Optimized Convolutional Neural Network Models for Skin Lesion Classification
Source abstract
Abstract
Skin cancer is one of the most severe diseases, and medical imaging is among the main tools for cancer diagnosis. The images provide information on the evolutionary stage, size, and location of tumor lesions. This paper focuses on the classification of skin lesion images considering a framework of four experiments to analyze the classification performance of Convolutional Neural Networks (CNNs) in distinguishing different skin lesions. The CNNs are based on transfer learning, taking advantage of ImageNet weights. Accordingly, in each experiment, different workflow stages are tested, including data augmentation and fine-tuning optimization. Three CNN models based on DenseNet-201, Inception-ResNet-V2, and Inception-V3 are proposed and compared using the HAM10000 dataset. The results obtained by the three models demonstrate accuracies of 98%, 97%, and 96%, respectively. Finally, the best model is tested on the ISIC 2019 dataset showing an accuracy of 93%. The proposed methodology using CNN represents a helpful tool to accurately diagnose skin cancer disease.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Cutaneous Melanoma Detection and Management · AI in cancer detection · Nonmelanoma Skin Cancer Studies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (42)
Show source-provided references
1. Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries
2. C. Ferlay, J. Colombet, M. Soerjomataram, I. Mathers, D. Parkin et al., “Global cancer observatory: Cancer tomorrow. Lyon, France: International Agency for Research on Cancer, 2020. [Online]. Available: https://gco.iarc.fr/tomorrow [Accessed: 30-May-2021].
3. Intelligent skin cancer detection applying autoencoder, MobileNetV2 and spiking neural networks10.1016/j.chaos.2021.110714 ↗
4. Disease risk scores for skin cancers10.1038/s41467-020-20246-5 ↗
5. The global burden of skin cancer: A longitudinal analysis from the global burden of disease study, 1990–201710.1016/j.jdin.2020.10.013 ↗
6. Deep learning in skin disease image recognition: A review10.1109/ACCESS.2020.3037258 ↗
7. Automated deep learning design for medical image classification by health-care professionals with no coding experience: A feasibility study10.1016/S2589-7500(19)30108-6 ↗
8. Deep learning techniques for skin lesion analysis and melanoma cancer detection: A survey of state-of-the-art10.1007/s10462-020-09865-y ↗
9. Dermatologist-level classification of skin cancer with deep neural networks10.1038/nature21056 ↗
10. Classification of skin lesions using transfer learning and augmentation with Alex-net10.1371/journal.pone.0217293 ↗
11. Classification of dermoscopy skin lesion color-images using fractal-deep learning features10.3390/app10175954 ↗
12. Automated multi-class classification of skin lesions through deep convolutional neural network with dermoscopic images10.1016/j.compmedimag.2020.101843 ↗
13. A convolutional neural network framework for accurate skin cancer detection
14. A comparative study of machine learning and deep learning algorithms to classify cancer types based on microarray gene expression data
15. A survey on deep learning in medical image analysis10.1016/j.media.2017.07.005 ↗
16. Cervical cancer classification using convolutional neural networks, transfer learning and data augmentation
17. Hassaballah · Deep Learning in Computer Vision: Principles and Applications · 202010.1201/9781351003827 ↗
18. Efficient processing of deep neural networks10.1007/978-3-031-01766-7 ↗
19. Accuracy of computer-aided diagnosis of melanoma a meta-analysis10.1001/jamadermatol.2019.1375 ↗
20. Systematic outperformance of 112 dermatologists in multiclass skin cancer image classification by convolutional neural networks10.1016/j.ejca.2019.06.013 ↗
21. Diagnosis of melanoma from dermoscopic images using a deep depthwise separable residual convolutional network10.1049/iet-ipr.2018.6669 ↗
22. Deep ensemble learning for skin lesion classification from dermoscopic images
23. Deep learning for two-step clas-sification of malignant pigmented skin lesions
24. Enhanced skin lesions classification using deep convolutional networks
25. Deep learning solutions for skin cancer detection and diagnosis10.1007/978-3-030-40850-3_8 ↗
26. Skin lesion diagnosis using ensembles, unscaled multi-crop evaluation and loss weighting
27. Skin cancer detection based on deep learning and entropy to detect outlier samples
28. Skin lesion classification with deep CNN ensembles
29. Skin lesion classification using ensembles of multi-resolution EfficientNets with meta data10.1016/j.mex.2020.100864 ↗
30. ImageNet large scale visual recognition challenge10.1007/s11263-015-0816-y ↗
31. Multi-model deep neural network based features extraction and optimal selection approach for skin lesion classification
32. Classification of skin cancer images using TensorFlow and inception v310.14419/ijet.v7i2.7.10930 ↗
33. Transfer learning based method for two-step skin cancer images classification
34. Segmented and non-segmented skin lesions classification using transfer learning and adaptive moment learning rate technique using pretrained convolutional neural network10.4028/www.scientific.net/JBBBE.42.67 ↗
35. Skin lesions classification into eight classes for ISIC, 2019 using deep convolutional neural network and transfer learning10.1109/ACCESS.2020.3003890 ↗
36. The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions10.1038/sdata.2018.161 ↗
37. Skin lesion analysis toward melanoma detection 2018: A challenge hosted by the international skin imaging collaboration
38. Ensembled skin cancer classification (ISIC 2019 challenge submission)
39. Convolutional neural networks for medical image analysis: Full training or fine tuning10.1109/TMI.2016.2535302 ↗
40. Image captioning using google’s inception-resnet-v2 and recurrent neural network
41. Dermatologist level dermoscopy skin cancer classification using different deep learning convolutional neural networks algorithms
42. Deep convolutional neural network with TensorFlow and Keras to classify skin cancer images