EUVIMEDEUVIMED entdecken
Systematische ÜbersichtOpen Access · CC BY 4.0

Lightweight Explainable and Reliable Deep Learning for Multiclass Skin Lesion ClassificationA Systematic Review of Metadata Fusion Class Imbalance Calibration and Leakage Safe Evaluation

Baibhav Tiwari, Prakash kumar Maravi, Kamlesh Raghuwanshi, Surabhi Karsoliya

IJAICET - International Journal of Artificial Intelligence, Cybersecurity and Emerging Technologies · 2026

DOI: 10.68307/z27de086 ↗

Kurz gefasst

Systematische Übersicht in der Zeitschrift IJAICET - International Journal of Artificial Intelligence, Cybersecurity and Emerging Technologies, 2026. Verfasst von Baibhav Tiwari und 3 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep learning has improved automated skin lesion classification while practical clinical research still requires efficient models reliable confidence estimates interpretable predictions and evaluation designs that prevent information leakage; therefore this review examines lightweight architectures patient metadata fusion class imbalance strategies explainable artificial intelligence probability calibration and lesion grouped validation within multiclass dermoscopic classification; the review protocol covers major scientific databases with structured screening and evidence extraction while the current evidence map contains 68 deduplicated seed records with 30 priority studies and 29 completed abstract level extractions; preliminary synthesis shows rapid progress in convolutional and transformer models although direct comparison remains limited by inconsistent datasets split units class definitions metrics and reporting practices; moreover calibration and quantitative explanation assessment appear less common than accuracy reporting while lesion or patient grouped splitting is not always stated clearly; consequently future studies should combine class sensitive metrics transparent split governance calibration analysis explanation validation and measured computational efficiency within one reproducible protocol.

Zitieren

APA

Tiwari, B., Maravi, P. K., Raghuwanshi, K., & Karsoliya, S. (2026). Lightweight Explainable and Reliable Deep Learning for Multiclass Skin Lesion ClassificationA Systematic Review of Metadata Fusion Class Imbalance Calibration and Leakage Safe Evaluation. IJAICET - International Journal of Artificial Intelligence, Cybersecurity and Emerging Technologies. https://doi.org/10.68307/z27de086

Vancouver

Tiwari B, Maravi PK, Raghuwanshi K, Karsoliya S. Lightweight Explainable and Reliable Deep Learning for Multiclass Skin Lesion ClassificationA Systematic Review of Metadata Fusion Class Imbalance Calibration and Leakage Safe Evaluation. IJAICET - International Journal of Artificial Intelligence, Cybersecurity and Emerging Technologies. 2026. doi:10.68307/z27de086

BibTeX
@article{Tiwari2026,
  author = {Tiwari, Baibhav and Maravi, Prakash kumar and Raghuwanshi, Kamlesh and Karsoliya, Surabhi},
  title = {Lightweight Explainable and Reliable Deep Learning for Multiclass Skin Lesion ClassificationA Systematic Review of Metadata Fusion Class Imbalance Calibration and Leakage Safe Evaluation},
  journal = {IJAICET - International Journal of Artificial Intelligence, Cybersecurity and Emerging Technologies},
  year = {2026},
  doi = {10.68307/z27de086}
}
Kostenlos starten →