Utility of AI digital pathology as an aid for pathologists scoring fibrosis in MASH

Abstract

Background & aims: Intra and inter-pathologist variability poses a significant challenge in metabolic dysfunction-associated steatohepatitis (MASH) biopsy evaluation, leading to suboptimal selection of patients and confounded assessment of histological response in clinical trials. We evaluated the utility of an artificial intelligence (AI) digital pathology (DP) platform to help pathologists improve the reliability of fibrosis staging.

Methods: A total of 120 digitized histology slides from two trials (NCT03517540, NCT03912532) were analyzed by four expert hepatopathologists, with and without AI assistance in a randomized, crossover design. We utilized an AI DP platform consisting of unstained second harmonic generation/two photon excitation fluorescence (SHG/TPEF) images and AI quantitative fibrosis (qFibrosis) values.

Results: AI assistance significantly improved inter-pathologist kappa for fibrosis staging, particularly for early fibrosis (F0-F2), with reduced variance around the median reads. Intra-pathologist kappa was unchanged. AI assistance increased pathologist concordance for identifying clinical trial inclusion cases (F2-F3) from 45% to 71%, exclusion cases (F0/F1/F4) from 38% to 55%, and evaluation of fibrosis response to treatment from 49% to 61%. SHG/TPEF images, qFibrosis continuous values, and qFibrosis stage were considered useful by at least three out of four pathologists in 83%, 55%, and 38% of cases, respectively. In the context of a clinical trial, the increase in inter-pathologist concordance was modeled to result in a ∼25% reduction in the potential need for adjudication as well as a ∼45% increase in the study power for a kappa improvement from ∼0.4 to ∼0.7.

Conclusions: The use of AI DP enhances inter-rater reliability of fibrosis staging for MASH. This indicates that the SHG/TPEF-based AI DP tool is useful for assisting pathologists in assessing fibrosis, thereby enhancing clinical trial efficiency and reliability of fibrosis readouts in response to treatments.

Impact and implications: Implementing an AI DP platform as a tool for pathologists significantly improved inter-pathologist agreement on fibrosis staging, particularly for early-stage fibrosis (F0-F2), which is critical for clinical trial eligibility. The second harmonic generation imaging technology used in conjunction with AI quantitative scores provided enhanced visualization of fibrosis with an indication of severity along the disease continuum. This led to increased pathologist confidence in fibrosis staging and, therefore, increased pathologist concordance for the classification of clinical trial inclusion/exclusion and evaluation of treatment, compared to a standard scoring method based on traditional stains without AI assistance. Improved pathologist concordance with AI assistance could streamline clinical trial processes, reducing the need for adjudication and enhancing study power, potentially decreasing required sample sizes. Continued exploration of the utility of AI assistance across a broader range of pathologists and in prospective clinical trials will be essential for validating the effectiveness of AI assistance.

Keywords: AI; MASH; digital pathology; fibrosis staging; inter-reader variability; pathologist assistance; pathologist scoring; second harmonic generation.