Pathobiological Dictionary Defining Pathomics and Texture Features: Addressing Understandable AI Issues in Personalized Liver Cancer; Dictionary Version LCP1.0

2025-05-20

AI Summary

This study addresses the clinical deployment barrier of AI in hepatocellular carcinoma (HCC) diagnosis and treatment—namely, insufficient interpretability and clinical alignment—by introducing LCP1.0, the first clinically validated pathological-biological lexicon for HCC. Methodologically, it integrates QuPath-based cellular quantification, IBSI-compliant PyRadiomics feature extraction, variable-threshold filtering, and SVM modeling to semantically align 333 standardized pathomic and radiomic features with WHO grading, nuclear pleomorphism, staining intensity, and other histopathological criteria. The lexicon was validated through consensus among eight pathology and oncology experts. Results identify 20 clinically salient features—including nuclear-to-cytoplasmic ratio—with an SVM classification accuracy of 0.80 (p < 0.05). LCP1.0 bridges the gap between AI model outputs and expert clinical reasoning, thereby enhancing diagnostic transparency, trustworthiness, and integration into routine clinical workflows.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Computer Vision: Interpretability, Explainability, and Transparency
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models

Application Category

• Search and Retrieval-Augmented AI: Large language models for search
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Artificial intelligence (AI) holds strong potential for medical diagnostics, yet its clinical adoption is limited by a lack of interpretability and generalizability. This study introduces the Pathobiological Dictionary for Liver Cancer (LCP1.0), a practical framework designed to translate complex Pathomics and Radiomics Features (PF and RF) into clinically meaningful insights aligned with existing diagnostic workflows. QuPath and PyRadiomics, standardized according to IBSI guidelines, were used to extract 333 imaging features from hepatocellular carcinoma (HCC) tissue samples, including 240 PF-based-cell detection/intensity, 74 RF-based texture, and 19 RF-based first-order features. Expert-defined ROIs from the public dataset excluded artifact-prone areas, and features were aggregated at the case level. Their relevance to the WHO grading system was assessed using multiple classifiers linked with feature selectors. The resulting dictionary was validated by 8 experts in oncology and pathology. In collaboration with 10 domain experts, we developed a Pathobiological dictionary of imaging features such as PFs and RF. In our study, the Variable Threshold feature selection algorithm combined with the SVM model achieved the highest accuracy (0.80, P-value less than 0.05), selecting 20 key features, primarily clinical and pathomics traits such as Centroid, Cell Nucleus, and Cytoplasmic characteristics. These features, particularly nuclear and cytoplasmic, were strongly associated with tumor grading and prognosis, reflecting atypia indicators like pleomorphism, hyperchromasia, and cellular orientation.The LCP1.0 provides a clinically validated bridge between AI outputs and expert interpretation, enhancing model transparency and usability. Aligning AI-derived features with clinical semantics supports the development of interpretable, trustworthy diagnostic tools for liver cancer pathology.

Problem

• Develops a dictionary to translate AI pathomics features into clinical insights
• Validates key imaging features linked to liver cancer grading and prognosis
• Enhances AI interpretability for liver cancer diagnostics via expert-aligned semantics

Innovation

• Developed Pathobiological Dictionary for liver cancer
• Used QuPath and PyRadiomics for feature extraction
• Integrated SVM with feature selection for accuracy