{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T18:13:37Z","timestamp":1764785617871,"version":"3.45.0"},"reference-count":36,"publisher":"Tech Science Press","issue":"2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["CMC"],"published-print":{"date-parts":[[2025]]},"DOI":"10.32604\/cmc.2025.061977","type":"journal-article","created":{"date-parts":[[2025,4,16]],"date-time":"2025-04-16T02:58:11Z","timestamp":1744772291000},"page":"2221-2244","source":"Crossref","is-referenced-by-count":1,"title":["Multi-Scale Vision Transformer with Dynamic Multi-Loss Function for Medical Image Retrieval and Classification"],"prefix":"10.32604","volume":"83","author":[{"given":"Omar","family":"Alqahtani","sequence":"first","affiliation":[]},{"given":"Mohamed","family":"Ghouse","sequence":"additional","affiliation":[]},{"given":"Asfia","family":"Sabahath","sequence":"additional","affiliation":[]},{"given":"Omer Bin","family":"Hussain","sequence":"additional","affiliation":[]},{"given":"Arshiya","family":"Begum","sequence":"additional","affiliation":[]}],"member":"17807","published-online":{"date-parts":[[2025]]},"reference":[{"key":"ref1","doi-asserted-by":"crossref","unstructured":"Wang X, Peng Y, Lu L, Lu Z, Bagheri M, Summers RM. ChestX-ray8: hospital-scale chest X-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. arXiv:1705.02315. 2017.","DOI":"10.1109\/CVPR.2017.369"},{"key":"ref2","doi-asserted-by":"crossref","unstructured":"Harley AW, Ufkes A, Derpanis KG. Evaluation of deep convolutional nets for document image classification and retrieval. arXiv:1502.07058. 2015.","DOI":"10.1109\/ICDAR.2015.7333910"},{"key":"ref3","unstructured":"Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556. 2015."},{"key":"ref4","doi-asserted-by":"crossref","unstructured":"Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, et al. Going deeper with convolutions. arXiv:1409.4842. 2014.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref5","series-title":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"ref6","series-title":"International Conference on Learning Representations","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2021"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"2037","DOI":"10.1007\/s11517-024-03055-6","article-title":"Echoes of images: multi-loss network for image retrieval in vision transformers","volume":"62","author":"Pundhir","year":"2024","journal-title":"Med Biolo Eng Comput"},{"key":"ref8","series-title":"2023 26th International Conference on Computer and Information Technology (ICCIT)","first-page":"1","article-title":"SynthEnsemble: a fusion of CNN, vision transformer, and hybrid models for multi-label chest X-ray classification","author":"Ashraf","year":"2023"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"1087438","DOI":"10.3389\/fonc.2022.1087438","article-title":"Automatic polyp image segmentation and cancer prediction based on deep learning","volume":"12","author":"Shen","year":"2023","journal-title":"Front Oncol"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"130603","DOI":"10.1109\/ACCESS.2024.3447888","article-title":"Fast&Focused-Net: enhancing small object encoding with VDP layer in deep neural networks","volume":"12","author":"Ali","year":"2024","journal-title":"IEEE Access"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"6381","DOI":"10.1038\/s41598-019-42294-8","article-title":"Comparison of deep learning approaches for multi-label chest X-ray classification","volume":"9","author":"Baltruschat","year":"2019","journal-title":"Sci Rep"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"180161","DOI":"10.1038\/sdata.2018.161","article-title":"The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions","volume":"5","author":"Tschandl","year":"2018","journal-title":"Sci Data"},{"key":"ref13","unstructured":"Codella N, Rotemberg V, Tschandl P, Celebi ME, Dusza S, Gutman D, et al. Skin lesion analysis toward melanoma detection 2018: a challenge hosted by the international skin imaging collaboration (ISIC). arXiv:1902.03368. 2019."},{"key":"ref14","doi-asserted-by":"crossref","first-page":"6247","DOI":"10.1038\/s41598-023-32611-7","article-title":"A convolutional attention mapping deep neural network for classification and localization of cardiomegaly on chest X-rays","volume":"13","author":"Innat","year":"2023","journal-title":"Sci Rep"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"3731","DOI":"10.1109\/JBHI.2022.3227540","article-title":"A multi-scale context aware attention model for medical image segmentation","volume":"27","author":"Alam","year":"2023","journal-title":"IEEE J Biomed Health Inform"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"71665","DOI":"10.1007\/s11042-024-18334-5","article-title":"Towards improved U-Net for efficient skin lesion segmentation","volume":"83","author":"Nampalle","year":"2024","journal-title":"Multimed Tools Appl"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"33371","DOI":"10.1007\/s11042-023-16759-y","article-title":"Improved U-Net based on contour attention for efficient segmentation of skin lesion","volume":"83","author":"Liang","year":"2023","journal-title":"Multimed Tools Appl"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"2703","DOI":"10.1007\/s11517-024-03095-y","article-title":"Efficient skin lesion segmentation with boundary distillation","volume":"62","author":"Zhang","year":"2024","journal-title":"Med Biol Eng Comput"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"486","DOI":"10.3390\/info14090486","article-title":"GSCEU-Net: an end-to-end lightweight skin lesion segmentation model with feature fusion based on U-Net enhancements","volume":"14","author":"Hao","year":"2023","journal-title":"Information"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"93992","DOI":"10.1109\/ACCESS.2022.3203691","article-title":"GMIF: a gated multiscale input feature fusion scheme for scene text detection","volume":"10","author":"Ali","year":"2022","journal-title":"IEEE Access"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1023\/A:1010091220143","article-title":"The cross-entropy method for combinatorial and continuous optimization","volume":"1","author":"Rubinstein","year":"1999","journal-title":"Methodol Comput Appl Probab"},{"key":"ref22","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"815","article-title":"FaceNet: a unified embedding for face recognition and clustering","author":"Schroff","year":"2015"},{"key":"ref23","series-title":"2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201906)","first-page":"1735","article-title":"Dimensionality reduction by learning an invariant mapping","volume":"2","author":"Hadsell","year":"2006"},{"key":"ref24","unstructured":"Hinton G, Vinyals O, Dean J. Distilling the knowledge in a neural network. arXiv:1503.02531. 2015."},{"key":"ref25","series-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"2261","article-title":"Densely connected convolutional networks","author":"Huang","year":"2017"},{"key":"ref26","unstructured":"Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, et al. MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv:1704.04861. 2017."},{"key":"ref27","unstructured":"Iandola FN, Han S, Moskewicz MW, Ashraf K, Dally WJ, Keutzer K. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size. arXiv:1602.07360. 2016."},{"key":"ref28","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s42492-023-00140-9","article-title":"Vision transformer architecture and applications in digital health: a tutorial and survey","volume":"6","author":"Al-hammuri","year":"2023","journal-title":"Visual Comput Indust, Biomed Art"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"12567","DOI":"10.1038\/s41598-024-63094-9","article-title":"Implementing vision transformer for classifying 2D biomedical images","volume":"14","author":"Halder","year":"2024","journal-title":"Sci Rep"},{"key":"ref30","series-title":"Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support. (DLMIA 2018, ML-CDS 2018)","first-page":"3","article-title":"UNet++: a nested U-Net architecture for medical image segmentation","author":"Zhou","year":"2018"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"2663","DOI":"10.1109\/TMI.2018.2845918","article-title":"H-DenseUNet: hybrid densely connected UNet for liver and tumor segmentation from CT volumes","volume":"37","author":"Li","year":"2018","journal-title":"IEEE Trans Med Imag"},{"key":"ref32","series-title":"2016 Fourth International Conference on 3D Vision (3DV)","first-page":"565","article-title":"V-Net: fully convolutional neural networks for volumetric medical image segmentation","author":"Milletari","year":"2016"},{"key":"ref33","doi-asserted-by":"crossref","first-page":"103829","DOI":"10.1016\/j.bspc.2022.103829","article-title":"DGCU\u2013Net: a new dual gradient-color deep convolutional neural network for efficient skin lesion segmentation","volume":"77","author":"Ramadan","year":"2022","journal-title":"Biomed Signal Process Control"},{"key":"ref34","doi-asserted-by":"crossref","first-page":"2625","DOI":"10.3390\/diagnostics12112625","article-title":"A hybrid preprocessor DE-ABC for efficient skin-lesion segmentation with improved contrast","volume":"12","author":"Malik","year":"2022","journal-title":"Diagnostics"},{"key":"ref35","unstructured":"Rajpurkar P, Irvin J, Zhu K, Yang B, Mehta H, Duan T, et al. CheXNet: radiologist-level pneumonia detection on chest X-rays with deep learning. arXiv:1711.05225. 2017."},{"key":"ref36","series-title":"2009 IEEE Conference on Computer Vision and Pattern Recognition","first-page":"248","article-title":"ImageNet: a large-scale hierarchical image database","author":"Deng","year":"2009"}],"container-title":["Computers, Materials &amp; Continua"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/cdn.techscience.cn\/files\/cmc\/2025\/TSP_CMC-83-2\/TSP_CMC_61977\/TSP_CMC_61977.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T01:07:56Z","timestamp":1763341676000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.techscience.com\/cmc\/v83n2\/60568"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":36,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025]]},"published-print":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.32604\/cmc.2025.061977","relation":{},"ISSN":["1546-2226"],"issn-type":[{"type":"electronic","value":"1546-2226"}],"subject":[],"published":{"date-parts":[[2025]]}}}