An evolutionary algorithm based feature selection and fuzzy rule reduction technique for the prediction of skin cancer

Abstract

Summary In current years, the death rate from skin cancers (SCs) tends to develop pretty. Various research verified that SC rank third as a deadliest disease, after breast and lung cancer. It will become vital to diagnose this malignancy at an early stage. The objective of this research is to mix machine learning and soft computing techniques to gain higher accuracy within the prediction of SC. To play out the exploration work, we utilized two data sets, one from “Save Life Hospital,” India, and the other is the UCI repository skin cancer data set. In this article, three meta‐heuristic algorithms, the FS_GA, the FS_PSO, and the FS_ACO, were used to select the best features from the data set provided to it. The AFRG_algorithm generates a set of fuzzy rules automatically and the RR_algorithm reduces certain fuzzy rules from the fuzzy system. For the SCC_dataset, the end accuracy obtained was 97.67%, 98.45%, and 99.22%. For the UCI_dataset, the end accuracy obtained was 98.81%, 99.72%, and 99.67%. Experimental results on the used datasets show that the proposed method strikingly improves the forecast exactitude of skin malignancy.

Deep Learning-Based Dermatological Condition Detection: A Systematic Review With Recent Methods, Datasets, Challenges, and Future Directions

“…In reference [79], a technique for skin disease classification is proposed, leveraging the integration of MobileNet V2 with LSTM. The key advantage of this technique lies in the utilization of LSTM to enhance classification accuracy by preserving the state information of the features.…”

“…As observed from the preceding section, most deep learningbased methods diagnose a few dermatological conditions [78][79][80]. The procedure to determine whether a skin sample is a predefined category of dermatological condition or its subtype is an important task and can be done by an experienced pathologist.…”

“…It is essential to be familiar with diagnostic metadata including skin cancer history, age, sex, ethnicity, general anatomic site, size, and structure of patients' skin lesions in order to correctly diagnose the dermatological condition the patient is suffering from (and occasionally associated information from their family). It has been demonstrated in the work [75][76][77][78][79][80][81][82][83][84][85][86][87][88][89][90][91] that more clinical information can enhance the performance of both novice and experienced dermatologists. However, most previous deep learning-based methods to detect dermatological conditions have focused on giving dermoscopic or histopathological images as input, ignoring the patient's medical history and clinical data.…”

“…Though the fair skin colour population has a higher rate of suffering from dermatological conditions, dark skin colour populations also suffer from the same conditions but are diagnosed at a later stage. Deep learning models can better accurately classify skin disease from fair skin than dark skin [79][80]. In a recent study, Han et al [96] built a deep learning algorithm using a training dataset of Asian skin lesions.…”