Diagnostic Assessment of Deep Learning Algorithms for Frozen Tissue Section Analysis in Women with Breast Cancer.

PURPOSE: Assessing the metastasis status of the sentinel lymph nodes (SLNs) for hematoxylin and eosin-stained frozen tissue sections by pathologists is an essential but tedious and time-consuming task that contributes to accurate breast cancer staging. This study aimed to review a challenge competition (HeLP 2019) for the development of automated solutions for classifying the metastasis status of breast cancer patients. Materials and Methods: A total of 524 digital slides were obtained from frozen SLN sections: 297 (56.7%) from Asan Medical Center (AMC) and 227 (43.4%) from Seoul National University Bundang Hospital (SNUBH), South Korea. The slides were divided into training, development, and validation sets, where the development set comprised slides from both institutions and training and validation set included slides from only AMC and SNUBH, respectively. The algorithms were assessed for area under the receiver operating characteristic curve (AUC) and measurement of the longest metastatic tumor diameter. The final total scores were calculated as the mean of the two metrics, and the three teams with AUC values greater than 0.500 were selected for review and analysis in this study. RESULTS: The top three teams showed AUC values of 0.891, 0.809, and 0.736 and major axis prediction scores of 0.525, 0.459, and 0.387 for the validation set. The major factor that lowered the diagnostic accuracy was micro-metastasis. CONCLUSION: In this challenge competition, accurate deep learning algorithms were developed that can be helpful for making a diagnosis on intraoperative SLN biopsy. The clinical utility of this approach was evaluated by including an external validation set from SNUBH.

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.

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 SLNs 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 SLN biopsy. Whether this approach has clinical utility will require evaluation in a clinical setting.

Current practice and usual care of major cervical disorders in Korea: A cross-sectional study of Korean health insurance review and assessment service national patient sample data.

Neck pain is a highly common condition and is the 4th major cause of years lived with disability. Previous literature has focused on the effect of specific treatments, and observations of actual practice are lacking to date. This study examined Korean health insurance review and assessment service (HIRA) claims data to the aim of assessing prevalence and comparing current medical practice and costs of cervical disorders in Korea.Current practice trends were determined through assessment of prevalence, total expenses, per-patient expense, average days in care, average days of visits, sociodemographic characteristics, distribution of medical costs, and frequency of treatment types of high frequency cervical disorders (cervical sprain/strain, cervical intervertebral disc displacement [IDD], and cervicalgia).Although the number of cervical IDD patients was few, total expenses, per-patient expense, average days in care, and average days of visits were highest. The proportion of women was higher than men in all 3 groups with highest prevalence in the ≥50s middle-aged population for IDD compared to sprain/strain. Primary care settings were commonly used for ambulatory care, of which approximately 70% chose orthopedic specialist treatment. In analysis of medical expenditure distribution, costs of visit (consultation) (22%-34%) and physical therapy (14%-16%) were in the top 3 for all 3 disorders. Although heat and electrical therapies were the most frequently used physical therapies, traction use was high in the cervical IDD group. In nonnarcotics, aceclofenac and diclofenac were the most commonly used NSAIDs, and pethidine was their counterpart in narcotics.This study investigated practice trends and cost distribution of treatment regimens for major cervical disorders, providing current usage patterns to healthcare policy decision makers, and the detailed treatment reports are expected to be of use to clinicians and researchers in understanding current usual care.

Assessment of the Toxicity and the Stability of Saeng Mak San by Using Repeated Intravenous Injections in Sprague-Dawley Rats.

OBJECTIVES: This study used repeated intravenous injections of Saeng Maek San (SMS) injection in Sprague-Dawley (SD) rats to assess the toxicity and the stability of SMS. METHODS: Six-week-old male and female SD rats reared by Orient bio Inc were chosen for this pilot study. They were randomly split into four groups: Group 1 (G1), the control group (0.3 mL of normal saline solution/day/animal), and Groups 2, 3 and 4 (G2, G3 and G4), the experimental groups (0.1, 0.2 and 0.3 mL/day/animal of SMS), respectively. Each animal received an intravenous injection of SMS once a day for four weeks. Clinical signs, body weight changes, and food consumption were monitored during the observation period, and urinalysis and hematology were conducted after four weeks of SMS or saline administration. RESULTS: No deaths occurred in any of the four groups during the observation period. Compared to the control group, male and female rats in groups 3 and 4 (0.2 and 0.3 mL/animal/day) showed hemoglobinuria, but the low-dosage group (G2, 0.1 mL/animal/day) showed no significant changes in the clinical signs test. No significant changes due to SMS were observed in the experimental groups regarding body weight changes, food consumption urinalysis, or hematology. CONCLUSION: During this study, no mortalities were observed in any of the experimental groups and no hemoglobinuria was observed in the low dosage group (0.1 mL/animal/day) while it was intermittently observed in groups 3 and 4 (0.2 and 0.3 mL/animal/day). Thus, we suggest that the no-observed adverse-effect level (NOAEL) is 0.1 mL/animal/day in male and female SD rats.