China 
Africa 
Explore chapters and articles related to this topic
CAD of Dermatological Ulcers (Computational Aspects of CAD for Image Analysis of Foot and Leg Dermatological Lesions)
Published in de Azevedo-Marques Paulo Mazzoncini, Mencattini Arianna, Salmeri Marcello, Rangayyan Rangaraj M., Medical Image Analysis and Informatics: Computer-Aided Diagnosis and Therapy, 2018
Marco Andrey Cipriani Frade, Guilherme Ferreira Caetano, Éderson Dorileo
Rahman et al. [34] explored features such as color and textures for matching by similarity: 358 images of pigmented skin lesions were classified as benign, dysplastic nevi and melanoma. Quantitative evaluation was only based on precision curve and shows an average precision of around 60%. A CBIR approach was proposed for skin lesion images, classified as actinic keratosis, basal cell carcinoma, melanocytic nevus, squamous cell carcinoma and seborrhoeic keratosis [35]. The system relies on color and texture features and the classification is using genetic algorithms. Precision values were observed between 67% and 82%.
ADTBO: Aquila driving training-based optimization with deep learning for skin cancer detection
Published in The Imaging Science Journal, 2023
Vadamodula Prasad, Emil Selvan G. S. R., Ramkumar M. P.
The repeated identification of lesions from dermoscopy image overcomes numerous complications owing to the complex lesion features and its shape. Melanoma, Benign Keratosis, Actinic Keratosis, Basal Cell Carcinoma, Melanocytic Nevus, Dermatofibroma and Vascular are the eight different types of skin cancer in which Melanoma is the harmful type of skin cancer causing severe damage to the skin and spreading to other areas of the body. Timely detection of skin cancer has been shown in studies to significantly reduce the death rate. Detecting skin cancer at an early stage is a tedious task for dermatologists, which motivates researchers to design a simplified and automatic skin cancer detector to detect skin cancer at an early stage, which can greatly assist dermatologists [4]. Melanoma is most commonly found on the behind of a person's lower limb and also it can occur anywhere on the human body. Moreover, individuals’ risk aspects for skin cancer illness have to be condensed by sensing it at an early stage. The detection of skin cancer in its primary stages can effect in a significant diminution in death. As a result, identifying and classifying this disease in its early stages is critical [3].
An automated hybrid attention based deep convolutional capsule with weighted autoencoder approach for skin cancer classification
Published in The Imaging Science Journal, 2023
Figure 3 illustrates the confusion matrix of the proposed method. The proposed method classifies eight different classes of skin tumour classification. A total of 15 images are used to classify the actinic keratosis, and all 15 images are correctly classified. For the BCC, a total of 18 images are used. 16 are correctly classified, and the remaining 2 are wrongly classified as benign keratosis and melanocytic nevus. 32 images are used for benign keratosis, and 27 are correctly classified. The remaining five are wrongly classified as vascular lesions, melanoma and actinic keratosis. 21 images are used for the dermatofibroma, and all the images are correctly classified as dermatofibroma. For the melanocytic nevus, a total of 17 images are used, and 16 images are correctly classified. The remaining 1 is wrongly classified as dermatofibroma. For melanoma, 21 images are used, and 20 are correctly classified. The remaining 1 is wrongly classified as BCC. A total of 17 images are used for the SCC, and 12 are correctly classified. The remaining 5 are wrongly classified as BCC, melanocytic nevus and dermatofibroma. A total of 19 images are used for the vascular lesion, and all 19 images are correctly classified as vascular lesions.