Automatic Skin Lesion Segmentation and Melanoma Detection: Transfer Learning Approach with U-Net and DCNN-SVM

2019 ◽  
pp. 371-381 ◽  
Author(s):  
Zabir Al Nazi ◽  
Tasnim Azad Abir
Keyword(s):  
Skin Lesion ◽  
Transfer Learning ◽  
Learning Approach ◽  
Lesion Segmentation ◽  
Melanoma Detection

scholarly journals Bucket of Deep Transfer Learning Features and Classification Models for Melanoma Detection

2020 ◽  
Vol 6 (12) ◽  
pp. 129
Author(s):  
Mario Manzo ◽  
Simone Pellino
Keyword(s):  
Neural Networks ◽  
Skin Lesion ◽  
Transfer Learning ◽  
Convolutional Neural Networks ◽  
Image Features ◽  
Ensemble Classification ◽  
Deep Convolutional Neural Networks ◽  
Melanoma Detection ◽  
Statistical Measures ◽  
Different Types

Malignant melanoma is the deadliest form of skin cancer and, in recent years, is rapidly growing in terms of the incidence worldwide rate. The most effective approach to targeted treatment is early diagnosis. Deep learning algorithms, specifically convolutional neural networks, represent a methodology for the image analysis and representation. They optimize the features design task, essential for an automatic approach on different types of images, including medical. In this paper, we adopted pretrained deep convolutional neural networks architectures for the image representation with purpose to predict skin lesion melanoma. Firstly, we applied a transfer learning approach to extract image features. Secondly, we adopted the transferred learning features inside an ensemble classification context. Specifically, the framework trains individual classifiers on balanced subspaces and combines the provided predictions through statistical measures. Experimental phase on datasets of skin lesion images is performed and results obtained show the effectiveness of the proposed approach with respect to state-of-the-art competitors.

Lesion Boundary Segmentation With Artifacts Removal and Melanoma Detection in Skin Lesion Images

2019 ◽  
pp. 219-233
Author(s):  
Julie Ann Acebuque Salido ◽  
Conrado Ruiz Jr. ◽  
Nelson Marcos
Keyword(s):  
Skin Lesion ◽  
Severe Form ◽  
Skin Area ◽  
Lesion Segmentation ◽  
Simple Method ◽  
Melanoma Detection ◽  
Artifacts Removal ◽  
True Detection ◽  
Augmentation Techniques ◽  
Water Residue

Melanoma is a severe form of skin cancer characterized by the rapid multiplication of pigment-producing cells. A problem on analysis of these images is interesting because of the existence of artifacts that produces noise such as hair, veins, water residue, illuminations, and light reflections. An important step in the diagnosis of melanoma is the removal and reduction of these artifacts that can inhibit the examination to accurately segment the skin lesion from the surrounding skin area. A simple method for artifacts removal for extracting skin lesion is implemented based on image enhancement and morphological operators. This is used for training together with some augmentation techniques on images for melanoma detection. The experimental results show that artifact removal and lesion segmentation in skin lesion images performed a true detection rate of 95.37% for melanoma skin lesion segmentation, and as high as 92.5% accuracy for melanoma detection using both GoogLeNet and Resnet50.

scholarly journals Using Transfer Learning and Hierarchical Classifier to Diagnose Melanoma From Dermoscopic Images

2021 ◽  
Vol 16 (2) ◽  
pp. 73-86
Author(s):  
Priti Bansal ◽  
Sumit Kumar ◽  
Ritesh Srivastava ◽  
Saksham Agarwal
Keyword(s):  
Skin Lesion ◽  
Transfer Learning ◽  
Intelligent Systems ◽  
Nearest Neighbor ◽  
Critical Role ◽  
K Nearest Neighbor ◽  
Melanoma Detection ◽  
Proposed Model ◽  
Medical Image Diagnosis ◽  
Hierarchical Classifier

The deadliest form of skin cancer is melanoma, and if detected in time, it is curable. Detection of melanoma using biopsy is a painful and time-consuming task. Alternate means are being used by medical experts to diagnose melanoma by extracting features from skin lesion images. Medical image diagnosis requires intelligent systems. Many intelligent systems based on image processing and machine learning have been proposed by researchers in the past to detect different kinds of diseases that are successfully used by healthcare organisations worldwide. Intelligent systems to detect melanoma from skin lesion images are also evolving with the aim of improving the accuracy of melanoma detection. Feature extraction plays a critical role. In this paper, a model is proposed in which features are extracted using convolutional neural network (CNN) with transfer learning and a hierarchical classifier consisting of random forest (RF), k-nearest neighbor (KNN), and adaboost is used to detect melanoma using the extracted features. Experimental results show the effectiveness of the proposed model.

scholarly journals Skin Lesion Segmentation in Dermoscopic Images with Combination of YOLO and GrabCut Algorithm

Diagnostics ◽  
2019 ◽  
Vol 9 (3) ◽  
pp. 72 ◽  
Author(s):  
Halil Murat Ünver ◽  
Enes Ayan
Keyword(s):  
Skin Lesion ◽  
Automatic Segmentation ◽  
Critical Role ◽  
Skin Lesions ◽  
Lesion Segmentation ◽  
Low Contrast ◽  
Melanoma Detection ◽  
Sensitivity Rate ◽  
Dermoscopic Image ◽  
Grabcut Algorithm

Skin lesion segmentation has a critical role in the early and accurate diagnosis of skin cancer by computerized systems. However, automatic segmentation of skin lesions in dermoscopic images is a challenging task owing to difficulties including artifacts (hairs, gel bubbles, ruler markers), indistinct boundaries, low contrast and varying sizes and shapes of the lesion images. This paper proposes a novel and effective pipeline for skin lesion segmentation in dermoscopic images combining a deep convolutional neural network named as You Only Look Once (YOLO) and the GrabCut algorithm. This method performs lesion segmentation using a dermoscopic image in four steps: 1. Removal of hairs on the lesion, 2. Detection of the lesion location, 3. Segmentation of the lesion area from the background, 4. Post-processing with morphological operators. The method was evaluated on two publicly well-known datasets, that is the PH2 and the ISBI 2017 (Skin Lesion Analysis Towards Melanoma Detection Challenge Dataset). The proposed pipeline model has achieved a 90% sensitivity rate on the ISBI 2017 dataset, outperforming other deep learning-based methods. The method also obtained close results according to the results obtained from other methods in the literature in terms of metrics of accuracy, specificity, Dice coefficient, and Jaccard index.

scholarly journals Self-Supervised Learning to Increase the Performance of Skin Lesion Classification

Electronics ◽  
2020 ◽  
Vol 9 (11) ◽  
pp. 1930
Author(s):  
Arkadiusz Kwasigroch ◽  
Michał Grochowski ◽  
Agnieszka Mikołajczyk
Keyword(s):  
Skin Lesion ◽  
Supervised Learning ◽  
Transfer Learning ◽  
The Self ◽  
Real Problem ◽  
Learning Approach ◽  
Neural Models ◽  
Network Training ◽  
Learning Technique ◽  
Lesion Classification

To successfully train a deep neural network, a large amount of human-labeled data is required. Unfortunately, in many areas, collecting and labeling data is a difficult and tedious task. Several ways have been developed to mitigate the problem associated with the shortage of data, the most common of which is transfer learning. However, in many cases, the use of transfer learning as the only remedy is insufficient. In this study, we improve deep neural models training and increase the classification accuracy under a scarcity of data by the use of the self-supervised learning technique. Self-supervised learning allows an unlabeled dataset to be used for pretraining the network, as opposed to transfer learning that requires labeled datasets. The pretrained network can be then fine-tuned using the annotated data. Moreover, we investigated the effect of combining the self-supervised learning approach with transfer learning. It is shown that this strategy outperforms network training from scratch or with transfer learning. The tests were conducted on a very important and sensitive application (skin lesion classification), but the presented approach can be applied to a broader family of applications, especially in the medical domain where the scarcity of data is a real problem.

Sign in / Sign up

Export Citation Format

Share Document