Survey of liver pathologists to assess attitudes towards digital pathology and artificial intelligence

Improving HCC Prognostic Models after Liver Resection by AI-Extracted Tissue Fiber Framework Analytics

Despite advances in diagnostic and treatment technologies, predicting outcomes of patients with hepatocellular carcinoma (HCC) remains a challenge. Prognostic models are further obscured by the variable impact of the tumor properties and the remaining liver parenchyma, often affected by cirrhosis or non-alcoholic fatty liver disease that tend to precede HCC. This study investigated the prognostic value of reticulin and collagen microarchitecture in liver resection samples. We analyzed 105 scanned tissue sections that were stained using a Gordon and Sweet's silver impregnation protocol combined with Picric Acid-Sirius Red. A convolutional neural network was utilized to segment the red-staining collagen and black linear reticulin strands, generating a detailed map of the fiber structure within the HCC and adjacent liver tissue. Subsequent hexagonal grid subsampling coupled with automated epithelial edge detection and computational fiber morphometry provided the foundation for region-specific tissue analysis. Two penalized Cox regression models using LASSO achieved a concordance index (C-index) greater than 0.7. These models incorporated variables such as patient age, tumor multifocality, and fiber-derived features from the epithelial edge in both the tumor and liver compartments. The prognostic value at the tumor edge was derived from the reticulin structure, while collagen characteristics were significant at the epithelial edge of peritumoral liver. The prognostic performance of these models was superior to models solely reliant on conventional clinicopathologic parameters, highlighting the utility of AI-extracted microarchitectural features for the management of HCC.

Perspective of a Pathologist on Benchmark Strategies for Artificial Intelligence Development in Organ Transplantation

Transplant pathology of donors is a highly specialized field comprising both the evaluation of organ donor biopsy for the oncological risk transmission and to guide the organ allocation. Timing is critical in transplant procurement since organs must be recovered as soon as possible to ensure the best possible outcome for the recipient. To all this is added the fact that the evaluation of a donor causes difficulties in many cases and the impact of these assessments is paramount, considering the possible recovery of organs that would have been erroneously discarded or, conversely, the possibly correct discarding of donors with unacceptable risk profiles. In transplant pathology histology is still the gold standard for diagnosis dictating the subsequent decisions and course of clinical care. Digital pathology has played an important role in accelerating healthcare progression and nowadays artificial intelligence powered computational pathology can effectively improve diagnostic needs, supporting the quality and safety of the process. Mapping the shape of the journey would suggest a progressive approach from supervised to semi/unsupervised models, which would involve training these models directly for clinical endpoints. In machine learning, this generally delivers better performance, compensating for a potential lack in interpretability. With planning and enough confidence in the performance of learning-based methods from digital pathology and artificial intelligence, there is great potential to augment the diagnostic quality and correlation with clinical endpoints. This may improve the donor pool and vastly reduce diagnostic and prognostic errors that are known but currently are unavoidable in transplant donor pathology.