Ji-Hee Hwang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Ji-Hee Hwang has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
Byoung-Seok Lee
Toxicologic Pathology Research Group, Department of Advanced Toxicology Research, Korea Institute of Toxicology, Daejeon, Korea
1 shared publicationHeejin Park
Toxicologic Pathology Research Group, Department of Advanced Toxicology Research, Korea Institute of Toxicology, Daejeon, Korea
1 shared publicationHwa-Young Son
College of Veterinary Medicine, Chungnam National University, Daejeon, Korea
1 shared publicationHyun-Ji Kim
Toxicologic Pathology Research Group, Department of Advanced Toxicology Research, Korea Institute of Toxicology, Daejeon, Korea
1 shared publicationJae-Woo Cho
Toxicologic Pathology Research Group, Department of Advanced Toxicology Research, Korea Institute of Toxicology, Daejeon, Korea
1 shared publicationJaeku Lee
Research & Development Team, LAC Inc, Seoul, Korea
1 shared publication
Latest Publications
- 5 December 2021
- Published by SAGE Publications in Toxicologic Pathology
- Vol. 50 (2) , 186-196
Implementation and Practice of Deep Learning-Based Instance Segmentation Algorithm for Quantification of Hepatic Fibrosis at Whole Slide Level in Sprague-Dawley Rats
Exponential development in artificial intelligence or deep learning technology has resulted in more trials to systematically determine the pathological diagnoses using whole slide images (WSIs) in clinical and nonclinical studies. In this study, we applied Mask Regions with Convolution Neural Network (Mask R-CNN), a deep learning model that uses instance segmentation, to detect hepatic fibrosis induced by N-nitrosodimethylamine (NDMA) in Sprague-Dawley rats. From 51 WSIs, we collected 2011 cropped images with hepatic fibrosis annotations. Training and detection of hepatic fibrosis via artificial intelligence methods was performed using Tensorflow 2.1.0, powered by an NVIDIA 2080 Ti GPU. From the test process using tile images, 95% of model accuracy was verified. In addition, we validated the model to determine whether the predictions by the trained model can reflect the scoring system by the pathologists at the WSI level. The validation was conducted by comparing the model predictions in 18 WSIs at 20× and 10× magnifications with ground truth annotations and board-certified pathologists. Predictions at 20× showed a high correlation with ground truth ( R 2 = 0.9660) and a good correlation with the average fibrosis rank by pathologists ( R 2 = 0.8887). Therefore, the Mask R-CNN algorithm is a useful tool for detecting and quantifying pathological findings in nonclinical studies.
- 5 December 2021
- Published by SAGE Publications in Toxicologic Pathology
- Vol. 50 (2) , 186-196
Implementation and Practice of Deep Learning-Based Instance Segmentation Algorithm for Quantification of Hepatic Fibrosis at Whole Slide Level in Sprague-Dawley Rats
Exponential development in artificial intelligence or deep learning technology has resulted in more trials to systematically determine the pathological diagnoses using whole slide images (WSIs) in clinical and nonclinical studies. In this study, we applied Mask Regions with Convolution Neural Network (Mask R-CNN), a deep learning model that uses instance segmentation, to detect hepatic fibrosis induced by N-nitrosodimethylamine (NDMA) in Sprague-Dawley rats. From 51 WSIs, we collected 2011 cropped images with hepatic fibrosis annotations. Training and detection of hepatic fibrosis via artificial intelligence methods was performed using Tensorflow 2.1.0, powered by an NVIDIA 2080 Ti GPU. From the test process using tile images, 95% of model accuracy was verified. In addition, we validated the model to determine whether the predictions by the trained model can reflect the scoring system by the pathologists at the WSI level. The validation was conducted by comparing the model predictions in 18 WSIs at 20× and 10× magnifications with ground truth annotations and board-certified pathologists. Predictions at 20× showed a high correlation with ground truth ( R 2 = 0.9660) and a good correlation with the average fibrosis rank by pathologists ( R 2 = 0.8887). Therefore, the Mask R-CNN algorithm is a useful tool for detecting and quantifying pathological findings in nonclinical studies.