International Skin Imaging Collaboration Research Articles

Automated Prediction of Malignant Melanoma using Two-Stage Convolutional Neural Network.

A skin lesion refers to an area of the skin that exhibits anomalous growth or distinctive visual characteristics compared to the surrounding skin. Benign skin lesions are noncancerous and generally pose no threat. These irregular skin growths can vary in appearance. On the other hand, malignant skin lesions correspond to skin cancer, which happens to be the most prevalent form of cancer in the United States. Skin cancer involves the unusual proliferation of skin cells anywhere on the body. The conventional method for detecting skin cancer is relatively more painful. This work involves the automated prediction of skin cancer and its types using two stage Convolutional Neural Network (CNN). The first stage of CNN extracts low level features and second stage extracts high level features. Feature selection is done using these two CNN and ABCD (Asymmetry, Border irregularity, Colour variation, and Diameter) technique. The features extracted from the two CNNs are fused with ABCD features and fed into classifiers for the final prediction. The classifiers employed in this work include ensemble learning methods such as gradient boosting and XG boost, as well as machine learning classifiers like decision trees and logistic regression. This methodology is evaluated using the International Skin Imaging Collaboration (ISIC) 2018 and 2019 dataset. As a result, the first stage CNN which is used for creation of new dataset achieved an accuracy of 97.92%. Second stage CNN which is used for feature selection achieved an accuracy of 98.86%. Classification results are obtained for both with and without fusion of features. Therefore, two stage prediction model achieved better results with feature fusion.

NTSM: a non-salient target segmentation model for oral mucosal diseases

BackgroundOral mucosal diseases are similar to the surrounding normal tissues, i.e., their many non-salient features, which poses a challenge for accurate segmentation lesions. Additionally, high-precision large models generate too many parameters, which puts pressure on storage and makes it difficult to deploy on portable devices.MethodsTo address these issues, we design a non-salient target segmentation model (NTSM) to improve segmentation performance while reducing the number of parameters. The NTSM includes a difference association (DA) module and multiple feature hierarchy pyramid attention (FHPA) modules. The DA module enhances feature differences at different levels to learn local context information and extend the segmentation mask to potentially similar areas. It also learns logical semantic relationship information through different receptive fields to determine the actual lesions and further elevates the segmentation performance of non-salient lesions. The FHPA module extracts pathological information from different views by performing the hadamard product attention (HPA) operation on input features, which reduces the number of parameters.ResultsThe experimental results on the oral mucosal diseases (OMD) dataset and international skin imaging collaboration (ISIC) dataset demonstrate that our model outperforms existing state-of-the-art methods. Compared with the nnU-Net backbone, our model has 43.20% fewer parameters while still achieving a 3.14% increase in the Dice score.ConclusionsOur model has high segmentation accuracy on non-salient areas of oral mucosal diseases and can effectively reduce resource consumption.

Lightweight semantic segmentation network for tumor cell nuclei and skin lesion.

In the field of medical image segmentation, achieving fast and accurate semantic segmentation of tumor cell nuclei and skin lesions is of significant importance. However, the considerable variations in skin lesion forms and cell types pose challenges to attaining high network accuracy and robustness. Additionally, as network depth increases, the growing parameter size and computational complexity make practical implementation difficult. To address these issues, this paper proposes MD-UNet, a fast cell nucleus segmentation network that integrates Tokenized Multi-Layer Perceptron modules, attention mechanisms, and Inception structures. Firstly, tokenized MLP modules are employed to label and project convolutional features, reducing computational complexity. Secondly, the paper introduces Depthwise Attention blocks and Multi-layer Feature Extraction modules. The Depthwise Attention blocks eliminate irrelevant and noisy responses from coarse-scale extracted information, serving as alternatives to skip connections in the UNet architecture. The Multi-layer Feature Extraction modules capture a wider range of high-level and low-level semantic features during decoding and facilitate feature fusion. The proposed MD-UNet approach is evaluated on two datasets: the International Skin Imaging Collaboration (ISIC2018) dataset and the PanNuke dataset. The experimental results demonstrate that MD-UNet achieves the best performance on both datasets.

LAMA: Lesion-Aware Mixup Augmentation for Skin Lesion Segmentation.

Deep learning can exceed dermatologists' diagnostic accuracy in experimental image environments. However, inaccurate segmentation of images with multiple skin lesions can be seen with current methods. Thus, information present in multiple-lesion images, available to specialists, is not retrievable by machine learning. While skin lesion images generally capture a single lesion, there may be cases in which a patient's skin variation may be identified as skin lesions, leading to multiple false positive segmentations in a single image. Conversely, image segmentation methods may find only one region and may not capture multiple lesions in an image. To remedy these problems, we propose a novel and effective data augmentation technique for skin lesion segmentation in dermoscopic images with multiple lesions. The lesion-aware mixup augmentation (LAMA) method generates a synthetic multi-lesion image by mixing two or more lesion images from the training set. We used the publicly available International Skin Imaging Collaboration (ISIC) 2017 Challenge skin lesion segmentation dataset to train the deep neural network with the proposed LAMA method. As none of the previous skin lesion datasets (including ISIC 2017) has considered multiple lesions per image, we created a new multi-lesion (MuLe) segmentation dataset utilizing publicly available ISIC 2020 skin lesion images with multiple lesions per image. MuLe was used as a test set to evaluate the effectiveness of the proposed method. Our test results show that the proposed method improved the Jaccard score 8.3% from 0.687 to 0.744 and the Dice score 5% from 0.7923 to 0.8321 over a baseline model on MuLe test images. On the single-lesion ISIC 2017 test images, LAMA improved the baseline model's segmentation performance by 0.08%, raising the Jaccard score from 0.7947 to 0.8013 and the Dice score 0.6% from 0.8714 to 0.8766. The experimental results showed that LAMA improved the segmentation accuracy on both single-lesion and multi-lesion dermoscopic images. The proposed LAMA technique warrants further study.

Melanoma skin cancer detection using mask-RCNN with modified GRU model.

Introduction: Melanoma Skin Cancer (MSC) is a type of cancer in the human body; therefore, early disease diagnosis is essential for reducing the mortality rate. However, dermoscopic image analysis poses challenges due to factors such as color illumination, light reflections, and the varying sizes and shapes of lesions. To overcome these challenges, an automated framework is proposed in this manuscript. Methods: Initially, dermoscopic images are acquired from two online benchmark datasets: International Skin Imaging Collaboration (ISIC) 2020 and Human against Machine (HAM) 10000. Subsequently, a normalization technique is employed on the dermoscopic images to decrease noise impact, outliers, and variations in the pixels. Furthermore, cancerous regions in the pre-processed images are segmented utilizing the mask-faster Region based Convolutional Neural Network (RCNN) model. The mask-RCNN model offers precise pixellevel segmentation by accurately delineating object boundaries. From the partitioned cancerous regions, discriminative feature vectors are extracted by applying three pre-trained CNN models, namely ResNeXt101, Xception, and InceptionV3. These feature vectors are passed into the modified Gated Recurrent Unit (GRU) model for MSC classification. In the modified GRU model, a swish-Rectified Linear Unit (ReLU) activation function is incorporated that efficiently stabilizes the learning process with better convergence rate during training. Results and discussion: The empirical investigation demonstrate that the modified GRU model attained an accuracy of 99.95% and 99.98% on the ISIC 2020 and HAM 10000 datasets, where the obtained results surpass the conventional detection models.

An internet of health things-driven skin cancer classification using progressive cyclical convolutional neural network with ResNexT50 optimized by exponential particle swarm optimization

Skin cancer has become more common in the last few decades according to reports by the World Health Organization. Currently, 1,32,000 melanoma skin cancer cases and around three million non-melanoma cases are reported annually worldwide. Early skin cancer identification with classification allows for effective diagnosis and therapy for patients. Therefore, an internet of health things-driven deep learning approach for identification with classification of skin cancer based on Progressive Cyclical Convolutional Neural Network with ResNexT50 transfer learning optimized by Exponential Particle Swarm Optimization (IoHT-SC-PCCNN-RNT-EXPSO) is proposed in this manuscript. Here, the input skin cancer images are amassed from international Skin Imaging Collaboration (ISIC) image archive dataset. The Dynamic Temporal Filter (DTF) is used for removing the noise, and also enhances the skin cancer images quality. In which, PCCNN does not adopt any optimization methods for determining the optimum parameter to offer accurate skin cancer classification. So, Exponential Particle Swarm Optimization (EXPSO) is proposed for optimizing PCCNN to help it precisely classify the skin cancer. The proposed IoHT-SC-PCCNN-RNT-EXPSO method is implemented in MATLAB. The metrics, like accuracy, recall, precision, f1-Score, specificity, computation time, error rate are evaluated to evaluate the effectiveness of the proposed technique. The proposed MSCC-DI-SDRN-JSOA demonstrated improved specificity with percentages of 27.35 %, 28.64 %, and 24.38 %. Additionally, it showed lower computation time by 37.28 %, 29.39 %, and 28.44 %, and higher accuracy by 30.50 %, 32.39 %, and 31.54 % compared to the existing methods, like IoHT-SC-CNN, IoHT-SC-KNN and IoHT-SC-DWNN-EPO respectively.

A novel end-to-end deep convolutional neural network based skin lesion classification framework

Background:Skin diseases are reported to contribute 1.79% of the global burden of disease. The accurate diagnosis of specific skin diseases is known to be a challenging task due, in part, to variations in skin tone, texture, body hair, etc. Classification of skin lesions using machine learning is a demanding task, due to the varying shapes, sizes, colors, and vague boundaries of some lesions. The use of deep learning for the classification of skin lesion images has been shown to help diagnose the disease at its early stages. Recent studies have demonstrated that these models perform well in skin detection tasks, with high accuracy and efficiency. Objective:Our paper proposes an end-to-end framework for skin lesion classification, and our contributions are two-fold. Firstly, two fundamentally different algorithms are proposed for segmenting and extracting features from images during image preprocessing. Secondly, we present a deep convolutional neural network model, S-MobileNet that aims to classify 7 different types of skin lesions. Methods:We used the HAM10000 dataset, which consists of 10000 dermatoscopic images from different populations and is publicly available through the International Skin Imaging Collaboration (ISIC) Archive. The image data was preprocessed to make it suitable for modeling. Exploratory data analysis (EDA) was performed to understand various attributes and their relationships within the dataset. A modified version of a Gaussian filtering algorithm and SFTA was applied for image segmentation and feature extraction. The processed dataset was then fed into the S-MobileNet model. This model was designed to be lightweight and was analyzed in three dimensions: using the Relu Activation function, the Mish activation function, and applying compression at intermediary layers. In addition, an alternative approach for compressing layers in the S-MobileNet architecture was applied to ensure a lightweight model that does not compromise on performance. Results:The model was trained using several experiments and assessed using various performance measures, including, loss, accuracy, precision, and the F1-score. Our results demonstrate an improvement in model performance when applying a preprocessing technique. The Mish activation function was shown to outperform Relu. Further, the classification accuracy of the compressed S-MobileNet was shown to outperform S-MobileNet. Conclusions:To conclude, our findings have shown that our proposed deep learning-based S-MobileNet model is the optimal approach for classifying skin lesion images in the HAM10000 dataset. In the future, our approach could be adapted and applied to other datasets, and validated to develop a skin lesion framework that can be utilized in real-time.

Stand-Alone Melanoma Diagnostic System Using the Raspberry PI 4

Skin cancer, in general, is a growing threat to human health. Melanoma skin cancer is one of the most severe types of skin cancer in humans. In the initial stages, melanoma affects the skin in general, and it may develop and spread to other parts of the human body in its advanced stages. Early detection can reduce its severity and improve treatment outcomes. In this study, the proposed system includes image processing techniques and feature extraction by combining Local Binary Pattern (LBP) and Gray Level Co-occurrence Matrix (GLCM), in addition to enhancing the extracted features with the diameter feature. A Support Vector Machine (SVM) model with a radial basis function (RBF) kernel was employed to train and predict the results of the test data on the Raspberry Pi 4 platform. The available International Skin Imaging Collaboration (ISIC) dataset of skin images was used in the training and testing of this system. The test results showed that the proposed system achieves high specificity (99.35%), medium sensitivity (75.35%), and comprehensive accuracy (93.71%).

Classifying Real-world Macroscopic Images in the Primary-Secondary Care Interface using Transfer Learning: Implications for Development of Artificial Intelligence Solutions using Non- dermoscopic Images.

Application of deep learning to diagnostic dermatology has been the subject of numerous studies, with some reporting skin lesion classification performance on curated datasets comparable to that of experienced dermatologists. Most skin disease images encountered in clinical settings are macroscopic, without dermoscopic information, and exhibit considerable variability. Further research is necessary to determine the generalisability of deep learning algorithms across populations and acquisition settings. We assessed the extent to which deep learning can generalise to non-dermoscopic datasets acquired at the primary-secondary care interface in the National Health Service (NHS). We explored how to obtain clinically satisfactory performance on non-standardised, real-world local data without availability of large diagnostically labelled local datasets. We measured the impact of pre-training deep learning algorithms on external, public-domain datasets. Diagnostic macroscopic image datasets were created from previous referrals from primary to secondary care. These included 2213 images referred from primary care practitioners in NHS Tayside and 1510 images from NHS Forth Valley acquired by medical photographers. Two further datasets with identical diagnostic labels were obtained from public domain sources, namely the International Skin Imaging Collaboration (ISIC) dermoscopic dataset and the SD-260 non-dermoscopic dataset. Deep learning algorithms, specifically SWIN transformers and an EfficientNets, were trained using data from each of these datasets. Algorithms were also fine-tuned on images from the NHS datasets after pre-training on different data combinations, including the larger public domain datasets. ROC curves and area under such curves (AUC) were used to assess performance. SWIN transformers tested on Forth Valley data had AUCs of 0.85 and 0.89 when trained on SD-260 and Forth Valley data, respectively. Training on SD-260 followed by fine-tuning of Forth Valley data gave an AUC of 0.91. Similar effects of pre-training and tuning on local data were observed using Tayside data, and EfficientNets. Pre-training on the larger dermoscopic image dataset (ISIC-2019) provided no additional benefit. Pre-training on public macroscopic images, followed by tuning to local data, gave promising results. Further improvements are needed to afford deployment in real clinical pathways. Larger datasets local to the target domain might be expected to yield further improved performance.

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

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.

Özel Derin Konvolüsyonel Sinir Ağı Kullanarak Cilt Kanseri Tanıma

Skin cancer is a common form of cancer that affects millions of people worldwide. Early detection and accurate diagnosis of skin cancer are crucial for effective treatment and management of the disease. There has been a growing interest in using deep learning techniques and computer vision algorithms to develop automated skin cancer detection systems in recent years. Among these techniques, convolutional neural networks (CNN) have shown remarkable performance in detecting and classifying skin lesions. This paper presents a comprehensive study using CNN and deep learning techniques for skin cancer detection using the International Skin Imaging Collaboration (ISIC) dataset. The proposed architecture is a compact deep CNN that is trained using a dataset of benign and malignant skin lesion images. The proposed architecture has achieved 84.8% accuracy, 83.8% TPR, 83.7% TNR, 81.6% F1-score and 80.5% precision for performance evaluation. The experimental results show promising results for the accurate and efficient detection of skin cancer, which has the potential to improve the diagnosis and treatment of this life-threatening disease.

Comparison of humans versus mobile phone-powered artificial intelligence for the diagnosis and management of pigmented skin cancer in secondary care: a multicentre, prospective, diagnostic, clinical trial

Diagnosis of skin cancer requires medical expertise, which is scarce. Mobile phone-powered artificial intelligence (AI) could aid diagnosis, but it is unclear how this technology performs in a clinical scenario. Our primary aim was to test in the clinic whether there was equivalence between AI algorithms and clinicians for the diagnosis and management of pigmented skin lesions. In this multicentre, prospective, diagnostic, clinical trial, we included specialist and novice clinicians and patients from two tertiary referral centres in Australia and Austria. Specialists had a specialist medical qualification related to diagnosing and managing pigmented skin lesions, whereas novices were dermatology junior doctors or registrars in trainee positions who had experience in examining and managing these lesions. Eligible patients were aged 18-99 years and had a modified Fitzpatrick I-III skin type; those in the diagnostic trial were undergoing routine excision or biopsy of one or more suspicious pigmented skin lesions bigger than 3 mm in the longest diameter, and those in the management trial had baseline total-body photographs taken within 1-4 years. We used two mobile phone-powered AI instruments incorporating a simple optical attachment: a new 7-class AI algorithm and the International Skin Imaging Collaboration (ISIC) AI algorithm, which was previously tested in a large online reader study. The reference standard for excised lesions in the diagnostic trial was histopathological examination; in the management trial, the reference standard was a descending hierarchy based on histopathological examination, comparison of baseline total-body photographs, digital monitoring, and telediagnosis. The main outcome of this study was to compare the accuracy of expert and novice diagnostic and management decisions with the two AI instruments. Possible decisions in the management trial were dismissal, biopsy, or 3-month monitoring. Decisions to monitor were considered equivalent to dismissal (scenario A) or biopsy of malignant lesions (scenario B). The trial was registered at the Australian New Zealand Clinical Trials Registry ACTRN12620000695909 (Universal trial number U1111-1251-8995). The diagnostic study included 172 suspicious pigmented lesions (84 malignant) from 124 patients and the management study included 5696 pigmented lesions (18 malignant) from the whole body of 66 high-risk patients. The diagnoses of the 7-class AI algorithm were equivalent to the specialists' diagnoses (absolute accuracy difference 1·2% [95% CI -6·9 to 9·2]) and significantly superior to the novices' ones (21·5% [13·1 to 30·0]). The diagnoses of the ISIC AI algorithm were significantly inferior to the specialists' diagnoses (-11·6% [-20·3 to -3·0]) but significantly superior to the novices' ones (8·7% [-0·5 to 18·0]). The best 7-class management AI was significantly inferior to specialists' management (absolute accuracy difference in correct management decision -0·5% [95% CI -0·7 to -0·2] in scenario A and -0·4% [-0·8 to -0·05] in scenario B). Compared with the novices' management, the 7-class management AI was significantly inferior (-0·4% [-0·6 to -0·2]) in scenario A but significantly superior (0·4% [0·0 to 0·9]) in scenario B. The mobile phone-powered AI technology is simple, practical, and accurate for the diagnosis of suspicious pigmented skin cancer in patients presenting to a specialist setting, although its usage for management decisions requires more careful execution. An AI algorithm that was superior in experimental studies was significantly inferior to specialists in a real-world scenario, suggesting that caution is needed when extrapolating results of experimental studies to clinical practice. MetaOptima Technology.

Classification of skin lesion using deep convolutional neural network by applying transfer learning

<p>The early and accurate diagnosis of skin cancer is crucial for improving patient outcomes and reducing the need for invasive biopsies. This study proposes a deep learning model for classifying skin malignancy using transfer learning and data augmentation techniques to address limitations observed in previous models and enhance diagnostic accuracy. The approach involves applying transfer learning to a pre-trained ResNet152 architecture using tensorflow and keras. Data augmentation techniques are employed on a dataset consisting of 10,015 skin lesion images obtained from the international skin imaging collaboration (ISIC) 2018 challenge, which encompasses diverse lesion types, sizes, and colors, posing a challenging classification task. Binary cross-entropy serves as the loss function, and the Adam optimizer is utilized for training the model. The results demonstrate a specificity of 87.42% and an F1 score of 0.854, outperforming other models in the field. These statistical findings highlight the effectiveness of transfer learning and data augmentation techniques in improving the accuracy of skin cancer diagnosis. The novelty of this study lies in the combination of transfer learning and data augmentation methods to enhance diagnostic accuracy. However, it is important to acknowledge the limitations of this study, including the necessity for further investigation to evaluate the clinical practicality of the model and address potential biases. Future research could explore the application of this model in a clinical setting and the development of models for detecting other types of skin lesions. In conclusion, the proposed deep learning model based on the ResNet152 architecture showcases promising results in the classification of skin lesions, demonstrating its potential for accurate skin cancer diagnosis. With further research and improvement, these models have the potential to revolutionize healthcare, improving patient outcomes, reducing healthcare costs, and increasing accessibility to screening and diagnosis, particularly for underserved populations.</p>

Skin lesion image segmentation by using backchannel filling CNN and level sets

Pigmented skin lesion image segmentation is a key step in the computer-aided diagnosis of melanoma. This image segmentation task is also difficult due to blurred skin lesion boundaries, uneven color, and diverse textures. To improve the accuracy of skin lesion image segmentation, this paper proposes an image segmentation method that combines convolutional neural networks (CNN) and level sets. First, a backchannel filling (BCF) method is proposed. Through the first forward propagation of the CNN, the target position estimated by the CNN is backfilled into the position prior channel. Then, end-to-end deep learning models based on BCF multibranch encoding–decoding CNN (BCF-CNN) and level sets are built. The initial level set and driving energy are predicted through the second forward propagation of the BCF-CNN and then input into the level set segmentation model to complete the evolution. Additionally, a learning algorithm that combines a joint BCF-CNN and a level set is designed to train the segmentation model. The experimental results of the proposed algorithm are compared with those of other state-of-the-art algorithms on both the International Skin Imaging Collaboration (ISIC) 2017 and 2016 skin lesion challenge datasets, demonstrating that the proposed algorithm outperforms the others in terms of accuracy with a Jaccard index of approximately 77.0% and 85.1% on the ISIC 2017 and 2016 skin lesion challenge datasets, respectively.

Diagnostic Accuracy of Hyperpigmented Microcircles in Dermatoscopy of Non-Facial Non-Acral Melanomas: A Pilot Retrospective Study using a Public Image Database

Background: Grey perifollicular circles are a dermatoscopic clue to melanoma, especially in facial skin. So far, no other adnexal clues than follicular have been investigated in this diagnosis. Objectives: The study aimed to analyse the prevalence of hyperpigmented periadnexal microcircles (HMs) in melanoma and its common simulators at non-facial non-acral sites, analyse the relation between the presence of HM, regression and hypopigmentation, and evaluate the diagnostic accuracy of this structure in melanoma. Methods: International Skin Imaging Collaboration (69,445 images) was searched in April 2020 for the pathology-confirmed dermatoscopic images with metadata including sex, age bin, and declared non-acral non-facial anatomic site. The final study sample (5,408 images, 1,326 of which were melanomas) was evaluated by expert dermatoscopist blinded to the diagnosis and labelled for the presence of ≥3 HM distributed centrally (cHM) or peripherally (pHM), hypopigmentation, and classic dermatoscopic regression structures. A subset of 40 images was labelled by 7 raters (2 residents, 5 experts) to assess interobserver agreement. We compared the presence of pHM with the presence of regression as well as performed a set of independent χ² tests to evaluate the discriminatory power and its fragility. Performance of the models was assessed using measures of discrimination and calibration. Results: HM were significantly more prevalent in melanomas than in non-melanomas and nevi. Fair/good interobserver agreement for HM was reached for all the raters, and moderate/good for experts only (single rater/average, respectively). Regardless of regression/hypopigmentation status, pHM were significantly more common in melanoma than in non-melanomas or nevi and were observed significantly more often in melanomas on sun-damaged skin (upper extremity, posterior torso). No significant differences between the groups were found for cHM. pHM proved a high odds ratio in the tests as to the classical indicators such as classic dermatoscopic regression structures. Conclusion: pHM could be considered a novel dermatoscopic clue to melanoma.

A Hybrid Model for Classification of Skin Cancer Images After Segmentation

For dermatoscopic skin lesion images, deep learning-based algorithms, particularly convolutional neural networks (CNN), have demonstrated good classification and segmentation capabilities. The impact of utilizing lesion segmentation data on classification performance, however, is still up for being subject to discussion. Being driven in this direction, in this work we propose a hybrid deep learning-based model to classify the skin cancer using segmented images. In the first stage, a fully convolutional encoder–decoder network (FCEDN) is employed to segment the skin cancer image and then in the second phase, a CNN is applied on the segmented images for classification. As the model’s success depends on the hyper-parameters it uses and fine-tuning these hyper-parameters by hand is time-consuming, so in this study the hyper-parameters of the hybrid model are optimized by utilizing an exponential neighborhood gray wolf optimization (ENGWO) technique. Extensive experiments are carried out using the International Skin Imaging Collaboration (ISIC) 2016 and ISIC 2017 datasets to show the efficacy of the model. The suggested model has been evaluated on both balanced and unbalanced datasets. With the balanced dataset, the proposed hybrid model achieves training accuracy up to 99.98%, validation accuracy up to 92.13% and testing accuracy up to 89.75%. It is evident from the findings that the proposed hybrid model outperforms previous known models in a competitive manner over balanced data.

Generative adversarial networks based skin lesion segmentation

Skin cancer is a serious condition that requires accurate diagnosis and treatment. One way to assist clinicians in this task is using computer-aided diagnosis tools that automatically segment skin lesions from dermoscopic images. We propose a novel adversarial learning-based framework called Efficient-GAN (EGAN) that uses an unsupervised generative network to generate accurate lesion masks. It consists of a generator module with a top-down squeeze excitation-based compound scaled path, an asymmetric lateral connection-based bottom-up path, and a discriminator module that distinguishes between original and synthetic masks. A morphology-based smoothing loss is also implemented to encourage the network to create smooth semantic boundaries of lesions. The framework is evaluated on the International Skin Imaging Collaboration Lesion Dataset. It outperforms the current state-of-the-art skin lesion segmentation approaches with a Dice coefficient, Jaccard similarity, and accuracy of 90.1%, 83.6%, and 94.5%, respectively. We also design a lightweight segmentation framework called Mobile-GAN (MGAN) that achieves comparable performance as EGAN but with an order of magnitude lower number of training parameters, thus resulting in faster inference times for low compute resource settings.

Ψnet: a parallel network with deeply coupled spatial and squeezed features for segmentation of medical images

AbstractThe process of delineating a region of interest or an object in an image is called image segmentation. Efficient medical image segmentation can contribute to the early diagnosis of illnesses, and accordingly, patient survival possibilities can be enhanced. Recently, deep semantic segmentation methods demonstrate state-of-the-art (SOTA) performance. In this paper, we propose a generic novel deep medical segmentation framework, denoted as Ψnet. This model introduces a novel parallel encoder-decoder structure that draws up the power of triple U-Nets. In addition, a multi-stage squeezed-based encoder is employed to raise the network sensitivity to relevant features and suppress the unnecessary ones. Moreover, atrous spatial pyramid pooling (ASPP) is employed in the bottleneck of the network which helps in gathering more effective features during the training process, hence better performance can be achieved in segmentation tasks. We have evaluated the proposed Ψnet on a variety of challengeable segmentation tasks, including colonoscopy, microscopy, and dermoscopy images. The employed datasets include Data Science Bowl (DSB) 2018 challenge as a cell nuclei segmentation from microscopy images, International Skin Imaging Collaboration (ISIC) 2017 and 2018 as skin lesion segmentation from dermoscopy images, Kvasir-SEG, CVC-ClinicDB, ETIS-LaribDB, and CVC-ColonDB as polyp segmentation from colonoscopy images. Despite the variety in the employed datasets, the proposed model, with extensive experiments, demonstrates superior performance to advanced SOTA models, such as U-Net, ResUNet, Recurrent Residual U-Net, ResUNet++, UNet++, BCDU-Net, MultiResUNet, MCGU-Net, FRCU-Net, Attention Deeplabv3p, DDANet, ColonSegNet, and TMD-Unet.

SKIN CANCER CLASSIFICATION: A DEEP LEARNING APPROACH

Skin diseases are common in human beings because of significant changes in surrounding environments.The most of these diseases are curable if diagnosed at initial stages. Therefore, earlydiagnosis can spare people’s precious lives. To address these issues, we proposed a novel model based on deep learning to diagnose the skin disease at a preliminary stage using classification. The developedmodel correctly identifies six different skin diseases namely, actinic keratosis, benign keratosis, melanoma,basal cell carcinoma, insects bite and skin acne. Several state-of-the-art algorithms are examinedon benchmark datasets (International Skin Imaging Collaboration (ISIC) 2019 dataset andUCI Data Center) for accuracy, precision, recall and F1-score metrics. The results show that convolutionalneural network (CNN) has a distinct superiority over its peers with accuracy rate of97%, precision 91%, recall 91% and F1-score 91%. This system will provide skin care handlingservices that are precise and accurate and help the dermatologist in early diagnosis of skin diseases

An automated hybrid attention based deep convolutional capsule with weighted autoencoder approach for skin cancer classification

ABSTRACT Skin cancer is a serious cancer caused by the uncontrollable growth of damaged DNA that leads to death. It is essential to identify the disease at the initial stage and eliminate it from spreading. Hence, this research introduces an automated hybrid deep learning (DL) technique for improving the accuracy of cancer diagnostic systems. In the pre-processing, histogram stretching, colour constancy, hair removal and noise elimination process are undertaken. Then, the Adaptive fuzzy c-means clustering (AFC) is introduced for segmenting the tumour portion. Then, the feature extraction and classification stage is performed using an attention-based deep convolutional capsule weighted auto-encoder classifier network (A-DCCN-WAE) technique. For experimentation, the dataset is collected from International Skin Imaging Collaboration (ISIC) 2019 dataset and is implemented in the PYTHON platform. The proposed method obtains an accuracy of 97%, Precision of 95.6%, F-measure of 97.2%, Mathew's correlation coefficient (MCC) of 90.6% and specificity of 96.9%.