Gabor wavelet-based deep learning for skin lesion classification

doi:10.1016/j.compbiomed.2019.103423

Computers in Biology and Medicine

Volume 113, October 2019, 103423

https://doi.org/10.1016/j.compbiomed.2019.103423 Get rights and content

Abstract

Skin cancer cases are increasing and becoming one of the main problems worldwide. Skin cancer is known as a malignant type of skin lesion, and early detection and treatment are necessary. Malignant melanoma and seborrheic keratosis are known as common skin lesion types. A fast and accurate medical diagnosis of these lesions is crucial. In this study, a novel Gabor wavelet-based deep convolutional neural network is proposed for the detection of malignant melanoma and seborrheic keratosis. The proposed method is based on the decomposition of input images into seven directional sub-bands. Seven sub-band images and the input image are used as inputs to eight parallel CNNs to generate eight probabilistic predictions. Decision fusion based on the sum rule is utilized to classify the skin lesion. Gabor based approach provides directional decomposition where each sub-band gives isolated decisions that can be fused for improved overall performance. The results show that the proposed method outperforms alternative methods in the literature developed for skin cancer detection.

Introduction

Cancer is one of the main problems worldwide [1]. The disease can take in several forms and occurs in different locations of the human body. One of the most commonly seen and deadly cancer types in women is breast cancer. Another widely recognized and cancer type with high mortality rates among men is prostate cancer. Melanoma skin cancer is also common and deadly among men and women. This type of cancer is known as the most commonly treated skin cancer type, and $9 %$ of the population is affected in the United States. Moreover, it has also been reported that melanoma skin cancer type is the leading cause of cancer-related deaths in the United States. A recent study [1] has reported the estimated number of new cases and new cancer-related deaths.

Melanoma is one of the skin cancer types, and its associated mortality rate is higher than other types of skin cancer. This malignant type also causes more deaths than different skin cancer types, [[2], [3], [4]]. Melanoma and nevus are known as melanocytic skin lesions. Non-melanocytic skin lesions also occur in malignant and benign forms. Basal cell and squamous cell carcinoma are non-melanocytic malignant skin lesions. Actinic keratosis is the early form of squamous cell carcinoma. Dermatofibroma, vascular, and benign keratosis are known as non-melanocytic benign lesions. Although Basal-cell and squamous-cell carcinoma are more common, melanoma causes a greater number of deaths, [2,5].

Early detection of skin cancer leads to effective treatment. Early detection of cancer could be achieved via automated detection of cancer types using deep learning techniques. Recent studies show that accurate automatic detection of skin cancer can be achieved using deep convolutional neural networks (CNNs). Recent surveys [[6], [7], [8]] have also explained the automated detection of skin cancer forms.

Esteva et al. [1]. used a single GoogleNet CNN model [9,10] for skin lesion prediction. Han et al. [2]. also utilized the ResNet-152 CNN model [11] for skin cancer type recognition. Kaymak and Serener [12] used several single CNN models for the prediction of different categories of skin lesions. On the other hand, several studies have used an ensemble of CNN models for skin cancer detection. Hagari [13] combined AlexNet [14], GoogleNet, VGG [15], RestNet for lesion prediction. Mahbod [16] proposed to fusion of AlexNet, ResNet-18, ResNet-100 and VGG16 for malignant type lesion classification.

The proposed method is different than the above mentioned methods. The proposed new model contains several Gabor wavelet and skin image-based CNN models. This method is an extension of previous techniques and utilizes Gabor representations in a unified CNN model. The model also allows the integration of image data for further enhancements. The Gabor wavelet-based deep convolutional neural network method utilizes Gabor filters on skin images to obtain detailed representations of the skin lesions. Then these details are modeled using deep convolutional neural network models. Furthermore, the fusion of skin images and Gabor representations is performed to increase the accuracy of the proposed method. All details are modeled using deep networks, and then outputs are fused using a probabilistic fusion method to detect skin cancer types.

Previous studies [12,13,16,21] have used skin images as inputs and an ensemble of CNN models for the prediction of skin lesion types. In contrast, this work is based on the decomposition of input images into seven directional sub-bands and then seven sub-band images along with the input image are used as inputs to eight parallel CNNs channels. Eight probabilistic predictions originating from the input channel and seven directional sub band channels are fused for the prediction of skin lesion type.

The main novelties of this work can be summarized as follows. Primarily, a novel Gabor wavelet-based deep convolutional neural network is proposed for the detection of malignant melanoma and seborrheic keratosis. The proposed method is based on the decomposition of input images into seven directional sub-bands. Gabor based approach provides directional decomposition where each sub-band gives isolated decisions that can be fused for improved overall performance. Seven sub band images and the input image are used as inputs to eight parallel CNNs to generate eight probabilistic predictions. Decision fusion based on the sum rule is utilized to classify the skin lesion. Gabor based approach provides directional decomposition where each sub-band generates isolated directional information in the respective sub-band channel. CNN processing in each channel generates learning in the respective direction which can be regarded as decorrelated from the other directions. Hence, combining the decisions of these channels improve the overall classification performance. This approach can be regarded as an augmentation method coupled with multi-channel CNN learning.

The organization of this paper is as follows. The related work section describes previous studies on this subject. In Section 3, we describe the proposed method and give explanations for both the single and ensemble of deep convolutional neural network models. This section also explains Gabor representations and model generations. In Section 4, we report the proposed model evaluation. This section also compares the results of the proposed and other methods. Finally, we conclude the proposed methodology in Section 5.

Section snippets

Related work

There are two different classification approaches for skin lesion classification. These categories are single deep learning-based methods and the ensemble of deep learning methods.

Method

The proposed method builds on Gabor wavelet-based CNN models and an image-based CNN model, Fig. 1. First, seven directional Gabor wavelets represent skin images. Then, the seven Gabor-based CNN models are learned to recognize skin lesion classes. The image-based CNN model is also generated using only skin images. Finally, the CNN model outputs are combined for the estimation of melanoma and seborrheic keratosis classes (see Fig. 2).

Decision fusion allows a combination of output probabilities of

Performance evaluation

The performance of the proposed Gabor wavelet-based deep learning model is evaluated for melanoma and seborrheic keratosis recognition tasks. The area under the receiver operating characteristic curve (M-AUC), accuracy (M-ACC), sensitivity (M-SE), and specificity (M-SP) shows the performance of the melanoma. Similarly, the area under the receiver operating characteristic curve (SK-AUC), accuracy (SK-ACC), sensitivity (SK-SE), and specificity (SK-SP) defines the performance of seborrheic

Conclusion

This work proposes a novel Gabor wavelet-based deep learning model for melanoma and seborrheic keratosis. This model builds on an ensemble of seven Gabor wavelet-based CNN models. Furthermore, this model fuses the Gabor wavelet-based model and an image-based CNN model. The performance evaluation results show that an ensemble of the image and Gabor wavelet-based model outperforms a single image and Gabor wavelet-based models. This ensemble also outperformed the group of only Gabor wavelet-based

References (29)

A.C. Geller et al.
(2018)
B. Harangi
Skin lesion classification with ensembles of deep convolutional neural networks
Biomed. Inf.
(2018)
A. Mahbod et al.
Fusing fine-tuned deep features for skin lesion classification
Comput. Med. Imag. Graph.
(2019)
Y. Li et al.
(2018)
L.R. Siegel et al.
Cancer statistics
Cancer J.
(2018)
A. Esteva et al.
Dermatologist-level classification of skin cancer with deep neural networks
Nature
(2017)
S.,S. Han et al.
Classification of the clinical images for benign and malignant cutaneous tumors using a deep learning algorithm
J. Investig. Dermatol.
(2018)
P. Tschandl et al.
The HAM10000 Dataset: A Large Collection of Multi-Source Dermatoscopic Images of Common Pigmented Skin Lesions
(2018)
K.,S. Nehal et al.
Update on keratinocyte carcinomas
N. Engl. J. Med.
(2018)
R.,B. Oliveira et al.
(2015)

Y. Li et al.

Dermoscopy image analysis: overview and future directions

IEEE J. Biomed. Health Inf.

(2019)

C. Szegedy et al.

Going deeper with convolutions

C. Szegedy et al.

Rethinking the inception architecture for computer vision

S. Targ et al.

Resnet in Resnet: Generalizing Residual Architectures

(2016)

Cited by (78)

Fractional WSD: Fractional war strategy dingo optimization with unified segmentation for detection of skin cancer
2024, Biomedical Signal Processing and Control
Skin cancer represents a general cancer type. Earlier treatment and diagnosis are important tasks in skin cancer. The models, like deep learning, are generally utilized for diagnosing skin lesions and aid in precise treatment. This paper devises a new optimized deep model for discovering skin cancer with a group of skin images. The model utilized pre-processing with a Gaussian filter to filter out the noise and include contrast enhancement to improve image quality. Then segmentation process is done and it is accomplished by fusing two networks, namely Pyramid Based Multi-Scale Encoder-Decoder Network (PMED-Net) and U-Net. The weight optimization takes place using Dingo War Strategy optimization (DWSO). Various operations, like flipping, brightness, shifting, and random erasing are performed for data augmentation to increase dimensionality. The features are extracted to acquire the imperative information from the pixels. The Deep Convolution Neural Network (DCNN) is adapted finally for discovering skin cancer and is subsequently trained with Fractional DWSO. The proposed Fractional DWSO-based DCNN outperformed with an utmost testing accuracy of 95.8 %, sensitivity of 96.9 %, and specificity of 96.6 % respectively.
The power of deep learning for intelligent tumor classification systems: A review
2023, Computers and Electrical Engineering
A tumor is a life-threatening disease that refers to the abnormal growth of cells in any part of the human body. Early detection of this abnormality not only helps with appropriate treatment but also increases life expectancy. In this era of technology, Machine Learning (ML) and Deep Learning (DL) offer reliable and effective techniques for creating intelligent data-driven systems. It thus also serves as a prominent aid in the intelligent diagnosis of various fatal diseases, like tumors or cancer. This study conducts in-depth research on recent deep learning based studies on the classification of tumors at various sites of the human body. Research questions pertinent to the tumor classification are framed, and the literature is explored to answer the questions. After providing insights into the concepts of ML and DL, the study highlights the strengths and limitations of the existing studies. It also provides a qualitative and quantitative comparison of pioneer studies in terms of approach, methods, datasets, and performance metrics. Finally, this study summarizes the challenges confronted by the researchers and makes recommendations for the future application of DL techniques for tumor classification.
A survey, review, and future trends of skin lesion segmentation and classification
2023, Computers in Biology and Medicine
The Computer-aided Diagnosis or Detection (CAD) approach for skin lesion analysis is an emerging field of research that has the potential to alleviate the burden and cost of skin cancer screening. Researchers have recently indicated increasing interest in developing such CAD systems, with the intention of providing a user-friendly tool to dermatologists to reduce the challenges encountered or associated with manual inspection. This article aims to provide a comprehensive literature survey and review of a total of 594 publications (356 for skin lesion segmentation and 238 for skin lesion classification) published between 2011 and 2022. These articles are analyzed and summarized in a number of different ways to contribute vital information regarding the methods for the development of CAD systems. These ways include: relevant and essential definitions and theories, input data (dataset utilization, preprocessing, augmentations, and fixing imbalance problems), method configuration (techniques, architectures, module frameworks, and losses), training tactics (hyperparameter settings), and evaluation criteria. We intend to investigate a variety of performance-enhancing approaches, including ensemble and post-processing. We also discuss these dimensions to reveal their current trends based on utilization frequencies. In addition, we highlight the primary difficulties associated with evaluating skin lesion segmentation and classification systems using minimal datasets, as well as the potential solutions to these difficulties. Findings, recommendations, and trends are disclosed to inform future research on developing an automated and robust CAD system for skin lesion analysis.
An adaptive weight search method based on the Grey wolf optimizer algorithm for skin lesion ensemble classification
2024, International Journal of Imaging Systems and Technology
Effective melanoma classification using inter neighbour mean order interleaved pattern on dermoscopy images
2024, Multimedia Tools and Applications
Fine-tuning pre-trained neural networks for medical image classification in small clinical datasets
2024, Multimedia Tools and Applications

View all citing articles on Scopus

View full text

Gabor wavelet-based deep learning for skin lesion classification

Abstract

Introduction

Section snippets

Related work

Method

Performance evaluation

Conclusion

Biomed. Inf.

Comput. Med. Imag. Graph.

Cancer statistics

Cancer J.

Dermatologist-level classification of skin cancer with deep neural networks

Nature

Classification of the clinical images for benign and malignant cutaneous tumors using a deep learning algorithm

J. Investig. Dermatol.

The HAM10000 Dataset: A Large Collection of Multi-Source Dermatoscopic Images of Common Pigmented Skin Lesions

Update on keratinocyte carcinomas

N. Engl. J. Med.

Dermoscopy image analysis: overview and future directions

IEEE J. Biomed. Health Inf.

Going deeper with convolutions

Rethinking the inception architecture for computer vision

Resnet in Resnet: Generalizing Residual Architectures