Top

Graefe's Archive for Clinical and Experimental Ophthalmology

03-05-2024 | Mucosa Associated Lymphoid Tissue | Oncology

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

Authors: Mizuki Tagami, Mizuho Nishio, Atsuko Yoshikawa, Norihiko Misawa, Atsushi Sakai, Yusuke Haruna, Mami Tomita, Atsushi Azumi, Shigeru Honda

Published in: Graefe's Archive for Clinical and Experimental Ophthalmology

Abstract

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.

Goto H, Yamakawa N, Komatsu H, Asakage M, Tsubota K, Ueda SI, Nemoto R, Umazume K, Usui Y, Mori H (2021) Clinico-epidemiological analysis of 1000 cases of orbital tumors. Jpn J Ophthalmol 65:704–723. https://doi.org/10.1007/s10384-021-00857-1CrossRefPubMed

Sogabe Y, Ohshima K-i, Azumi A, Takahira M, Kase S, Tsuji H, Yoshikawa H, Nakamura T (2014) Location and frequency of lesions in patients with IgG4-related ophthalmic diseases. Graefes Arch Clin Exp Ophthalmol 252:531–538CrossRefPubMed

Deshpande V, Zen Y, Chan JK, Yi EE, Sato Y, Yoshino T, Klöppel G, Heathcote JG, Khosroshahi A, Ferry JA (2012) Consensus statement on the pathology of IgG4-related disease. Mod Pathol 25:1181–1192CrossRefPubMed

Andrew NH, Sladden N, Kearney DJ, Selva D (2015) An analysis of IgG4-related disease (IgG4-RD) among idiopathic orbital inflammations and benign lymphoid hyperplasias using two consensus-based diagnostic criteria for IgG4-RD. Br J Ophthalmol 99:376–381CrossRefPubMed

Cleary ML, Chao J, Warnke R, Sklar J (1984) Immunoglobulin gene rearrangement as a diagnostic criterion of B-cell lymphoma. Proc Natl Acad Sci 81:593–597CrossRefPubMedPubMedCentral

Shimizu H, Usui Y, Wakita R, Aita Y, Tomita A, Tsubota K, Asakage M, Nezu N, Komatsu H, Umazume K, Sugimoto M, Goto H (2021) Differential Tissue Metabolic Signatures in IgG4-Related Ophthalmic Disease and Orbital Mucosa-Associated Lymphoid Tissue Lymphoma. Invest Ophthalmol Vis Sci 62:15. https://doi.org/10.1167/iovs.62.1.15CrossRefPubMedPubMedCentral

Tagami M, Nishio M, Katsuyama-Yoshikawa A, Misawa N, Sakai A, Haruna Y, Azumi A, Honda S (2023) Machine learning model with texture analysis for automatic classification of histopathological images of ocular adnexal mucosa-associated lymphoid tissue lymphoma of two different origins. Curr Eye Res 1–8. https://doi.org/10.1080/02713683.2023.2246696

Yamashita R, Nishio M, Do RKG, Togashi K (2018) Convolutional neural networks: an overview and application in radiology. Insights Imaging 9:611–629. https://doi.org/10.1007/s13244-018-0639-9CrossRefPubMed

Fang Y, Wang W, Xie B, Sun Q, Wu L, Wang X, Huang T, Wang X, Cao Y (2023) Eva: exploring the limits of masked visual representation learning at scale. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 19358–19369. https://arxiv.org/abs/2211.07636

10.

Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S (2020) An image is worth 16x16 words: transformers for image recognition at scale. https://arxiv.org/abs/2010.11929

11.

Tan M, Le Q (2019) EfficientNet: rethinking model scaling for convolutional neural networks. In: Kamalika C, Ruslan S (eds) Proceedings of the 36th International Conference on Machine Learning. PMLR, Proceedings of Machine Learning Research, pp. 6105–6114. https://arxiv.org/abs/1905.11946

12.

Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 4700–4708. https://ieeexplore.ieee.org/document/8099726

13.

Miyoshi H, Sato K, Kabeya Y, Yonezawa S, Nakano H, Takeuchi Y, Ozawa I, Higo S, Yanagida E, Yamada K (2020) Deep learning shows the capability of high-level computer-aided diagnosis in malignant lymphoma. Lab Invest 100:1300–1310CrossRefPubMed

14.

Cheuk W, Yuen HK, Chan JK (2007) Chronic sclerosing dacryoadenitis: part of the spectrum of IgG4-related Sclerosing disease? Am J Surg Pathol 31:643–645CrossRefPubMed

15.

Umehara H, Okazaki K, Masaki Y, Kawano M, Yamamoto M, Saeki T, Matsui S, Yoshino T, Nakamura S, Kawa S, Hamano H, Kamisawa T, Shimosegawa T, Shimatsu A, Nakamura S, Ito T, Notohara K, Sumida T, Tanaka Y, Mimori T, Chiba T, Mishima M, Hibi T, Tsubouchi H, Inui K, Ohara H (2012) Comprehensive diagnostic criteria for IgG4-related disease (IgG4-RD), 2011. Mod Rheumatol 22:21–30. https://doi.org/10.1007/s10165-011-0571-zCrossRefPubMed

16.

He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770–778. https://arxiv.org/abs/1512.03385

17.

Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. https://arxiv.org/abs/1409.1556

18.

Tagami M, Kasashima H, Kakehashi A, Yoshikawa A, Nishio M, Misawa N, Sakai A, Wanibuchi H, Yashiro M, Azumi A, Honda S (2024) Stromal area differences with epithelial-mesenchymal transition gene changes in conjunctival and orbital mucosa-associated lymphoid tissue lymphoma. Front Oncol 14:1277749. https://doi.org/10.3389/fonc.2024.1277749CrossRefPubMedPubMedCentral

19.

Swiderska-Chadaj Z, Hebeda KM, van den Brand M, Litjens G (2021) Artificial intelligence to detect MYC translocation in slides of diffuse large B-cell lymphoma. Virchows Arch 479:617–621CrossRefPubMed

20.

El Hussein S, Chen P, Medeiros LJ, Wistuba II, Jaffray D, Wu J, Khoury JD (2022) Artificial intelligence strategy integrating morphologic and architectural biomarkers provides robust diagnostic accuracy for disease progression in chronic lymphocytic leukemia. J Pathol 256:4–14CrossRefPubMed

21.

El Achi H, Khoury JD (2020) Artificial intelligence and digital microscopy applications in diagnostic hematopathology. Cancers (Basel) 12:797CrossRefPubMed

22.

Li D, Bledsoe JR, Zeng Y, Liu W, Hu Y, Bi K, Liang A, Li S (2020) A deep learning diagnostic platform for diffuse large B-cell lymphoma with high accuracy across multiple hospitals. Nat Commun 11:1–9CrossRef

23.

Sato Y, Notohara K, Kojima M, Takata K, Masaki Y, Yoshino T (2010) IgG4-related disease: historical overview and pathology of hematological disorders. Pathol Int 60:247–258CrossRefPubMed

24.

Bledsoe JR, Wallace ZS, Deshpande V, Richter JR, Klapman J, Cowan A, Stone JH, Ferry JA (2017) Atypical IgG4+ plasmacytic proliferations and lymphomas: characterization of 11 cases. Am J Clin Pathol 148:215–235CrossRefPubMed

25.

Bledsoe JR, Wallace ZS, Stone JH, Deshpande V, Ferry JA (2018) Lymphomas in IgG4-related disease: clinicopathologic features in a Western population. Virchows Arch 472:839–852CrossRefPubMed

26.

Li K-M, Xu M-H, Wu X, He W-M (2020) The expression of IgG and IgG4 in orbital MALT lymphoma: the similarities and differences of IgG4-related diseases. Onco Targets Ther 5755–5761. https://doi.org/10.2147/OTT.S242852

27.

Jung SK, Lim J, Yang SW, Won YJ (2021) Nationwide trends in the incidence of orbital lymphoma from 1999 to 2016 in South Korea. Br J Ophthalmol 105:1341–1345. https://doi.org/10.1136/bjophthalmol-2020-316796CrossRefPubMed

28.

Olsen TG, Heegaard S (2019) Orbital lymphoma. Surv Ophthalmol 64:45–66. https://doi.org/10.1016/j.survophthal.2018.08.002CrossRefPubMed

Title: Artificial intelligence-based differential diagnosis of orbital MALT lymphoma and IgG4 related ophthalmic disease using hematoxylin–eosin images
Authors: Mizuki Tagami
Mizuho Nishio
Atsuko Yoshikawa
Norihiko Misawa
Atsushi Sakai
Yusuke Haruna
Mami Tomita
Atsushi Azumi
Shigeru Honda
Publication date: 03-05-2024
Publisher: Springer Berlin Heidelberg
Keywords: Mucosa Associated Lymphoid Tissue
Artificial Intelligence
Published in: Graefe's Archive for Clinical and Experimental Ophthalmology
Print ISSN: 0721-832X
Electronic ISSN: 1435-702X
DOI: https://doi.org/10.1007/s00417-024-06501-1

At a glance: The STEP trials

Springer Medicine

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

Abstract

Purpose

Methods

Results

Conclusions

At a glance: The STEP trials

Springer Medicine

Abstract

Purpose

Methods

Results

Conclusions

Please log in to get access to this content