Extraction of skin lesions from non-dermoscopic images for surgical excision of melanoma

  title={Extraction of skin lesions from non-dermoscopic images for surgical excision of melanoma},
  author={M. Jafari and Ebrahim Nasr-Esfahani and Nader Karimi and S. Mohamad R. Soroushmehr and Shadrokh Samavi and Kayvan Najarian},
  journal={International Journal of Computer Assisted Radiology and Surgery},
PurposeComputerized prescreening of suspicious moles and lesions for malignancy is of great importance for assessing the need and the priority of the removal surgery. Detection can be done by images captured by standard cameras, which are more preferable due to low cost and availability. One important step in computerized evaluation is accurate detection of lesion’s region, i.e., segmentation of an image into two regions as lesion and normal skin.MethodsIn this paper, a new method based on deep… 

U-Net Based Segmentation and Multiple Feature Extraction of Dermascopic Images for Efficient Diagnosis of Melanoma

  • D. RamaniS. Ranjani
  • Medicine, Computer Science
    Computer Aided Intervention and Diagnostics in Clinical and Medical Images
  • 2019
A U-Net based segmentation and multiple feature extraction of the dermascopic images for the efficient diagnosis of skin cancer is presented and yields better performance than the existing segmentations and feature extraction techniques.

Diagnosis of melanoma from dermoscopic images using a deep depthwise separable residual convolutional network

A deep depthwise separable residual convolutional algorithm is introduced to perform binary melanoma classification on a dermoscopic skin lesion image dataset and dynamic effectiveness of the model is shown through its performance in multiple skin lesions image datasets.

Dense Fully Convolutional Network for Skin Lesion Segmentation

This paper proposes a new class of fully convolutional networks with novel dense pooling layers for segmentation of lesion regions in non-dermoscopic images and produces dice score of 91.6% which outperforms all state-of-the-art algorithms in segmentations of skin lesions based on the Dermquest dataset.

Melanoma diagnosis using deep learning techniques on dermatoscopic images

The results achieved with the proposed model suggest a significant improvement over the results obtained in the state of the art as far as performance of skin lesion classifiers (malignant/benign) is concerned.

Skin lesion segmentation using object scale-oriented fully convolutional neural networks

This work proposes end-to-end object scale-oriented fully convolutional networks (OSO–FCNs) for skin lesion segmentation and shows that the segmentation accuracy of the algorithm is higher or very close to the performances of the other algorithms.

MelaNet: an effective deep learning framework for melanoma detection using dermoscopic images

An improved deep learning-based solution with a convolutional neural network is proposed that can be adopted for assisting dermatologists with melanoma diagnosis and the obtained results demonstrate its effectiveness when compared to the state-of-the-art methods.

Effects of objects and image quality on melanoma classification using deep neural networks

The effect of ruler/hair and image blur, noise and contrast on the melanoma detection performance of four commonly used CNN models: ResNet50, DenseNet121, VGG16 and AlexNet is investigated.



Skin lesion segmentation in clinical images using deep learning

The experimental results show that the proposed method for accurate extraction of lesion region can outperform the existing state-of-the-art algorithms in terms of segmentation accuracy.

Automatic segmentation of skin lesions from dermatological photographs

The goal of this research is to develop a framework to automatically correct and segment the skin lesion from an input photograph and produce the highest classification accuracy and is tied for the highest sensitivity and specificity.

Segmentation of Skin Lesions From Digital Images Using Joint Statistical Texture Distinctiveness

The proposed segmentation framework has higher segmentation accuracy compared to all other tested algorithms and is tested by comparing lesion segmentation results and melanoma classification results to results using other state-of-art algorithms.

Set of descriptors for skin cancer diagnosis using non-dermoscopic color images

Experimental results show that classification accuracy of suspicious moles, by the proposed set of features, outperforms comparable state-of-the-art methods.

Automated prescreening of pigmented skin lesions using standard cameras

Pigmented skin lesion segmentation on macroscopic images

A new method for segmenting pigmented skin lesions on macroscopic images acquired with standard cameras is proposed, which can achieve an average segmentation error of 24.85%, which is better than the accuracy of comparable methods available in the literature.

Computerized analysis of pigmented skin lesions: A review

Vessel extraction in X-ray angiograms using deep learning

Experimental results on angiography images of a dataset show that the proposed deep learning approach using convolutional neural networks has a superior performance in extraction of vessel regions.