A Novel Digital Algorithm for Identifying Liver Steatosis Using Smartphone-Captured Images.

Area of Science:

• Hepatology
• Medical Imaging
• Digital Pathology

Background:

• Liver transplantation is limited by organ shortages.
• High discard rates of steatotic livers contribute to this shortage.
• Current histologic assessment of steatosis is subjective and image-dependent.

Purpose of the Study:

• To develop an automated digital algorithm for calculating histologic steatosis.
• To utilize smartphone-captured liver biopsy images for steatosis assessment.
• To address the bottleneck in subjective pathologist evaluation.

Main Methods:

• Smartphone images of liver histology slides were captured using a light microscope.
• An automated algorithm was designed to quantify steatotic droplets, excluding artifacts.
• Algorithm's steatosis estimates were compared to pathologist assessments from 80 liver transplant patients.

Main Results:

• Interobserver agreement among pathologists was low, improving with specialist training.
• A significant linear relationship was observed between the algorithm and expert pathologists' steatosis estimates.
• Expert pathologists consistently provided higher steatosis estimates than the algorithm.

Conclusions:

• Smartphone images and a digital algorithm can reliably measure liver steatosis.
• This technology offers a proof of concept for improved organ utilization.
• Integration into transplant workflows may enhance organ acceptance rates.