|
|
|
| GLCFormer: A Breast Cancer TMB Prediction Model Based on Digital Pathological Images |
| Zhang Xiaoyan1, Liu Yan1, Zhao Zheng1, Meng Xiangfu1*, Li Shuai2 |
1(School of Electronics and Information Engineering, Liaoning Technical University, Huludao 125000, Liaoning, China)
2(Department of Neurosurgery, Liaoning Health Industry Group Fuxin Mining Group General Hospital, Fuxin 123000,Liaoning, China) |
|
|
|
|
Abstract Tumor mutation burden (TMB) is a key biomarker to predict the efficacy of immune checkpoint inhibitors (ICIs) in breast cancer patients. Existing deep learning methods for WSI-based TMB prediction face two critical challenges: 1) Self-attention easily induces redundant global interaction responses, reducing global modeling efficiency; 2) Lack of adaptability in global-local feature fusion causes redundancy, hindering effective cross-scale integration. To address these issues, this study proposed GLCFormer, a global-local dual-branch parallel collaborative model. ReLU linear attention was integrated into the global branch to suppress weakly correlated features via nonlinear mapping, enhancing computational efficiency and extracting global semantic information from pathological images. To strengthen fine-grained structural representation at the same feature level, the local branch was designed with a multi-scale convolution block composed of parallel depthwise separable convolutions. Dual-branch features were fed into the dynamic cross-scalefusion (DCSF) module, which adaptively generates weights to reduce redundancy and enable efficient global-local integration. Five independent repeated experiments were conducted on TCGA-BRCA (198 patients’ WSI data, 614,253 training samples). Results showed that GLCFormer achieved an AUC of 98.8%±0.1% in TMB classification (4.6% higher than state-of-the-art CoAtNet), with statistical significance (P<0.05) via independent two-sample t-test. In regression, it yielded a mean absolute percentage error (MAPE) of 0.2874, outperforming all comparators. These results validated the proposed method’s favorable accuracy and stability in WSI-level TMB prediction, supporting clinical precise immunotherapy.
|
|
Received: 04 June 2025
|
|
|
|
Corresponding Authors:
*E-mail:marxi@126.com
|
|
|
|
[1] Schmid P, Adams S, Rugo HS, et al. Atezolizumab and nab-paclitaxel in advanced triple-negative breast cancer [J]. New England Journal of Medicine, 2018, 379 (22): 2108-2121.
[2] Yates LR, Gerstung M, Knappskog S, et al. Subclonal diversification of primary breast cancer revealed by multiregion sequencing[J]. Nature Medicine, 2015, 21(7): 751-759.
[3] McGranahan N, Furness AJS, Rosenthal R, et al. Clonal neoantigens elicit T cell immunoreactivity and sensitivity to immune checkpoint blockade[J]. Science, 2016, 351(6280):1463-1469.
[4] Sueangoen N, Thuwajit P, Yenchitsomanus PT, et al. Public neoantigens in breast cancer immunotherapy[J]. International Journal of Molecular Medicine, 2024, 54(1): 65.
[5] Ahmed J, Das B, Shin S, et al. Challenges and future directions in the management of tumor mutational burden-high (TMB-H) advanced solid malignancies [J]. Cancers, 2023, 15 (24): 5841.
[6] Kumar N, Gupta R, Gupta S. Whole slide imaging (WSI) in pathology: current perspectives and future directions [J]. Journal of Digital Imaging, 2020, 33 (4): 1034-1040.
[7] Huang Kaimei, Lin Binghu, Liu Jinyang, et al. Predicting colorectal cancer tumor mutational burden from histopathological images and.
[8] Liu Yongguang, Huang Kaimei, Yang Yachao, et al. Prediction of tumor mutation load in colorectal cancer histopathological images based on deep learning [J]. Frontiers in Oncology, 2022, 12: 906888.
[9] Coudray N, Ocampo PS, Sakellaropoulos T, et al. Classification and mutation prediction from non-small cell lung cancer histopathology images using deep learning [J]. Nature Medicine, 2018, 24 (10): 1559-1567.
[10] 孙德伟,王志刚,杨啸林,等. 基于深度学习的肺腺癌肿瘤突变负荷的预测 [J]. 中国生物医学工程学报,2021, 40 (6): 681-690.
[11] 刘邓,杨啸林,孟祥福. RcaNet: 一种预测肿瘤突变负荷的深度学习模型 [J]. 中国生物医学工程学报,2023, 42 (1): 51-61.
[12] Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need [C] // The 31st Conference on Neural Information Processing Systems. Long Beach: Neural Information Processing Systems, 2017: 1-11.
[13] Dosovitskiy A, Beyer L, Kolesnikov A, et al. An image is worth 16x16 words: transformers for image recognition at scale [C] // The 9th International Conference on Learning Representations. Vienna: Elsevier, 2021: 1-21.
[14] Liu Z, Lin Y, Cao Y, et al. Swin transformer: hierarchical vision transformer using shifted windows[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. Montreal: IEEE, 2021: 10012-10022.
[15] Wang Chingwei, Liu Tzuchien, Lai Pojen, et al. Ensemble transformer-based multiple instance learning to predict pathological subtypes and tumor mutational burden from histopathological whole slide images of endometrial and colorectal cancer[J]. Medical Image Analysis, 2025, 99: 103372.
[16] Dai Zihang, Liu Hui, Le QV, et al. CoAtNet: marrying convolution and attention for all data sizes [C] // The 35th Conference on Neural Information Processing Systems. Virtual: Curran Associates, 2021: 3965-3977.
[17] Guo Jianyuan, Han Kai, Wu Hao, et al. CMT: convolutional neural networks meet vision transformers [C] // 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans: IEEE, 2022: 12165-12175.
[18] Wadekar SN, Chaurasia A. Mobilevitv3: mobile-friendly vision transformer with simple and effective fusion of local, global and input features[J/OL]. https://arxiv.org/abs/2209.15159, 2022-09-30/2026-01-31.
[19] Chauhan NK, Singh K. Diagnosis of cervical cancer with oversampled unscaled and scaled data using machine learning classifiers [C] // 2022 IEEE Delhi Section Conference. New Delhi: IEEE, 2022: 1-6.
[20] Campbell BB, Light N, Fabrizio D, et al. Comprehensive analysis of hypermutation in human cancer[J]. Cell, 2017, 171(5): 1042-1056.
[21] Yu Weihao, Si Chenyang, Zhou Pan, et al. MetaFormer baselines for vision[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024, 46(2): 896-912.
[22] Katharopoulos A, Vyas A, Pappas N, et al. Transformers are RNNs: fast autoregressive transformers with linear attention [C] //The 37th International Conference on Machine Learning (ICML 2020). Vienna: PMLR, 2020: 5156-5165.
[23] Han Kai, Wang Yunhe, Tian Qi, et al. GhostNet: More Features From Cheap Operations [C] // 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020: 1577-1586.
[24] Szegedy C, Liu W, Jia Y, et al. Going deeper with convolutions [C] // 2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston: IEEE Computer Society, 2015: 1-9.
[25] Woo S, Park J, Lee JY, et al. CBAM: convolutional block attention module [C] // Proceedings of the European Conference on Computer Vision. Munich: Springer International Publishing, 2018: 3-19.
[26] Hou Qibin, Zhou Daquan, Feng Jiashi. Coordinate attention for efficient mobile network design[C] // 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Nashville: IEEE, 2021: 13708-13717.
[27] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition [C] // Proceedings of the 3rd International Conference on Learning Representations. San Diego: ICLR, 2015: 1-14.
[28] He Kaiming, Zhang Xiangyu, Ren Shaoqing, et al. Deep residual learning for image recognition [C] // 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE Computer Society, 2016: 770-778.
[29] Kang Zhaoxin, Zhang Hejun, Chen Mingqiu. et al. EsccNet: a hybrid CNN and transformers model for the classification of whole slide images of esophageal squamous cell carcinoma[C] // 2024 5th International Conference on Computer Engineering and Application (ICCEA). Hangzhou:IEEE,2024:918-922.
[30] Zaheer M, Guruganesh G, Dubey KA, et al. Big Bird: transformers for longer sequences[C] // Advances in Neural Information Processing Systems. Vancouver: Curran Associates Inc., 2020: 17283-17297.
[31] Ho J, Kalchbrenner N, Weissenborn D, et al. Axial attention in multidimensional transformers [J/OL]. https://arxiv.org/abs/1912.12180, 2019-12-20/2023-08-22. |
|
|
|
