Pathologist Computer-Aided Diagnostic Scoring of Tumor Cell Fraction: A Swiss National Study.

Details

Ressource 1Download: 37742926.pdf (6874.25 [Ko])
State: Public
Version: Final published version
License: CC BY-NC-ND 4.0
Serval ID
serval:BIB_92821151D630
Type
Article: article from journal or magazin.
Collection
Publications
Institution
Title
Pathologist Computer-Aided Diagnostic Scoring of Tumor Cell Fraction: A Swiss National Study.
Journal
Modern pathology
Author(s)
Frei A.L., Oberson R., Baumann E., Perren A., Grobholz R., Lugli A., Dawson H., Abbet C., Lertxundi I., Reinhard S., Mookhoek A., Feichtinger J., Sarro R., Gadient G., Dommann-Scherrer C., Barizzi J., Berezowska S., Glatz K., Dertinger S., Banz Y., Schoenegg R., Rubbia-Brandt L., Fleischmann A., Saile G., Mainil-Varlet P., Biral R., Giudici L., Soltermann A., Chaubert A.B., Stadlmann S., Diebold J., Egervari K., Bénière C., Saro F., Janowczyk A., Zlobec I.
ISSN
1530-0285 (Electronic)
ISSN-L
0893-3952
Publication state
Published
Issued date
12/2023
Peer-reviewed
Oui
Volume
36
Number
12
Pages
100335
Language
english
Notes
Publication types: Journal Article
Publication Status: ppublish
Abstract
Tumor cell fraction (TCF) estimation is a common clinical task with well-established large interobserver variability. It thus provides an ideal test bed to evaluate potential impacts of employing a tumor cell fraction computer-aided diagnostic (TCFCAD) tool to support pathologists' evaluation. During a National Slide Seminar event, pathologists (n = 69) were asked to visually estimate TCF in 10 regions of interest (ROIs) from hematoxylin and eosin colorectal cancer images intentionally curated for diverse tissue compositions, cellularity, and stain intensities. Next, they re-evaluated the same ROIs while being provided a TCFCAD-created overlay highlighting predicted tumor vs nontumor cells, together with the corresponding TCF percentage. Participants also reported confidence levels in their assessments using a 5-tier scale, indicating no confidence to high confidence, respectively. The TCF ground truth (GT) was defined by manual cell-counting by experts. When assisted, interobserver variability significantly decreased, showing estimates converging to the GT. This improvement remained even when TCFCAD predictions deviated slightly from the GT. The standard deviation (SD) of the estimated TCF to the GT across ROIs was 9.9% vs 5.8% with TCFCAD (P < .0001). The intraclass correlation coefficient increased from 0.8 to 0.93 (95% CI, 0.65-0.93 vs 0.86-0.98), and pathologists stated feeling more confident when aided (3.67 ± 0.81 vs 4.17 ± 0.82 with the computer-aided diagnostic [CAD] tool). TCFCAD estimation support demonstrated improved scoring accuracy, interpathologist agreement, and scoring confidence. Interestingly, pathologists also expressed more willingness to use such a CAD tool at the end of the survey, highlighting the importance of training/education to increase adoption of CAD systems.
Keywords
Humans, Pathologists, Switzerland, Computers, artificial intelligence, computer-aided diagnostic tool, digital pathology, interobserver variability, pathology, tumor cell fraction
Pubmed
Web of science
Open Access
Yes
Create date
25/09/2023 13:16
Last modification date
03/02/2024 7:22
Usage data