A Computer‐Aided Diagnosis System Using Deep Learning for Multiclass Skin Lesion Classification

Abstract

In the USA, each year, almost 5.4 million people are diagnosed with skin cancer. Melanoma is one of the most dangerous types of skin cancer, and its survival rate is 5%. The development of skin cancer has risen over the last couple of years. Early identification of skin cancer can help reduce the human mortality rate. Dermoscopy is a technology used for the acquisition of skin images. However, the manual inspection process consumes more time and required much cost. The recent development in the area of deep learning showed significant performance for classification tasks. In this research work, a new automated framework is proposed for multiclass skin lesion classification. The proposed framework consists of a series of steps. In the first step, augmentation is performed. For the augmentation process, three operations are performed: rotate 90, right-left flip, and up and down flip. In the second step, deep models are fine-tuned. Two models are opted, such as ResNet-50 and ResNet-101, and updated their layers. In the third step, transfer learning is applied to train both fine-tuned deep models on augmented datasets. In the succeeding stage, features are extracted and performed fusion using a modified serial-based approach. Finally, the fused vector is further enhanced by selecting the best features using the skewness-controlled SVR approach. The final selected features are classified using several machine learning algorithms and selected based on the accuracy value. In the experimental process, the augmented HAM10000 dataset is used and achieved an accuracy of 91.7%. Moreover, the performance of the augmented dataset is better as compared to the original imbalanced dataset. In addition, the proposed method is compared with some recent studies and shows improved performance.

Multiclass Skin Lesion Classification Using Hybrid Deep Features Selection and Extreme Learning Machine

“…The selection of the best features is an important step, with the advantage of improving the classification accuracy and reducing the computational time [ 38 ]. In this work, two methods are applied for the selection of best features.…”

Systematic Review of Supervised Machine Learning Models in Prediction of Medical Conditions

“…Accurate predicting the development of cancers or complications of cancers could indicate earlier diagnosis and therapeutic approaches that would improve outcomes. [26,31,33,35,37,39,41,53,55,[58][59][60]73] The majority of these ML applications use imaging data (most often histologic type) for classification of malignant versus benign tumors. Cardiovascular conditions and DM are among the most common medical conditions used in predictive analysis.…”

“…[38,52,67] The most successful and meaningful application of deep learning ML models was achieved in the imaging field. [53,[55][56][57][58][59][60][61][62][63][64][65] Analyses of CT scans, X-rays, Doppler ultrasound, histo-pathological images obtained high accuracy results, which often outperform medical experts. RNN models capture the temporal nature of EHR, imaging and other medical data to predict diseases, complications, and outcomes.…”

Mango Leaf Disease Recognition and Classification Using Novel Segmentation and Vein Pattern Technique

“…The overall performance of the proposed method is much improved compared to already available methods. However, the following improvements will be considered in the future: (1) increase the number of images in the dataset, (2) minimize the identification time through feature optimization algorithms [39][40][41] to implement it in real time, and (3) implement some latest deep learning models [42][43][44][45].…”