Ensembled convolutional neural network for multi-class skin cancer detection

Title

Ensembled convolutional neural network for multi-class skin cancer detection

Creator

Siva Balan R.V.; Senthilnathan T.; Jayapriya J.; Balakrishnan C.

Description

A skin cancer diagnosis is critically important in medical image processing. The role of dermoscopy and dermatologists is inevitable in skin cancer diagnosis. But, considering the time constraints on diagnosing patients on time, even medical experts need computer-assisted methods to automate the diagnosis process with a higher accuracy rate and with good performance. Such computer-assisted methods with induced artificial intelligence (AI) algorithms are gaining significance. The challenging task of medical image processing is finding benign/malignant pigmented skin lesions after the input image of patients. To identify this difference, AI-based classification algorithms shall be deployed. During the implementation of such algorithms, several performance aspects are evaluated. Once the best such algorithm is identified and evaluated for its performance attributes, it shall be deployed to assist dermatologists. This book chapter explains such a novel multiclass skin cancer classification algorithm. The proposed algorithm uses the best of the attributes and parameters of a deep convolutional neural network (CNN) to give the best-ever enactment among similar existing algorithms. The result achievement of the developed deep CNN based multi-class skin cancer classification algorithm (DCNN-MSCCA) is demonstrated using the HAM10000 dataset. To establish the significance of the developed algorithm, the performance parameters of the DCNN-MSCCA are compared with a few existing significant algorithms. The maximum accuracy of DCNN-MSCCA in predicting the exact multi-class skin cancer is 95.1%. This book chapter explains the implementation details of DCNN-MSCCA using python and libraries supporting CNN. 2024 River Publishers.

Source

Predictive Data Modelling for Biomedical Data and Imaging, pp. 205-230.

Date

2024-01-01

Publisher

River Publishers

Subject

Artificial intelligence; Classification; HAM10000 dataset; Medical image processing; Multi-class skin cancer

Coverage

Siva Balan R.V., Department of Computer Science, Christ (Deemed to be University), India; Senthilnathan T., Department of Computer Science, Christ (Deemed to be University), India; Jayapriya J., Department of Computer Science, Christ (Deemed to be University), India; Balakrishnan C., Department of Computer Science, Christ (Deemed to be University), India

Rights

Restricted Access

Relation

ISBN: 978-877004076-1; 978-877004077-8

Format

Online

Language

English

Type

Book chapter

Identifier

https://www.scopus.com/inward/record.uri?eid=2-s2.0-85196236418&partnerID=40&md5=510b8a08acec16ed10d3e6c5b4a69ba9