoscopic findings in the normal stomach without Helicobacter Pylori infection10.1046/j.1440-1746.2002.02665.x ↗
24. An endoscopic recognition of the atrophic border and its significance in chronic gastritis10.1055/s-0028-1098086 ↗
25. Automated classification of benign and malignant cells from lung cytological images using deep convolutional neural network10.1016/j.imu.2019.100205 ↗
26. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep residual learning for image recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
27. Abdulla, W. (2020, May 10). Mask R-CNN for Object Detection and Instance Segmentation on Keras and TensorFlow. GitHub Repos. Available online: https://github.com/matterport/Mask_RCNN.
28. Estimating the error rate of a prediction rule: Improvement on cross-validation10.1080/01621459.1983.10477973 ↗