Skin lesion classification using HG-PSO and YOLOv7 based convolutional network in real time

Abstract

Skin cancer is a chronic illness seen visually and further diagnosed with a dermoscopic examination. It is crucial to precisely localize and classify lesions from dermoscopic images to diagnose and treat skin cancers as soon as possible. This work presents melanoma identification, and the classification method significantly improves accuracy and precision. This work proposes a method Hybrid of Genetic and Particle swarm optimization (HG-PSO), and You only look once version 7 (YOLOv7) based convolutional network for skin cancer classification. The infected region is first located using optimized YOLOv7 object detection. Then color thresholding is applied to segment it, which is passed to the proposed convolutional network for classification. This work is tested on the Human Against Machine with 10,000 training images (HAM10000), International Skin Imaging Collaboration (ISIC)-2019, and Hospital Pedro Hispano (PH2) datasets, and the findings are compared to the state-of-the-art methods for classifying skin cancer. The proposed method achieves 98.86% accuracy, 99.00% average precision, 98.85% average recall, and 98.85% average F1-score on the HAM10000 dataset. It achieves 97.10% accuracy on ISIC-2019 datasets. The average precision obtained is 97.37%, the average recall is 97.13%, and the average F1-score is 97.13% on the ISIC-2019 dataset. It achieves a 97.7% accuracy on the PH2 dataset. The average precision obtained is 99.00%, the average recall is 96.00%, and the average F1-score is 97.00% on the PH2 dataset. The test time taken by this method on datasets HAM10000, ISIC-2019, and PH2 dataset is 2, 3, and 2 s, respectively, which may help give faster responses in telemedicine.

Graphical abstract

Keywords

Deep learning skin lesions classification skin cancer dermoscopic images HAM10000 dataset

Get full access to this article

View all access options for this article.

References

Sung

Ferlay

Siegel

, et al. Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin 2021; 71(3): 209–249.

Lee

di Meo

Ylamos

. Dermoscopy/confocal microscopy for melanoma diagnosis. In: Balch

Atkins

Garbe

, et al. (eds) Cutaneous melanoma. Cham: Springer, 2020, pp.145–194.

Pham

Doucet

Luong

, et al. Improving skin-disease classification based on customized loss function combined with balanced mini-batch logic and real-time image augmentation. IEEE Access 2020; 8: 150725–150737.

Swetter

Geller

Leachman

, et al. Melanoma prevention and screening. In: Balch

Atkins

Garbe

, et al. (eds) Cutaneous melanoma. Cham: Springer, 2020, pp.525–570.

Esteva

Kuprel

Novoa

, et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature 2017; 542(7639): 115–118.

NCBI Bookshelf. Introduction and background - telemedicine: a guide to assessing telecommunications in health care, https://www.ncbi.nlm.nih.gov/books/NBK45440/ (1996, accessed 3 July 2023).

Batista

Bugatti

Saito

PTM

. Classification of skin lesion through active learning strategies. Comput Methods Programs Biomed 2022; 226: 107122.

Öztürk

Özkaya

. Skin lesion segmentation with improved convolutional neural network. J Digit Imaging 2020; 33: 958–970.

Iqbal

Younus

Walayat

, et al. Automated multi-class classification of skin lesions through deep convolutional neural network with dermoscopic images. Comput Med Imaging Graph 2021; 88: 101843.

10.

Ünver

Ayan

. Skin lesion segmentation in dermoscopic images with combination of YOLO and grabcut algorithm. Diagnostics 2019; 9(3): 72.

11.

Banerjee

Singh

Chakraborty

, et al. Melanoma diagnosis using deep learning and fuzzy logic. Diagnostics 2020; 10(8): 577.

12.

Rehman

Nida

Shah

, et al. Automatic melanoma detection and segmentation in dermoscopy images using deep RetinaNet and conditional random fields. Multimed Tools Appl 2022; 81(18): 25765–25785.

13.

Nersisson

Iyer

Joseph Raj

, et al. A dermoscopic skin lesion classification technique using YOLO-CNN and traditional feature model. Arab J Sci Eng 2021; 46: 9797–9808.

14.

Redmon

Divvala

Girshick

, et al. You only look once: unified, real-time object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, Las Vegas, NV, USA, 27–30 June 2016, pp.779–788. New York: IEEE.

15.

Cao

Zheng

Fang

. The semantic segmentation of standing tree images based on the Yolo V7 deep learning algorithm. Electronics 2023; 12(4): 929.

16.

Wang

Bochkovskiy

Liao

. YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, Vancouver Convention Center, Canada, June 18–22 2023, pp.7464–7475.

17.

Mishra

Sarkar

Choudhury

, et al. Allergen30: detecting food items with possible allergens using deep learning-based computer vision. Food Anal Methods 2022; 15(11): 3045–3078.

18.

Szegedy

Liu

Jia

, et al. Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, Boston, MA, USA, 7–12 June 2015, pp.1–9. New York: IEEE.

19.

El-Gendy

Saafan

Elksas

, et al. Applying hybrid genetic–PSO technique for tuning an adaptive PID controller used in a chemical process. Soft Comput 2020; 24: 3455–3474.

20.

Tschandl

Rosendahl

Kittler

. The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions. Sci Data 2018; 5(1): 180161.

21.

Mendona

Ferreira

Marques

, et al. PH²-a dermoscopic image database for research and benchmarking. In: International conference of the IEEE engineering in medicine and biology society, Osaka, Japan, 3–7 July 2013, pp.5437–5440. New York: IEEE.

22.

Masood

Iqbal

Khan

, et al. Multi-class skin cancer detection and classification using hybrid features extraction techniques. J Med Imaging Health Informat 2020; 10(10): 2466–2472.

23.

Zhang

, et al. Symmetry GAN detection network: an automatic one-stage high-accuracy detection network for various types of lesions on CT images. Symmetry 2022; 14(2): 234.

24.

Kousis

Perikos

Hatzilygeroudis

, et al. Deep learning methods for accurate skin cancer recognition and mobile application. Electronics 2022; 11(9): 1294.

25.

Thurnhofer-Hemsi

Domínguez

. A convolutional neural network framework for accurate skin cancer detection. Neural Process Lett 2021; 53(5): 3073–3093.

26.

Popescu

El-Khatib

Ichim

. Skin lesion classification using collective intelligence of multiple neural networks. Sensors 2022; 22(12): 4399.

27.

Villa-Pulgarin

Ruales-Torres

Arias-Garzon

, et al. Optimized convolutional neural network models for skin lesion classification. Comput Mater Contin 2022; 70(2): 2131–2148.

28.

Abd Elaziz

Dahou

Mabrouk

, et al. An efficient artificial rabbits optimization based on mutation strategy for skin cancer prediction. Comput Biol Med 2023; 163: 107154.

29.

Rodrigues

DDA

Ivo

Satapathy

, et al. A new approach for classification skin lesion based on transfer learning, deep learning, and IoT system. Pattern Recognit Lett 2020; 136: 8–15.

30.

Adegun

Viriri

. Deep learning-based system for automatic melanoma detection. IEEE Access 2020; 8: 7160–7172.

31.

Nawaz

Mehmood

Nazir

, et al. Skin cancer detection from dermoscopic images using deep learning and fuzzy k-means clustering. Microsc Res Tech 2022; 85(1): 339–351.

32.

Tong

Wei

Sun

, et al. ASCU-Net: attention gate, spatial and channel attention u-net for skin lesion segmentation. Diagnostics 2021; 11(3): 501.