EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Image-Driven Multimodal Deep Learning for Skin Cancer Diagnosis: Cross-Attention Fusion of Dermoscopic Imaging Clinical Data and Knowledge Graphs

Syeda Sitara Waseem, Saman Iftikhar iD, Ammar Rafiq, Kangyoon Lee iD, Syed Rizwan Hassan iD

Sensors · 2026

DOI: 10.3390/s26154728 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2026. Verfasst von Syeda Sitara Waseem und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, Government Sadiq College Women University, Bahawalpur 63100, Pakistan. Hauptthemen laut MEDLINE: Deep Learning, Skin Neoplasms, Dermoscopy, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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’ 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 < 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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningSkin NeoplasmsDermoscopyImage Processing, Computer-AssistedHumansFemaleAlgorithms

Stichwörter der Autor:innen

attention-based fusionbiomedical knowledge graphbiomedical sensorsdermoscopic imagingdermoscopymultimodal deep learningsensor fusionskin cancer diagnosis

Autor:innen und Institutionen

  • Department of Computer Science, Government Sadiq College Women University, Bahawalpur 63100, Pakistan.
  • Faculty of Computer Studies, Arab Open University, Riyadh 84901, Saudi Arabia.
  • Department of Computer Science, National University of Computer and Emerging Sciences, Islamabad, Chiniot-Faisalabad Campus, Chiniot 35400, Pakistan.
  • Department of Computer Engineering, Gachon University, Seongnam-si 13120, Republic of Korea.

ORCID-Profile: Saman Iftikhar, Kangyoon Lee, Syed Rizwan Hassan

Zitieren

APA

Waseem, S. S., Iftikhar, S., Rafiq, A., Lee, K., & Hassan, S. R. (2026). Image-Driven Multimodal Deep Learning for Skin Cancer Diagnosis: Cross-Attention Fusion of Dermoscopic Imaging Clinical Data and Knowledge Graphs. Sensors. https://doi.org/10.3390/s26154728

Vancouver

Waseem SS, Iftikhar S, Rafiq A, Lee K, Hassan SR. Image-Driven Multimodal Deep Learning for Skin Cancer Diagnosis: Cross-Attention Fusion of Dermoscopic Imaging Clinical Data and Knowledge Graphs. Sensors. 2026. doi:10.3390/s26154728

BibTeX
@article{Waseem2026,
  author = {Waseem, Syeda Sitara and Iftikhar, Saman and Rafiq, Ammar and Lee, Kangyoon and Hassan, Syed Rizwan},
  title = {Image-Driven Multimodal Deep Learning for Skin Cancer Diagnosis: Cross-Attention Fusion of Dermoscopic Imaging Clinical Data and Knowledge Graphs},
  journal = {Sensors},
  year = {2026},
  doi = {10.3390/s26154728}
}
Kostenlos starten →