{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T23:58:43Z","timestamp":1792022323502,"version":"4.4.0"},"reference-count":46,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T00:00:00Z","timestamp":1771632000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Background: Accurate and timely diagnosis of skin lesions, including Melanoma (MEL), Basal Cell Carcinoma (BCC), Squamous Cell Carcinoma (SCC), Actinic Keratosis (ACK), Seborrheic Keratosis (SEK), and Nevus (NEV), is often hindered by the severe class imbalance and high morphological similarity among pathologies in clinical practice. Although multimodal learning has shown potential in resolving these issues, existing approaches often fail to address predictive uncertainty or effectively integrate heterogeneous clinical metadata. Therefore, this study proposes DermaCalibra, a robust and explainable multimodal framework optimized for small-scale, imbalanced clinical datasets. Methods: The proposed framework integrates three essential modules: First, the Attention-Based Multimodal Channel Recalibration (AMCR) module introduces a probabilistic Bayesian uncertainty estimation mechanism via Monte Carlo dropout to adjust focal loss weights, prioritizing features from underrepresented classes. Second, the Metadata-Driven Dynamic Feature Modulation and Cross-Attention Fusion (MDFM-CAF) module, designed to resolve inter-class visual ambiguity, dynamically rescales dermoscopic feature maps using non-linear clinical context transformations. Lastly, the Gradient Feature Attribution (GFA) module is implemented to provide pixel-level diagnostic heatmaps and metadata importance scores. Results: Evaluated on the PAD-UFES-20 dataset, DermaCalibra achieves a balanced accuracy (BACC) of 84.2%, outperforming current state-of-the-art (SOTA) methods by 3.6%, and a Macro Area Under the Receiver Operating Characteristic Curve (Macro AUC) of 96.9%. Extensive external validation on unseen hospital and synthetic datasets confirms robust generalizability across diverse clinical settings without the need for retraining. Conclusions: DermaCalibra effectively bridges the gap between deep learning complexity and clinical intuition through uncertainty-aware reasoning and transparent interpretability. The framework provides a reliable and scalable computer-aided diagnostic tool for early skin lesion detection, particularly in resource-limited clinical environments.<\/jats:p>","DOI":"10.3390\/diagnostics16040630","type":"journal-article","created":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T11:39:10Z","timestamp":1771846750000},"page":"630","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["DermaCalibra: A Robust and Explainable Multimodal Framework for Skin Lesion Diagnosis via Bayesian Uncertainty and Dynamic Modulation"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-3492-520X","authenticated-orcid":false,"given":"Ben","family":"Wang","sequence":"first","affiliation":[{"name":"Shanghai Advanced Research Institute, Chinese Academy of Sciences, Shanghai 201210, China"},{"name":"University of Chinese Academy of Sciences, Beijing 100049, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingjun","family":"Niu","sequence":"additional","affiliation":[{"name":"Shanghai Advanced Research Institute, Chinese Academy of Sciences, Shanghai 201210, China"},{"name":"University of Chinese Academy of Sciences, Beijing 100049, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2640-6434","authenticated-orcid":false,"given":"Chengying","family":"She","sequence":"additional","affiliation":[{"name":"Shanghai Advanced Research Institute, Chinese Academy of Sciences, Shanghai 201210, China"},{"name":"University of Chinese Academy of Sciences, Beijing 100049, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jialu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Advanced Research Institute, Chinese Academy of Sciences, Shanghai 201210, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Gao","sequence":"additional","affiliation":[{"name":"Department of Dermatology, The Second People\u2019s Hospital of Changzhou, Changzhou 213003, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8032-4598","authenticated-orcid":false,"given":"Lizhuang","family":"Liu","sequence":"additional","affiliation":[{"name":"Shanghai Advanced Research Institute, Chinese Academy of Sciences, Shanghai 201210, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,2,21]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"106221","DOI":"10.1016\/j.dib.2020.106221","article-title":"PAD-UFES-20: A skin lesion dataset composed of patient data and clinical images collected from smartphones","volume":"32","author":"Pacheco","year":"2020","journal-title":"Data Brief"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"18119","DOI":"10.1038\/s41598-025-03546-y","article-title":"Mobile applications for skin cancer detection are vulnerable to physical camera-based adversarial attacks","volume":"15","author":"Oda","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1016\/j.ejca.2019.06.003","article-title":"Diagnosis and treatment of basal cell carcinoma: European consensus-based interdisciplinary guidelines","volume":"118","author":"Peris","year":"2019","journal-title":"Eur. J. Cancer"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"808","DOI":"10.1038\/s44222-025-00350-1","article-title":"Biophotonics technologies for skin disease diagnosis and monitoring","volume":"3","author":"Bi","year":"2025","journal-title":"Nat. Rev. Bioeng."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1302","DOI":"10.1038\/s41597-024-04104-3","article-title":"DERM12345: A large, multisource dermatoscopic skin lesion dataset with 40 subclasses","volume":"11","author":"Yilmaz","year":"2024","journal-title":"Sci. Data"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"456","DOI":"10.1038\/s41569-021-00663-9","article-title":"Update on the pathophysiology and medical treatment of peripheral artery disease","volume":"19","author":"Golledge","year":"2022","journal-title":"Nat. Rev. Cardiol."},{"key":"ref_7","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_8","doi-asserted-by":"crossref","first-page":"28850","DOI":"10.1038\/s41598-024-80087-w","article-title":"Enhanced MobileNet for skin cancer image classification with fused spatial channel attention mechanism","volume":"14","author":"Cheng","year":"2024","journal-title":"Sci. Rep."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"3554","DOI":"10.1109\/JBHI.2021.3062002","article-title":"An attention-based mechanism to combine images and metadata in deep learning models applied to skin cancer classification","volume":"25","author":"Pacheco","year":"2021","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Li, W., Zhuang, J., Wang, R., Zhang, J., and Zheng, W.-S. (2020, January 3\u20137). Fusing metadata and dermoscopy images for skin disease diagnosis. Proceedings of the 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI), Iowa City, IA, USA.","DOI":"10.1109\/ISBI45749.2020.9098645"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Khurshid, M., Vatsa, M., and Singh, R. (2024, January 27\u201330). Optimizing skin lesion classification via multimodal data and auxiliary task integration. Proceedings of the 2024 IEEE International Symposium on Biomedical Imaging (ISBI), Athens, Greece.","DOI":"10.1109\/ISBI56570.2024.10635277"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"He, Y., Liu, J., Li, Y., Zhou, H., Cai, L., and Cui, T. (2024, January 5\u20138). Multimodal Bayesian networks for automatic skin disease diagnosis. Proceedings of the 2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Lisbon, Portugal.","DOI":"10.1109\/BIBM62325.2024.10822856"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"5649","DOI":"10.1038\/s41467-024-50043-3","article-title":"Pre-trained multimodal large language model enhances dermatological diagnosis using SkinGPT-4","volume":"15","author":"Zhou","year":"2024","journal-title":"Nat. Commun."},{"key":"ref_14","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_15","first-page":"1","article-title":"Exploring the influence of transformer-based multimodal modeling on clinicians\u2019 diagnosis of skin diseases: A quantitative analysis","volume":"10","author":"Zhang","year":"2024","journal-title":"Digit. Health"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Lin, T.-L., Chen, H.-T., Lin, Y.-S., Huang, S.-Y., Wang, C.-H., Chuang, Y.-C., and Lin, C.-H. (2025). Hyperspectral imaging for enhanced skin cancer classification using machine learning. Bioengineering, 12.","DOI":"10.3390\/bioengineering12070755"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Huang, H.Y., Hsiao, Y.P., Karmakar, R., Mukundan, A., Chaudhary, P., Hsieh, S.C., and Wang, H.C. (2023). A Review of Recent Advances in Computer-Aided Detection Methods Using Hyperspectral Imaging Engineering to Detect Skin Cancer. Cancers, 15.","DOI":"10.3390\/cancers15235634"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"9335","DOI":"10.1007\/s11063-023-11204-5","article-title":"A novel vision transformer model for skin cancer classification","volume":"55","author":"Yang","year":"2023","journal-title":"Neural Process. Lett."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"107627","DOI":"10.1016\/j.bspc.2025.107627","article-title":"A novel CNN-ViT-based deep learning model for early skin cancer diagnosis","volume":"104","author":"Pacal","year":"2025","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"6713","DOI":"10.1007\/s00521-022-08053-z","article-title":"Multiclass skin lesion classification in dermoscopic images using swin transformer model","volume":"35","author":"Ayas","year":"2023","journal-title":"Neural Comput. Appl."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"78402","DOI":"10.1109\/ACCESS.2023.3299850","article-title":"TS-CNN: A three-tier self-interpretable CNN for multi-region medical image classification","volume":"11","author":"Ashwath","year":"2023","journal-title":"IEEE Access"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_23","unstructured":"Baxter, J.S.H., Rekik, I., Eagleson, R., Zhou, L., Syeda-Mahmood, T., Wang, H., and Hajij, M. (2022). Visually aware metadata-guided supervision for improved skin lesion classification using deep learning. Ethical and Philosophical Issues in Medical Imaging, Multimodal Learning and Fusion Across Scales for Clinical Decision Support, and Topological Data Analysis for Biomedical Imaging, Springer Nature."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A. (2015, January 7\u201312). Going deeper with convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., van der Maaten, L., and Weinberger, K.Q. (2017, January 21\u201326). Densely connected convolutional networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref_26","unstructured":"Tan, M., and Le, Q.V. (2019, January 9\u201315). EfficientNet: Rethinking model scaling for convolutional neural networks. Proceedings of the 36th International Conference on Machine Learning (ICML), Long Beach, CA, USA."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"100278","DOI":"10.1016\/j.dajour.2023.100278","article-title":"A deep neural network using modified EfficientNet for skin cancer detection in dermoscopic images","volume":"8","author":"Venugopal","year":"2023","journal-title":"Decis. Anal. J."},{"key":"ref_28","unstructured":"Gal, Y., and Ghahramani, Z. (2016, January 20\u201322). Dropout as a Bayesian approximation: Representing model uncertainty in deep learning. Proceedings of the 33rd International Conference on Machine Learning (ICML), New York, NY, USA."},{"key":"ref_29","unstructured":"Kendall, A., and Gal, Y. (2017, January 4\u20139). What uncertainties do we need in Bayesian deep learning for computer vision?. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Ahmad, N., Shah, J.H., Khan, M.A., Baili, J., Ansari, G.J., Tariq, U., Kim, Y.J., and Cha, J.H. (2023). A novel framework of multiclass skin lesion recognition from dermoscopic images using deep learning and explainable AI. Front. Oncol., 13.","DOI":"10.3389\/fonc.2023.1151257"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Jabeen, K., Khan, M.A., Balili, J., Alhaisoni, M., Almujally, N.A., Alrashidi, H., Tariq, U., and Cha, J.-H. (2023). BC2NetRF: Breast cancer classification from mammogram images using enhanced deep learning features and equilibrium-Jaya controlled Regula Falsi-based features selection. Diagnostics, 13.","DOI":"10.3390\/diagnostics13071238"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"104186","DOI":"10.1016\/j.bspc.2022.104186","article-title":"A comprehensive analysis of dermoscopy images for melanoma detection via deep CNN features","volume":"79","author":"Gajera","year":"2023","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_33","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., and Polosukhin, I. (2017, January 4\u20139). Attention is all you need. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"106321","DOI":"10.1016\/j.compbiomed.2022.106321","article-title":"Learning from dermoscopic images in association with clinical metadata for skin lesion segmentation and classification","volume":"152","author":"Dong","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"ref_35","unstructured":"Shrikumar, A., Greenside, P., and Kundaje, A. (2017, January 6\u201311). Learning important features through propagating activation differences. Proceedings of the 34th International Conference on Machine Learning (ICML), Sydney, Australia."},{"key":"ref_36","unstructured":"Sundararajan, M., Taly, A., and Yan, Q. (2017, January 6\u201311). Axiomatic attribution for deep networks. Proceedings of the 34th International Conference on Machine Learning (ICML), Sydney, Australia."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"2771","DOI":"10.1001\/jama.292.22.2771","article-title":"Early diagnosis of cutaneous melanoma: Revisiting the ABCD criteria","volume":"292","author":"Abbasi","year":"2004","journal-title":"JAMA"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., and Batra, D. (2017, January 22\u201329). Grad-CAM: Visual explanations from deep networks via gradient-based localization. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref_39","unstructured":"Lundberg, S.M., and Lee, S.-I. (2017, January 4\u20139). A unified approach to interpreting model predictions. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_40","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_41","doi-asserted-by":"crossref","first-page":"1342","DOI":"10.1038\/s41591-018-0107-6","article-title":"Clinically applicable deep learning for diagnosis and referral in retinal disease","volume":"24","author":"Ledsam","year":"2018","journal-title":"Nat. Med."},{"key":"ref_42","first-page":"87","article-title":"Enhanced skin disease diagnosis through convolutional neural networks and data augmentation techniques","volume":"7","author":"Abbas","year":"2024","journal-title":"J. Comput. Biomed. Inform."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1038\/s41591-018-0316-z","article-title":"A guide to deep learning in healthcare","volume":"25","author":"Esteva","year":"2019","journal-title":"Nat. Med."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., He, K., and Doll\u00e1r, P. (2017, January 22\u201329). Focal loss for dense object detection. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Chollet, F. (2017, January 21\u201326). Xception: Deep learning with depthwise separable convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"30065","DOI":"10.1007\/s11042-022-14267-z","article-title":"Skin lesion analysis using generative adversarial networks: A review","volume":"82","author":"Gilani","year":"2023","journal-title":"Multimed. Tools Appl."}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/4\/630\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T15:43:26Z","timestamp":1772552606000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/4\/630"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,21]]},"references-count":46,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2026,2]]}},"alternative-id":["diagnostics16040630"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics16040630","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,21]]}}}