Artificial intelligence-based differential diagnosis of orbital MALT lymphoma and IgG4 related ophthalmic disease using hematoxylin–eosin images

• Published in: Graefe's archive for clinical and experimental ophthalmology Vol. 262; no. 10; pp. 3355 - 3366
• Main Authors: Tagami, Mizuki, Nishio, Mizuho, Yoshikawa, Atsuko, Misawa, Norihiko, Sakai, Atsushi, Haruna, Yusuke, Tomita, Mami, Azumi, Atsushi, Honda, Shigeru
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.10.2024; Springer Nature B.V
• Subjects: Artificial intelligence; Breakthroughs in artificial intelligence for ophthalmology; Deep learning; Differential diagnosis; Eye diseases; Gene rearrangement; Genetic analysis; Immunoglobulin G; Lymphoma; Medical personnel; Medicine; Medicine & Public Health; Mucosal-associated lymphoid tissue; Oncology; Ophthalmology; Visual discrimination learning; Deep learning; IgG4-related ophthalmic disease (IgG4-ROD); Hematoxylin–eosin (HE); Orbital MALT lymphoma; Artificial intelligence (AI)
• ISSN: 0721-832X; 1435-702X; 1435-702X
• DOI: 10.1007/s00417-024-06501-1

Purpose To investigate the possibility of distinguishing between IgG4-related ophthalmic disease (IgG4-ROD) and orbital MALT lymphoma using artificial intelligence (AI) and hematoxylin–eosin (HE) images. Methods After identifying a total of 127 patients from whom we were able to procure tissue blocks with IgG4-ROD and orbital MALT lymphoma, we performed histological and molecular genetic analyses, such as gene rearrangement. Subsequently, pathological HE images were collected from these patients followed by the cutting out of 10 different image patches from the HE image of each patient. A total of 970 image patches from the 97 patients were used to construct nine different models of deep learning, and the 300 image patches from the remaining 30 patients were used to evaluate the diagnostic performance of the models. Area under the curve (AUC) and accuracy (ACC) were used for the performance evaluation of the deep learning models. In addition, four ophthalmologists performed the binary classification between IgG4-ROD and orbital MALT lymphoma. Results EVA, which is a vision-centric foundation model to explore the limits of visual representation, was the best deep learning model among the nine models. The results of EVA were ACC = 73.3% and AUC = 0.807. The ACC of the four ophthalmologists ranged from 40 to 60%. Conclusions It was possible to construct an AI software based on deep learning that was able to distinguish between IgG4-ROD and orbital MALT. This AI model may be useful as an initial screening tool to direct further ancillary investigations.