TY - JOUR
T1 - Endometrial Pipelle biopsy computer-aided diagnosis (ENDO-AID)
T2 - a feasibility study
AU - Vermorgen, Sanne
AU - Gelton, Thijs
AU - Bult, Peter
AU - Kusters-Vandevelde, Heidi V N
AU - Hausnerová, Jitka
AU - Van de Vijver, Koen
AU - Davidson, Ben
AU - Stefansson, Ingunn Marie
AU - Kooreman, Loes F S
AU - Qerimi, Adelina
AU - Huvila, Jutta
AU - Gilks, Blake
AU - Shahi, Maryam
AU - Zomer, Saskia
AU - Bartosch, Carla
AU - Pijnenborg, Johanna Ma
AU - Bulten, Johan
AU - Ciompi, Francesco
AU - Simons, Michiel
PY - 2024/2
Y1 - 2024/2
N2 - Endometrial biopsies are important in the diagnostic work-up of women who present with abnormal uterine bleeding or women with hereditary risk of endometrial cancer. In general, about 10% of all endometrial biopsies demonstrate endometrial (pre)malignancy that requires specific treatment. As the diagnostic evaluation of mostly benign cases results in a substantial workload for pathologists, artificial intelligence (AI) assisted pre-selection of biopsies could optimize the workflow. This study aimed to assess the feasibility of AI-assisted diagnosis for endometrial biopsies (ENDO-AID), trained on daily-practice whole slide images instead of highly selected images. Endometrial biopsies were classified into six clinically relevant categories defined as: non-representative, normal, non-neoplastic, hyperplasia without atypia, hyperplasia with atypia and malignant. The agreement among 15 pathologists, within these classifications, was evaluated in 91 endometrial biopsies. Next, an algorithm (trained on a total of 2,819 endometrial biopsies) rated the same 91 cases and we compared its performance using the pathologist's classification as reference standard. The interrater reliability among pathologists was moderate with a mean Cohen's kappa of 0.51, whereas for a binary classification into benign versus (pre)malignant, the agreement was substantial with a mean Cohen's kappa of 0.66. The AI algorithm performed slightly worse for the six categories with a moderate Cohen's kappa of 0.43, but was comparable for the binary classification with a substantial Cohen's kappa of 0.65. AI-assisted diagnosis of endometrial biopsies was demonstrated to be feasible in discriminating between benign and (pre)malignant endometrial tissue, even when trained on unselected cases. Endometrial premalignancies remain challenging for both pathologists and AI algorithms. Future steps to improve reliability of the diagnosis are needed to achieve a more refined AI-assisted diagnostic solution for endometrial biopsies that covers both premalignant and malignant diagnoses.
AB - Endometrial biopsies are important in the diagnostic work-up of women who present with abnormal uterine bleeding or women with hereditary risk of endometrial cancer. In general, about 10% of all endometrial biopsies demonstrate endometrial (pre)malignancy that requires specific treatment. As the diagnostic evaluation of mostly benign cases results in a substantial workload for pathologists, artificial intelligence (AI) assisted pre-selection of biopsies could optimize the workflow. This study aimed to assess the feasibility of AI-assisted diagnosis for endometrial biopsies (ENDO-AID), trained on daily-practice whole slide images instead of highly selected images. Endometrial biopsies were classified into six clinically relevant categories defined as: non-representative, normal, non-neoplastic, hyperplasia without atypia, hyperplasia with atypia and malignant. The agreement among 15 pathologists, within these classifications, was evaluated in 91 endometrial biopsies. Next, an algorithm (trained on a total of 2,819 endometrial biopsies) rated the same 91 cases and we compared its performance using the pathologist's classification as reference standard. The interrater reliability among pathologists was moderate with a mean Cohen's kappa of 0.51, whereas for a binary classification into benign versus (pre)malignant, the agreement was substantial with a mean Cohen's kappa of 0.66. The AI algorithm performed slightly worse for the six categories with a moderate Cohen's kappa of 0.43, but was comparable for the binary classification with a substantial Cohen's kappa of 0.65. AI-assisted diagnosis of endometrial biopsies was demonstrated to be feasible in discriminating between benign and (pre)malignant endometrial tissue, even when trained on unselected cases. Endometrial premalignancies remain challenging for both pathologists and AI algorithms. Future steps to improve reliability of the diagnosis are needed to achieve a more refined AI-assisted diagnostic solution for endometrial biopsies that covers both premalignant and malignant diagnoses.
KW - classification
KW - digital pathology
KW - endometrial cancer
KW - inter-observer variability
U2 - 10.1016/j.modpat.2023.100417
DO - 10.1016/j.modpat.2023.100417
M3 - Article
SN - 0893-3952
VL - 37
JO - Modern Pathology
JF - Modern Pathology
IS - 2
M1 - 100417
ER -