Skin cancer detection from dermoscopic images using deep learning and fuzzy k‐means clustering

• Published in: Microscopy research and technique Vol. 85; no. 1; pp. 339 - 351
• Main Authors: Nawaz, Marriam, Mehmood, Zahid, Nazir, Tahira, Naqvi, Rizwan Ali, Rehman, Amjad, Iqbal, Munwar, Saba, Tanzila
• Format: Journal Article
• Language: English
• Published: Hoboken, USA John Wiley & Sons, Inc 01.01.2022; Wiley Subscription Services, Inc
• Subjects: Algorithms; Artificial neural networks; Automation; Cancer; Cluster Analysis; Clustering; Datasets; Deep Learning; Dermoscopy; faster‐RCNN; fuzzy c‐means clustering; Humans; Image enhancement; Image segmentation; Lesions; Localization; Medical imaging; Melanoma; Melanoma - diagnostic imaging; Neural networks; Skin cancer; Skin diseases; Skin lesions; Skin Neoplasms - diagnostic imaging; deep learning; skin cancer; fuzzy c-means clustering; melanoma; faster-RCNN
• ISSN: 1059-910X; 1097-0029; 1097-0029
• DOI: 10.1002/jemt.23908

Melanoma skin cancer is the most life‐threatening and fatal disease among the family of skin cancer diseases. Modern technological developments and research methodologies made it possible to detect and identify this kind of skin cancer more effectively; however, the automated localization and segmentation of skin lesion at earlier stages is still a challenging task due to the low contrast between melanoma moles and skin portion and a higher level of color similarity between melanoma‐affected and ‐nonaffected areas. In this paper, we present a fully automated method for segmenting the skin melanoma at its earliest stage by employing a deep‐learning‐based approach, namely faster region‐based convolutional neural networks (RCNN) along with fuzzy k‐means clustering (FKM). Several clinical images are utilized to test the presented method so that it may help the dermatologist in diagnosing this life‐threatening disease at its earliest stage. The presented method first preprocesses the dataset images to remove the noise and illumination problems and enhance the visual information before applying the faster‐RCNN to obtain the feature vector of fixed length. After that, FKM has been employed to segment the melanoma‐affected portion of skin with variable size and boundaries. The performance of the presented method is evaluated on the three standard datasets, namely ISBI‐2016, ISIC‐2017, and PH2, and the results show that the presented method outperforms the state‐of‐the‐art approaches. The presented method attains an average accuracy of 95.40, 93.1, and 95.6% on the ISIC‐2016, ISIC‐2017, and PH2 datasets, respectively, which is showing its robustness to skin lesion recognition and segmentation. Accurate and precise detection of skin lesion‐affected parts using precise localization power of faster‐RCNN. The robust segmentation of melanoma‐affected images using competence and the power of the FKM algorithm to deal with the overfitted training data. The presented method can be extended to other skin diseases as well. To the best of our knowledge, it is the first time in medical image analysis when faster‐RCNN has been employed for skin lesion detection. Reported results exhibit the efficacy of faster‐RCNN to detect the melanoma moles and computing a deep and discriminative set of features with improved performance results.