In the last decades, skin cancer has been considered one of the most common and spread cancers around the world. It is essential to detect skin cancer early to reduce mortality. The skin protects the body from infection, viruses such as coronavirus, heat and dangerous UV radiation. It also can store water and fat, maintain body temperature, and form vitamin D. The World Health Organization estimates approximately 132,000 skin melanoma cases per year. The Middle East has the highest skin cancer rates, Egypt has a 1.52 rate, and its world rank is 117.

A paper published titled “Early automated detection system for skin cancer diagnosis using artificial intelligent techniques” implements an automated skin cancer detection system using dermoscopic images to identify benign and malignant skin lesions using AI.

After analysing the research, the scientists behind the study concluded that the proposed methodology outperformed traditional methods. Consistent classification performance in all the metrics across various classifiers indicates the suitability of the proposed features and methodologies.

Therefore, the proposed system is easy to use, enables patients to monitor remotely, detects skin cancer early, and is highly efficient. It also improves the diagnosis rate of skin cancer. An automated early detection system for skin cancer dermoscopic images using artificial intelligence improves diagnosis performance.

Limitations in skin cancer detection

There are many methods to detect skin cancer. Traditional methods for skin cancer detection, such as BIOPSY and the naked eye (visual inspection by dermatologists or general practitioners), have several challenges and limitations. It can result in both overdiagnosis (identifying benign lesions as malignant) and underdiagnosis (missing malignant lesions). Therefore, the visual inspection method is a non-dependable way. 

One limitation of traditional methods is their inaccuracy in differentiating lesions. Another limitation is the accessibility of dermatologists or specialised healthcare providers to skin cancer diagnoses in many regions, especially in rural or underserved areas. This limitation can lead to delays in diagnosis and treatment. 

To overcome these limitations, ongoing research and development of technologies such as dermoscopy, teledermatology, and computer-aided diagnosis systems aim to improve the accuracy, efficiency, and accessibility of skin cancer detection.

Digital skin cancer microscopic images can be improved by Machine Learning (ML) and Deep Learning (DL) techniques. Artificial intelligence and adaptation of technology to human service are used to detect different diseases. Computer-based detection systems can improve the diagnosis rate of skin cancer in comparison with traditional methods.

Better detection with AI

The proposed system accelerates dermatologists’ time and improves diagnosis performance. It is developed to detect benign and malignant skin lesions using multiple steps, including pre-processing, different methods for segmentation, feature extraction/feature selection, and other methods of classification used for analysing automated dermoscopic images. 

This study utilised two ML models (ANN and SVM); they offer advantages for skin cancer detection using the PH2 dataset. ANN is excellent at learning complex representations from raw data, and SVM provides robustness and efficiency. The proposed system is efficient, accurate, and easy to use by different users (doctors and patients). Early detection and diagnosis of skin cancer can lead to more successful treatment outcomes and potentially save lives. In addition, it can reduce the overall cost of treatment.

Nature

Image: Unsplash