Liver-Quant: Feature-based image analysis toolkit for automatic quantification of metabolic dysfunction-associated steatotic liver disease.
No Thumbnail Available
All Authors
Farzi, M.
McGenity, C.
Cratchley, A.
Leplat, L.
Bankhead, P.
Wright, A.
Treanor, D.
LTHT Author
McGenity, Clare
Cratchley, Alyn
Wright, Alexander
Treanor, Darren
Cratchley, Alyn
Wright, Alexander
Treanor, Darren
LTHT Department
Pathology
Histopathology
National Pathology Imaging Cooperative
Histopathology
National Pathology Imaging Cooperative
Non Medic
Digital Pathology Systems Lead
Publication Date
2025
Item Type
Journal Article
Language
Subject
Subject Headings
Abstract
BACKGROUND: Liver biopsy assessment by pathologists remains the gold standard for diagnosing metabolic dysfunction-associated steatotic liver disease (MASLD). Current automated image analysis tools for patient risk stratification are often proprietary or not applicable to whole slide images (WSIs). Here, we introduce "Liver-Quant," an open-source Python package for quantifying steatosis and fibrosis in liver WSIs.
METHOD: Liver-Quant leverages colour and morphological features to measure Steatosis Proportionate Area (SPA) and Collagen Proportionate Area (CPA). We evaluated the method using an internal dataset of 414 WSIs from adult patients (Leeds Teaching Hospitals NHS Trust, 2016-2022) and an external public dataset (109 WSIs). Semi-quantitative scores were extracted from pathological reports. The Spearman rank coefficient (rho) assessed correlations between computed SPA/CPA and pathologist scores.
RESULTS: Steatosis quantification showed a substantial correlation (rho = 0.92), while fibrosis quantification yielded a moderate correlation (rho = 0.51). We further investigated the impact of three staining dyes (Van Gieson (VG), Picro Sirius Red (PSR), and Masson's Trichrome (MTC)) on fibrosis quantification (n = 18). Stain normalisation yielded excellent agreement in CPA measurements across all three stains. Without normalisation, PSR achieved the strongest correlation with human scores (rho = 0.9) followed by VG (rho = 0.8) and MTC (rho = 0.59). Finally, we explored the impact of apparent magnification on SPA and CPA. High-resolution images (0.25 or 0.50 mcm per pixel (MPP)) were necessary for accurate SPA measurement, while lower resolution (10 MPP) sufficed for CPA measurements.
CONCLUSIONS: Liver-Quant offers an open-source solution for rapid and precise MASLD quantification in WSIs applicable to multiple histological stains.
Journal
Computers in Biology & Medicine