Comparison of Deep Learning and Machine Learning Models and Frameworks for Skin Lesion Classification
share
The incidence rate for skin cancer has been steadily increasing throughout the world, leading to it being a serious issue. Diagnosis at an early stage has the potential to drastically reduce the harm caused by the disease, however, the traditional biopsy is a labor-intensive and invasive procedure. In addition, numerous rural communities do not have easy access to hospitals and do not prefer visiting one for what they feel might be a minor issue. Using machine learning and deep learning for skin cancer classification can increase accessibility and reduce the discomforting procedures involved in the traditional lesion detection process. These models can be wrapped in web or mobile apps and serve a greater population. In this paper, two such models are tested on the benchmark HAM10000 dataset of common skin lesions. They are Random Forest with Stratified K-Fold Validation, and MobileNetV2 (throughout the rest of the paper referred to as MobileNet). The MobileNet model was trained separately using both TensorFlow and PyTorch frameworks. A side-by-side comparison of both deep learning and machine learning models and a comparison of the same deep learning model on different frameworks for skin lesion diagnosis in a resource-constrained mobile environment has not been conducted before. The results indicate that each of these models fares better at different classification tasks. For greater overall recall, accuracy, and detection of malignant melanoma, the TensorFlow MobileNet was the better choice. However, for detecting noncancerous skin lesions, the PyTorch MobileNet proved to be better. Random Forest was the better algorithm when it came to having a low computational cost with moderate correctness.
READ FULL TEXT