Challenge for Diagnostic Assessment of Deep Learning Algorithm for Metastases Classification in Sentinel Lymph Nodes on Frozen Tissue Section Digital Slides in Women with Breast Cancer / Journal of the Korean Cancer Association, 대한암학회지

Purpose@#Assessing the status of metastasis in sentinel lymph nodes (SLNs) by pathologists is an essential task for the accurate staging of breast cancer. However, histopathological evaluation of sentinel lymph nodes by a pathologist is not easy and is a tedious and time-consuming task. The purpose of this study is to review a challenge competition (HeLP 2018) to develop automated solutions for the classification of metastases in hematoxylin and eosin–stained frozen tissue sections of SLNs in breast cancer patients. @*Materials and Methods@#A total of 297 digital slides were obtained from frozen SLN sections, which include post–neoadjuvant cases (n = 144, 48.5%) in Asan Medical Center, South Korea. The slides were divided into training, development, and validation sets. All of the imaging datasets have been manually segmented by expert pathologists. A total of 10 participants were allowed to use the Kakao challenge platform for six weeks with two P40 GPUs. The algorithms were assessed in terms of the AUC (area under receiver operating characteristic curve). @*Results@#The top three teams showed 0.986, 0.985, and 0.945 AUCs for the development set and 0.805, 0.776, and 0.765 AUCs for the validation set. Micrometastatic tumors, neoadjuvant systemic therapy, invasive lobular carcinoma, and histologic grade 3 were associated with lower diagnostic accuracy. @*Conclusion@#In a challenge competition, accurate deep learning algorithms have been developed, which can be helpful in making frozen diagnosis of intraoperative sentinel lymph node biopsy. Whether this approach has clinical utility will require evaluation in a clinical setting

A Study on the Expression of Proliferating Cell Nuclear Antigen and Apoptosis of the Hepatocellular Carcinoma in Human and Hepatitis B Virus X Transgenic Mice

BACKGROUND: This experiment was designed to study the cell kinetics of hepatocellular carcinoma (HCC) in both hepatitis B virus X (HBx) transgenic mice and humans. METHODS: The immunohistochemical stain of proliferating cell nuclear antigen (PCNA) and TdT-mediated dUTP-biotin nick end labeling (TUNEL) assay of apoptosis were used on formalin fixed-paraffin embedded tissues. RESULTS: PCNA labeling indices (PCNA-LI) in the liver of HBx transgenic mice were markedly increased in HCC (11.3%) compare to the dysplastic areas (1.3%) and in the liver of non-transgenic littermates (0.1%). There was no significant difference of PCNA-LI in the dysplastic areas between HCC developed mice and non-HCC developed mice. Apoptosis labeling indices (Apoptosis-LI) in both the dysplastic areas and HCC of HBx transgenic mice were similar to those of non-transgenic littermates. PCNA-LI was markedly increased in human HCC (28.9%) compare to the background of HCC (2.9%) and the control liver (2.9%). Apoptosis-LI was decreased in human HCC (0.3%) compare to the background of HCC (0.4%) and the control liver (1.0%). Conclusion : There is a marked increase of cell proliferating activity in human HCC and in HCC of HBx transgenic mice, and there is a decrease of apoptosis in human HCC, but not in HCC of HBx transgenic mice.

Comparison of Cell Proliferation between Chronic Ulcerative Colitisand Acute Self-limited Colitis

PURPOSE: The ulcerative colitis is a major chronic intestinal disease of unknown etiology affecting principally the rectum and left colon, and its incidence is markedly increasing in Korea. The main differential diagnosis of ulcerative colitis is an acute self-limited colitis. This study was performed to evaluate difference of cell kinetics between chronic ulcerative colitis and acute self-limited colitis. METHODS: The normal colon (n=25), acute self-limited colitis (n=25) and chronic ulcerative colitis (n=25) were investigated by using Ki-67 immunohistochemical staining for proliferation and TUNEL method for apoptosis. The Ki-67 labeling indices and TUNEL labeling indices were determined. RESULTS: The means of Ki-67 labeling indices in normal colon, acute self-limited colitis and chronic ulcerative colitis were 5.14 5.25%, 6.81 5.73%, 13.10 10.15%, respectively. And the means of TUNEL labeling indices in normal colon, acute self-limited colitis and chronic ulcerative colitis were 1.59 0.10%, 2.54 1.60%, 2.51 1.40%, respectively. CONCLUSIONS: The apoptosis is one of method of cell loss in both acute self-limited colitis and chronic ulcerative colitis. High proliferative activity of chronic ulcerative colitis may predispose to mutational events in colonic mucosa, therefore may be one of the increased cancer risk factors in chronic ulcerative colitis.