Classification of the Confocal Microscopy Images of Colorectal Tumor and Inflammatory Colitis Mucosa Tissue Using Deep Learning

被引:0
作者
Jeong, Jaehoon [1 ]
Hong, Seung Taek [2 ,3 ]
Ullah, Ihsan [1 ]
Kim, Eun Sun [2 ,3 ]
Park, Sang Hyun [1 ]
机构
[1] Daegu Gyeongbuk Inst Sci & Technol DGIST, Dept Robot Engn, 333 Techno Jungang Daero, Daegu 42988, South Korea
[2] Korea Univ, Coll Med, Inst Gastrointestinal Med Instrument Res, 73 Inchon Ro, Seoul 02841, South Korea
[3] Korea Univ, Coll Med, Dept Internal Med, 73 Inchon Ro, Seoul 02841, South Korea
关键词
colorectal neoplasm; colorectal inflammation; confocal microscopy; deep learning; machine learning; LASER ENDOMICROSCOPY; BOWEL-DISEASE; ARTIFICIAL-INTELLIGENCE; CANCER; ENDOSCOPY; DIAGNOSIS; RISK; COLONOSCOPY; PREVENTION; NEOPLASIA;
D O I
10.3390/diagnostics12020288
中图分类号
R5 [内科学];
学科分类号
1002 ; 100201 ;
摘要
Confocal microscopy image analysis is a useful method for neoplasm diagnosis. Many ambiguous cases are difficult to distinguish with the naked eye, thus leading to high inter-observer variability and significant time investments for learning this method. We aimed to develop a deep learning-based neoplasm classification model that classifies confocal microscopy images of 10x magnified colon tissues into three classes: neoplasm, inflammation, and normal tissue. ResNet50 with data augmentation and transfer learning approaches was used to efficiently train the model with limited training data. A class activation map was generated by using global average pooling to confirm which areas had a major effect on the classification. The proposed method achieved an accuracy of 81%, which was 14.05% more accurate than three machine learning-based methods and 22.6% better than the predictions made by four endoscopists. ResNet50 with data augmentation and transfer learning can be utilized to effectively identify neoplasm, inflammation, and normal tissue in confocal microscopy images. The proposed method outperformed three machine learning-based methods and identified the area that had a major influence on the results. Inter-observer variability and the time required for learning can be reduced if the proposed model is used with confocal microscopy image analysis for diagnosis.
引用
收藏
页数:10
相关论文
共 50 条
[1]   Colonoscopy Is Associated With a Reduced Risk for Colon Cancer and Mortality in Patients With Inflammatory Bowel Diseases [J].
Ananthakrishnan, Ashwin N. ;
Cagan, Andrew ;
Cai, Tianxi ;
Gainer, Vivian S. ;
Shaw, Stanley Y. ;
Churchill, Susanne ;
Karlson, Elizabeth W. ;
Murphy, Shawn N. ;
Kohane, Isaac ;
Liao, Katherine P. .
CLINICAL GASTROENTEROLOGY AND HEPATOLOGY, 2015, 13 (02) :322-U163
[2]  
Breiman L., 2001, Machine Learning, V45, P5
[3]   Artificial Intelligence Enhances Studies on Inflammatory Bowel Disease [J].
Chen, Guihua ;
Shen, Jun .
FRONTIERS IN BIOENGINEERING AND BIOTECHNOLOGY, 2021, 9
[4]  
Chen T, 2016, ARXIV
[5]   Role of endoscopy in the staging and management of colorectal cancer [J].
Fisher, Deborah A. ;
Shergill, Amandeep K. ;
Early, Dayna S. ;
Acosta, Ruben D. ;
Chandrasekhara, Vinay ;
Chathadi, Krishnavel V. ;
Decker, G. Anton ;
Evans, John A. ;
Fanelli, Robert D. ;
Foley, Kimberly Q. ;
Fonkalsrud, Lisa ;
Hwang, Joo Ha ;
Jue, Terry ;
Khashab, Mouen A. ;
Lightdale, Jenifer R. ;
Muthusamy, V. Raman ;
Pasha, Shabana F. ;
Saltzman, John R. ;
Sharaf, Ravi ;
Cash, Brooks D. .
GASTROINTESTINAL ENDOSCOPY, 2013, 78 (01) :8-12
[6]  
Gessert N., 2019, BILDVERARBEITUNG F R, P327, DOI [10.1007/978-3-658-25326-4_72, DOI 10.1007/978-3-658-25326-4_72]
[7]   Radiomics: Images Are More than Pictures, They Are Data [J].
Gillies, Robert J. ;
Kinahan, Paul E. ;
Hricak, Hedvig .
RADIOLOGY, 2016, 278 (02) :563-577
[8]   Classification Criteria for Advanced Adenomas of the Colon by Using Probe-Based Confocal Laser Endomicroscopy: A Preliminary Study [J].
Gomez, Victoria ;
Shahid, Muhammad W. ;
Krishna, Murli ;
Heckman, Michael G. ;
Crook, Julia E. ;
Wallace, Michael B. .
DISEASES OF THE COLON & RECTUM, 2013, 56 (08) :967-973
[9]   Artificial intelligence applications in inflammatory bowel disease: Emerging technologies and future directions [J].
Gubatan, John ;
Levitte, Steven ;
Patel, Akshar ;
Balabanis, Tatiana ;
Wei, Mike T. ;
Sinha, Sidhartha R. .
WORLD JOURNAL OF GASTROENTEROLOGY, 2021, 27 (17) :1920-1935
[10]   Deep Residual Learning for Image Recognition [J].
He, Kaiming ;
Zhang, Xiangyu ;
Ren, Shaoqing ;
Sun, Jian .
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :770-778