BF2SkNet: best deep learning features fusion-assisted framework for multiclass skin lesion classification

被引:0
作者
Muhammad Ajmal
Muhammad Attique Khan
Tallha Akram
Abdullah Alqahtani
Majed Alhaisoni
Ammar Armghan
Sara A. Althubiti
Fayadh Alenezi
机构
[1] COMSATS University Islamabad,Department of Electrical and Computer Engineering
[2] Wah Campus,Department of Computer Science
[3] HITEC University,College of Computer Engineering and Sciences
[4] Prince Sattam Bin Abdulaziz University,Computer Sciences Department, College of Computer and Information Sciences
[5] Princess Nourah Bint Abdulrahman University,Department of Electrical Engineering, College of Engineering
[6] Jouf University,Department of Computer Science, College of Computer and Information Sciences
[7] Majmaah University,undefined
来源
Neural Computing and Applications | 2023年 / 35卷
关键词
Skin cancer; Artificial intelligence; Dermoscopy; Deep learning; Features optimization; Features fusion; Machine learning;
D O I
暂无
中图分类号
学科分类号
摘要
The convolutional neural network showed considerable success in medical imaging with explainable AI for cancer detection and recognition. However, the irrelevant and large number of features increases the computational time and decreases the accuracy. This work proposes a deep learning and fuzzy entropy slime mould algorithm-based architecture for multiclass skin lesion classification. In the first step, we employed the data augmentation technique to increase the training data and further utilized it for training two fine-tuned deep learning models such as Inception-ResNetV2 and NasNet Mobile. Then, we used transfer learning on augmented datasets to train both models and obtained two feature vectors from newly fine-tuned models. Later, we applied a fuzzy entropy slime mould algorithm on both vectors to get optimal features that are finally fused using the Serial-Threshold fusion technique and classified using several machine learning classifiers. Eventually, the explainable AI technique named Gradcam opted for the visualization of the lesion region. The experimental process was conducted on two datasets, such as HAM10000 and ISIC 2018, and achieved 97.1 and 90.2% accuracy, better than the other techniques.
引用
收藏
页码:22115 / 22131
页数:16
相关论文
共 218 条
  • [1] Spyridonos P(2021)Characterizing malignant melanoma clinically resembling seborrheic keratosis using deep knowledge transfer Cancers 13 6300-452
  • [2] Gaitanis G(2020)The effects of skin lesion segmentation on the performance of dermatoscopic image classification Comput Methods Programs Biomed 197 105725-12050
  • [3] Likas A(2021)Skin pigmentation Medicine 49 447-54
  • [4] Bassukas I(2021)Automated multi-class classification of skin lesions through deep convolutional neural network with dermoscopic images Comput Med Imaging Graph 88 101843-118
  • [5] Mahbod A(2020)Transfer learning using a multi-scale and multi-network ensemble for skin lesion classification Comput Methods Programs Biomed 193 105475-114832
  • [6] Tschandl P(2021)A deep convolutional neural network-based pigmented skin lesion classification application and experts evaluation Neural Comput Appl 33 12039-9
  • [7] Langs G(2005)The causes of skin cancer: a comprehensive review Drugs Today 41 37-2776
  • [8] Ecker R(2017)Dermatologist-level classification of skin cancer with deep neural networks Nature 542 115-636
  • [9] Ellinger I(2020)Multi-label classification of multi-modality skin lesion via hyper-connected convolutional neural network Pattern Recognit 107 107502-16
  • [10] Lakhan MK(2018)Skin cancer classification using convolutional neural networks: systematic review J Med Internet Res 20 e11936-7517