Skin Cancer Detection System Research Articles

FusionEXNet: an interpretable fused deep learning model for skin cancer detection

Skin cancer poses a significant burden on mankind and healthcare systems globally, necessitating the development of effective diagnostic and treatment strategies. This paper introduces FusionEXNet, an innovative and interpretable fused deep-learning model for skin cancer detection. FusionEXNet leverages the strengths of EfficientNetV2S and XceptionNet architectures to extract robust features from dermoscopic images, achieving superior performance compared to individual models. While XceptionNet and EfficientNetV2S attained accuracies of 88.82% and 88.01%, respectively, FusionEXNet surpassed them with an impressive accuracy of 90.83%. To enhance model interpretability, Explainable Artificial Intelligence (XAI) techniques, such as SmoothGrad and Faster Score-CAM, are integrated, providing valuable insights into the decision-making process. The model was trained and evaluated using the extensive HAM10000 dataset, consisting of over 10,000 high-resolution images across seven skin lesion categories. The proposed FusionEXNet model offers a reliable, accurate, and interpretable system for skin cancer detection, contributing to improved patient outcomes and more efficient diagnostic processes. This study underscores the potential of combining advanced CNN architectures with XAI methods to create powerful tools for dermatological diagnostics.

An intelligent skin cancer detection system using two-level multi-column convolutional neural network architecture

An intelligent skin cancer detection system using two-level multi-column convolutional neural network architecture

CACBL-Net: a lightweight skin cancer detection system for portable diagnostic devices using deep learning based channel attention and adaptive class balanced focal loss function

CACBL-Net: a lightweight skin cancer detection system for portable diagnostic devices using deep learning based channel attention and adaptive class balanced focal loss function

Investigating Skin Cancer Diagnosis Using a Webcam-based Microcontroller System

Skin cancer can spread fast to nearby tissue and other parts of the human body if it's not diagnosed early. Most are curable only if skin cancer is found and treated in the early stages. Therefore, it's essential to seek a casual way of early diagnosis. This paper assesses a prototype system for skin cancer detection using an Arduino with an ArduCam Mega 5MP, benchmarked against smartphone diagnosis. Bandpass filters capture skin images at red (650 nm), green (532 nm), and blue (450 nm) wavelengths, measuring reflectance values. The approach aims to quantitatively determine skin melanin, oxyhemoglobin, and deoxyhemoglobin levels, aiding in various skin lesions' diagnosis. Evaluation involves comparing pixel reflectance values of images taken by smartphones and the prototype using a 3D mesh grid. Applying the modified Lambert-Beer law to reflectance values of moles, pimples, scars, scabs, and traces predicts relative levels of skin components. The system shows an 87% match with the smartphone standard, demonstrating high reliability. Further study might be needed to clarify the confirmation with clinical cases.

Multimodal ensemble neural network system for skin cancer detection on heterogeneous dermatological data

Multimodal ensemble neural network system for skin cancer detection on heterogeneous dermatological data

A computer aided system for skin cancer detection based on Developed version of the Archimedes Optimization algorithm

In recent years, skin cancer has been recognized as the most dangerous and common type of cancer in humans. Melanoma is a common skin cancer, and the diagnosis of melanoma in the early stages of the disease can significantly prevent death from this deadly skin cancer. Providing a method that facilitates the diagnosis of melanoma in the early stages is very useful and valuable. The current paper proposes a new methodology for the best diagnosis of melanoma cancer using dermoscopic images. The proposed method begins with a normalization of scaling the data to a standard range and a histogram equalization to enhance the quality of the input images. Then, some different features based on the Gray-Level Co-occurrence Matrix (GLCM) are extracted from the image. GLCM features capture the spatial distribution and correlation of the pixel intensities, which reflect the texture information of the images. For reducing the complexity of the method, minimum features have been selected using a newly Developed version of Archimedes Optimization Algorithm (DAOA). Then, the selected features are classified by a Support Vector Machine (SVM) to distinguish between benign and malignant lesions. The proposed method is applied to the American Cancer Society (ACS) dataset, which consists of 68 pairs of TLM and XLM images with a size of 180×180 pixels. The results have been compared with five different methods based on five performance indicators: precision, sensitivity, accuracy, specificity, and F-measure. The results indicate that the presented approach gives a proper efficiency for the diagnosis of the melanoma. The proposed method achieves the highest values for all the performance indicators among the compared methods. The proposed method achieves an accuracy of 88 %, a sensitivity of 96 %, a specificity of 81 %, a precision of 97 %, and an F-measure of 97 % for the diagnosis of melanoma.

An Integrated Ensemble Network Model for Skin Abnormality Detection with Combined Textural Features.

Melanoma is the most lethal of all skin cancers. This necessitates the need for a machine learning-driven skin cancer detection system to help medical professionals with early detection. We propose an integrated multi-modal ensemble framework that combines deep convolution neural representations with extracted lesion characteristics and patient meta-data. This study intends to integrate transfer-learned image features, global and local textural information, and patient data using a custom generator to diagnose skin cancer accurately. The architecture combines multiple models in a weighted ensemble strategy, which was trained and validated on specific and distinct datasets, namely, HAM10000, BCN20000 + MSK, and the ISIC2020 challenge datasets. They were evaluated on the mean values of precision, recall or sensitivity, specificity, and balanced accuracy metrics. Sensitivity and specificity play a major role in diagnostics. The model achieved sensitivities of 94.15%, 86.69%, and 86.48% and specificity of 99.24%, 97.73%, and 98.51% for each dataset, respectively. Additionally, the accuracy on the malignant classes of the three datasets was 94%, 87.33%, and 89%, which is significantly higher than the physician recognition rate. The results demonstrate that our weighted voting integrated ensemble strategy outperforms existing models and could serve as an initial diagnostic tool for skin cancer.

Skin Melanoma Cancer Detection and Classification using Machine Learning

Skin cancer is a common and potentially life-threatening disease that affects millions of people worldwide. Early detection and accurate classification of skin lesions are critical for effective therapy and improved patient outcomes. In recent years, advances in machine learning and computer vision techniques have shown promising results in automating skin cancer detection and classification. The goal of this project is to develop an automated system for skin cancer detection and classification using machine learning algorithms. The proposed system uses a dataset of dermatoscopic images collected from different sources covering different types of skin lesions, including malignant melanoma, basal cell carcinoma, and squamous cell carcinoma. The project includes several main stages. First, preprocessing techniques including noise reduction, normalization, and feature extraction are used to improve image quality. Next, a comprehensive set of features such as color, texture, and portrait features are extracted from the preprocessed images. These features are input to various machine learning models, including Convolutional Neural Networks (CNNs), Support Vector Machines (SVMs) and Random Forests.

SKIN CANCER IMAGE DETECTION SYSTEM USING THE CONVOLUTIONAL NEURAL NETWORK MODEL

The development of science and technology (IPTEK) in the current era is growing very rapidly in various fields such as industry, education, especially the health sector. Many technologies can be used, one of which is artificial intelligence technology. This study aims to detect skin cancer images using CNN so that they can be efficient and precise. This research method uses the convolutional neural network (CNN) method, namely image processing, the development of a multilayer perceptron (MLP), in which the neurons of the data are propagated in two dimensions. Because this method has very high accuracy compared to the fuzzy k-nearest neighbors. The results of this study are that there are 7 classes of skin cancer images including actinic keratosis, basal cell carcinoma, dermatofibroma, benign keratosis, melanocytic nevi, vascular lesions and melanoma. From the results of testing the 7 classes using the convolutional neural network (CNN) method with a very high accuracy rate of 99%, 96%, 98%, 99%, 100%, 99% and 96%, respectively. With the conclusion that using the convolutional neural network (CNN) method produces an average accuracy of 98% compared to the Mobilnetv2, Resnet50 and VGG16 models, which means that the CNN model is proven to be more accurate. So it is hoped that this detection system can be applied as a skin cancer detection system for the world of health.

Benign and Malignant Skin Lesions: Dielectric Characterization, Modelling and Analysis in Frequency Band 1 to 14 GHz.

This paper aims to characterize Non-Melanoma malignancies and their corresponding benign conditions in ex-vivo/in-vivo tissue environments to study the feasibility of microwave techniques for skin cancer detection. The dielectric dataset is developed across the frequency band 1 to 14 GHz using Keysight slim-form and RG405 probe characterization systems. The acquired reflection data captured by the systems is converted to dielectric values using the Open-Water-Short and Open-Water-Liquid calibration methods, respectively. Furthermore, the impact of anaesthesia application during skin excision procedure on ex-vivo dielectric data is investigated. The observations suggest that the dielectric properties (DPs) of excised skin lesions may not accurately represent actual tissue properties as they vary significantly (Dielectric Constant Contrast = 30.7%, Loss-Factor Contrast = 66.6%) compared to pre-excision conditions. In-vivo dielectric data analysis indicates that when compared to healthy skin, malignant Basal Cell Carcinoma presents increased DPs (dielectric constant & loss factor) of (24.8 & 38.6 %), respectively. On the other hand, for malignant Squamous Cell Carcinoma and pre-malignant Actinic Keratosis, the measured results show decreased DPs (dielectric constant & loss factor) accordingly by (19.4 & 18.2 %) and (19.2 & 27.9 %). The corresponding benign lesions have less than 13 % dielectric contrast compared to healthy skin across the tested band. The significant contrasts between in-vivo healthy and cancerous skin DPs strongly suggest the viability of the microwave band for skin cancer detection. The research finding of this study would be critical in developing a portable electromagnetic system for skin cancer detection.

Enhanced Cuckoo Search Optimization Technique for Skin Cancer Diagnosis Application

Skin cancer segmentation is a critical task in a clinical decision support system for skin cancer detection. The suggested enhanced cuckoo search based optimization model will be used to evaluate several metrics in the skin cancer picture segmentation process. Because time and resources are always limited, the proposed enhanced cuckoo search optimization algorithm is one of the most effective strategies for dealing with global optimization difficulties. One of the most significant requirements is to design optimal solutions to optimize their use. There is no particular technique that can answer all optimization issues. The proposed enhanced cuckoo search optimization method indicates a constructive precision for skin cancer over with all image segmentation in computerized diagnosis. The accuracy of the proposed enhanced cuckoo search based optimization for melanoma has increased with a 23% to 29% improvement than other optimization algorithm. The total sensitivity and specificity attained in the proposed system are 99.56% and 99.73% respectively. The proposed method outperforms by offering accuracy of 99.26% in comparisons to other conventional methods. The proposed enhanced optimization technique achieved 98.75%, 98.96% for Dice and Jaccard coefficient. The model trained using the suggested measure outperforms those trained using the conventional method in the segmentation of skin cancer picture data.

Skin cancer recognition using SVM image processing technique

According to some estimates, skin cancer is the leading cause of death for people in the modern period. Although it can happen anywhere on the body, the majority of the time, this sort of cancer targets particular body regions that are more prone to being exposed to light. Skin cells proliferate in an erratic or patchy manner as a symptom. The majority of skin cancers can be treated if they are discovered early. Therefore, a patient’s life can be saved by promptly and precisely diagnosing skin cancer. Modern technology has made it feasible to detect skin cancer in its earliest stages. Skin cancer can be diagnosed systematically using the biopsy procedure (1). Skin cells are removed and supplied as a sample, following which they are evaluated in several laboratories. It’s an extremely unpleasant and time-consuming process. For primitive detection of skin cancer disease, we proposed a skin cancer detection system based on support vector machine (SVM). It is more helpful to patients. Various methods of image processing and the supervised learning algorithm called SVM are used in the identification process. In particular, epiluminescence microscopy is utilized using an image and several preprocessing techniques which are used in the reduction of sound artifacts and improve the quality of images. Segmentation is done by using certain thresholding techniques like Otsu. The gray level co-occurrence matrix technique must be used to remove certain image features. These characteristics are fed into the classifier as input. The supervised learning model called SVM is used to distinguish data sets. It determines whether a picture is cancerous or not.

Efficient and Low-Cost Skin Cancer Detection System Implementation with a Comparative Study Between Traditional and CNN-Based Models

Medical image classification is an essential task in the field of combining medical applications with Artificial Intelligence. This study is carried out to introduce an accurate, precise method for skin cancer recognition. This research investigates the performance of classifying skin cancer dataset HAM10000 using ResNet50, MobileNet, and the traditional Support Vector Machines (SVM) model. The dataset combines seven cancer types: Actinic Keratosis, Basal Cell Carcinoma, Benign Keratosis, Dermatofibroma, Melanoma, Melanocytic Nevus, and Vascular Lesion. The SVM classifier is designed to employ a Histogram of Oriented Gradient (HOG) features with Principle Component Analysis (PCA). Moreover, the Synthetic Minority Oversampling Technique is used to balance the dataset. Additionally, six conventional machine learning (ML) methods are used to compare the results with the calculation of precision, recall, F1 Score, and accuracy. The results confirm that the SVM method outperforms the other algorithms with an accuracy of 99.15%. The novelty contribution of this research activity is mainly based on the development of a high accuracy, low computational complex machine method for skin cancer types recognition in the domain of medical image classification.

Skin Cancer Detection Based on Deep Learning.

The conventional procedure of skin-related disease detection is a visual inspection by a dermatologist or a primary care clinician, using a dermatoscope. The suspected patients with early signs of skin cancer are referred for biopsy and histopathological examination to ensure the correct diagnosis and the best treatment. Recent advancements in deep convolutional neural networks (CNNs) have achieved excellent performance in automated skin cancer classification with accuracy similar to that of dermatologists. However, such improvements are yet to bring about a clinically trusted and popular system for skin cancer detection. This study aimed to propose viable deep learning (DL) based method for the detection of skin cancer in lesion images, to help physicians in diagnosis. In this analytical study, a novel DL based model was proposed, in which other than the lesion image, the patient's data, including the anatomical site of the lesion, age, and gender were used as the model input to predict the type of the lesion. An Inception-ResNet-v2 CNN pretrained for object recognition was employed in the proposed model. Based on the results, the proposed method achieved promising performance for various skin conditions, and also using the patient's metadata in addition to the lesion image for classification improved the classification accuracy by at least 5% in all cases investigated. On a dataset of 57536 dermoscopic images, the proposed approach achieved an accuracy of 89.3%±1.1% in the discrimination of 4 major skin conditions and 94.5%±0.9% in the classification of benign vs. malignant lesions. The promising results highlight the efficacy of the proposed approach and indicate that the inclusion of the patient's metadata with the lesion image can enhance the skin cancer detection performance.

Malignant Melanoma Classification using GLCM and SVM

In today’s modern world, Skin cancer is the most common cause of death amongst humans. Skin cancer is abnormal growth of skin cells most often develops on body exposed to the sunlight, but can occur anywhere on the body. Most of the skin cancers are curable at early stages. So, an early and fast detection of skin cancer can save the patient’s life. With the new technology, early detection of skin cancer is possible at initial stage. Formal method for diagnosis skin cancer detection is Biopsy method. It is done by removing skin cells and that sample goes to various laboratory testing. It is painful and time-consuming process. We have proposed skin cancer detection system using Support Vector Machine (SVM) for early detection of skin cancer disease. It is more advantageous to patients. The diagnosing methodology uses Image processing methods and SVM algorithm. The dermoscopy image of skin cancer is taken and it goes under various pre-processing technique for noise removal and image enhancement. Then the image is undergone to segmentation using Thresholding method. Some features of image have to be extracted using GLCM methodology. These features are given as the input to classifier. Support vector Machine (SVM) is used for classification purpose. It classifies the given image into cancerous or non-cancerous.

Automated Detection of Nonmelanoma Skin Cancer Based on Deep Convolutional Neural Network.

One of the deadliest diseases is skin cancer, especially melanoma. The high resemblance between different skin lesions such as melanoma and nevus in the skin colour images increases the complexity of identification and diagnosis. An efficient automated early detection system for skin cancer detection is essential in order to save human lives, time, and effort. In this article, an automatic skin lesion classification system using a pretrained deep learning network and transfer learning was proposed. Here, diagnosing melanoma in premature stages, a detection system has been designed which contains the following digital image processing techniques. First, dermoscopy images of skin were taken and this is subjected to a preprocessing step for noise removal and postprocessing step for image enhancement. Then the processed image undergoes image segmentation using k-means and modified k-means clustering. Second, using feature extraction technology, Gray Level Co-occurrence Matrix, and first order statistics, characteristics are extracted. Features are selected on the basis of Harris Hawks optimization (HHO). Finally, various classifiers are used for predicting the stages and efficiency of the proposed work. Measures of well-known quantities, sensitivity, precision, accuracy, and specificity are used in assessing the efficiency of the suggested method, where higher values were obtained. Compared to the current methods, it is found that the classification rate exceeded the output of the current approaches in the performance of the proposed approach.

Skin Cancer Recognition Using SVM Image Processing Technique

According to some estimates, skin cancer is the leading cause of death for people in the modern period. Although it can happen anywhere on the body, the majority of the time, this sort of cancer targets particular body regions that are more prone to being exposed to light. Skin cells proliferate in an erratic or patchy manner as a symptom. The majority of skin cancers can be treated if they are discovered early. Therefore, a patient’s life can be saved by promptly and precisely diagnosing skin cancer. Modern technology has made it feasible to detect skin cancer in its earliest stages. Skin cancer can be diagnosed systematically using the biopsy procedure [1]. Skin cells are removed and supplied as a sample, following which they are evaluated in several laboratories. It’s an extremely unpleasant and time-consuming process. For primitive detection of skin cancer disease, we proposed a skin cancer detection system based on support vector machine (SVM). It is more helpful to patients. Various methods of image processing and the supervised learning algorithm called SVM are used in the identification process. In particular, epiluminescence microscopy is utilized using an image and several preprocessing techniques which are used in the reduction of sound artifacts and improve the quality of images. Segmentation is done by using certain thresholding techniqueslikeOtsu.Thegraylevelco-occurrencematrixtechniquemustbeusedtoremovecertainimagefeatures. These characteristics are fed into the classifier as input. The supervised learning model called SVM is used to distinguish data sets. It determines whether a picture is cancerous or not.

Comparative Study of Single Biological Neuron with an Artificial Neuro

A number of artificial neural models have been presented in the literature in an effort to suggest a more accurate representation of a single biological neuron. There are numerous publications on synthetic neurons that attemptedtoreplicateasinglebiologicalneuron,however,suchmodelswereunabletogeneratethespikingpatterns of a real biological neuron. Therefore, there is still scope to design and research improved spiking neural models that more accurately reflect the functions of a biological neuron. This motivation drives extensive modification of an artificial neuron model to produce the spike patterns of a real biological neuron. The modified single artificial neuronmodel thathasbeen proposedexhibitsthefunctions ofabiological neuron.It’sstill crucialtomodel spiking bio-neuronbehavior.Modelingaspikingbio-neuronisstillanimportantexerciseinviewofpossibleapplicationsof the underlying features in the areas of neuromorphic engineering, cognitive radio, and spiking neural networks.

Identification of Risk of Occurring Skin Cancer (Melanoma) Using Convolutional Neural Network (CNN)

Skin cancer is one of the most common malignancy in human, has drawn attention from researchers around the world. As skin cancer can turn into fatal if not treated in its earliest stages, the necessity of devising automated skin cancer diagnosis system that can automatically detect skin cancer efficiently in its earliest stage in a faster process than traditional one is of crucial importance. In this paper, a computer aided skin cancer diagnosis system based Convolutional Neural Network method has been shown. Our proposed system consists of five stages namely image acquisition, image preprocessing, image segmentation, feature extraction and classification We remove hair any noise from the images using dull then use median filter to smoothen the images. Next, k-means algorithm was applied for image segmentation on the preprocessed images. Finally, the segmented images were fed into CNN model for feature extraction and classification. The developed system can classify benign and melanoma type skin cancers from Dermoscopic images as accurate as 80.47%. While developing the skin cancer detection system, we compare accuracy score of other models such as Artificial Neural Network (ANN), K-Nearest Neighbor (KNN) and Random Forest with our proposed system. The proposed method has been tested on ‘ISIC Challenge 2016’ test dataset and an accuracy rate of 80.47% was obtained for accurately classifying benign and malignant skin lesions by our proposed model.

Deep learning enhances polarization speckle for in vivo skin cancer detection

Polarization speckle is a growing research field, especially for the purposes of biomedical imaging and diagnostics. The statistical uniformity of speckle creates novel opportunities for AI methods to analyze speckle patterns, as they are difficult for a human to interpret. We employed deep learning and traditional machine learning methods (Support Vector Machine, K Nearest Neighbor, and Random Forests) to analyze polarization speckle images generated from the general categories of malignant and benign lesions, a classification task previously found to be very difficult. Their performance in classifying the patterns were compared both to each other and to the previous statistical methods of speckle analysis. A collection of 122 malignant and 196 benign skin lesion speckle images were augmented for deep learning using patch cropping, an advantageous method given the patterns’ statistical homogeneity. The machine learning technique performed with a diagnostic accuracy of less than 65%, a result comparable to those of previous statistical methods, despite the fact that the same machine learning technique could achieve a high 90% accuracy in the simpler classification task of differentiating malignant melanoma and the benign lookalike seborrheic keratosis. However, ResNet, our chosen deep learning architecture, achieved the best performance of 82% diagnostic accuracy in the general classification task of malignant and benign. These results show that deep learning extracts previously hidden information from polarization speckle, which further develops towards a rapid, real-time, analysis technique for an automatic skin cancer detection system.