A Novel Digital Algorithm for Identifying Liver Steatosis Using Smartphone-Captured Images. Issue 9 (4th August 2022)

• Record Type: Journal Article
• Authors: Xu, Katherine; Raigani, Siavash; Shih, Angela; Baptista, Sofia G.; Rosales, Ivy; Parry, Nicola M.; Shroff, Stuti G.; Misdraji, Joseph; Uygun, Korkut; Yeh, Heidi; Fairchild, Katherine; Anne Dageforde, Leigh
• Is Part Of: Transplantation direct. Volume 8:Issue 9(2022)
• Page Start: e1361
• Publication Date: 2022-08-04
• Subjects: Transplantation of organs, tissues, etc -- Periodicals; Transplantation -- Periodicals; 362.19795
• DOI: 10.1097/TXD.0000000000001361
• Languages: English
• ISSNs: 2373-8731

Abstract

Abstract : Background: Access to lifesaving liver transplantation is limited by a severe organ shortage. One factor contributing to the shortage is the high rate of discard in livers with histologic steatosis. Livers with <30% macrosteatosis are generally considered safe for transplant. However, histologic assessment of steatosis by a pathologist remains subjective and is often limited by image quality. Here, we address this bottleneck by creating an automated digital algorithm for calculating histologic steatosis using only images of liver biopsy histology obtained with a smartphone. Methods: Multiple images of frozen section liver histology slides were captured using a smartphone camera via the optical lens of a simple light microscope. Biopsy samples from 80 patients undergoing liver transplantation were included. An automated digital algorithm was designed to capture and count steatotic droplets in liver tissue while discounting areas of vascular lumen, white space, and processing artifacts. Pathologists of varying experience provided steatosis scores, and results were compared with the algorithm's assessment. Interobserver agreement between pathologists was also assessed. Results: Interobserver agreement between all pathologists was very low but increased with specialist training in liver pathology. A significant linear relationship was found between steatosis estimates of the algorithm compared with expert liver pathologists, though the latter had consistently higher estimates. Conclusions: This study demonstrates proof of the concept that smartphone-captured images can be used in conjunction with a digital algorithm to measure steatosis. Integration of this technology into the transplant workflow may significantly improve organ utilization rates.