Melanoma detection by analysis of clinical images using convolutional neural network

By Ebrahim Nasr-Esfahani, Shadrokh Samavi, Nader Karimi, S. M. Reza Soroushmehr, M. Jafari, Kevin Ward, Kayvan Najarian. 2016

310 citations recorded by the source corpus.

Melanoma, most threatening type of skin cancer, is on the rise. In this paper an implementation of a deep-learning system on a computer server, equipped with graphic processing unit (GPU), is proposed for detection of melanoma lesions. Clinical (non-dermoscopic) images are used in the proposed system, which could assist a dermatologist in early diagnosis of this type of skin cancer. In the proposed system, input clinical images, which could contain illumination and noise effects, are preprocessed in order to reduce such artifacts. Afterward, the enhanced images are fed to a pre-trained convolutional neural network (CNN) which is a member of deep learning models. The CNN classifier, which is trained by large number of training samples, distinguishes between melanoma and benign cases. Experimental results show that the proposed method is superior in terms of diagnostic accuracy in comparison with the state-of-the-art methods.

Subfields: Artificial Intelligence, Biophysics, Oncology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Biophysics

In Oncology

Ryuji Hamamoto

Citations in the corpus

Opportunities and obstacles for deep learning in biology and medicine (2017, background): “Such features were also repurposed to detect melanoma, the deadliest form of skin cancer, from dermoscopic [47,48] and non-dermoscopic images of skin lesions [4,49,50] as well as age-related macular degeneration [51].”
Extraction of skin lesions from non-dermoscopic images for surgical excision of melanoma (2016, methodology): “Moreover a CNN in [26] is applied for classification of suspicious skin lesions.”
The Development of a Skin Cancer Classification System for Pigmented Skin Lesions Using Deep Learning (2020, background): “In recent years, many skin cancer classiﬁcation systems using deep learning have been developed for classifying images of skin tumors, including malignant melanoma (MM) and other skin cancer [2].”
Skin Cancer Detection: A Review Using Deep Learning Techniques (2021, methodology): “[31] Melanoma/benign CNN classifier 170 skin lesion images Two convolving layers in CNN Accuracy (81), sensitivity (81), specificity (80)”
Cancer Diagnosis Using Deep Learning: A Bibliographic Review (2019, methodology): “In total, 27 different algorithms provided by 27 different researchers [42,65,67,68,70,74,86,141– 145, 147– 153”
Skin Cancer Classification Using Convolutional Neural Networks: Systematic Review (2018, methodology): “In Nasr-Esfahani et al [32], a two-layer CNN was trained from scratch for the distinction of melanoma versus benign nevi based on clinical images.”
Convolutional neural networks in medical image understanding: a survey (2021, background): “…image understanding applications like detection of tumors and their classification into benign and malignant [52], detection of skin lesions [50], detection of optical coherence tomography images [39], detection of colon cancer [71], blood cancer, anomalies of the heart [40], breast [36],…”