Zachary Goodman, Kutbuddin Akbary, Mazen Noureddin, Yayun Ren, Elaine Chng, Dean Tai, Pol Boudes, Guadalupe Garcia-Tsao, Stephen Harrison, Naga Chalasani
This study addresses the need for precise histopathological assessment of liver biopsies in Metabolic dysfunction-Associated Steatohepatitis (MASH) cirrhosis, where assessing nuanced drug effects on fibrosis becomes pivotal. The study describes a framework for the development and validation of an Artificial Intelligence (AI) model, leveraging SHG/TPE microscopy along with insights from an expert hepatopathologist, to precisely annotate fibrous septa and nodules in liver biopsies in MASH cirrhosis. A total of 25 liver biopsies from the Belapectin trial (NCT04365868) were randomly selected for training, and an additional 10 for validation. Each biopsy underwent three sections: Smooth Muscle Actin (SMA) and Sirius Red (SR) staining for septa and nodule annotation by pathologists and an unstained section for SHG/TPE imaging and AI annotation using qSepta and qNodule algorithms. Re-training of qSepta and qNodule algorithms was executed based on pathologist annotations. Sensitivity and positive predictive value (PPV) were employed to evaluate concordance with pathologist annotations, both pre- and post-training and during validation. Post-re-training by pathologist annotations, the AI demonstrated improved sensitivity for qSepta annotations, achieving 91% post-training (versus 84% pre-training). Sensitivity for qSepta in the validation cohort also improved to 91%. Additionally, PPV significantly improved from 69% pre-training to 85% post-training and reached 94% during validation. For qNodule annotations, sensitivity increased from 82% post-training to 90% in the validation cohort, while the PPV was consistent at 95% across both training and validation cohorts.This study outlines a strategic framework for developing and validating an AI model tailored for precise histopathological assessment of MASH cirrhosis, using pathologist training and annotations. The outcomes emphasise the crucial role of disease-specific customisation of AI models, based on expert pathologist training, in improving accuracy and applicability in clinical trials, marking a step forward in understanding and addressing the histopathological evaluation of MASH cirrhosis.
{"title":"Enhancing Histology Detection in MASH Cirrhosis for Artificial Intelligence Pathology Platform by Expert Pathologist Training","authors":"Zachary Goodman, Kutbuddin Akbary, Mazen Noureddin, Yayun Ren, Elaine Chng, Dean Tai, Pol Boudes, Guadalupe Garcia-Tsao, Stephen Harrison, Naga Chalasani","doi":"10.1002/lci2.70007","DOIUrl":"https://doi.org/10.1002/lci2.70007","url":null,"abstract":"<p>This study addresses the need for precise histopathological assessment of liver biopsies in Metabolic dysfunction-Associated Steatohepatitis (MASH) cirrhosis, where assessing nuanced drug effects on fibrosis becomes pivotal. The study describes a framework for the development and validation of an Artificial Intelligence (AI) model, leveraging SHG/TPE microscopy along with insights from an expert hepatopathologist, to precisely annotate fibrous septa and nodules in liver biopsies in MASH cirrhosis. A total of 25 liver biopsies from the Belapectin trial (NCT04365868) were randomly selected for training, and an additional 10 for validation. Each biopsy underwent three sections: Smooth Muscle Actin (SMA) and Sirius Red (SR) staining for septa and nodule annotation by pathologists and an unstained section for SHG/TPE imaging and AI annotation using qSepta and qNodule algorithms. Re-training of qSepta and qNodule algorithms was executed based on pathologist annotations. Sensitivity and positive predictive value (PPV) were employed to evaluate concordance with pathologist annotations, both pre- and post-training and during validation. Post-re-training by pathologist annotations, the AI demonstrated improved sensitivity for qSepta annotations, achieving 91% post-training (versus 84% pre-training). Sensitivity for qSepta in the validation cohort also improved to 91%. Additionally, PPV significantly improved from 69% pre-training to 85% post-training and reached 94% during validation. For qNodule annotations, sensitivity increased from 82% post-training to 90% in the validation cohort, while the PPV was consistent at 95% across both training and validation cohorts.This study outlines a strategic framework for developing and validating an AI model tailored for precise histopathological assessment of MASH cirrhosis, using pathologist training and annotations. The outcomes emphasise the crucial role of disease-specific customisation of AI models, based on expert pathologist training, in improving accuracy and applicability in clinical trials, marking a step forward in understanding and addressing the histopathological evaluation of MASH cirrhosis.</p>","PeriodicalId":93331,"journal":{"name":"Liver cancer international","volume":"5 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/lci2.70007","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142860569","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
African individuals with metabolic dysfunction-associated steatotic liver disease (MAFLD) may have unique genetic factors that influence the clinical manifestations of MAFLD. The paucity of both epidemiological data on MAFLD within Africa and the lack of genetic research thereof have disadvantaged the population, as extrapolated data out the region has been utilised to direct health care policy and management of the disease. This unique cohort of MAFLD individuals within Africa requires further epidemiological and genomic research to advance precision medicine within the realm of clinical hepatology. With the anticipated increase in non-communicable disease that sub-Saharan African may experience in the near future, a robust large study within Africa may provide insight as to whether MAFLD prevalence may be expected to significantly add to this impending health burden; furthermore, a genetic research component may provide insight into whether protective genetic variants are present or whether there is a lack of pathogenic variants, thereby allowing clinicians and policy strategists to have a better understanding of the disease prevalence and manifestations in African individuals. The aim of this publication was to review the current prevalence trends of MAFLD within Africa and the knowledge of the genetic landscape of MAFLD individuals of African descent.
{"title":"An Insight into the Genetic Predisposition of Metabolic Dysfunction-Associated Steatotic Liver Disease in Africa","authors":"Yusuf Moolla, Veron Ramsuran","doi":"10.1002/lci2.70006","DOIUrl":"https://doi.org/10.1002/lci2.70006","url":null,"abstract":"<p>African individuals with metabolic dysfunction-associated steatotic liver disease (MAFLD) may have unique genetic factors that influence the clinical manifestations of MAFLD. The paucity of both epidemiological data on MAFLD within Africa and the lack of genetic research thereof have disadvantaged the population, as extrapolated data out the region has been utilised to direct health care policy and management of the disease. This unique cohort of MAFLD individuals within Africa requires further epidemiological and genomic research to advance precision medicine within the realm of clinical hepatology. With the anticipated increase in non-communicable disease that sub-Saharan African may experience in the near future, a robust large study within Africa may provide insight as to whether MAFLD prevalence may be expected to significantly add to this impending health burden; furthermore, a genetic research component may provide insight into whether protective genetic variants are present or whether there is a lack of pathogenic variants, thereby allowing clinicians and policy strategists to have a better understanding of the disease prevalence and manifestations in African individuals. The aim of this publication was to review the current prevalence trends of MAFLD within Africa and the knowledge of the genetic landscape of MAFLD individuals of African descent.</p>","PeriodicalId":93331,"journal":{"name":"Liver cancer international","volume":"5 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/lci2.70006","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142762539","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Radiotherapy has been proven to act synergistically with immunotherapy to prime the immune response against the immunosuppressive tumour microenvironment. Stereotactic body radiation therapy (SBRT) produces a greater variety of tumour-associated antigens. This can elicit an even stronger anti-tumour immune response, especially when combined with immune checkpoint inhibitors to prevent T cell exhaustion. This response is particularly useful in hepatocellular carcinoma patients due to a naturally immunosuppressive environment. SBRT has provided excellent local control rates in patients with hepatocellular carcinoma (HCC). Retrospective and prospective clinical trials involving advanced-stage HCC patients support combining SBRT with immune checkpoint inhibitors. Actively recruiting phase III randomised controlled trials are currently testing this promising combination in HCC patients. This mini-review outlines the rationale for combining the two modalities in HCC patients. Current guidelines for HCC and successes in the field using the combination treatment will also be discussed.
{"title":"Stereotactic Body Radiation Therapy Combined With Immunotherapy for Patients With Hepatocellular Carcinoma-A Review","authors":"Ajay Patel","doi":"10.1002/lci2.70005","DOIUrl":"https://doi.org/10.1002/lci2.70005","url":null,"abstract":"<p>Radiotherapy has been proven to act synergistically with immunotherapy to prime the immune response against the immunosuppressive tumour microenvironment. Stereotactic body radiation therapy (SBRT) produces a greater variety of tumour-associated antigens. This can elicit an even stronger anti-tumour immune response, especially when combined with immune checkpoint inhibitors to prevent T cell exhaustion. This response is particularly useful in hepatocellular carcinoma patients due to a naturally immunosuppressive environment. SBRT has provided excellent local control rates in patients with hepatocellular carcinoma (HCC). Retrospective and prospective clinical trials involving advanced-stage HCC patients support combining SBRT with immune checkpoint inhibitors. Actively recruiting phase III randomised controlled trials are currently testing this promising combination in HCC patients. This mini-review outlines the rationale for combining the two modalities in HCC patients. Current guidelines for HCC and successes in the field using the combination treatment will also be discussed.</p>","PeriodicalId":93331,"journal":{"name":"Liver cancer international","volume":"5 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/lci2.70005","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142707918","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jinyoung Byun, Hyun-Seok Kim, Younghun Han, Aaron P. Thrift, Sabrina M. Lin, Xiangjun Xiao, Hyeyeun Lim, Goo Jun, Stacia M. Desantis, Hashem B. El-Serag, Fasiha Kanwal, Christopher I. Amos