AB024. MIST: a weakly supervised deep learning system for multicenter diagnosis of mediastinal tumors
Original Research

AB024. MIST: a weakly supervised deep learning system for multicenter diagnosis of mediastinal tumors

Xiaofeng Jiang1, Hengrui Liang2, Jianxing He2, Yongtao Han1, Jakob Nikolas Kather3, Xuefeng Leng1

1Department of Thoracic Surgery, Sichuan Clinical Research Center for Cancer, Sichuan Cancer Hospital & Institute, Sichuan Cancer Center, University of Electronic Science and Technology of China (UESTC), Chengdu, China; 2Department of Thoracic Surgery, The First Affiliated Hospital of Guangzhou Medical University, Guangzhou, China; 3Else Kroener Fresenius Center for Digital Health, Faculty of Medicine and University Hospital Carl Gustav Carus, TUD Dresden University of Technology, Dresden, Germany

Correspondence to: Xuefeng Leng, MD, PhD. Department of Thoracic Surgery, Sichuan Clinical Research Center for Cancer, Sichuan Cancer Hospital & Institute, Sichuan Cancer Center, University of Electronic Science and Technology of China (UESTC), No. 55, Section 4, South Renmin Road, Chengdu 610041, China. Email: doc.leng@uestc.edu.cn.

Background: Mediastinal tumors represent a distinct group of thoracic diseases, with a rising global incidence and generally poor prognosis. Clinical diagnosis remains challenging due to the complex anatomical structure of the mediastinum and the often ambiguous boundaries between different pathological subtypes. The objective of this study is to develop and validate a high-performance deep learning diagnostic system—Mediastinal tumor Identification with weakly Supervised Training (MIST)—that can accurately and automatically identify mediastinal tumors from chest computed tomography (CT) scans using multicenter data.

Methods: The MIST system was trained using a dataset comprising 1,173 cases of mediastinal tumors with ten pathological subtypes, collected from a high-volume medical center in China. The system processes chest CT scans as input. It first applies a pretrained segmentation model to roughly localize tumor regions within the mediastinum. Then, imaging features are extracted using BiomedCLIP, a multimodal biomedical foundation model. These features are subsequently aggregated by the Transformer based Correlated Multiple Instance Learning (TransMIL) approach to assess tumor malignancy and predict specific pathological subtypes (Figure 1A). MIST’s generalizability was evaluated using an external validation cohort of 227 cases from five independent medical centers (Figure 1B).

Results: MIST demonstrated strong performance in 5-fold cross-validation on the training set, achieving an average area under the curve (AUC) of 0.741±0.045 for malignancy classification and a macro-average AUC of 0.760±0.004 for multiclass subtype classification. In the external validation cohort, MIST maintained comparable performance, with an AUC of 0.818 [95% confidence interval (CI): 0.744, 0.883] for malignancy detection and a macro-average AUC of 0.763 (95% CI: 0.715, 0.807) for subtype classification (Figure 1C). The detailed classification performance is shown in the confusion matrix (Figure 1D). The system achieved a top-1 accuracy of 0.194 (95% CI: 0.145, 0.247) and a top-3 accuracy of 0.480 (95% CI: 0.419, 0.542).

Conclusions: MIST enables accurate identification of both the malignancy and pathological subtypes of mediastinal tumors, with robust generalization across external multicenter datasets. This weakly supervised, foundation model-based approach holds promise for improving diagnostic accuracy and efficiency in clinical settings.

Keywords: Mediastinal tumors; deep learning; weakly supervised learning; subtype prediction; multicenter study

Figure 1 Overview and performance of the MIST system. (A) The overall workflow of the MIST diagnostic system. Slices from chest CT scans are processed by the BiomedCLIP model to extract image features (embeddings). These features are then aggregated by the TransMIL model to predict both malignancy and specific pathological subtypes. (B) The distribution of 10 pathological subtypes across the training set (n=1,173) and the external validation set (n=227). (C) Performance evaluation on the external validation set. The confusion matrix (left) illustrates the performance of binary malignancy classification. The ROC curves (right) show the performance for multiclass subtype classification, with corresponding AUC values for each subtype. (D) A detailed confusion matrix for the 10-class pathological subtype classification on the external validation set. AUC, area under the curve; CT, computed tomography; MIST, Mediastinal tumor Identification with weakly Supervised Training; TransMIL, Transformer based Correlated Multiple Instance Learning; ROC, receiver operating characteristic.

Acknowledgments

We gratefully acknowledge the participating medical centers and the patients whose anonymized data enabled this research.

Footnote

Funding: This work was supported by grants from the National Natural Science Foundation of China (No. 82472663), National Key Research and Development Program (No. 2022YFC2403400), International Cooperation Projects of the Science and Technology Department of Sichuan Province (grant No. 2024YFHZ0322), the Sichuan Key Research and Development Project from the Science and Technology Department of Sichuan Province (grant Nos. 2023YFS0044, 2023YFQ0056 and 2022YFQ0008), the Chengdu Science and Technology Bureau Key Research Project (No. 2024-YF05-00797-SN), the Wu Jieping Clinical Research Projects (grant No. 320.6750.2023-05-141), the Sichuan Province Clinical Key Specialty Construction Project [(2022)70], German Cancer Aid (DECADE, 70115166), the German Federal Ministry of Education and Research (PEARL, 01KD2104C; CAMINO, 01EO2101; SWAG, 01KD2215A; TRANSFORM LIVER, 031L0312A; TANGERINE, 01KT2302 through ERA-NET Transcan; Come2Data, 16DKZ2044A; DEEP-HCC, 031L0315A), the German Academic Exchange Service (SECAI, 57616814), the German Federal Joint Committee (TransplantKI, 01VSF21048), the European Union’s Horizon Europe and innovation programme (ODELIA, 101057091; GENIAL, 101096312), the European Research Council (ERC; NADIR, 101114631), the National Institutes of Health (EPICO, R01 CA263318) and the National Institute for Health and Care Research (NIHR, NIHR203331) Leeds Biomedical Research Centre (for J.N.K.).

Conflicts of Interest: All authors have completed the ICMJE uniform disclosure form (available at https://med.amegroups.com/article/view/10.21037/med-25-ab024/coif). J.N.K. is supported by the German Cancer Aid (DECADE, 70115166), the German Federal Ministry of Education and Research (PEARL, 01KD2104C; CAMINO, 01EO2101; SWAG, 01KD2215A; TRANSFORM LIVER, 031L0312A; TANGERINE, 01KT2302 through ERA-NET Transcan; Come2Data, 16DKZ2044A; DEEP-HCC, 031L0315A), the German Academic Exchange Service (SECAI, 57616814), the German Federal Joint Committee (TransplantKI, 01VSF21048), the European Union’s Horizon Europe and innovation programme (ODELIA, 101057091; GENIAL, 101096312), the European Research Council (ERC; NADIR, 101114631), the National Institutes of Health (EPICO, R01 CA263318) and the National Institute for Health and Care Research (NIHR, NIHR203331) Leeds Biomedical Research Centre. He declares consulting services for Bioptimus (France), Panakeia (UK), AstraZeneca (UK), and MultiplexDx (Slovakia). Furthermore, he holds shares in StratifAI (Germany), Synagen (Germany), and Ignition Labs (Germany), has received an institutional research grant by GSK, and has received honoraria by AstraZeneca, Bayer, Daiichi Sankyo, Eisai, Janssen, Merck, MSD, BMS, Roche, Pfizer, and Fresenius. The other authors have no conflicts of interest to declare.

Ethical Statement: The authors are accountable for all aspects of the work in ensuring that questions related to the accuracy or integrity of any part of the work are appropriately investigated and resolved. The study was conducted in accordance with the Declaration of Helsinki and its subsequent amendments. The study was approved by the institutional Ethics Committee of the National Center for Respiratory Medicine/The First Affiliated Hospital of Guangzhou Medical University (Oct 12, 2020; Institutional Review Board number: 2020 No.138) and individual consent for this retrospective analysis was waived. Approval from the Ethics Committee of Sichuan Cancer Hospital was waived, as the study involved retrospectively collected medical images that had been anonymized prior to data processing.

Open Access Statement: This is an Open Access article distributed in accordance with the Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International License (CC BY-NC-ND 4.0), which permits the non-commercial replication and distribution of the article with the strict proviso that no changes or edits are made and the original work is properly cited (including links to both the formal publication through the relevant DOI and the license). See: https://creativecommons.org/licenses/by-nc-nd/4.0/.

doi: 10.21037/med-25-ab024
Cite this abstract as: Jiang X, Liang H, He J, Han Y, Kather JN, Leng X. AB024. MIST: a weakly supervised deep learning system for multicenter diagnosis of mediastinal tumors. Mediastinum 2025;9:AB024.

Article Options

Download Citation

Share