Complexity of ballooned hepatocyte feature recognition: Defining a training atlas for artificial intelligence-based imaging in NAFLD

Abstract

This is a PDF file of an article that has undergone enhancements after acceptance, such as the addition of a cover page and metadata, and formatting for readability, but it is not yet the definitive version of record. This version will undergo additional copyediting, typesetting and review before it is published in its final form, but we are providing this version to give early visibility of the article. Please note that, during the production process, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.

Impact of non-invasive biomarkers on hepatology practice: Past, present and future

“…Liver histology remains the reference standard for assessing diagnostic biomarker performance. It should however be noted that, beyond the issues with sampling variability and inter-observer variation already alluded to, [12][13][14] there are inherent issues with the use of semi-quantitative histological scoring systems as a reference standard. Semi-quantitative scores conflate anatomical distribution of specific lesions with severity and impose a structure whereby continuous variables are assigned into discrete categorical grading bins.…”

“…Its' accuracy for the assessment of fibrosis has been questioned, in relation to sampling errors and intra-and interobserver variability that may lead to over-or under-staging. [12][13][14] Liver biopsy is also a costly procedure, requiring medical expertise as well as an ambulatory facility with periprocedural monitoring by nurses. 15 Finally, it is an invasive procedure associated with complications, some common and mild (transient pain in 30% to 50% of cases), 16 others rare but potentially life-threatening (serious haemorrhage in 0.6% of cases and mortality in up to 0.1%).…”

Nonalcoholic Steatohepatitis Drug Development Pipeline: An Update

“…Specifically, NAFLD polygenic risk scores may be useful in both early disease detection and the clinical application of actionable measures in NAFLD 236 . The use of artificial intelligence-based approaches should be considered in clinical trials to provide more reliable ways in assessing liver-related outcomes, such as the evaluation of hepatocyte ballooning in evaluating the range hepatocyte injury 237 . Enthusiasm for the approval of targeted NASH therapies is increasing but should not diminish utilization of the already available, affordable, and effective interventions of optimizing cardiovascular comorbidities and executing lifestyle changes.…”

Best Practices in Liver Biopsy Histologic Assessment for Nonalcoholic Steatohepatitis Clinical Trials: Expert Opinion

“…While there are well defined histologic criteria describing a ballooned 5 GastroHep hepatocyte, there are discrepancies in the definition in the early stages of formation. A recent paper concludes, "The substantial divergence in hepatocyte ballooning identified amongst expert hepatopathologists suggests that ballooning is a spectrum, too subjective for its presence or complete absence to be unequivocally determined as a trial endpoint [21]" (iii) Reasons for low interobserver concordance could also be related to technical problems. In particular, inadequate biopsy length and poor quality of the histology, like inappropriate thickness or inadequate staining as well as fragmentation or folding of sections, making it difficult for pathologists to agree on scorings.…”