Ji-Hee Hwang, Minyoung Lim, Gyeongjin Han, Heejin Park, Yong-Bum Kim, Jinseok Park, Sang-Yeop Jun, Jaeku Lee, Jae-Woo Cho
{"title":"分割算法可用于SD大鼠肝纤维化的检测。","authors":"Ji-Hee Hwang, Minyoung Lim, Gyeongjin Han, Heejin Park, Yong-Bum Kim, Jinseok Park, Sang-Yeop Jun, Jaeku Lee, Jae-Woo Cho","doi":"10.1186/s42826-023-00167-2","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Liver fibrosis is an early stage of liver cirrhosis. As a reversible lesion before cirrhosis, liver failure, and liver cancer, it has been a target for drug discovery. Many antifibrotic candidates have shown promising results in experimental animal models; however, due to adverse clinical reactions, most antifibrotic agents are still preclinical. Therefore, rodent models have been used to examine the histopathological differences between the control and treatment groups to evaluate the efficacy of anti-fibrotic agents in non-clinical research. In addition, with improvements in digital image analysis incorporating artificial intelligence (AI), a few researchers have developed an automated quantification of fibrosis. However, the performance of multiple deep learning algorithms for the optimal quantification of hepatic fibrosis has not been evaluated. Here, we investigated three different localization algorithms, mask R-CNN, DeepLabV3<sup>+</sup>, and SSD, to detect hepatic fibrosis.</p><p><strong>Results: </strong>5750 images with 7503 annotations were trained using the three algorithms, and the model performance was evaluated in large-scale images and compared to the training images. The results showed that the precision values were comparable among the algorithms. However, there was a gap in the recall, leading to a difference in model accuracy. The mask R-CNN outperformed the recall value (0.93) and showed the closest prediction results to the annotation for detecting hepatic fibrosis among the algorithms. DeepLabV3<sup>+</sup> also showed good performance; however, it had limitations in the misprediction of hepatic fibrosis as inflammatory cells and connective tissue. The trained SSD showed the lowest performance and was limited in predicting hepatic fibrosis compared to the other algorithms because of its low recall value (0.75).</p><p><strong>Conclusions: </strong>We suggest it would be a more useful tool to apply segmentation algorithms in implementing AI algorithms to predict hepatic fibrosis in non-clinical studies.</p>","PeriodicalId":17993,"journal":{"name":"Laboratory Animal Research","volume":null,"pages":null},"PeriodicalIF":2.7000,"publicationDate":"2023-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10303341/pdf/","citationCount":"0","resultStr":"{\"title\":\"Segmentation algorithm can be used for detecting hepatic fibrosis in SD rat.\",\"authors\":\"Ji-Hee Hwang, Minyoung Lim, Gyeongjin Han, Heejin Park, Yong-Bum Kim, Jinseok Park, Sang-Yeop Jun, Jaeku Lee, Jae-Woo Cho\",\"doi\":\"10.1186/s42826-023-00167-2\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Background: </strong>Liver fibrosis is an early stage of liver cirrhosis. As a reversible lesion before cirrhosis, liver failure, and liver cancer, it has been a target for drug discovery. Many antifibrotic candidates have shown promising results in experimental animal models; however, due to adverse clinical reactions, most antifibrotic agents are still preclinical. Therefore, rodent models have been used to examine the histopathological differences between the control and treatment groups to evaluate the efficacy of anti-fibrotic agents in non-clinical research. In addition, with improvements in digital image analysis incorporating artificial intelligence (AI), a few researchers have developed an automated quantification of fibrosis. However, the performance of multiple deep learning algorithms for the optimal quantification of hepatic fibrosis has not been evaluated. Here, we investigated three different localization algorithms, mask R-CNN, DeepLabV3<sup>+</sup>, and SSD, to detect hepatic fibrosis.</p><p><strong>Results: </strong>5750 images with 7503 annotations were trained using the three algorithms, and the model performance was evaluated in large-scale images and compared to the training images. The results showed that the precision values were comparable among the algorithms. However, there was a gap in the recall, leading to a difference in model accuracy. The mask R-CNN outperformed the recall value (0.93) and showed the closest prediction results to the annotation for detecting hepatic fibrosis among the algorithms. DeepLabV3<sup>+</sup> also showed good performance; however, it had limitations in the misprediction of hepatic fibrosis as inflammatory cells and connective tissue. The trained SSD showed the lowest performance and was limited in predicting hepatic fibrosis compared to the other algorithms because of its low recall value (0.75).</p><p><strong>Conclusions: </strong>We suggest it would be a more useful tool to apply segmentation algorithms in implementing AI algorithms to predict hepatic fibrosis in non-clinical studies.</p>\",\"PeriodicalId\":17993,\"journal\":{\"name\":\"Laboratory Animal Research\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.7000,\"publicationDate\":\"2023-06-28\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10303341/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Laboratory Animal Research\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1186/s42826-023-00167-2\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"MEDICINE, RESEARCH & EXPERIMENTAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Laboratory Animal Research","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1186/s42826-023-00167-2","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"MEDICINE, RESEARCH & EXPERIMENTAL","Score":null,"Total":0}
Segmentation algorithm can be used for detecting hepatic fibrosis in SD rat.
Background: Liver fibrosis is an early stage of liver cirrhosis. As a reversible lesion before cirrhosis, liver failure, and liver cancer, it has been a target for drug discovery. Many antifibrotic candidates have shown promising results in experimental animal models; however, due to adverse clinical reactions, most antifibrotic agents are still preclinical. Therefore, rodent models have been used to examine the histopathological differences between the control and treatment groups to evaluate the efficacy of anti-fibrotic agents in non-clinical research. In addition, with improvements in digital image analysis incorporating artificial intelligence (AI), a few researchers have developed an automated quantification of fibrosis. However, the performance of multiple deep learning algorithms for the optimal quantification of hepatic fibrosis has not been evaluated. Here, we investigated three different localization algorithms, mask R-CNN, DeepLabV3+, and SSD, to detect hepatic fibrosis.
Results: 5750 images with 7503 annotations were trained using the three algorithms, and the model performance was evaluated in large-scale images and compared to the training images. The results showed that the precision values were comparable among the algorithms. However, there was a gap in the recall, leading to a difference in model accuracy. The mask R-CNN outperformed the recall value (0.93) and showed the closest prediction results to the annotation for detecting hepatic fibrosis among the algorithms. DeepLabV3+ also showed good performance; however, it had limitations in the misprediction of hepatic fibrosis as inflammatory cells and connective tissue. The trained SSD showed the lowest performance and was limited in predicting hepatic fibrosis compared to the other algorithms because of its low recall value (0.75).
Conclusions: We suggest it would be a more useful tool to apply segmentation algorithms in implementing AI algorithms to predict hepatic fibrosis in non-clinical studies.