EUVIMEDEUVIMED entdecken
Crossref

An Integrated Uncertainty-Based Deep Learning Framework for Melanoma Diagnosis and Lesion Segmentation

Shubhendu Banerjee, Shilpi Pal, Avishek Chakraborty, Aritra Bandyopadhyay, Pushpita Roy

Journal of Uncertain Systems · 08.07.2026

DOI: 10.1142/s1752890926500133 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Uncertain Systems, online erschienen am 08.07.2026. Verfasst von Shubhendu Banerjee und 4 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

A dangerous kind of skin cancer that may develop anywhere on the body is melanoma. Early identification of melanoma lesions greatly improves the likelihood of successful therapy. In picture segmentation, learning-based segmentation techniques have recently surpassed conventional algorithms. A deep learning-based classification and Triangular Intuitionistic fuzzy-based segmentation framework is introduced in this paper to enhance the identification and categorization of malignant skin lesions. The Skin Lesion Analysis toward Melanoma Detection Challenge dataset is used to test the framework. In order to segment and detect lesions in real time, the approach consists of two primary processes. Preprocessing involves K-Medoid Clustering-based noise detection followed by Fuzzy logic-oriented noise removal to enhance image quality and remove unwanted artifacts. After preprocessing, skin lesions are precisely localized using You-Only-Look-Once edition 8 (YOLOv8). There are two steps in the segmentation process to determine the affected areas. Phase I computes the smallest spanning tree for identifying impacted zones based on threshold values using a graph-based framework. In the phase II, two segmentation approaches — Triangular Intuitionistic Fuzzy Numbers (TIFNs) and Triangular Dense Neutrosophic Numbers (TDNNs) — are comparatively evaluated. The comparative analysis demonstrates that TDNNs offer superior performance, yielding more accurate and reliable segmentation results. The [Formula: see text] photos used in the experiments are from three public datasets: PH2, ISBI [Formula: see text], and ISIC [Formula: see text]. With a Jac score of [Formula: see text] on the ISIC [Formula: see text] dataset and [Formula: see text] accuracy on the ISBI [Formula: see text] and [Formula: see text] PH2 datasets, the findings were encouraging. The suggested strategy performed marginally better than current frameworks with predetermined settings in the majority of circumstances.

Zitieren

APA

Banerjee, S., Pal, S., Chakraborty, A., Bandyopadhyay, A., & Roy, P. (2026). An Integrated Uncertainty-Based Deep Learning Framework for Melanoma Diagnosis and Lesion Segmentation. Journal of Uncertain Systems. https://doi.org/10.1142/s1752890926500133

Vancouver

Banerjee S, Pal S, Chakraborty A, Bandyopadhyay A, Roy P. An Integrated Uncertainty-Based Deep Learning Framework for Melanoma Diagnosis and Lesion Segmentation. Journal of Uncertain Systems. 2026. doi:10.1142/s1752890926500133

BibTeX
@article{Banerjee2026,
  author = {Banerjee, Shubhendu and Pal, Shilpi and Chakraborty, Avishek and Bandyopadhyay, Aritra and Roy, Pushpita},
  title = {An Integrated Uncertainty-Based Deep Learning Framework for Melanoma Diagnosis and Lesion Segmentation},
  journal = {Journal of Uncertain Systems},
  year = {2026},
  doi = {10.1142/s1752890926500133}
}
Kostenlos starten →