Complexity of ballooned hepatocyte feature recognition: Defining a training atlas for artificial intelligence-based imaging in NAFLD
Résumé
Background
Histologically assessed hepatocyte ballooning is a key feature discriminating nonalcoholic steatohepatitis (NASH) from steatosis (NAFL). Reliable identification underpins patient inclusion in clinical trials and serves as a key regulatory-approved surrogate endpoint for drug efficacy. High inter/intra-observer variation in ballooning measured using the NASH-CRN semi-quantitative score has been reported yet no actionable solutions have been proposed.
Methods
A focussed evaluation of hepatocyte ballooning recognition was conducted. Digitised slides were evaluated by 9 internationally recognized expert liver pathologists on two separate occasions: each pathologist independently marked every ballooned hepatocyte and later provided an overall non-NASH NAFL/NASH assessment. Interobserver variation was assessed and a ‘concordance atlas’ of ballooned hepatocytes generated to train second harmonic generation/two-photon excitation fluorescence imaging-based artificial intelligence (AI).
Results
Fleiss kappa statistic for overall interobserver agreement for presence/absence of ballooning was 0.197 (95%CI 0.094-0.300), rising to 0.362 (0.258-0.465) with a ≥5-cell threshold. However, intraclass correlation coefficient for consistency was higher (0.718 [0.511-0.900]), indicating ‘moderate’ agreement on ballooning burden. 133 ballooned cells were identified using a ≥5/9 majority to train AI ballooning detection (AI-pathologist pairwise concordance 19–42%, comparable to inter-pathologist pairwise concordance of between 8–75%). AI quantified change in ballooned cell burden in response to therapy in a separate slide set.
Conclusions
The substantial divergence in hepatocyte ballooning identified amongst expert hepato-pathologists suggests that ballooning is a spectrum, too subjective for its presence or complete absence to be unequivocally determined as a trial endpoint. A concordance atlas may be used to train AI assistive technologies to reproducibly quantify ballooned hepatocytes that standardise assessment of therapeutic efficacy. This atlas serves as a reference-standard for ongoing work to refine how ballooning is classified by both pathologists and AI.
| Origine | Publication financée par une institution |
|---|