{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T05:02:21Z","timestamp":1785301341797,"version":"3.55.0"},"reference-count":41,"publisher":"MDPI AG","issue":"15","license":[{"start":{"date-parts":[[2026,7,25]],"date-time":"2026-07-25T00:00:00Z","timestamp":1784937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Early detection of skin cancer significantly improves patient outcomes yet remains challenging due to the visual similarity of lesions and the need for clinical context. This paper proposes a novel Image-driven multimodal deep learning framework for automated skin cancer diagnosis integrating dermoscopic imaging sensors\u2019 clinical metadata and biomedical knowledge graphs. Dermoscopic images acquired from optical skin imaging sensors undergo advanced signal processing including multi-scale CLAHE enhancement and artifact suppression. A YOLOv8-nano sensor-based lesion detector achieves 97.2% mAP@0.5 for region-of-interest extraction. The biomedical knowledge graph (26 nodes 86 edges) encodes dermatological domain knowledge into 32-dimensional disease embeddings. Clinical metadata (age gender anatomical site) is encoded via learned feature vectors. A cross-attention fusion mechanism integrates these multimodal sensor-derived signals. Evaluated on the HAM10000 dataset (10,015 images 7 classes), our full multimodal model achieves 91.35% accuracy outperforming image-only (86.96%) and image+metadata (88.45%) baselines. An ensemble reaches 92.78% state-of-the-art accuracy with significant improvements on challenging classes (BCC +6.0% melanoma +3.8%). Statistical significance is confirmed (p &lt; 0.01 95% CI [90.7% 92.0%]). This work demonstrates that Image-based multimodal signal fusion with structured medical knowledge enhances both diagnostic accuracy and clinical interpretability.<\/jats:p>","DOI":"10.3390\/s26154728","type":"journal-article","created":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T08:15:56Z","timestamp":1785140156000},"page":"4728","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Image-Driven Multimodal Deep Learning for Skin Cancer Diagnosis: Cross-Attention Fusion of Dermoscopic Imaging Clinical Data and Knowledge Graphs"],"prefix":"10.3390","volume":"26","author":[{"given":"Syeda Sitara","family":"Waseem","sequence":"first","affiliation":[{"name":"Department of Computer Science, Government Sadiq College Women University, Bahawalpur 63100, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5675-1570","authenticated-orcid":false,"given":"Saman","family":"Iftikhar","sequence":"additional","affiliation":[{"name":"Faculty of Computer Studies, Arab Open University, Riyadh 84901, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ammar","family":"Rafiq","sequence":"additional","affiliation":[{"name":"Department of Computer Science, National University of Computer and Emerging Sciences, Islamabad, Chiniot-Faisalabad Campus, Chiniot 35400, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3078-6166","authenticated-orcid":false,"given":"Kangyoon","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Gachon University, Seongnam-si 13120, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6206-3934","authenticated-orcid":false,"given":"Syed Rizwan","family":"Hassan","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Gachon University, Seongnam-si 13120, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,7,25]]},"reference":[{"key":"ref_1","first-page":"229","article-title":"Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"74","author":"Bray","year":"2024","journal-title":"CA Cancer J. Clin."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1007\/s40257-020-00517-z","article-title":"A review of noninvasive techniques for skin cancer detection in dermatology","volume":"21","author":"Heibel","year":"2020","journal-title":"Am. J. Clin. Dermatol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"474","DOI":"10.1109\/JBHI.2019.2895803","article-title":"Dermoscopy image analysis: Overview and future directions","volume":"23","author":"Celebi","year":"2019","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1038\/nature21056","article-title":"Dermatologist-level classification of skin cancer with deep neural networks","volume":"542","author":"Esteva","year":"2017","journal-title":"Nature"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"538","DOI":"10.1109\/JBHI.2018.2824327","article-title":"Seven-point checklist and skin lesion classification using multitask multimodal neural nets","volume":"23","author":"Kawahara","year":"2019","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"e64","DOI":"10.1016\/S2589-7500(21)00252-1","article-title":"Characteristics of publicly available skin cancer image datasets: A systematic review","volume":"4","author":"Wen","year":"2022","journal-title":"Lancet Digit. Health"},{"key":"ref_7","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":"ref_8","unstructured":"Tan, M., and Le, Q. (2019). EfficientNet: Rethinking model scaling for convolutional neural networks. Proceedings of the International Conference on Machine Learning, ML Research Press."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Datta, S.K., Shaikh, M.A., Srihari, S.N., and Gao, M. (2021). Soft-attention improves skin cancer classification performance. arXiv.","DOI":"10.31219\/osf.io\/hjp56"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Yang, G., Luo, S., and Greer, P. (2025). Boosting skin cancer classification: A multi-scale attention and ensemble approach with vision transformers. Sensors, 25.","DOI":"10.3390\/s25082479"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"100659","DOI":"10.1016\/j.imu.2021.100659","article-title":"An approach for multiclass skin lesion classification based on ensemble learning","volume":"25","author":"Rahman","year":"2021","journal-title":"Inform. Med. Unlocked"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"8659","DOI":"10.1109\/ACCESS.2021.3049600","article-title":"Dermoscopy image classification based on StyleGAN and DenseNet201","volume":"9","author":"Zhao","year":"2021","journal-title":"IEEE Access"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Alam, T.M., Hossain, M.A., and Lee, H.S. (2022). An efficient deep learning-based skin cancer classifier for an imbalanced dataset. Diagnostics, 12.","DOI":"10.3390\/diagnostics12092115"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Wu, Y., Chen, B., Zeng, A., Pan, D., Wang, R., and Zhao, S. (2022). Skin cancer classification with deep learning: A systematic review. Front. Oncol., 12.","DOI":"10.3389\/fonc.2022.893972"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1081","DOI":"10.1001\/jamadermatol.2015.1187","article-title":"Incidence estimate of nonmelanoma skin cancer in the U.S. population, 2012","volume":"151","author":"Rogers","year":"2015","journal-title":"JAMA Dermatol."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1","DOI":"10.33371\/ijoc.v11i1.494","article-title":"Sebaran kanker di Indonesia, riset kesehatan dasar 2007","volume":"11","author":"Dewi","year":"2017","journal-title":"Indones. J. Cancer"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"3287","DOI":"10.1007\/s00432-022-04180-1","article-title":"MDFNet: Application of multimodal fusion method based on skin image and clinical data to skin cancer classification","volume":"149","author":"Chen","year":"2023","journal-title":"J. Cancer Res. Clin. Oncol."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"106712","DOI":"10.1016\/j.compbiomed.2023.106712","article-title":"TFormer: A throughout fusion transformer for multi-modal skin lesion diagnosis","volume":"157","author":"Zhang","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"ref_19","unstructured":"Rusch, T.K., Bronstein, M.M., and Mishra, S. (2023). A survey on oversmoothing in graph neural networks. arXiv."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Ramirez, R., Chai, Y., and Zhang, J. (2020). Classification of cancer types using graph convolutional neural networks. Front. Phys., 8.","DOI":"10.3389\/fphy.2020.00203"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"btad643","DOI":"10.1093\/bioinformatics\/btad643","article-title":"Explainable multilayer graph neural network for cancer gene prediction","volume":"39","author":"Chatzianastasis","year":"2023","journal-title":"Bioinformatics"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1016\/j.patrec.2023.01.003","article-title":"Image classification using graph neural network and multiscale wavelet superpixels","volume":"166","author":"Vasudevan","year":"2023","journal-title":"Pattern Recognit. Lett."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"109886","DOI":"10.1016\/j.bspc.2026.109886","article-title":"Graph-enhanced neighborhood association learning model for semi-supervised skin lesion diagnosis","volume":"119","author":"Yu","year":"2026","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"103076","DOI":"10.1016\/j.jnca.2021.103076","article-title":"Domain-specific knowledge graphs: A survey","volume":"185","year":"2021","journal-title":"J. Netw. Comput. Appl."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"D267","DOI":"10.1093\/nar\/gkh061","article-title":"The unified medical language system (UMLS): Integrating biomedical terminology","volume":"32","author":"Bodenreider","year":"2004","journal-title":"Nucleic Acids Res."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"4206","DOI":"10.1016\/j.acra.2025.02.045","article-title":"Knowledge graph-based few-shot learning for label of medical imaging reports","volume":"32","author":"Li","year":"2025","journal-title":"Acad. Radiol."},{"key":"ref_27","unstructured":"Zhang, C., Wu, R., Zhou, T., and Zhou, Y. (2026). MedKCO: Medical Vision-Language Pretraining via Knowledge-Driven Cognitive Orchestration. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"103545","DOI":"10.1016\/j.compbiomed.2019.103545","article-title":"The impact of patient clinical information on automated skin cancer detection","volume":"116","author":"Pacheco","year":"2020","journal-title":"Comput. Biol. Med."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"3706581","DOI":"10.1155\/2019\/3706581","article-title":"Influence of acquisition time on MR image quality estimated with nonparametric measures based on texture features","volume":"2019","author":"Obuchowicz","year":"2019","journal-title":"BioMed Res. Int."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1109\/TIP.2003.819861","article-title":"Image quality assessment: From error visibility to structural similarity","volume":"13","author":"Wang","year":"2004","journal-title":"IEEE Trans. Image Process."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Hore, A., and Ziou, D. (2010). Image quality metrics: PSNR vs. SSIM. Proceedings of the 2010 20th International Conference on Pattern Recognition (ICPR), IEEE.","DOI":"10.1109\/ICPR.2010.579"},{"key":"ref_32","unstructured":"Jocher, G., Chaurasia, A., and Qiu, J. (2026, April 22). Ultralytics YOLOv8. GitHub. Available online: https:\/\/github.com\/ultralytics\/ultralytics."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., He, K., and Doll\u00e1r, P. (2017). Focal loss for dense object detection. Proceedings of the IEEE International Conference on Computer Vision, IEEE.","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref_34","unstructured":"Yue, Y., and Li, Z. (2024). MedMamba: Vision Mamba for Medical Image Classification. arXiv."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"143029","DOI":"10.1109\/ACCESS.2024.3468612","article-title":"EFAM-Net: A multi-class skin lesion classification model utilizing enhanced feature fusion and attention mechanisms","volume":"12","author":"Ji","year":"2024","journal-title":"IEEE Access"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Shafin, S., Efat, A.H., Hasan, S.M., Jannat, N., Oishe, M., Mitu, M., and Zaman, M.U. (2023). Skin lesion classification through sequential triple attention DenseNet: Diverse utilization of the combination of attention modules. Proceedings of the 2023 26th International Conference on Computer and Information Technology (ICCIT), IEEE.","DOI":"10.1109\/ICCIT60459.2023.10441280"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"100999","DOI":"10.1016\/j.eij.2026.100999","article-title":"Enhancing melanoma identification and classification in dermoscopic images using optimal deep ensemble learning","volume":"34","author":"Maniraj","year":"2026","journal-title":"Egypt. Inform. J."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"109691","DOI":"10.1016\/j.bspc.2026.109691","article-title":"Skin cancer classification using a borderline-SMOTE enhanced neural network model on dermoscopic images","volume":"118","author":"Naeem","year":"2026","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"110287","DOI":"10.1016\/j.bspc.2026.110287","article-title":"Explainable CNN framework with Grad-CAM analysis for real-time skin disease detection","volume":"122","author":"Rahimi","year":"2026","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"109544","DOI":"10.1016\/j.bspc.2026.109544","article-title":"Enhancing skin cancer detection using attention-based CapsNet with transfer learning from pre-trained CNN","volume":"116","author":"Rahman","year":"2026","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_41","unstructured":"Ramanujam, E., Sekar, K., Sangeetha, K., Niranjan, S., Madhu Mitha, M., and Nithya Shree, A.K. (2026). Hybrid Multi-Scale CNN and Vision Transformer Model for Accurate Skin Lesion Classification. Proceedings of the 2026 2nd International Conference on Big Data & Machine Learning (ICBDML), IEEE."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/15\/4728\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T04:33:21Z","timestamp":1785299601000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/15\/4728"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,25]]},"references-count":41,"journal-issue":{"issue":"15","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["s26154728"],"URL":"https:\/\/doi.org\/10.3390\/s26154728","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,25]]}}}