{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T09:16:45Z","timestamp":1785403005678,"version":"3.56.0"},"reference-count":29,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T00:00:00Z","timestamp":1785369600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>Medical image analysis has undergone transformative progress with the application of deep learning models. However, existing architectures often struggle to effectively balance local feature extraction with global contextual understanding, which is crucial for complex diagnostic tasks such as Retinopathy of Prematurity (ROP) detection. In this study, we present a pretrained lightweight Conformer model tailored for medical image classification. The model integrates convolutional layers for capturing fine-grained spatial features with transformer blocks that capture long-range dependencies, creating a unified architecture capable of robust representation learning. We evaluate the model across multiple benchmark medical imaging datasets, including ROP, BloodMNIST, RetinalMNIST and other MedMNIST benchmark datasets. With 93.61% accuracy on the ROP dataset and 99.12% accuracy on BloodMNIST, experimental results show competitive classification performance while lowering model complexity to 12.4 million parameters and 3.2 GFLOPs. Experimental results demonstrate that the comparative studies versus CNN-based and transformer-based architectures, such as ResNet50, Swin-Tiny, ConvNeXt-Tiny, Vision Transformer, and MedViT. The findings show that in clinical settings with limited resources, the suggested lightweight Conformer offers a practical and computationally efficient alternative for medical image interpretation. Furthermore, the lightweight design ensures computational efficiency, making it suitable for deployment in resource-constrained healthcare environments. These findings validate the lightweight Conformer model\u2019s potential for scalable, accurate, and real-time medical image classification.<\/jats:p>","DOI":"10.3390\/jimaging12080344","type":"journal-article","created":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T08:09:42Z","timestamp":1785398982000},"page":"344","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Lightweight Conformer-Based Framework for Medical Image Classification"],"prefix":"10.3390","volume":"12","author":[{"given":"Sreelekshmi","family":"Vijayasree","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Amrita School of Computing, Amrita Vishwa Vidyapeetham, Amritapuri, Kollam 690525, Kerala, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adithya","family":"Krishna","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Amrita School of Computing, Amrita Vishwa Vidyapeetham, Amritapuri, Kollam 690525, Kerala, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Akarsh S.","family":"Nair","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Amrita School of Computing, Amrita Vishwa Vidyapeetham, Amritapuri, Kollam 690525, Kerala, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alfy","family":"Alex","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Amrita School of Computing, Amrita Vishwa Vidyapeetham, Amritapuri, Kollam 690525, Kerala, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shyamdev Krishnan","family":"Jayakrishnan","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Amrita School of Computing, Amrita Vishwa Vidyapeetham, Amritapuri, Kollam 690525, Kerala, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jyothisha J.","family":"Nair","sequence":"additional","affiliation":[{"name":"School of Computer Sciences, Mahatma Gandhi University, Kottayam 686001, Kerala, India"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,7,30]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Peng, Z., Huang, W., Gu, S., Xie, L., Wang, Y., Jiao, J., and Ye, Q. (2021). Conformer: Local Features Coupling Global Representations for Visual Recognition. Proceedings of the IEEE-CVF International Conference on Computer Vision (ICCV), IEEE.","DOI":"10.1109\/ICCV48922.2021.00042"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"106791","DOI":"10.1016\/j.compbiomed.2023.106791","article-title":"MedViT: A robust vision transformer for generalized medical image classification","volume":"157","author":"Manzari","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"ref_3","unstructured":"Matsoukas, C., Haslum, J.F., Sorkhei, M., Soerberg, M., and Smith, K. (2023). Pretrained vits yield versatile representations for medical images. arXiv."},{"key":"ref_4","unstructured":"Alzubaidi, L., Santamar, J., Manoufali, M., Mohammed, B., Fadhel, M.A., Zhang, J., Al-Timemy, A.H., Al-Shamma, O., and Duan, Y. (2021). MedNet: Pre-trained convolutional neural network model for the medical imaging tasks. arXiv."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Huang, Y., Zou, J., Meng, L., Yue, X., Zhao, Q., Li, J., Song, C., Jimenez, G., Li, S., and Fu, G. (2024). Comparative analysis of imagenet pre-trained deep learning models and dinov2 in medical imaging classification. Proceedings of the 2024 IEEE 48th Annual Computers, Software, and Applications Conference (COMPSAC), IEEE.","DOI":"10.1109\/COMPSAC61105.2024.00049"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"36341","DOI":"10.1007\/s11042-021-11208-0","article-title":"Automated detection of retinopathy of prematurity by deep attention network multimedia tools and applications","volume":"80","author":"Lei","year":"2022","journal-title":"Multimed. Tools. Appl."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1097\/00004397-200110000-00013","article-title":"Recent Advances in Retinopathy of Prematurity","volume":"41","author":"Nguyen","year":"2001","journal-title":"Int. Ophthalmol. Clin."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Abnar, S., and Zuidema, W. (2020). Quantifying attention flow in transformers. arXiv.","DOI":"10.18653\/v1\/2020.acl-main.385"},{"key":"ref_9","unstructured":"Ba, J.L., Kiros, J.R., and Hinton, G.E. (2016). Layer normalization. arXiv."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Chen, H., Wang, Y., Guo, T., Xu, C., Deng, Y., Liu, Z., Ma, S., Xu, C., Xu, C., and Gao, W. (2020). Pre-trained image processing transformer. arXiv.","DOI":"10.1109\/CVPR46437.2021.01212"},{"key":"ref_11","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume":"Volume 25","author":"Krizhevsky","year":"2012","journal-title":"Proceedings of the NeurIPS"},{"key":"ref_12","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., and J\u00e9gou, H. (2020). Training data-efficient image transformers and distillation through attention. arXiv."},{"key":"ref_13","unstructured":"Wu, B., Xu, C., Dai, X., Wan, A., Zhang, P., Tomizuka, M., Keutzer, K., and Vajda, P. (2020). Visual transformers: Token-based image representation and processing for computer vision. arXiv."},{"key":"ref_14","first-page":"261","article-title":"Advances in Retinopathy of Prematurity","volume":"41","author":"Xu","year":"2019","journal-title":"Zhongguo Yi Xue Ke Xue Yuan Xue Bao"},{"key":"ref_15","unstructured":"Devlin, J., Chang, M.W., Lee, K., and Toutanova, K. (2018). BERT: Pre-training of deep bidirectional transformers for language understanding. arXiv."},{"key":"ref_16","unstructured":"Bundele, V., Sar\u0131ta\u015f, K., Kargi, B., \u00c7al, O.A., Tez\u00f6ren, K., Ghaderi, Z., and Lensch, H. (2024). Evaluating self-supervised learning in medical imaging: A benchmark for robustness, generalizability, and multi-domain impact. arXiv."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"173","DOI":"10.4103\/sjopt.sjopt_91_23","article-title":"Vision transformers: The next frontier for deep learning-based ophthalmic image analysis","volume":"37","author":"Wu","year":"2023","journal-title":"Saudi J. Ophthalmol."},{"key":"ref_18","unstructured":"Tuba, M., Akashe, S., and Joshi, A. (2023). Ensemble Deep Learning Model for Breast Histopathology Image Classification. Proceedings of the ICT Infrastructure and Computing, Springer Nature."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"68697","DOI":"10.1109\/ACCESS.2024.3397667","article-title":"SwinCNN: An Integrated Swin Trasformer and CNN for Improved Breast Cancer Grade Classification","volume":"12","author":"Sreelekshmi","year":"2024","journal-title":"IEEE Access"},{"key":"ref_20","first-page":"55","article-title":"Comparative study on image restoration techniques using the partial differential equation and filters","volume":"2","author":"Laxman","year":"2013","journal-title":"Int. J. Eng. Res. Technol."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"801","DOI":"10.1016\/j.procs.2024.03.269","article-title":"Variational Auto encoders for Improved Breast Cancer Classification","volume":"233","author":"Sreelekshmi","year":"2024","journal-title":"Procedia Comput. Sci."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"195658","DOI":"10.1109\/ACCESS.2024.3518612","article-title":"Unleashing the Power of Hierarchical Variational Autoencoder for Predicting Breast Cancer","volume":"12","author":"Sreelekshmi","year":"2024","journal-title":"IEEE Access"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1007\/s44163-025-00775-y","article-title":"An integrated model for early breast cancer prediction using microcalcifications and patient risk factors","volume":"6","author":"Sreelekshmi","year":"2026","journal-title":"Discov. Artif. Intell."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"2774","DOI":"10.1109\/TEM.2021.3103334","article-title":"Lung-GANs: Unsupervised representation learning for lung disease classification using chest CT and X-ray images","volume":"70","author":"Yadav","year":"2021","journal-title":"IEEE Trans. Eng. Manag."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"100105","DOI":"10.1109\/ACCESS.2025.3576825","article-title":"Advancing breast cancer detection: Se-conformer framework for malignancy detection in histopathology images","volume":"13","author":"Nair","year":"2025","journal-title":"IEEE Access"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"101865","DOI":"10.1016\/j.atech.2026.101865","article-title":"Unsupervised Autoencoder Detection with a Local Context-Based Correction for Mixed Pixels in Thermal Images","volume":"13","author":"Sarath","year":"2026","journal-title":"Smart Agric. Technol."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., and Guo, B. (2021). Swin transformer: Hierarchical vision transformer using shifted windows. Proceedings of the IEEE\/CVF International Conference on Computer Vision, IEEE.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"107262","DOI":"10.1016\/j.neunet.2025.107262","article-title":"Augmenting interaction effects in convolutional networks with taylor polynomial gated units","volume":"185","author":"Zou","year":"2025","journal-title":"Neural Netw."},{"key":"ref_29","first-page":"476","article-title":"From public to clinical data: External validation of an explainable MedViT model for retinal OCT images","volume":"76","author":"Gibala","year":"2025","journal-title":"J. Electr. Eng."}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/12\/8\/344\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T08:51:36Z","timestamp":1785401496000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/12\/8\/344"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,30]]},"references-count":29,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["jimaging12080344"],"URL":"https:\/\/doi.org\/10.3390\/jimaging12080344","relation":{},"ISSN":["2313-433X"],"issn-type":[{"value":"2313-433X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,30]]}}}