Comparing the performance of linear regression versus deep learning on detecting melanoma skin cancer using apple core ML

Abstract

Melanoma is a type of deadly skin cancer. The survival rate of the patients can fall as low as 15.7% if the cancer cell has reached its final stage. Delayed treatment of melanoma can be attributed to its likeness to that of common nevus (moles). Two machine learning models were developed, each with a different approach and algorithm, to detect the presence of melanoma. Image classification is using the regression algorithm, and object detection is using deep learning. The two models are then compared, and the best model is determined according to the achieved metrics. The testing was conducted using 120 testing data and is made up of 60 positive data and 60 negative data. The testing result shows that object detection achieved 70% accuracy than image classification’s 68%. More importantly, linear regression’s 43% false-negative rate is noticeably high compared to convolutional neural network’s (CNN) 25%. A false-negative rate of 43% means almost half of sick patients tested using image classification will be diagnosed as healthy. This is dangerous as it can lead to delayed treatment and, ultimately, death. Thus it can be concluded that CNN is the best method in detecting the presence of melanoma.

Skin cancer classification using EfficientNet architecture

“…Skin cancer is the corrupted cells that grew at abnormal pace in skin tissue and is often caused by overexposure to ultraviolet (UV) rays [1]- [6]. Skin cancer is without a doubt, one of the most prevalent cancers worldwide [1], [3], [7]- [9].…”

“…If treated early, all skin cancers have a potential to be cured. Therefore, early diagnosis or detection is essential for effective and efficient treatment [5], [6], [9]- [11]. Unfortunately, diagnosing skin cancer in the early stages by using regular methods can be really challenging and prone to error [10], [11].…”

“…Computer vision is a subset of artificial intelligence (AI) that is becoming more popular and impactful especially in dermatology [5], [6], [12]. Convolutional neural network (CNN) is a computer vision method that utilizes deep learning concept to be able to imitate visual cortex.…”

“…The designed CNN model achieved 92.64% accuracy. Meanwhile, Sujaini et al [6] compared linear regression model and deep learning model in melanoma detection. The results proved that the deep learning CNN model is better than the linear regression model with higher accuracy and lower false negative rate in detecting melanoma.…”

An accurate Alzheimer's disease detection using a developed convolutional neural network model

“…Since a few years ago, deep learning models have gained substantial attention in Alzheimer's disease detection research. These models have been stated to be more accurate in this area than general techniques of machine learning [10], [11]. However, the detection of Alzheimer's disease is a burdensome task.…”