A LIGHTWEIGHT SHUFFLENET-V2 MODEL FOR MULTI-CLASS GASTRIC HISTOPATHOLOGY CLASSIFICATION WITH EXPLAINABLE AI

Harshal Wankhade; Dr.Amol Zade

doi:10.4314/njt.2026.6165

Authors

H. Wankhade Department of Computer Science and Engineering, G.H.Raisoni University, Amravati, Maharashtra, INDIA
A. Zade Department of Computer Science and Engineering, G.H.Raisoni University, Amravati, Maharashtra, INDIA

DOI:

https://doi.org/10.4314/njt.2026.6165

Keywords:

Gastric Cancer, Histopathology image classification, Deep learning, Explainable AI, Digital pathology, Medical image analysis

Abstract

Gastric cancer is among the predominant causes of cancer-related death in the world that must be accurately and dependably examined by the histopathology. Proper interpretation of tissues is critical in early diagnosis in proper staging, and effective therapeutic decisions. Nevertheless, whole slide analysis using a manual method is tedious and subject to inter-rater error, whereas currently used deep learning systems tend to be computationally expensive and lack interpretability. The proposed paper uses a lightweight but a high-performing framework utilizing ShuffleNet-V2 to classify the gastric histopathology images into multi-classes. A subsample of 8000 histopathological image patches was taken out of a publicly accessible Kaggle dataset that comprises of 1000 samples of eight tissue classes. The proposed ShuffleNet-V2 with SE attention model was trained on dataset and compared with a number of pretrained models CNN, ResNet50, DenseNet201, EfficientNet-B3, MobileNet-V3 Large and Inception-V3 and identify best performing model. The proposed models were assessed in the different evaluation parameters. Also analyze the Mahalanobis distance, explainable AI and complemented by Mahalanobis distance. The model of ShuffleNet-V2 achieved an accuracy of 98.98. The ideal ROC and PR curves of the model are 99.90 and 99.90 respectively and high class-wise F1-score constantly, in comparison to all the other models. The explainable AI visualize the attribution maps that show the model to pay attention to the histologically significant structures, and favor meaningful clinical interpretability. The ultimate conclusion is that, ShuffleNet-V2 model is an accurate, efficient and explainable model to classify gastric tissue, and has high potential to be incorporated in the digital pathology process.

References

REFERENCE

[1] Yang, Q., Xu, D., Yang, Y., Lu, S., Wang, D., and Wang, L., “Global, regional, and national burden of gastric cancer in adolescents and young adults, 1990–2019: A systematic analysis for the Global Burden of Disease Study 2019,” American Journal of Gastroenterology, 119(3), pp. 454–467, 2024. https://doi.org/10.14309/ajg.0000000000002551

[2] Tseng, L. J., Matsuyama, A., and MacDonald-Dickinson, V., “Histology: The gold standard for diagnosis?,” Canadian Veterinary Journal, 64 (4), pp. 389–391, 2023.

[3] Ahuja, S., and Zaheer, S. “Advancements in pathology: Digital transformation, precision medicine, and beyond,” Journal of Pathology Informatics, 16, p. 100408, 2024. https://doi.org/10.1016/j.jpi.2024.100408

[4] Li, J., Li, W., Sisk, A., Ye, H., Wallace, W. D., Speier, W., and Arnold, C. W. “A multi-resolution model for histopathology image classification and localization with multiple instance learning,” Computers in Biology and Medicine, 131, p. 104253, 2021. https://doi.org/10.1016/j.compbiomed.2021.104253

[5] Shin, J., and Park, Y. S. “Unusual or uncommon histology of gastric cancer,” Journal of Gastric Cancer, 24 (1), pp. 69–88, 2024. https://doi.org/10.5230/jgc.2024.24.e7

[6] Ren, T., Govindarajan, V., Bourouis, S., et al. “An interpretable hybrid deep learning framework for gastric cancer diagnosis using histopathological imaging,” Scientific Reports, 15, p. 34204, 2025. https://doi.org/10.1038/s41598-025-15702-5

[7] Zhou, S., Xie, Y., Feng, X., Li, Y., Shen, L., and Chen, Y. “Artificial intelligence in gastrointestinal cancer research: Image learning advances and applications,” Cancer Letters, 614, p. 217555, 2025. https://doi.org/10.1016/j.canlet.2025.217555

[8] Zhao, P., Cai, L., Chen, D., and Wei, H. “Processing and recognition of gastric cancer pathological images based on ResNet,” Proceedings of SPIE, 12604, p. 1260439, 2023. https://doi.org/10.1117/12.2674511

[9] Yong, M. P., Hum, Y. C., Lai, K. W., Goh, C.-H., Yap, W.-S., and Tee, Y. K. “Histopathological gastric cancer detection using transfer learning,” International Conference on Bioinformatics and Computational Biology (ICBCB), Hangzhou, China, pp. 123–129, 2023. https://doi.org/10.1109/ICBCB57893.2023.10246524

[10] Klang, E., Sourosh, A., Nadkarni, G. N., Sharif, K., and Lahat, A., “Deep learning and gastric cancer: Systematic review of AI-assisted endoscopy,” Diagnostics, 13(24), p. 3613, 2023. https://doi.org/10.3390/diagnostics13243613

[11] Qiu, H., Tao, H., Jin, H., Li, Z., and Wang, B., “MILISS: Multi-instance learning with instance selection strategy for gastric cancer classification,” Chinese Control Conference, Kunming, China, pp. 7546–7552, 2024. https://doi.org/10.23919/ccc63176.2024.10661837

[12] Xia, S., Xia, Y., Liu, T., Luo, Y., and Pang, P. C. “Application of deep learning models in gastric cancer pathology image analysis: A systematic scoping review,” BMC Cancer, 25 (1), pp. 1257-1265, 2025. https://doi.org/10.1186/s12885-025-14662-3

[13] Gul, R., Akbar, H. O., Ali, S., Khan, M. A., Sardar, N., Álam, I., Iqbal, N., and Ahmad, Y. “Detection of early gastric cancer and lesion segmentation based on deep learning,” Journal of Health and Rehabilitation Research, 4(2), pp. 944–948, 2024. https://doi.org/10.61919/jhrr.v4i2.984

[14] Almarshad, F. A., Balaji, P., Syed, L., Aljohani, E., Dharmarajlu, S. M., Vaiyapuri, T., and AlAseem, N. A. “An efficient optimal CapsNet model-based computer-aided diagnosis for gastrointestinal cancer classification,” IEEE Access, 12(5), pp.137237-137246, 2024. https://doi.org/10.1109/access.2024.3442831

[15] Uçar, E. “Transformer-based feature extraction and optimized deep neural network for gastric cancer detection,” Journal of Digital Imaging, 12 (5), pp.1-19, 2025. https://doi.org/10.1007/s10278-025-01699-w

[16] Zubair, M., Owais, M., Hassan, T., Bendechache, M., Hussain, M., Hussain, I., and Werghi, N. “An interpretable framework for gastric cancer classification using multi-channel attention mechanisms and transfer learning on histopathology images,” Research Square, 15(1), pp. 13087-13095, 2024. https://doi.org/10.21203/rs.3.rs-5316440/v1

[17] Ul Haq, E., Yong, Q., Yuan, Z., Huang, J., Ul Haq, R., and Qin, X. “Accurate multiclassification and segmentation of gastric cancer using a hybrid cascaded deep learning model with vision transformer from endoscopic images,” Information Sciences, 670(2), pp. 120568-120574, 2024. https://doi.org/10.1016/j.ins.2024.120568

[18] Kim, B. S., Kim, B., Cho, M., Chung, H., Ryu, J. K., and Kim, S. “Enhanced multi-class pathology lesion detection in gastric neoplasms using deep learning-based approach and validation,” Scientific Reports, 14(1), pp. 11527, 2024. https://doi.org/10.1038/s41598-024-62494-1

[19] Kalimuthu, M., Ramya, M., Sreethar, S., and Nandhagopal, N. “Gastric cancer classification in saliva data using Levy search updated rainfall hybrid deep dual-stage BiLSTM,” Expert Systems, 2024. https://doi.org/10.1080/0952813X.2023.2301371

[20] Wang, X., Yue, X., Hang, T., and Liu, S. “Analysis of hyperspectral imaging using CNN–GRU for gastric adenomatous polyp and adenocarcinoma classification,” Journal of Biophotonics, 18(9), pp. 47 – 58, 2025. https://doi.org/10.1002/jbio.70047

[21] Bhardwaj, P., Kim, S., Koul, A., Kumar, Y., Changela, A., Shafi, J., and Ijaz, M. F. “Advanced CNN models in gastric cancer diagnosis: Enhancing endoscopic image analysis with deep transfer learning,” Frontiers in Oncology, 14, pp.143-162 2024. https://doi.org/10.3389/fonc.2024.1431912

[22] Subedi, A., Regmi, S., Regmi, N., Bhusal, B., Bağcı, U., and Jha, D. “Classification of endoscopy and video capsule images using CNN-transformer model,” arXiv Preprint, pp. 26-36, 2024. https://doi.org/10.48550/arxiv.2408.10733

[23] Jamil, D., Palaniappan, S., Khan, M. N. A., and Shah, S. M. A. “Revolutionizing gastric cancer diagnosis through advanced machine learning approaches,” Journal of Autonomous Intelligence, 7(4), pp. 1245-1258, 2024. https://doi.org/10.32629/jai.v7i4.1021

[24] Haseeb, A., Khan, M. A., Alhaisoni, M., Aldehim, G., Jamel, L., Tariq, U., Kim, T., and Cha, J. “A fusion of residual blocks and stack auto encoder features for stomach cancer classification,” CMC—Computers, Materials & Continua, 77 (3), p. 3895–3920, 2023. https://doi.org/10.32604/cmc.2023.045244

[25] Lou, S., Ji, J., Zhang, X., Li, H., Jiang, Y., Hua, M., Chen, K., Zheng, X., Zhang, Q., Han, P., Cao, L., and Wang, L. “Gastric Cancer Histopathology Tissue Image Dataset (GCHTID),” Figshare Dataset, 2024. https://doi.org/10.6084/m9.figshare.26014469.v

[26] Bayode, O., Aiyelokun, O., Osanyinlokun, O., and Adanikin, A. “Enhancing road crash prediction: A comparative study of machine learning algorithms and safety performance functions on the Lagos–Ibadan Expressway,” Nigerian Journal of Technology, 44(2), pp. 215–221, 2025.

[27] Hamzaa, M. T., Raheem, M. A., Kadhim, R. R., Abed, H. A., Kamil, M. Y., and Jassam, A.-L. A. “Change detection for urban expansion in Baghdad City Al-Doura area

using geographic information systems,” Nigerian Journal of Technology, 43(3), 2024.

[28] Balogun, N. A., Abdulrahaman, M. D., and Aka, K. “Exploring the prevalence of internet crimes among undergraduate students in a Nigerian University: A case study of the University of Ilorin,” Nigerian Journal of Technology, 43(1), p. 71–79, 2024. https://doi.org/10.4314/njt.v43i1.10