High-Precision Skin Disease Diagnosis through Deep Learning on Dermoscopic Images

Abstract

Dermatological conditions are primarily prevalent in humans and are primarily caused by environmental and climatic fluctuations, as well as various other reasons. Timely identification is the most effective remedy to avert minor ailments from escalating into severe conditions. Diagnosing skin illnesses is consistently challenging for health practitioners. Presently, they rely on conventional methods, such as examining the condition of the skin. State-of-the-art technologies can enhance the accuracy of skin disease diagnosis by utilizing data-driven approaches. This paper presents a Computer Assisted Diagnosis (CAD) framework that has been developed to detect skin illnesses at an early stage. We suggest a computationally efficient and lightweight deep learning model that utilizes a CNN architecture. We then do thorough experiments to compare the performance of shallow and deep learning models. The CNN model under consideration consists of seven convolutional layers and has obtained an accuracy of 87.64% when applied to three distinct disease categories. The studies were conducted using the International Skin Imaging Collaboration (ISIC) dataset, which exclusively consists of dermoscopic images. This study enhances the field of skin disease diagnostics by utilizing state-of-the-art technology, attaining exceptional levels of accuracy, and striving for efficiency improvements. The unique features and future considerations of this technology create opportunities for additional advancements in the automated diagnosis of skin diseases and tailored treatment.

Keywords: convolutional neural network (CNN); deep learning; machine learning; random forest (RF); skin disease; support vector machine (SVM).

Figure 1

Sample skin lesion images before rescaling operation.

Figure 2

Sample skin lesion images after the rescaling operation.

Figure 3

Basic CNN model.

Figure 4

Proposed CNN Model.

Figure 5

Basic CNN model imbalanced class: (a) without augmentation model accuracy; (b) without augmentation model loss; (c) with augmentation model accuracy; (d) with augmentation model loss.

Figure 5

Basic CNN model imbalanced class: (a) without augmentation model accuracy; (b) without augmentation model loss; (c) with augmentation model accuracy; (d) with augmentation model loss.

Figure 6

Basic CNN model balanced class: (a) without augmentation model accuracy; (b) without augmentation model loss; (c) with augmentation model accuracy; (d) with augmentation model loss.

Figure 7

Proposed CNN model imbalanced class (50 epochs): (a) without augmentation model accuracy; (b) without augmentation model loss; (c) with augmentation model accuracy; (d) with augmentation model loss.

Figure 8

Proposed CNN model balanced class (50 epochs): (a) without augmentation model accuracy; (b) without augmentation model loss; (c) with augmentation model accuracy; (d) with augmentation model loss.

Figure 8

Proposed CNN model balanced class (50 epochs): (a) without augmentation model accuracy; (b) without augmentation model loss; (c) with augmentation model accuracy; (d) with augmentation model loss.

Figure 9

Proposed CNN model imbalanced class (100 epochs): (a) without augmentation model accuracy; (b) without augmentation model loss; (c) with augmentation model accuracy; (d) with augmentation model loss.

Figure 10

Proposed CNN model balanced class (100 epochs): (a) without augmentation model accuracy; (b) without augmentation model loss; (c) with augmentation model accuracy; (d) with augmentation model loss.

Figure 11

Basic CNN model: (a) imbalanced class without augmentation; (b) imbalanced class with augmentation; (c) balanced class without augmentation; (d) balanced class with augmentation.

Figure 12

Proposed CNN model confusion matrix (50 epochs): (a) imbalanced class without augmentation; (b) imbalanced class with augmentation; (c) balanced class without augmentation; (d) balanced class with augmentation.

Figure 12

Proposed CNN model confusion matrix (50 epochs): (a) imbalanced class without augmentation; (b) imbalanced class with augmentation; (c) balanced class without augmentation; (d) balanced class with augmentation.

Figure 13

Proposed CNN model confusion matrix (100 epochs): (a) imbalanced class without augmentation; (b) imbalanced class with augmentation; (c) balanced class without augmentation; (d) balanced class with augmentation.

Figure 14

Random Forest confusion matrix: (a) imbalanced class without augmentation; (b) imbalanced class with augmentation; (c) balanced class without augmentation; (d) balanced class with augmentation.

Figure 15

SVM confusion matrix: (a) imbalanced class without augmentation; (b) imbalanced class with augmentation; (c) balanced class without augmentation; (d) balanced class with augmentation.

Figure 15

SVM confusion matrix: (a) imbalanced class without augmentation; (b) imbalanced class with augmentation; (c) balanced class without augmentation; (d) balanced class with augmentation.

Figure 16

Evaluation of proposed CNN model using test data.

Figure 17

Prediction of proposed CNN model.