International Skin Imaging Collaboration Research Articles

Classification of Skin Lesions Using Weighted Majority Voting Ensemble Deep Learning

The conventional dermatology practice of performing noninvasive screening tests to detect skin diseases is a source of escapable diagnostic inaccuracies. Literature suggests that automated diagnosis is essential for improving diagnostic accuracies in medical fields such as dermatology, mammography, and colonography. Classification is an essential component of an assisted automation process that is rapidly gaining attention in the discipline of artificial intelligence for successful diagnosis, treatment, and recovery of patients. However, classifying skin lesions into multiple classes is challenging for most machine learning algorithms, especially for extremely imbalanced training datasets. This study proposes a novel ensemble deep learning algorithm based on the residual network with the next dimension and the dual path network with confidence preservation to improve the classification performance of skin lesions. The distributed computing paradigm was applied in the proposed algorithm to speed up the inference process by a factor of 0.25 for a faster classification of skin lesions. The algorithm was experimentally compared with 16 deep learning and 12 ensemble deep learning algorithms to establish its discriminating prowess. The experimental comparison was based on dermoscopic images congregated from the publicly available international skin imaging collaboration databases. We propitiously recorded up to 82.52% average sensitivity, 99.00% average specificity, 98.54% average balanced accuracy, and 92.84% multiclass accuracy without prior segmentation of skin lesions to outstrip numerous state-of-the-art deep learning algorithms investigated.

Theory-Based Approaches to Support Dermoscopic Image Interpretation Education: A Review of the Literature.

Efficient interpretation of dermoscopic images relies on pattern recognition, and the development of expert-level proficiency typically requires extensive training and years of practice. While traditional methods of transferring knowledge have proven effective, technological advances may significantly improve upon these strategies and better equip dermoscopy learners with the pattern recognition skills required for real-world practice. A narrative review of the literature was performed to explore emerging directions in medical image interpretation education that may enhance dermoscopy education. This article represents the first of a two-part review series on this topic. To promote innovation in dermoscopy education, the International Skin Imaging Collaborative (ISIC) assembled a 12-member Education Working Group that comprises international dermoscopy experts and educational scientists. Based on a preliminary literature review and their experiences as educators, the group developed and refined a list of innovative approaches through multiple rounds of discussion and feedback. For each approach, literature searches were performed for relevant articles. Through a consensus-based approach, the group identified a number of emerging directions in image interpretation education. The following theory-based approaches will be discussed in this first part: whole-task learning, microlearning, perceptual learning, and adaptive learning. Compared to traditional methods, these theory-based approaches may enhance dermoscopy education by making learning more engaging and interactive and reducing the amount of time required to develop expert-level pattern recognition skills. Further exploration is needed to determine how these approaches can be seamlessly and successfully integrated to optimize dermoscopy education.

Application of a parallel branches network based on Transformer for skin melanoma segmentation

Cutaneous malignant melanoma is a common malignant tumor. Accurate segmentation of the lesion area is extremely important for early diagnosis of the disease. In order to achieve more effective and accurate segmentation of skin lesions, a parallel network architecture based on Transformer is proposed in this paper. This network is composed of two parallel branches: the former is the newly constructed multiple residual frequency channel attention network (MFC), and the latter is the visual transformer network (ViT). First, in the MFC network branch, the multiple residual module and the frequency channel attention module (FCA) module are fused to improve the robustness of the network and enhance the capability of extracting image detailed features. Second, in the ViT network branch, multiple head self-attention (MSA) in Transformer is used to preserve the global features of the image. Finally, the feature information extracted from the two branches are combined in parallel to realize image segmentation more effectively. To verify the proposed algorithm, we conducted experiments on the dermoscopy image dataset published by the International Skin Imaging Collaboration (ISIC) in 2018. The results show that the intersection-over-union (IoU) and Dice coefficients of the proposed algorithm achieve 90.15% and 94.82%, respectively, which are better than the latest skin melanoma segmentation networks. Therefore, the proposed network can better segment the lesion area and provide dermatologists with more accurate lesion data.

Classification of Skin Cancer with Deep Transfer Learning Method

Skin cancer is a serious health hazard for human society. This disease is developed when the pigments that produce skin color become cancerous. Dermatologists face difficulties in diagnosing skin cancer since many skin cancer colors seem identical. As a result, early diagnosis of lesions (the foundation of skin cancer) is very crucial and beneficial in totally curing skin cancer patients. Significant progress has been made in creating automated methods with the development of artificial intelligence (AI) technologies to aid dermatologists in the identification of skin cancer. The widespread acceptance of AI-powered technologies has enabled the use of a massive collection of photos of lesions and benign sores authorized by histology. This research compares six alternative transfer learning networks (deep networks) for skin cancer classification using the International Skin Imaging Collaboration (ISIC) dataset. DenseNet, Xception, InceptionResNetV2, ResNet50, and MobileNet were the transfer learning networks employed in the investigation which were successful in different studies recently. To compensate for the imbalance in the ISIC dataset, the photos of classes with low frequencies are augmented. The results show that augmentation is appropriate for the classification success, with high classification accuracies and F-scores with decreased false negatives. With an accuracy rate of 98.35%, modified DenseNet121 was the most successful model against the rest of the transfer learning nets utilized in the study.

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.

Skin cancers image classification using transformation and first order statistic features with artificial neural network classifier

&lt;span&gt;Skin cancer is one of the most dangerous types of cancer. Some types of this cancer lead to death, so cancer must be discovered and indexed to avoid its spread through initial detection in the impulsive stage. This paper deals with the detection and indexing of different types of melanomas using an artificial neural network (ANN) depending on the international skin imaging collaboration (ISIC) 2018 dataset that was used. The pre-processing is the most important part because it formulates an image by insolated the cancer part from the skin image. It consists of four stages, removable, cropping, thinning, and normalization. This phase has been used to eliminate all the undesirable hair particles on the image lesion. The cropped image transforms into frequency domain coefficients using discrete cosine transform (DCT), discrete wavelet transform (DWT), and gradient transform for sub-band images to extract its feature. The statistical feature extraction is implemented to minimize the size of data for ANN training. The experimental analysis used dataset ISIC 2018 consisting of seven different types of dermoscopic images (this paper deals with four types only). For classification purposes, ANN was implemented and the accuracy obtained is about 88.98% for DWT, 85.44% for sub-band DCT, and 76.07% for sub-band gradient transform.&lt;/span&gt;

Improving Skin Color Diversity in Cancer Detection: Deep Learning Approach.

The lack of dark skin images in pathologic skin lesions in dermatology resources hinders the accurate diagnosis of skin lesions in people of color. Artificial intelligence applications have further disadvantaged people of color because those applications are mainly trained with light skin color images. The aim of this study is to develop a deep learning approach that generates realistic images of darker skin colors to improve dermatology data diversity for various malignant and benign lesions. We collected skin clinical images for common malignant and benign skin conditions from DermNet NZ, the International Skin Imaging Collaboration, and Dermatology Atlas. Two deep learning methods, style transfer (ST) and deep blending (DB), were utilized to generate images with darker skin colors using the lighter skin images. The generated images were evaluated quantitively and qualitatively. Furthermore, a convolutional neural network (CNN) was trained using the generated images to assess the latter's effect on skin lesion classification accuracy. Image quality assessment showed that the ST method outperformed DB, as the former achieved a lower loss of realism score of 0.23 (95% CI 0.19-0.27) compared to 0.63 (95% CI 0.59-0.67) for the DB method. In addition, ST achieved a higher disease presentation with a similarity score of 0.44 (95% CI 0.40-0.49) compared to 0.17 (95% CI 0.14-0.21) for the DB method. The qualitative assessment completed on masked participants indicated that ST-generated images exhibited high realism, whereby 62.2% (1511/2430) of the votes for the generated images were classified as real. Eight dermatologists correctly diagnosed the lesions in the generated images with an average rate of 0.75 (360 correct diagnoses out of 480) for several malignant and benign lesions. Finally, the classification accuracy and the area under the curve (AUC) of the model when considering the generated images were 0.76 (95% CI 0.72-0.79) and 0.72 (95% CI 0.67-0.77), respectively, compared to the accuracy of 0.56 (95% CI 0.52-0.60) and AUC of 0.63 (95% CI 0.58-0.68) for the model without considering the generated images. Deep learning approaches can generate realistic skin lesion images that improve the skin color diversity of dermatology atlases. The diversified image bank, utilized herein to train a CNN, demonstrates the potential of developing generalizable artificial intelligence skin cancer diagnosis applications. RR2-10.2196/34896.

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.

Cancer-Net SCa: tailored deep neural network designs for detection of skin cancer from dermoscopy images

BackgroundSkin cancer continues to be the most frequently diagnosed form of cancer in the U.S., with not only significant effects on health and well-being but also significant economic costs associated with treatment. A crucial step to the treatment and management of skin cancer is effective early detection with key screening approaches such as dermoscopy examinations, leading to stronger recovery prognoses. Motivated by the advances of deep learning and inspired by the open source initiatives in the research community, in this study we introduce Cancer-Net SCa, a suite of deep neural network designs tailored for the detection of skin cancer from dermoscopy images that is open source and available to the general public. To the best of the authors’ knowledge, Cancer-Net SCa comprises the first machine-driven design of deep neural network architectures tailored specifically for skin cancer detection, one of which leverages attention condensers for an efficient self-attention design.ResultsWe investigate and audit the behaviour of Cancer-Net SCa in a responsible and transparent manner through explainability-driven performance validation. All the proposed designs achieved improved accuracy when compared to the ResNet-50 architecture while also achieving significantly reduced architectural and computational complexity. In addition, when evaluating the decision making process of the networks, it can be seen that diagnostically relevant critical factors are leveraged rather than irrelevant visual indicators and imaging artifacts.ConclusionThe proposed Cancer-Net SCa designs achieve strong skin cancer detection performance on the International Skin Imaging Collaboration (ISIC) dataset, while providing a strong balance between computation and architectural efficiency and accuracy. While Cancer-Net SCa is not a production-ready screening solution, the hope is that the release of Cancer-Net SCa in open source, open access form will encourage researchers, clinicians, and citizen data scientists alike to leverage and build upon them.

A Machine Vision Approach for Classification of Skin Cancer Using Hybrid Texture Features.

The main purpose of this study is to observe the importance of machine vision (MV) approach for the identification of five types of skin cancers, namely, actinic-keratosis, benign, solar-lentigo, malignant, and nevus. The 1000 (200 × 5) benchmark image datasets of skin cancers are collected from the International Skin Imaging Collaboration (ISIC). The acquired ISIC image datasets were transformed into texture feature dataset that was a combination of first-order histogram and gray level co-occurrence matrix (GLCM) features. For the skin cancer image, a total of 137,400 (229 × 3 x 200) texture features were acquired on three nonover-lapping regions of interest (ROIs). Principal component analysis (PCA) clustering approach was employed for reducing the dimension of feature dataset. Each image acquired twenty most discriminate features based on two different approaches of statistical features such as average correlation coefficient plus probability of error (ACC + POE) and Fisher (Fis). Furthermore, a correlation-based feature selection (CFS) approach was employed for feature reduction, and optimized 12 features were acquired. Furthermore, a classification algorithm naive bayes (NB), Bayes Net (BN), LMT Tree, and multilayer perception (MLP) using 10 K-fold cross-validation approach were employed on optimized feature datasets and the overall accuracy achieved by MLP is 97.1333%.

Dense and shuffle attention U‐Net for automatic skin lesion segmentation

AbstractThe segmentation of skin lesions is a critical step in the detection of skin cancer. However, it is also difficult because of unclear boundaries, various size and shape of skin lesions, the appearance of interference objects and different backgrounds in dermoscopic images. This study presents proposed multiple attention‐based methods based on U‐net architecture. At first, dense attention gates (DAG) are proposed to obtain the focus area of the feature map by capturing information through extern feature maps. Then, to extend the capability of capturing feature relationships of the DAG module. We introduced The shuffle attention module which can fuse two self‐attention modules in a lightweight yet effective way. According to the experiments conducted on International Skin Imaging Collaboration (ISIC) 2017 and PH2 datasets, the proposed model can generate satisfactory segmentation results and great capability in practical computer‐aided diagnosis systems.

Classification of Skin Cancer Images Using Convolutional Neural Networks

Skin cancer is the most common human malignancy according to American Cancer Society. It is primarily diagnosed visually, starting with an initial clinical screening and followed potentially by dermoscopic (related to skin) analysis, a biopsy and histopathological examination. Skin cancer occurs when errors (mutations) occur in the DNA of skin cells. The mutations cause cells to grow out of control and form a mass of cancer cells. The aim of this study was to try to classify images of skin lesions with the help of Convolutional Neural Networks. Deep neural networks show humongous potential for image classification while taking into account the large variability exhibited by the environment. Here, we trained images on the basis of pixel values and classified them on the basis of disease labels. The dataset was acquired from an Open Source Kaggle Repository (Kaggle Dataset) which itself was acquired from ISIC (International Skin Imaging Collaboration) archive. The training was performed on multiple models accompanied with Transfer Learning. The highest model accuracy achieved was over 86.65%. The dataset used is publicly available to ensure credibility and reproducibility of the aforementioned result.

Automatic lesion segmentation using atrous convolutional deep neural networks in dermoscopic skin cancer images

BackgroundMelanoma is the most dangerous and aggressive form among skin cancers, exhibiting a high mortality rate worldwide. Biopsy and histopathological analysis are standard procedures for skin cancer detection and prevention in clinical settings. A significant step in the diagnosis process is the deep understanding of the patterns, size, color, and structure of lesions based on images obtained through dermatoscopes for the infected area. However, the manual segmentation of the lesion region is time-consuming because the lesion evolves and changes its shape over time, making its prediction challenging. Moreover, it is challenging to predict melanoma at the initial stage as it closely resembles other skin cancer types that are not malignant as melanoma; thus, automatic segmentation techniques are required to design a computer-aided system for accurate and timely detection.MethodsAs deep learning approaches have gained significant attention in recent years due to their remarkable performance, therefore, in this work, we proposed a novel design of a convolutional neural network (CNN) framework based on atrous convolutions for automatic lesion segmentation. This architecture is built based on the concept of atrous/dilated convolutions which are effective for semantic segmentation. A deep neural network is designed from scratch employing several building blocks consisting of convolutional, batch normalization, leakyReLU layer, and fine-tuned hyperparameters contributing altogether towards higher performance.ConclusionThe network was tested on three benchmark datasets provided by International Skin Imaging Collaboration (ISIC), i.e., ISIC 2016, ISIC 2017, and ISIC 2018. The experimental results showed that the proposed network achieved an average Jaccard index of 90.4% on ISIC 2016, 81.8% on ISIC 2017, and 89.1% on ISIC 2018 datasets, respectively which is recorded as higher than the top three winners of the ISIC challenge and other state-of-the-art methods. Also, the model successfully extracts lesions from the whole image in one pass in less time, requiring no pre-processing step. The conclusions yielded that network is accurate in performing lesion segmentation on adopted datasets.

Machine Learning Algorithm for Detection of Deadliest Forms of Skin Cancer

Skin cancer is one of the most growing types and dangerous cancer in the world. The early diagnosis of melanoma and other ski cancer is a critical issue for dermatologists. In this paper, we using Machine Learning Algorithm for Detection of Deadliest Forms of Skin Cancer. This project aims to develop a skin cancer detection ML Model which can classify the skin cancer types and help in early detection. The ML Model is developed in Dot Net (. Net). The model is developed and tested with different network architectures by varying the type of layers used to train the machine. Basically our model use DNN (Deep Neural Network) and ResNet50 for detection of skin cancer. The model will be tested and trained on the dataset collected from the International Skin Imaging Collaboration (ISIC)

Validation of artificial intelligence prediction models for skin cancer diagnosis using dermoscopy images: the 2019 International Skin Imaging Collaboration Grand Challenge

BackgroundPrevious studies of artificial intelligence (AI) applied to dermatology have shown AI to have higher diagnostic classification accuracy than expert dermatologists; however, these studies did not adequately assess clinically realistic scenarios, such as how AI systems behave when presented with images of disease categories that are not included in the training dataset or images drawn from statistical distributions with significant shifts from training distributions. We aimed to simulate these real-world scenarios and evaluate the effects of image source institution, diagnoses outside of the training set, and other image artifacts on classification accuracy, with the goal of informing clinicians and regulatory agencies about safety and real-world accuracy.MethodsWe designed a large dermoscopic image classification challenge to quantify the performance of machine learning algorithms for the task of skin cancer classification from dermoscopic images, and how this performance is affected by shifts in statistical distributions of data, disease categories not represented in training datasets, and imaging or lesion artifacts. Factors that might be beneficial to performance, such as clinical metadata and external training data collected by challenge participants, were also evaluated. 25 331 training images collected from two datasets (in Vienna [HAM10000] and Barcelona [BCN20000]) between Jan 1, 2000, and Dec 31, 2018, across eight skin diseases, were provided to challenge participants to design appropriate algorithms. The trained algorithms were then tested for balanced accuracy against the HAM10000 and BCN20000 test datasets and data from countries not included in the training dataset (Turkey, New Zealand, Sweden, and Argentina). Test datasets contained images of all diagnostic categories available in training plus other diagnoses not included in training data (not trained category). We compared the performance of the algorithms against that of 18 dermatologists in a simulated setting that reflected intended clinical use.Findings64 teams submitted 129 state-of-the-art algorithm predictions on a test set of 8238 images. The best performing algorithm achieved 58·8% balanced accuracy on the BCN20000 data, which was designed to better reflect realistic clinical scenarios, compared with 82·0% balanced accuracy on HAM10000, which was used in a previously published benchmark. Shifted statistical distributions and disease categories not included in training data contributed to decreases in accuracy. Image artifacts, including hair, pen markings, ulceration, and imaging source institution, decreased accuracy in a complex manner that varied based on the underlying diagnosis. When comparing algorithms to expert dermatologists (2460 ratings on 1269 images), algorithms performed better than experts in most categories, except for actinic keratoses (similar accuracy on average) and images from categories not included in training data (26% correct for experts vs 6% correct for algorithms, p<0·0001). For the top 25 submitted algorithms, 47·1% of the images from categories not included in training data were misclassified as malignant diagnoses, which would lead to a substantial number of unnecessary biopsies if current state-of-the-art AI technologies were clinically deployed.InterpretationWe have identified specific deficiencies and safety issues in AI diagnostic systems for skin cancer that should be addressed in future diagnostic evaluation protocols to improve safety and reliability in clinical practice.FundingMelanoma Research Alliance and La Marató de TV3.

From machine learning to deep learning: experimental comparison of machine learning and deep learning for skin cancer image segmentation

Skin lesion analysis is a tedious and challenging task, thus, in this research the suitability of employing machine learning or deep learning approaches for automatic lesion segmentation on dermoscopic skin cancer images is determined. The segmented region can assist clinical experts in understanding the complex lesion structure and internal pattern to find the correct skin cancer type for its early diagnosis and prevention. In this study, I present two methodologies for performing lesion segmentation: machine learning-based optimized K-means with Firefly Algorithm (FA) and Convolutional Neural Network (CNN). In the first model, the FA is hybridized with K-means clustering based on the novel average intensity fitness function to optimize the segmentation map. It is observed in the experimental results that the K-means algorithm may lead to poor results due to the wrong selection of initial centroid value, thus FA is hybridized into it to improve the performance. The second model is an enhanced encoder-decoder-based CNN framework implemented in an end-to-end fashion. These two models are compared to understand whether machine learning or deep learning is suitable to perform medical image segmentation based on a few performance metrics such as accuracy, Intersection over Union (IoU), and DICE index. These methods are evaluated and compared on two benchmark datasets provided by the International Skin Imaging Collaboration (ISIC) named ISIC 2016 [1] and ISIC 2017 [2]. Experimental results showed that the CNN model outperformed the machine learning model with an accuracy difference of 7.98% on ISIC 2016, and 7.32% on ISIC 2017. I concluded from the experimental findings that the deep learning model is more accurate and efficient in segmenting the lesion area as compared to the machine learning model. Thus, findings from this experimental work will be considered for the design of an automatic classification system by incorporating a deep learning-based segmentation approach as a pre-processing step.

Dermoscopic Image Classification with Neural Style Transfer

Skin cancer, the most commonly found human malignancy, is primarily diagnosed visually via dermoscopic analysis, biopsy and histopathological examination. However, unlike other types of cancer, automated image classification of skin lesions is deemed to be more challenging due to the irregularity and variability in the lesions’ appearances. In this work, we propose an adaptation of the Neural Style Transfer (NST) as a novel image pre-processing step for skin lesion classification problems. We represent each dermoscopic image as a style image and transfer the style of the lesion onto a homogeneous content image. This transfers the main variability of each lesion onto the same localized region, which allows us to integrate the generated images together and extract low-rank latent embeddings via tensor decomposition. We evaluated the performance of our model on competition data sets collected and pre-processed from the International Skin Imaging Collaboration (ISIC) database. We show that the classification performance based on the extracted tensor features using the style-transferred images significantly outperforms that of the raw images by more than 10%, and is also competitive with well-studied, pre-trained CNN models using transfer learning. Additionally, the tensor decomposition also affords clinical interpretations and insights by examining the images which correspond to the largest loadings in the top style embedding features as identified by the common supervised learning models.

LinkNet-B7: Noise Removal and Lesion Segmentation in Images of Skin Cancer

Skin cancer is common nowadays. Early diagnosis of skin cancer is essential to increase patients’ survival rate. In addition to traditional methods, computer-aided diagnosis is used in diagnosis of skin cancer. One of the benefits of this method is that it eliminates human error in cancer diagnosis. Skin images may contain noise such as like hair, ink spots, rulers, etc., in addition to the lesion. For this reason, noise removal is required. The noise reduction in lesion images can be referred to as noise removal. This phase is very important for the correct segmentation of the lesions. One of the most critical problems in using such automated methods is the inaccuracy in cancer diagnosis because noise removal and segmentation cannot be performed effectively. We have created a noise dataset (hair, rulers, ink spots, etc.) that includes 2500 images and masks. There is no such noise dataset in the literature. We used this dataset for noise removal in skin cancer images. Two datasets from the International Skin Imaging Collaboration (ISIC) and the PH2 were used in this study. In this study, a new approach called LinkNet-B7 for noise removal and segmentation of skin cancer images is presented. LinkNet-B7 is a LinkNet-based approach that uses EfficientNetB7 as the encoder. We used images with 16 slices. This way, we lose fewer pixel values. LinkNet-B7 has a 6% higher success rate than LinkNet with the same dataset and parameters. Training accuracy for noise removal and lesion segmentation was calculated to be 95.72% and 97.80%, respectively.

Multi-class skin lesion classification using prism- and segmentation-based fractal signatures

Today, due to technological advances, specialists can count on a wide range of computer-aided diagnostic applications. However, there are still significant challenges to overcome. That is the case when it comes to automating the classification of skin lesions. Amorphous pigmentation, fuzzy edges, unbalanced databases, unrepresentative minority classes, images of different sizes, and resolutions. Reproducibility of the models are examples that we face to develop computer-assisted diagnostic models. In this work, we tackle the problem of amorphous pigmentation lesions and fuzzy edges by proposing two new fractal signatures, which we call a fractal signature based on statistical prisms (SSPF) and a statistical fractal signature (SSTF). The methodologies presented in this work for the multi-class classification of skin lesions were evaluated using the International Skin Imaging Collaboration (ISIC) database from 2019 containing 25,331 images divided into eight highly unbalanced classes. The database was randomly divided into 80%–20% for the training and test datasets images, respectively. In that manner, could be assured the reproducibility of the models. The performance metrics reported for both the training and testing part are accuracy, sensitivity, specificity, and precision. In our methodology, each study case was repeated 30 times to avoid bias, according to the central limit theorem, and the mean ±1 standard deviation was reported. The results showed that it is imperative to have balanced databases and that the marked imbalance affects minority classes. All works must report the training performance and the test datasets to ensure the reproducibility of the models. We obtained that SSTF (the signature that combines the statistical prism-based fractal signature SSPF and SSF) can increase the classifier’s performance instead of the use of each fractal signature by itself. The methodology proposed using the SSTF with the LDA classifier is robust and reproducible for the simultaneous classification of 4 classes; we achieved 87% accuracy, 63% sensitivity, 89% specificity, and 65% precision. In the case of the simultaneous 7-class classification, the results were 88% accuracy, 41% sensitivity, 92% specificity, and 46% precision.

Melanoma Classification Using a Novel Deep Convolutional Neural Network with Dermoscopic Images.

Automatic melanoma detection from dermoscopic skin samples is a very challenging task. However, using a deep learning approach as a machine vision tool can overcome some challenges. This research proposes an automated melanoma classifier based on a deep convolutional neural network (DCNN) to accurately classify malignant vs. benign melanoma. The structure of the DCNN is carefully designed by organizing many layers that are responsible for extracting low to high-level features of the skin images in a unique fashion. Other vital criteria in the design of DCNN are the selection of multiple filters and their sizes, employing proper deep learning layers, choosing the depth of the network, and optimizing hyperparameters. The primary objective is to propose a lightweight and less complex DCNN than other state-of-the-art methods to classify melanoma skin cancer with high efficiency. For this study, dermoscopic images containing different cancer samples were obtained from the International Skin Imaging Collaboration datastores (ISIC 2016, ISIC2017, and ISIC 2020). We evaluated the model based on accuracy, precision, recall, specificity, and F1-score. The proposed DCNN classifier achieved accuracies of 81.41%, 88.23%, and 90.42% on the ISIC 2016, 2017, and 2020 datasets, respectively, demonstrating high performance compared with the other state-of-the-art networks. Therefore, this proposed approach could provide a less complex and advanced framework for automating the melanoma diagnostic process and expediting the identification process to save a life.