A novel artificial intelligence-based predictive analytics technique to detect skin cancer.

Area of Science:

• Dermatology
• Medical Imaging
• Artificial Intelligence

Background:

• Skin cancer is a leading global cause of death, with early detection critical for melanoma curability.
• Over 75% of worldwide fatalities are linked to skin cancer, highlighting the need for improved diagnostic tools.

Purpose of the Study:

• To develop and evaluate a novel Artificial Golden Eagle-based Random Forest (AGEbRF) model for early skin cancer cell prediction.
• To accurately identify and segment cancerous areas in dermoscopic images.

Main Methods:

• Utilized dermoscopic images as the dataset for training the AGEbRF model.
• Employed the AGEbRF algorithm for processing image data to detect and segment skin cancer.
• Simulated the approach using a Python program and compared performance against existing studies.

Main Results:

• The proposed AGEbRF model demonstrated superior accuracy in predicting skin cancer through image segmentation compared to other models.
• The model effectively identified and segmented affected areas in dermoscopic images.

Conclusions:

• The novel AGEbRF model shows significant potential for improving early skin cancer detection and segmentation.
• This AI-driven approach offers a promising advancement in dermatological diagnostics for better patient outcomes.