China
Africa
Explore chapters and articles related to this topic
A Probabilistic Neural Network Framework for the Detection of Malignant Melanoma
Published in Raouf N.G. Naguib, Gajanan V. Sherbet, Artificial Neural Networks in Cancer Diagnosis, Prognosis, and Patient Management, 2001
M. Hintz-Madsen, L.K. Hansen, J. Larsen, K.T. Drzewiecki
Malignant melanoma is the deadliest form of skin cancer and arises from cancerous growth in pigmented skin lesions. The cancer can be removed by a fairly simple surgical incision if it has not entered the blood stream. It is thus vital that the cancer is detected at an early stage in order to increase the probability of a complete recovery. Skin lesions may in this context be grouped into three classes: Benign nevi is a common name for all healthy skin lesions. These have no increased risk of developing cancer.Atypical nevi are also healthy skin lesions but have an increased risk of developing into cancerous lesions. The special type of atypical nevi, called dysplastic nevi, has the highest risk and is, thus, often referred to as the precursor of malignant melanoma.Malignant melanoma are as already mentioned cancerous skin lesions.
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.
Multilayer vectorization to develop a deeper image feature learning model
Published in Automatika, 2023
D. Hemanand, N. P. G. Bhavani, Shahanaz Ayub, Mohd Wazih Ahmad, S. Narayanan, Anandakumar Haldorai
The HIS2828 dataset contains four different image types representing various tissue types, wherein each image possesses 720 * 480 RGB images. This dataset comprises 2828 images, 1026 nerve tissue images, 484 images of connective tissue, 804 images of epithelial tissue, and 514 images of muscle tissue. The International Skin Image Collaboration (ISIC2017) has produced a skin lesions dataset. It contains 2000 images, wherein 374 images of malignant skin cancers are termed “melanoma” while 1626 images of benign skin tumors are termed “nevus and seborrheic keratosis.” The binary input image vectorization and classification are quite challenging to differentiate between Melanoma and Nevus of Seborrheic Keratosis. This dataset is handled because each image has a different resolution.