Deep learning for skin melanoma classification using dermoscopic images in different color spaces (original) (raw)
Related papers
Biomolecules, 2020
Recent studies have demonstrated the usefulness of convolutional neural networks (CNNs) to classify images of melanoma, with accuracies comparable to those achieved by dermatologists. However, the performance of a CNN trained with only clinical images of a pigmented skin lesion in a clinical image classification task, in competition with dermatologists, has not been reported to date. In this study, we extracted 5846 clinical images of pigmented skin lesions from 3551 patients. Pigmented skin lesions included malignant tumors (malignant melanoma and basal cell carcinoma) and benign tumors (nevus, seborrhoeic keratosis, senile lentigo, and hematoma/hemangioma). We created the test dataset by randomly selecting 666 patients out of them and picking one image per patient, and created the training dataset by giving bounding-box annotations to the rest of the images (4732 images, 2885 patients). Subsequently, we trained a faster, region-based CNN (FRCNN) with the training dataset and check...
IOSR Journal of Engineering (IOSRJEN), 2018
Melanoma is the most common type of skin cancer. At first, for the diagnosis of melanoma, clinical screening is performed and then diagnosis is made by clinical imaging. It is followed up by dermoscopic analysis, biopsy and histopathological examination. Early diagnosis is important in the treatment of melanoma. Automatic recognition of melanoma from dermoscopy images is a difficult task. Therefore, computer aided systems are recommended to reduce time ,cost and accuracy diagnosis. In this paper, a deep learning-based system is used to classify melanoma in color images taken from dermoscopy devices. With this system, differentiation from previous studies can be done with good accuracy without segmentation step and feature extraction. This system provides a significant advantage in hardware implementation. Because there are no pre-processing and segmentation steps. The International Skin Imaging Collaboration database for the designed system is used and includes 1483 training, 517 test data(ISIC). As a result of the classification of these data, the success rate is reached 86-85%.
Skin cancer classification computer system development with deep learning
2020
Melanoma is a deadly form of skin cancer that is often undiagnosed or misdiagnosed as a benign skin lesion. Its early detection is extremely important, since the life of patients with melanoma depends on accurate and early diagnosis of the disease. However, doctors often rely on personal experience and assess each patient's injuries based on a personal examination. Clinical studies allow us to get the accuracy of the diagnosis of melatoma from 65 to 80 percents, which was a good result for some time. However, modern research claims that the use of dermoscopic images in diagnosis significantly increases the accuracy of diagnosis of skin lesions. The visual differences between melanoma and benign skin lesions can be very small, making diagnosis difficult even for an expert doctor. Recent advances in the use of artificial intelligence methods in the analysis of medical images have made it possible to consider the development of intelligent medical diagnostic systems based on visualization as a very promising direction that will help the doctor in making more effective decisions about the health of patients and making a diagnosis at an early stage and in adverse conditions. In this paper, we propose an approach to solving the problem of classification of skin diseases, namely, melanoma at an early stage, based on deep learning. In particular, a solution to the problem of classification of a dermoscopic image containing either malignant or benign skin lesions is proposed. For this purpose, the deep neural network architecture was developed and applied to image processing. Computer experiments on the ISIC data set have shown that the proposed approach provides 92% accuracy on the test sample, which is significantly higher than other algorithms in this data set have shown.
Classification of melanoma skin cancer using deep learning approach
TELKOMNIKA Telecommunication Computing Electronics and Control, 2024
In this study, the authors propose a deep learning (DL) approach for classifying melanoma skin cancer (MSC). They introduce a convolution neural network (CNN) model that consists of 27 layers, which are carefully designed to extract features from skin lesion images and classify them into melanoma and non-melanoma classes. The proposed CNN model comprises multiple convolution layers that apply filters to the input image to extract features such as edges, shapes, and patterns. Batch normalization layers that normalize the output of the convolution layers to accelerate the learning process and prevent overfitting follow these convolution layers. The performance of the proposed CNN model was evaluated on publicly available datasets of skin lesion images, and the findings showed that it outperformed several state-of-the-art methods for melanoma classification. The authors also conducted ablation studies to analyze each layer's contribution to the model's overall performance. The proposed DL approach has the potential to assist dermatologists in the early detection of MSC, which can lead to treatment that is more effective and improves patient outcomes. It also demonstrates the effectiveness of DL techniques for medical image analysis and highlights the importance of carefully designing and optimizing CNN models for high performance. The accuracy of the proposed system is 99.99%.
Deep learning model to improve melanoma detection in people of color
Arab Journal of Basic and Applied Sciences, 2023
Melanoma is a type of skin cancer that is particularly dangerous to people with dark skin. This is due to the disease's late diagnosis and detection in people with dark skin. When melanoma is detected, the prognosis is often poor. Advancement in Artificial Intelligence (AI) technology and image classification has brought about tremendous progress and applications in medicine and diagnosis of skin cancer. Albeit, these techniques continue to produce unsatisfactory results when applied to people with dark skin. This work considered the trend in cancer detection using AI techniques. Dark skin melanoma clinical images were acquired and pre-processed to remove illumination and noise to aid the other stages such as segmentation and data augmentation. The acquired images were combined with a curated and augmented version of the Human Against Machines 10000 image (HAM10000) dataset and split into two classes: melanoma and non-melanoma. A pre-trained DenseNet121 was used as a base model for training and in addition, a transfer learning process was performed to exclude the top layer and fine-tune all the layers in the final Dense Block of the model pretrained on ImageNet. The model achieved an accuracy of 99% for melanoma detection in white skin color and 98% for dark skin. The results show that the proposed model is effective in detecting melanoma in skin.
A Novel Technique on Detect Melanoma in Dermoscopy Images By using Deep Learning
International Journal of Innovative Technology and Exploring Engineering
Melanoma is a typical sort of malignant growth that influences countless. As of late, profound learning strategies have been appeared to be very precise in arranging pictures in different fields. This investigation utilizes profound figuring out how to consequently distinguish melanomas in dermoscopy pictures. To begin with, we preprocess the pictures to evacuate undesirable antiques, for example, hair, and afterward consequently fragment the skin sore. We at that point group the pictures utilizing a convolution neural system. To assess its viability, we test this classifier utilizing both preprocessed and natural pictures from the PH2 dataset. The outcomes a remarkable execution as far as affectability, explicitness, and exactness. Specifically, our methodology was 93% exact in distinguishing the nearness or nonappearance of melanoma, with sensitivities and specificities in the 86%– 94% territory
Melanoma Classification Using a Novel Deep Convolutional Neural Network with Dermoscopic Images
Sensors, 2022
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 S...
Skin Cancer Detection and Classification using Deep learning methods
FOREX Publication, 2023
Skin cancer is a very dangerous disease that needs to be found early, so that it can be treated effectively. In the past few years, classifiers built on convolutional neural networks (CNNs) have become the best way to find melanoma. According to the review, the CNN-based classifier is as accurate as dermatologist in classifying skin cancer images, allowing for faster and more accurate detection. This article examines the most recent studies on Machine learning and deep learning-based melanoma categorization in depth. We provide a comprehensive description of the machine learning and deep learning classifier, including details on the accuracy of these classifiers. The primary objective of this research is to analyze and collect current research trends, issues, and opportunities for melanoma diagnosis, as well as to investigate the current approach for using deep learning to detect and recognize melanoma. The main finding of this review is that the neural network provides high accuracy as comparison to machine learning methods.
CLASSIFICATION OF MELANOMA FROM DERMOSCOPIC IMAGES USING DEEP LEARNING
Malignant melanoma is one of the rapidly increasing and deadly diseases in the world. Early diagnosis is of great importance for treating the disease. Accurate observation of skin lesions is needed for melanoma detection. Dermoscopy is a non-invasive technique for observation of skin lesion. Manual observation of dermoscopic images for classification of lesion as benign or malignant can be inaccurate and subjective. Therefore computer aided diagnosis (CAD) plays a significant role for assisting in melanoma detection.
Automatic Malignant and Benign Skin Cancer Classification Using a Hybrid Deep Learning Approach
Diagnostics
Skin cancer is one of the major types of cancer with an increasing incidence in recent decades. The source of skin cancer arises in various dermatologic disorders. Skin cancer is classified into various types based on texture, color, morphological features, and structure. The conventional approach for skin cancer identification needs time and money for the predicted results. Currently, medical science is utilizing various tools based on digital technology for the classification of skin cancer. The machine learning-based classification approach is the robust and dominant approach for automatic methods of classifying skin cancer. The various existing and proposed methods of deep neural network, support vector machine (SVM), neural network (NN), random forest (RF), and K-nearest neighbor are used for malignant and benign skin cancer identification. In this study, a method was proposed based on the stacking of classifiers with three folds towards the classification of melanoma and benig...