Fully Convolutional Neural Networks to Detect Clinical Dermoscopic Features

@article{Kawahara2019FullyCN,
  title={Fully Convolutional Neural Networks to Detect Clinical Dermoscopic Features},
  author={Jeremy Kawahara and G. Hamarneh},
  journal={IEEE Journal of Biomedical and Health Informatics},
  year={2019},
  volume={23},
  pages={578-585}
}
  • J. Kawahara, G. Hamarneh
  • Published 2019
  • Computer Science, Medicine
  • IEEE Journal of Biomedical and Health Informatics
The presence of certain clinical dermoscopic features within a skin lesion may indicate melanoma, and automatically detecting these features may lead to more quantitative and reproducible diagnoses. We reformulate the task of classifying clinical dermoscopic features within superpixels as a segmentation problem, and propose a fully convolutional neural network to detect clinical dermoscopic features from dermoscopy skin lesion images. Our neural network architecture uses interpolated feature… Expand
Input space augmentation for skin lesion segmentation in dermoscopic images
TLDR
This thesis studies approaches to improve the segmentation of skin lesions in dermoscopic images, which is often the first and the most important task in the diagnosis of dermatological conditions and presents two methods to improve deep learning-based segmentation by augmenting the input space of convolutional neural network models. Expand
A Structure-Aware Convolutional Neural Network for Skin Lesion Classification
TLDR
By including information from learned pigment network segmentations, the recall for malignant melanoma was seen to increase and the “attention” to pigment networks paid by the deep classifier both location- and channel-wise was quantified. Expand
Leveraging Transfer Learning for Segmenting Lesions and their Attributes in Dermoscopy Images
TLDR
The proposed framework by incorporating transfer learning for segmenting lesions and their attributes based on the convolutional neural networks is inspired by the well-known UNet architecture and achieves promising results on the cross-validation experiments on the ISIC2018- Task1 and Task2 data sets. Expand
(De) Constructing Bias on Skin Lesion Datasets
TLDR
The results show that models can correctly classify skin lesion images without clinically-meaningful information, and show that the machine-learning model learned over images where no information about the lesion remains, presents an accuracy above the AI benchmark curated with dermatologists' performances. Expand
Segmentation of Skin Lesions and their Attributes Using Multi-Scale Convolutional Neural Networks and Domain Specific Augmentations
TLDR
A framework by incorporating transfer learning for segmenting lesions and their attributes based on the convolutional neural networks is proposed and outperforms other state-of-the-art approaches for ISIC2016 and ISIC2017 segmentation task and achieved the first rank on the leader-board of ISIC2018 attribute detection task. Expand
Attention-based skin lesion recognition
TLDR
To the knowledge, this thesis is the first to introduce an end-to-end trainable attention module with regularization for skin cancer recognition and to utilize prior information by regularizing attention maps with regions of interest (ROIs) (e.g., lesion segmentation or dermoscopic features). Expand
Pigment Network Detection in Dermoscopy Images using Deep Learning
Melanoma is considered to be the most dangerous form of skin cancer. However, if the melanoma is diagnosed in its early stages, it can be easily cured. Some medical techniques have been proposed toExpand
Early Melanoma Diagnosis with Sequential Dermoscopic Images.
  • Zhen Yu, Jennifer Nguyen, +6 authors Zongyuan Ge
  • Computer Science, Medicine
  • IEEE transactions on medical imaging
  • 2021
TLDR
The proposed model can be used to identify melanocytic lesions that are at high-risk of malignant transformation earlier in the disease process and thereby redefine what is possible in the early detection of melanoma. Expand
Pixels to Classes: Intelligent Learning Framework for Multiclass Skin Lesion Localization and Classification
TLDR
From the results, it is concluded that the proposed method outperforms several existing techniques, based on the selected set of parameters including sensitivity, precision, precision and accuracy, including sensitivity (85.57), precision, and accuracy (86.5%). Expand
Enhanced Dermatoscopic Skin Lesion Classification using Machine Learning Techniques
Malicious melanoma will create greatest impact to the people. Most of the research was done on this field to find out the benign and malignant images and also to classify the different kind of skinExpand
...
1
2
3
4
...

References

SHOWING 1-10 OF 38 REFERENCES
Deep features to classify skin lesions
TLDR
It is demonstrated that a linear classifier, trained on features extracted from a convolutional neural network pretrained on natural images, distinguishes among up to ten skin lesions with a higher accuracy than previously published state-of-the-art results on the same dataset. Expand
Deep Learning, Sparse Coding, and SVM for Melanoma Recognition in Dermoscopy Images
TLDR
An approach for melanoma recognition in dermoscopy images that combines deep learning, sparse coding, and support vector machine SVM learning algorithms is presented, suggesting the proposed approach is an effective improvement over prior state-of-art. Expand
Deep learning ensembles for melanoma recognition in dermoscopy images
TLDR
A system that combines recent developments in deep learning with established machine learning approaches, creating ensembles of methods that are capable of segmenting skin lesions, as well as analyzing the detected area and surrounding tissue for melanoma detection is proposed. Expand
Automated Melanoma Recognition in Dermoscopy Images via Very Deep Residual Networks
TLDR
This study corroborates that very deep CNNs with effective training mechanisms can be employed to solve complicated medical image analysis tasks, even with limited training data. Expand
Skin Lesion Analysis towards Melanoma Detection Using Deep Learning Network
TLDR
Two deep learning methods are proposed to address three main tasks emerging in the area of skin lesion image processing, i.e., lesion segmentation (task 1), lesion dermoscopic feature extraction (task 2) and lesion classification (task 3). Expand
Skin lesion classification from dermoscopic images using deep learning techniques
TLDR
This paper presents a deep-learning based approach to solve the problem of classifying a dermoscopic image containing a skin lesion as malignant or benign, built around the VGGNet convolutional neural network architecture and uses the transfer learning paradigm. Expand
Improving Dermoscopic Image Segmentation With Enhanced Convolutional-Deconvolutional Networks
  • Yading Yuan, Y. Lo
  • Computer Science, Medicine
  • IEEE Journal of Biomedical and Health Informatics
  • 2019
TLDR
A deeper network architecture with smaller kernels to enhance its discriminant capacity is developed and color information from multiple color spaces is explicitly included to facilitate network training and thus to further improve the segmentation performance. Expand
Learning features for streak detection in dermoscopic color images using localized radial flux of principal intensity curvature
TLDR
A machine-learning approach for identifying streaks in dermoscopic images using a novel melanoma feature, which captures the quaternion tubularness in the color dermosCopic images, is to the radial features of streaks, and is localized to different lesion bands. Expand
V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation
TLDR
This work proposes an approach to 3D image segmentation based on a volumetric, fully convolutional, neural network, trained end-to-end on MRI volumes depicting prostate, and learns to predict segmentation for the whole volume at once. Expand
Multi-resolution-Tract CNN with Hybrid Pretrained and Skin-Lesion Trained Layers
TLDR
This work proposes a novel convolutional neural network architecture for skin lesion classification designed to learn based on information from multiple image resolutions while leveraging pretrained CNNs, and shows how this proposed novel multi-tract network yields higher classification accuracy. Expand
...
1
2
3
4
...