Abstract
BackgroundAn automated image analysis system, e-Pathologist, was developed to improve the quality of colorectal biopsy diagnostics in routine pathology practice.ObjectiveThe aim of the study was to evaluate the classification accuracy of the e-Pathologist image analysis software in the setting of routine pathology practice in two institutions.Materials and methodsIn total, 1328 colorectal tissue specimens were consecutively obtained from two hospitals (1077 tissues from Tokyo hospital, and 251 tissues from East hospital) and the stained specimen slides were anonymized and digitized. At least two experienced gastrointestinal pathologists evaluated each slide for pathological diagnosis. We compared the 3-tier classification results (carcinoma or suspicion of carcinoma, adenoma, and lastly negative for a neoplastic lesion) between the human pathologists and that of e-Pathologist.ResultsFor the Tokyo hospital specimens, all carcinoma tissues were correctly classified (n=112), and 9.9% (80/810) of the adenoma tissues were incorrectly classified as negative. For the East hospital specimens, 0 out of the 51 adenoma tissues were incorrectly classified as negative while 9.3% (11/118) of the carcinoma tissues were incorrectly classified as either adenoma, or negative. For the Tokyo and East hospital datasets, the undetected rate of carcinoma, undetected rate of adenoma, and over-detected proportion were 0% and 9.3%, 9.9% and 0%, and 36.1% and 27.1%, respectively.ConclusionsThis image analysis system requires some improvements; however, it has the potential to assist pathologists in quality improvement of routine pathological practice in the not too distant future.
Highlights
Colorectal cancer is a major cause of morbidity and mortality in Japan, where it is the leading cause of death among women, and the third leading cause of death among men [1]
Esgiar et al [2] performed classification of normal and cancerous classes based on texture analysis techniques, and reported the classification result on a dataset that consists of 44 normal and 58 cancer images captured using a microscope with a 40x objective lens, and 512x512 image resolution
Altunbay et al [3] provided a method based on graph algorithm, and reported the classification result on a test image set consisting of normal specimens, low-grade cancerous specimens, and 29 high-grade cancerous specimens, captured by a microscope at 20x magnification, with a resolution of 480x640 pixels
Summary
Colorectal cancer is a major cause of morbidity and mortality in Japan, where it is the leading cause of death among women, and the third leading cause of death among men (from malignant neoplasms) [1]. While the number of pathologists has remained essentially constant, the number of cases has increased, and the diagnostic burden on pathologists has grown Under these circumstances mentioned above, histological image analysis methods have been proposed for colorectal cancer detection [2,3,4,5,6]. Esgiar et al [2] performed classification of normal and cancerous classes based on texture analysis techniques, and reported the classification result on a dataset that consists of 44 normal and 58 cancer images captured using a microscope with a 40x objective lens, and 512x512 image resolution. Altunbay et al [3] provided a method based on graph algorithm, and reported the classification result on a test image set consisting of normal specimens, low-grade cancerous specimens, and high-grade cancerous specimens, captured by a microscope at 20x magnification, with a resolution of 480x640 pixels. An automated image analysis system, e-Pathologist, was developed to improve the quality of colorectal biopsy diagnostics in routine pathology practice
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
