{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T17:52:55Z","timestamp":1774720375892,"version":"3.50.1"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T00:00:00Z","timestamp":1740096000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T00:00:00Z","timestamp":1740096000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SIViP"],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1007\/s11760-025-03866-6","type":"journal-article","created":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T17:42:57Z","timestamp":1740159777000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Explainable AI enhanced transformer based UNet for medical images segmentation using gradient weighted class activation map"],"prefix":"10.1007","volume":"19","author":[{"given":"Abtin","family":"Hasannezhad","sequence":"first","affiliation":[]},{"given":"Saeed","family":"Sharifian","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,2,21]]},"reference":[{"key":"3866_CR1","unstructured":"Adebayo, J., et al.: Sanity checks for saliency maps. Adv. Neural Inf. Process. Syst. 31 (2018)"},{"issue":"7","key":"3866_CR2","volume":"10","author":"S Bach","year":"2015","unstructured":"Bach, S., et al.: On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PLoS ONE 10(7), e0130140 (2015)","journal-title":"PLoS ONE"},{"key":"3866_CR3","unstructured":"Chen, J., et al.: Transunet: transformers make strong encoders for medical image segmentation. In: arXiv preprint arXiv:2102.04306 (2021)"},{"key":"3866_CR4","unstructured":"Child, R., et al.: Generating long sequences with sparse transformers. arXiv preprint arXiv:1904.10509 (2019)"},{"key":"3866_CR5","doi-asserted-by":"crossref","unstructured":"Deng, J., et al.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"3866_CR6","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"issue":"1","key":"3866_CR7","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1109\/TPAMI.2022.3152247","volume":"45","author":"K Han","year":"2022","unstructured":"Han, K., et al.: A survey on vision transformer. IEEE Trans. Pattern Anal. Mach. Intell. 45(1), 87\u2013110 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"4","key":"3866_CR8","doi-asserted-by":"crossref","first-page":"475","DOI":"10.3390\/e24040475","volume":"24","author":"C-T Hsiao","year":"2022","unstructured":"Hsiao, C.-T., et al.: Application of convolutional neural network for fingerprint-based prediction of gender, finger position, and height. Entropy 24(4), 475 (2022)","journal-title":"Entropy"},{"key":"3866_CR9","doi-asserted-by":"crossref","unstructured":"Jha, D., et al.: Doubleu-net: a deep convolutional neural network for medical image segmentation. In: 2020 IEEE 33rd International Symposium on Computer-based Medical Systems (CBMS), pp. 558\u2013564. IEEE (2020)","DOI":"10.1109\/CBMS49503.2020.00111"},{"key":"3866_CR10","doi-asserted-by":"crossref","first-page":"5875","DOI":"10.1109\/TIP.2021.3089943","volume":"30","author":"P-T Jiang","year":"2021","unstructured":"Jiang, P.-T., et al.: Layercam: exploring hierarchical class activation maps for localization. IEEE Trans. Image Process. 30, 5875\u20135888 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"3866_CR11","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1016\/j.media.2016.10.004","volume":"36","author":"K Kamnitsas","year":"2017","unstructured":"Kamnitsas, K., et al.: Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation. Med. Image Anal. 36, 61\u201378 (2017)","journal-title":"Med. Image Anal."},{"key":"3866_CR12","volume":"225","author":"SH Kim","year":"2023","unstructured":"Kim, S.H., et al.: Combining CNN and Grad-CAM for profitability and explainability of investment strategy: application to the KOSPI 200 futures. Expert Syst. Appl. 225, 120086 (2023)","journal-title":"Expert Syst. Appl."},{"issue":"1","key":"3866_CR13","doi-asserted-by":"crossref","first-page":"14888","DOI":"10.1038\/s41598-022-18646-2","volume":"12","author":"J Kugelman","year":"2022","unstructured":"Kugelman, J., et al.: A comparison of deep learning U-Net architectures for posterior segment OCT retinal layer segmentation. Sci. Rep. 12(1), 14888 (2022)","journal-title":"Sci. Rep."},{"issue":"3","key":"3866_CR14","doi-asserted-by":"crossref","first-page":"2047","DOI":"10.1007\/s11760-023-02835-1","volume":"18","author":"M Lalinia","year":"2024","unstructured":"Lalinia, M., Sahafi, A.: Colorectal polyp detection in colonoscopy images using YOLO-V8 network. Signal Image Video Process. 18(3), 2047\u20132058 (2024)","journal-title":"Signal Image Video Process."},{"key":"3866_CR15","first-page":"1","volume":"71","author":"A Lin","year":"2022","unstructured":"Lin, A., et al.: Ds-transunet: dual swin transformer u-net for medical image segmentation. IEEE Trans. Instrum. Measur. 71, 1\u201315 (2022)","journal-title":"IEEE Trans. Instrum. Measur."},{"key":"3866_CR16","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.\u00a03431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"issue":"1","key":"3866_CR17","doi-asserted-by":"crossref","first-page":"11","DOI":"10.3390\/sym9010011","volume":"9","author":"A Mehmood","year":"2017","unstructured":"Mehmood, A., et al.: Prognosis essay scoring and article relevancy using multi-text features and machine learning. Symmetry 9(1), 11 (2017)","journal-title":"Symmetry"},{"key":"3866_CR18","unstructured":"Parmar, N., et al.: Image transformer. In: International Conference on Machine Learning. PMLR. pp.\u00a04055\u20134064 (2018)"},{"key":"3866_CR19","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: Convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-assisted Intervention\u2013MICCAI 2015: 18th International Conference, Munich, Germany, October 5\u20139, 2015, proceedings, part III 18, pp.\u00a0234\u2013241. Springer (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"3866_CR20","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1016\/j.media.2019.01.012","volume":"53","author":"J Schlemper","year":"2019","unstructured":"Schlemper, J., et al.: Attention gated networks: learning to leverage salient regions in medical images. Med. Image Anal. 53, 197\u2013207 (2019)","journal-title":"Med. Image Anal."},{"key":"3866_CR21","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., et al.: Grad-cam: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp.\u00a0618\u2013626 (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"3866_CR22","unstructured":"Selvaraju, R.R., et al.: Grad-CAM: Why did you say that? arXiv preprint arXiv:1611.07450 (2016)"},{"key":"3866_CR23","unstructured":"Shrikumar, A., Greenside, P., Kundaje, A.: Learning important features through propagating activation differences. In: International Conference on Machine Learning. PMlR, pp.\u00a03145\u20133153 (2017)"},{"key":"3866_CR24","unstructured":"Srinivas, S., Fleuret, F.: Full-gradient representation for neural network visualization. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"issue":"1","key":"3866_CR25","doi-asserted-by":"crossref","first-page":"17709","DOI":"10.1038\/s41598-023-43871-8","volume":"13","author":"A Sujatha Ravindran","year":"2023","unstructured":"Sujatha Ravindran, A., Contreras-Vidal, J.: An empirical comparison of deep learning explainability approaches for EEG using simulated ground truth. Sci. Rep. 13(1), 17709 (2023)","journal-title":"Sci. Rep."},{"key":"3866_CR26","unstructured":"Tan, M.: Efficientnet: rethinking model scaling for convolutional neural networks. arXiv preprint arXiv:1905.11946 (2019)"},{"issue":"17","key":"3866_CR27","doi-asserted-by":"crossref","first-page":"5813","DOI":"10.3390\/s21175813","volume":"21","author":"M Umair","year":"2021","unstructured":"Umair, M., et al.: Detection of COVID-19 using transfer learning and Grad-CAM visualization on indigenously collected X-ray dataset. Sensors 21(17), 5813 (2021)","journal-title":"Sensors"},{"key":"3866_CR28","unstructured":"Vaswani, A.: Attention is all you need. Adv. Neural Inf. Process. Syst. (2017)"},{"key":"3866_CR29","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"3866_CR30","doi-asserted-by":"crossref","unstructured":"Wang, H., et al.: Score-CAM: score-weighted visual explanations for convolutional neural networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp.\u00a024\u201325 (2020)","DOI":"10.1109\/CVPRW50498.2020.00020"},{"issue":"10","key":"3866_CR31","doi-asserted-by":"crossref","first-page":"3349","DOI":"10.1109\/TPAMI.2020.2983686","volume":"43","author":"J Wang","year":"2020","unstructured":"Wang, J., et al.: Deep high-resolution representation learning for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 43(10), 3349\u20133364 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3866_CR32","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: Non-local neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.\u00a07794\u20137803 (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"3866_CR33","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1016\/j.patcog.2019.01.006","volume":"90","author":"W Zifeng","year":"2019","unstructured":"Zifeng, W., Shen, C., Van Den Hengel, A.: Wider or deeper: revisiting the resnet model for visual recognition. Pattern Recognit. 90, 119\u2013133 (2019)","journal-title":"Pattern Recognit."},{"key":"3866_CR34","doi-asserted-by":"crossref","unstructured":"Xiao, X.: Weighted res-unet for high-quality retina vessel segmentation. In: 2008 9th International Conference on Information Technology in Medicine and Education (ITME), pp. 327\u2013331. IEEE (2018)","DOI":"10.1109\/ITME.2018.00080"},{"key":"3866_CR35","doi-asserted-by":"crossref","unstructured":"Zhao, H., et al.: Pyramid scene parsing network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.\u00a02881\u20132890 (2017)","DOI":"10.1109\/CVPR.2017.660"},{"key":"3866_CR36","doi-asserted-by":"crossref","unstructured":"Zhou, Z., et al.: Unet++: a nested u-net architecture for medical image segmentation. In: Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support: 4th International Workshop, DLMIA 2018, and 8th International Workshop, ML-CDS 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 20, 2018, Proceedings 4, pp.\u00a03\u201311. Springer (2018)","DOI":"10.1007\/978-3-030-00889-5_1"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-025-03866-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-025-03866-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-025-03866-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,2]],"date-time":"2025-04-02T01:05:58Z","timestamp":1743555958000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-025-03866-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,21]]},"references-count":36,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,4]]}},"alternative-id":["3866"],"URL":"https:\/\/doi.org\/10.1007\/s11760-025-03866-6","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"value":"1863-1703","type":"print"},{"value":"1863-1711","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,21]]},"assertion":[{"value":"3 October 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 October 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 January 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 February 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"321"}}