Each block was sliced into 4-μm-thick sections. The specimens were fixed in 10% buffered formalin and embedded in paraffin. We consecutively collected a total of 3062 gastric biopsy specimens between January 19 and April 30 in 2015 at the National Cancer Center (Tsukiji and Kashiwa campus). The study was conducted in accordance with the Declaration of Helsinki, and with the approval of the Institutional Review Board of the National Cancer Center, Tokyo, Japan. Patient selection, tissue section preparation, and pathological diagnosis
Sims 4 cancer mod 2018 software#
The aim of the present study was to evaluate the accuracy of the classification of the e-Pathologist image analysis software and clarify the requirements for using an automated screening system in clinical settings. However, the validity of this software analysis in routine pathological practice remains unclear. NEC Corporation has developed the e-Pathologist image analysis software that can classify digitized histological images of gastric biopsy specimens into three categories that correspond to carcinoma or suspicion of carcinoma (positive), adenoma or suspicion of a neoplastic lesion (caution), and no malignancy (negative). Moreover, application of automated image analysis is expected to contribute to the quality control of routine pathological diagnosis. This considerable workload for surgical pathologists needs to be reduced automated screening for negative specimens that do not require the review of a pathologist could be effective. Gastric cancer and colorectal cancer are among the five major cancers in Japan thus, a large number of endoscopically obtained specimens are being submitted for pathological analysis. The need for automated image analysis of gastrointestinal cancers has been increasing. However, there has been no report on automated image analysis and histological classification in clinical settings for gastrointestinal cancers. For supporting diagnostic procedures, various novel devices have been reported to be effective, including an automated screening system for cytopathology, automated analysis for immunohistochemical biomarkers, and automated morphological analysis and classification for hematoxylin and eosin (H&E)-stained slides.
ConclusionsĪlthough there are limitations and requirements for applying automated histopathological classification of gastric biopsy specimens in the clinical setting, the results of the present study are promising.ĭigital pathology techniques including automated image analysis have been developed and widely utilized in research and in the practice of surgical pathology. For the negative biopsy specimens, the concordance rate was 90.6% (1033/1140), but for the positive biopsy specimens, the concordance rate was less than 50%. The kappa coefficient was 0.28 (95% CI, 0.26–0.30 fair agreement). For the three-tier classification, the overall concordance rate was 55.6% (1702/3062). Of 3062 cases, 33.4% showed an abnormal finding. We compared the three-tier (positive for carcinoma or suspicion of carcinoma caution for adenoma or suspicion of a neoplastic lesion or negative for a neoplastic lesion) or two-tier (negative or non-negative) classification results of human pathologists and of the e-Pathologist. At least two experienced gastrointestinal pathologists evaluated each slide for pathological diagnosis. The specimen slides were anonymized and digitized.
MethodsĪ total of 3062 gastric biopsy specimens were consecutively obtained and stained. The aim of the present study was to evaluate the classification accuracy of the e-Pathologist image analysis software.
Automated image analysis has been developed currently in the field of surgical pathology.