Skin Cancer Images Research Articles

Salp swarm algorithm with iterative mapping and local escaping for multi-level threshold image segmentation: a skin cancer dermoscopic case study

AbstractIf found and treated early, fast-growing skin cancers can dramatically prolong patients’ lives. Dermoscopy is a convenient and reliable tool during the fore-period detection stage of skin cancer, so the efficient processing of digital images of dermoscopy is particularly critical to improving the level of a skin cancer diagnosis. Notably, image segmentation is a part of image preprocessing and essential technical support in the process of image processing. In addition, multi-threshold image segmentation (MIS) technology is extensively used due to its straightforward and effective features. Many academics have coupled different meta-heuristic algorithms with MIS to raise image segmentation quality. Nonetheless, these meta-heuristic algorithms frequently enter local optima. Therefore, this paper suggests an improved salp swarm algorithm (ILSSA) method that combines iterative mapping and local escaping operator to address this drawback. Besides, this paper also proposes the ILSSA-based MIS approach, which is triumphantly utilized to segment dermoscopic images of skin cancer. This method uses two-dimensional (2D) Kapur’s entropy as the objective function and employs non-local means 2D histogram to represent the image information. Furthermore, an array of benchmark function test experiments demonstrated that ILSSA could alleviate the local optimal problem more effectively than other compared algorithms. Afterward, the skin cancer dermoscopy image segmentation experiment displayed that the proposed ILSSA-based MIS method obtained superior segmentation results than other MIS peers and was more adaptable at different thresholds.

Incorporating a Novel Dual Transfer Learning Approach for Medical Images.

Recently, transfer learning approaches appeared to reduce the need for many classified medical images. However, these approaches still contain some limitations due to the mismatch of the domain between the source domain and the target domain. Therefore, this study aims to propose a novel approach, called Dual Transfer Learning (DTL), based on the convergence of patterns between the source and target domains. The proposed approach is applied to four pre-trained models (VGG16, Xception, ResNet50, MobileNetV2) using two datasets: ISIC2020 skin cancer images and ICIAR2018 breast cancer images, by fine-tuning the last layers on a sufficient number of unclassified images of the same disease and on a small number of classified images of the target task, in addition to using data augmentation techniques to balance classes and to increase the number of samples. According to the obtained results, it has been experimentally proven that the proposed approach has improved the performance of all models, where without data augmentation, the performance of the VGG16 model, Xception model, ResNet50 model, and MobileNetV2 model are improved by 0.28%, 10.96%, 15.73%, and 10.4%, respectively, while, with data augmentation, the VGG16 model, Xception model, ResNet50 model, and MobileNetV2 model are improved by 19.66%, 34.76%, 31.76%, and 33.03%, respectively. The Xception model obtained the highest performance compared to the rest of the models when classifying skin cancer images in the ISIC2020 dataset, as it obtained 96.83%, 96.919%, 96.826%, 96.825%, 99.07%, and 94.58% for accuracy, precision, recall, F1-score, sensitivity, and specificity respectively. To classify the images of the ICIAR 2018 dataset for breast cancer, the Xception model obtained 99%, 99.003%, 98.995%, 99%, 98.55%, and 99.14% for accuracy, precision, recall, F1-score, sensitivity, and specificity, respectively. Through these results, the proposed approach improved the models' performance when fine-tuning was performed on unclassified images of the same disease.

Machine Learning-Based Classification of Skin Cancer Hyperspectral Images

Among the different contactless techniques for medical diagnosis, hyperspectral imaging has gained relevance due to the high accuracy in tissues classification. Several techniques have been proposed to elaborate these images, ranging from traditional machine learning methods to deep learning algorithms. This paper evaluates three popular machine learning methods, namely Support Vector Machine (SVM), Random Forest (RF) and eXtreme Gradient Boosting (XGBoost) considering a dataset of hyperspectral skin cancer images. The study demonstrates that the proposed algorithms are suitable for medical hyperspectral data classification, particularly when considering a small dataset.

Skin Cancer Image Detection and Classification by CNN based Ensemble Learning

Skin Cancer Image Detection and Classification by CNN based Ensemble Learning

Fuzzy SHmath.Mbio-transform generalization and application to skin cancer imaging (distributed diseases)

Fuzzy integral transformations are an important methodology for solving the relevant fuzzy boundary (initial) value issues that arise from solving fuzzy differential and integral equations. In this study, the way we classify the-for the corresponding-order fuzzy derivative, fuzzy Shmath.mbio.M-transform. Studies of this process are conducted on the assumption of substantial generalized Hukuhara differentiability. When comparing the suggested transform to another transform, the fuzzy Laplace transform, the effectiveness of the proposed transform in extracting melanoma edges was shown to be much higher. The accuracy and efficiency of the proposed transformation may be enhanced even more. statistical parameters were used to corroborate the findings.

Skin Lesion Segmentation Using K-means Clustering with Removal Unwanted Regions

The segmentation of skin lesions is crucial to the early and accurate identification of skin cancer by computerized systems. It is difficult to automatically divide skin lesions in dermoscopic images because of challenges such as hairs, gel bubbles, ruler marks, fuzzy boundaries, and low contrast. We proposed an effective method based on K-means and a trainable machine learning system to segment regions of interest (ROI) in skin cancer images. The proposed method was implemented in several stages, including grayscale image conversion, contrast image enhancement, artifact removal with noise reduction, skin lesion segmentation from image using K-means clustering, and ROI segmentation from unwanted objects using a trainable machine learning system. The proposed model has been evaluated using the ISIC 2017 publicly available dataset. The proposed method obtained a 90.09 accuracy rate, outperforming several methods in the literature.

Skin Cancer Detection and Segmentation Using Convolutional Neural Network Models

Skin cancer is known as one of the killing diseases in humans around the world. In this paper, melanoma skin cancer images are classified and the cancer regions are segmented using Convolutional Neural Networks (CNN). The skin images are data augmented into high number of skin images for obtaining the high classification accuracy. Then, CNN classifier is used to classify the skin image into either melanoma or normal. Finally, morphological segmentation method is used to segment the cancer regions. The simulation results are obtained by applying the proposed methods on ISIC and HAM dataset skin images.

Advances in terahertz technology for cancer detection applications.

Currently, there is an increasing demand for the diagnostic techniques that provide functional and morphological information with early cancer detection capability. Novel modern medical imaging systems driven by the recent advancements in technology such as terahertz (THz) and infrared radiation-based imaging technologies which are complementary to conventional modalities are being developed, investigated, and validated. The THz cancer imaging techniques offer novel opportunities for label free, non-ionizing, non-invasive and early cancer detection. The observed image contrast in THz cancer imaging studies has been mostly attributed to higher refractive index, absorption coefficient and dielectric properties in cancer tissue than that in the normal tissue due the local increase of the water molecule content in tissue and increased blood supply to the cancer affected tissue. Additional image contrast parameters and cancer biomarkers that have been reported to contribute to THz image contrast include cell structural changes, molecular density, interactions between agents (e.g., contrast agents and embedding agents) and biological tissue as well as tissue substances like proteins, fiber and fat etc. In this paper, we have presented a systematic and comprehensive review of the advancements in the technological development of THz technology for cancer imaging applications. Initially, the fundamentals principles and techniques for THz radiation generation and detection, imaging and spectroscopy are introduced. Further, the application of THz imaging for detection of various cancers tissues are presented, with more focus on the in vivo imaging of skin cancer. The data processing techniques for THz data are briefly discussed. Also, we identify the advantages and existing challenges in THz based cancer detection and report the performance improvement techniques. The recent advancements towards THz systems which are optimized and miniaturized are also reported. Finally, the integration of THz systems with artificial intelligent (AI), internet of things (IoT), cloud computing, big data analytics, robotics etc. for more sophisticated systems is proposed. This will facilitate the large-scale clinical applications of THz for smart and connected next generation healthcare systems and provide a roadmap for future research.

A Survey on Computer-Aided Intelligent Methods to Identify and Classify Skin Cancer

Melanoma is one of the skin cancer types that is more dangerous to human society. It easily spreads to other parts of the human body. An early diagnosis is necessary for a higher survival rate. Computer-aided diagnosis (CAD) is suitable for providing precise findings before the critical stage. The computer-aided diagnostic process includes preprocessing, segmentation, feature extraction, and classification. This study discusses the advantages and disadvantages of various computer-aided algorithms. It also discusses the current approaches, problems, and various types of datasets for skin images. Information about possible future works is also highlighted in this paper. The inferences derived from this survey will be useful for researchers carrying out research in skin cancer image analysis.

Deep Learning-based and Machine Learning-based Application in Skin Cancer Image Classification

Skin cancer arises from the skin and is capable of invading other parts of the body. The earlier detection of malignant skin lesions effectively helps cure skin disease and prevents fatal skin cancer. As part of AI, machine learning and deep learning can learn the characteristics of input datasets and perform classifications with high accuracy. In this paper, the CNN, KNN, and SVM models are implemented and tested based on the datasets collected from ISIC. The idea of the implementation is to classify the images of skin lesions into benign and malignant. The information of GANs based model is gathered. The results display the accuracy of using these models to classify different types of lesions. And the discussion of the results focuses on the efficiency to implement the machine learning and deep learning models and the accuracy of using them. The goal of the study is to figure out which method is more useful in skin cancer identification. And some of the possible practices are also discussed as future expectations.

Convolutional Neural Networks on Assembling Classification Models to Detect Melanoma Skin Cancer

In 2020, there were more than 1.2 million new skin cancer diagnoses, and melanoma was the most recurrent type of cancer. On the other hand, melanoma is the least common but most serious form of skin cancer affecting both men and women. This work aims to assemble classification models to detect a case of melanoma with high accuracy based on a Convolutional Neural Networks system. The methodology considers training 21 models for image classification, with the best assembly performance of EfficientNet and VGG-19 architectures, the data augmentation technique was used to the images to improve its performance. The results show 92.85% of accuracy, 71.50% of sensitivity, and 94.89% of specificity, with an improvement of 0.06% in accuracy and specificity. The assembly of the classification models achieved higher accuracy in melanoma skin cancer image classification.

Microbubble-Assisted Ultrasound for Imaging and Therapy of Melanoma Skin Cancer: A Systematic Review.

Recent technological developments in ultrasound (US) imaging and ultrasound contrast agents (UCAs) have improved diagnostic confidence in echography. In the clinical management of melanoma, contrast-enhanced ultrasound (CEUS) imaging complements conventional US imaging (i.e., high-resolution US and Doppler imaging) for clinical examination and therapeutic follow-up. These developments have set into motion the combined use of ultrasound and UCAs as a new modality for drug delivery. This modality, called sonoporation, has emerged as a non-invasive, targeted and safe method for the delivery of therapeutic drugs into melanoma. This review focuses on the results and prospects of using US and UCAs as dual modalities for CEUS imaging and melanoma treatment.

An efficient multi-threshold image segmentation for skin cancer using boosting whale optimizer

Due to the terrible manifestations of skin cancer, it seriously disturbs the quality of life status and health of patients, so we needs treatment plans to detect it early and avoid it causing more harm to patients. Medical disease image threshold segmentation technique can well extract the region of interest and effectively assist in disease recognition. Moreover, in multi-threshold image segmentation, the selection of the threshold set determines the image segmentation quality. Among the common threshold selection methods, the selection based on metaheuristic algorithm has the advantages of simplicity, easy implementation and avoidable local optimization. However, different algorithms have different performances for different medical disease images. For example, the Whale Optimization Algorithm (WOA) does not give a satisfactory performance for thresholding skin cancer images. We propose an improved WOA (LCWOA) in which the Levy operator and chaotic random mutation strategy are introduced to enhance the ability of the algorithm to jump out of the local optimum and to explore the search space. Comparing with different existing WOA variants on the CEC2014 function set, our proposed and improved algorithm improves the efficiency of the search. Experimental results show that our method outperforms the extant WOA variants in terms of optimization performances, improving the convergence accuracy and velocity. The method is also applied to solve the threshold selection in the skin cancer image segmentation problem, and LCWOA also gives excellent performance in obtaining optimal segmentation results.

MF-OMKT: Model fusion based on online mutual knowledge transfer for breast cancer histopathological image classification

Pathological diagnosis is considered as the benchmark for the detection of breast cancer. With the increasing number of patients, computer-aided histopathological image classification can assist pathologists in improving breast cancer diagnosis accuracy and working efficiency. However, a single model is insufficient for effective diagnosis, and this also does not accord with the principle of centralized decision-making. Starting from the real pathological diagnosis scenario, we propose a novel model fusion framework based on online mutual knowledge transfer (MF-OMKT) for breast cancer histopathological image classification. The OMKT part based on deep mutual learning (DML) imitates the mutual communication and learning between multiple experienced pathologists, which can break the isolation of single models and provides sufficient complementarity among heterogeneous networks for MF. The MF part based on adaptive feature fusion uses the complementarity to train a powerful fusion classifier. MF imitates the centralized decision-making process of these pathologists. We used the MF-OMKT model to classify breast cancer histopathological images (BreakHis dataset) into benign and malignant as well as eight subtypes. The accuracy of our model reaches the range of [99.27 %, 99.84 %] for binary classification. And that for multi-class classification reaches the range of [96.14 %, 97.53 %]. Additionally, MF-OMKT is applied to the classification of skin cancer images (ISIC 2018 dataset) and achieves an accuracy of 94.90 %. MF-OMKT is an effective and versatile framework for medical image classification.

Focus stacking in non-contact dermoscopy

Dermoscopy is the main tool for early detection of skin cancer. Non-contact dermoscopes often suffer from a small depth of field leading to images of skin topographies with regions that are not in focus. We aim to provide an easy-to-implement focus stacking-based approach to ensure all-in-focus images from a non-contact dermoscope. Further, we aim to extract additional information about the skin topography from the image stacks. The focus stacking procedure itself is implemented in a non-contact dermoscope with an electrically adjustable focus realized by using a tunable liquid lens. We show that all-in-focus imaging is possible for non-contact dermoscopy and deliver a method to extract topographical information for dermatologists from the acquired image stacks. Our finding indicate that the approach can be valuable for non-contact dermoscopic examination as well as for the early detection of skin diseases such as cancer as it possible to derive hyperfocus images and information on the skin topography. With this, we were able to develop a software for the acquisition of the raw image data and its processing into a high resolution hyperresolution dermoscopic image. In the next steps, we plan to apply the approach in the clinical environment for skin cancer diagnostics or imaging of inflammatory skin diseases.

A Hybrid System for Classification of Skin Cancer Images Using Artificial Neural Network and Support Vector Machine

A Hybrid System for Classification of Skin Cancer Images Using Artificial Neural Network and Support Vector Machine

Neural Networks-Based On-Site Dermatologic Diagnosis through Hyperspectral Epidermal Images.

Cancer originates from the uncontrolled growth of healthy cells into a mass. Chromophores, such as hemoglobin and melanin, characterize skin spectral properties, allowing the classification of lesions into different etiologies. Hyperspectral imaging systems gather skin-reflected and transmitted light into several wavelength ranges of the electromagnetic spectrum, enabling potential skin-lesion differentiation through machine learning algorithms. Challenged by data availability and tiny inter and intra-tumoral variability, here we introduce a pipeline based on deep neural networks to diagnose hyperspectral skin cancer images, targeting a handheld device equipped with a low-power graphical processing unit for routine clinical testing. Enhanced by data augmentation, transfer learning, and hyperparameter tuning, the proposed architectures aim to meet and improve the well-known dermatologist-level detection performances concerning both benign-malignant and multiclass classification tasks, being able to diagnose hyperspectral data considering real-time constraints. Experiments show 87% sensitivity and 88% specificity for benign-malignant classification and specificity above 80% for the multiclass scenario. AUC measurements suggest classification performance improvement above 90% with adequate thresholding. Concerning binary segmentation, we measured skin DICE and IOU higher than 90%. We estimated 1.21 s, at most, consuming 5 Watts to segment the epidermal lesions with the U-Net++ architecture, meeting the imposed time limit. Hence, we can diagnose hyperspectral epidermal data assuming real-time constraints.

Assessing the Generalizability of Deep Learning Models Trained on Standardized and Nonstandardized Images and Their Performance Against Teledermatologists: Retrospective Comparative Study.

Convolutional neural networks (CNNs) are a type of artificial intelligence that shows promise as a diagnostic aid for skin cancer. However, the majority are trained using retrospective image data sets with varying image capture standardization. The aim of our study was to use CNN models with the same architecture-trained on image sets acquired with either the same image capture device and technique (standardized) or with varied devices and capture techniques (nonstandardized)-and test variability in performance when classifying skin cancer images in different populations. In all, 3 CNNs with the same architecture were trained. CNN nonstandardized (CNN-NS) was trained on 25,331 images taken from the International Skin Imaging Collaboration (ISIC) using different image capture devices. CNN standardized (CNN-S) was trained on 177,475 MoleMap images taken with the same capture device, and CNN standardized number 2 (CNN-S2) was trained on a subset of 25,331 standardized MoleMap images (matched for number and classes of training images to CNN-NS). These 3 models were then tested on 3 external test sets: 569 Danish images, the publicly available ISIC 2020 data set consisting of 33,126 images, and The University of Queensland (UQ) data set of 422 images. Primary outcome measures were sensitivity, specificity, and area under the receiver operating characteristic curve (AUROC). Teledermatology assessments available for the Danish data set were used to determine model performance compared to teledermatologists. When tested on the 569 Danish images, CNN-S achieved an AUROC of 0.861 (95% CI 0.830-0.889) and CNN-S2 achieved an AUROC of 0.831 (95% CI 0.798-0.861; standardized models), with both outperforming CNN-NS (nonstandardized model; P=.001 and P=.009, respectively), which achieved an AUROC of 0.759 (95% CI 0.722-0.794). When tested on 2 additional data sets (ISIC 2020 and UQ), CNN-S (P<.001 and P<.001, respectively) and CNN-S2 (P=.08 and P=.35, respectively) still outperformed CNN-NS. When the CNNs were matched to the mean sensitivity and specificity of the teledermatologists on the Danish data set, the models' resultant sensitivities and specificities were surpassed by the teledermatologists. However, when compared to CNN-S, the differences were not statistically significant (sensitivity: P=.10; specificity: P=.053). Performance across all CNN models as well as teledermatologists was influenced by image quality. CNNs trained on standardized images had improved performance and, therefore, greater generalizability in skin cancer classification when applied to unseen data sets. This finding is an important consideration for future algorithm development, regulation, and approval.

An efficient image segmentation method for skin cancer imaging using improved golden jackal optimization algorithm

Skin cancer is one of the worst cancers nowadays that poses a severe threat to the health and safety of individuals. Therefore, skin cancer classification and early diagnosis are recommended to preserve human life. Multilevel thresholding image segmentation is well-known and influential technique for extracting regions of interest from skin cancer images to improve the classification process. Therefore, this paper proposes an efficient version of the recently developed golden jackal optimization (GJO) algorithm, the opposition-based golden jackal optimizer (IGJO). The IGJO algorithm is used to solve the multilevel thresholding problem using Otsu’s method as an objective function. The proposed algorithm is compared with seven other meta-heuristic algorithms: whale optimization algorithm, seagull optimization algorithm, salp swarm algorithm, Harris hawks optimization, artificial gorilla troops optimizer, marine predators’ algorithms, and original GJO algorithm. The performance of the proposed algorithm is evaluated using four popular performance measures: peak signal-to-noise ratio, structure similarity index, feature similarity index, and mean square error. Experimental results show that the proposed algorithm outperforms other alternative algorithms in terms of PSNR, SSIM, FSIM, and MSE segmentation metrics and effectively resolves the segmentation problem.

Detection and segmentation of melanoma skin cancer in dermoscopy images using modified Alexnet convolutional neural network‐morphological methodology

SummaryMelanoma is most vicious and dangerous type of skin cancer that its early detection can save patients' lives. Computer‐aided methods can be used for this early detection with acceptable performance. In this article, the melanoma skin cancer dermoscopy images are detected and cancer regions are segmented using the proposed modified AlexNet convolutional neural network‐morphological segmentation (CNN‐MS) method. This proposed work consists of enhancement stage, feature matrix construction stage, CNN classification stage, and segmentation stage. In enhancement stage, the skin pixels are contrast enhanced by histogram equalization technique and then non‐sub sampled contourlet transform (NSCT) is applied on the enhanced skin image to obtain the decomposed coefficients. Further, local ternary pattern (LTP) features are computed from the enhanced image and the feature matrix (FM) is constructed by integrating the NSCT coefficients and the LTP features. This constructed FM is fed to the CNN model for the classification of Melanoma skin cancer images from the normal skin images. Finally, morphological functions are applied on the classified melanoma skin image to segment the cancer regions. The performance of this developed model for skin cancer detection is analyzed on international skin imaging collaboration (ISIC) dataset images and achieves 98.11% of Se, 98.5% of Sp, 99.11% of Acc, and 0.96 of MCC. Also, the performance of this developed model for skin cancer detection is analyzed on SIIM‐ISIC dataset images and achieves 98.04% Se, 98.46% Sp, 99.12% Acc, and 0.97 MCC.