An End-to-End Multi-Task Deep Learning Framework for Skin Lesion Analysis

Song, Lixin; Lin, Jianzhe; Wang, Z. Jane; Wang, Haoqian

doi:10.1109/jbhi.2020.2973614

Cited by 111 publications

(55 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed CNN was used for skin lesion segmentation and pixel-wise classification. Song et al [190] suggested that CNNs could segment, detect, and classify skin lesions. To control the imbalanced datasets, they utilized a loss function based on the Jaccard distance and the focal loss.…”

Section: Deep Learningmentioning

confidence: 99%

Machine Learning and Deep Learning Methods for Skin Lesion Classification and Diagnosis: A Systematic Review

et al. 2021

View full text Add to dashboard Cite

Computer-aided systems for skin lesion diagnosis is a growing area of research. Recently, researchers have shown an increasing interest in developing computer-aided diagnosis systems. This paper aims to review, synthesize and evaluate the quality of evidence for the diagnostic accuracy of computer-aided systems. This study discusses the papers published in the last five years in ScienceDirect, IEEE, and SpringerLink databases. It includes 53 articles using traditional machine learning methods and 49 articles using deep learning methods. The studies are compared based on their contributions, the methods used and the achieved results. The work identified the main challenges of evaluating skin lesion segmentation and classification methods such as small datasets, ad hoc image selection and racial bias.

show abstract

Section: Deep Learningmentioning

confidence: 99%

Machine Learning and Deep Learning Methods for Skin Lesion Classification and Diagnosis: A Systematic Review

et al. 2021

View full text Add to dashboard Cite

show abstract

“…For AUC, the DermoExpert wins by defeating the second-highest [70] by a margin of 2.0 %. DermoExpert has beaten the work of Song et al [66] by the margins of 4.0 %, and 16.0 % with respective precision and AUC although it lost by Song et al [66] in terms of recall. However, the proposed DermoExpert produces the second-highest results by beating the third results [80] with a margin of 9.0 % for recall.…”

Section: Resultsmentioning

confidence: 89%

“…However, in terms of balanced accuracy (avg. of recall and precision), DermoExpert beats the state-of-the-art [66] by a 1.5 % margin.…”

Section: Resultsmentioning

confidence: 94%

“…The proposed DermoExpert produces the best results for the AUC by beating the state-of-the-art [70, 78] with a 10.0 % margin. Concerning the type-II errors (recall), DermoExpert is behind the state-of-the-art [66] by 7.0 %, but the DermoExpert outperforms the FPRPN [66] by a 10.0 % margin concerning the positive predictive value (precision). However, in terms of balanced accuracy (avg.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

DermoExpert: Skin lesion classification using a hybrid convolutional neural network through segmentation, transfer learning, and augmentation

Mte

2021

Preprint

View full text Add to dashboard Cite

Although automated Skin Lesion Classification (SLC) is a crucial integral step in computer-aided diagnosis, it remains a challenging task due to inconsistency in texture, color, indistinguishable boundaries, and shapes. In this article, we propose an automatic and robust framework for the dermoscopic SLC named Dermoscopic Expert (DermoExpert). The DermoExpert consists of a preprocessing, a hybrid Convolutional Neural Network (hybrid-CNN), and transfer learning. The proposed hybrid-CNN classifier consists of three distinct feature extractors, with the same input images, which are fused to achieve better-depth feature maps of the corresponding lesion. Those distinct and fused feature maps are classified using the different fully connected layers, which are then ensembled to get a final prediction probability. In the preprocessing, we use lesion segmentation, augmentation, and class rebalancing. For boosting the lesion recognition, we have also employed geometric and intensity-based augmentation as well as the class rebalancing by penalizing the loss of the majority class and adding extra images to the minority classes. Additionally, we leverage the knowledge from a pre-trained model, also known as transfer learning, to build a generic classifier, although small datasets are being used. In the end, we design and implement a web application by deploying the weights of our DermoExpert for automatic lesion recognition. We evaluate our DermoExpert on the ISIC-2016, ISIC-2017, and ISIC-2018 datasets, where our DermoExpert has achieved the area under the receiver operating characteristic curve (AUC) of 0.96, 0.95, and 0.97, respectively. The experimental results outperform the recent state-of-the-art by a margin of 10.0 % and 2.0 % respectively for ISIC-2016 and ISIC-2017 datasets in terms of AUC. The DermoExpert also outperforms, in concerning a balanced accuracy, by a margin of 3.0 % for ISIC-2018 dataset. Since our framework can provide better-classification on three different test datasets, even with limited training data, it can lead to better-recognition of melanoma to aid dermatologists. Our source code, and segmented masks, for ISIC-2018 dataset, will be made publicly available for the research community for further improvements.

show abstract

“…In terms of applications, deep learning networks have been employed for several medical imaging tasks including image classification 30 , object detection [31][32][33][34] , semantic segmentation 35,36 , artifact denoising 37 , and image reconstruction 38 . Also, many studies have been conducted for skin lesion boundary segmentation 8,35,[39][40][41] , retinal blood vessel segmentation [42][43][44] , and brain tumor segmentation [45][46][47][48] . Further, some works have been conducted for multiple medical image segmentation 24,26,27,49,50 .…”

Section: Related Workmentioning

confidence: 99%

CMM-Net: Contextual Multi-Scale Multi-Level Network for Efficient Biomedical Image Segmentation

Al‐masni

Kim

2021

Preprint

View full text Add to dashboard Cite

Medical image segmentation of tissue abnormalities, key organs, or blood vascular system is of great significance for any computerized diagnostic system. However, automatic segmentation in medical image analysis is a challenging task since it requires sophisticated knowledge of the target organ anatomy. This paper develops an end-to-end deep learning segmentation method called Contextual Multi-Scale Multi-Level Network (CMM-Net). The main idea is to fuse the global contextual features of multiple spatial scales at every contracting convolutional network level in the U-Net. Also, we re-exploit the dilated convolution module that enables an expansion of the receptive field with different rates depending on the size of feature maps throughout the networks. In addition, an augmented testing scheme referred to as Inversion Recovery (IR) which uses logical “OR” and “AND” operators is developed. The proposed segmentation network is evaluated on three medical imaging datasets, namely ISIC 2017 for skin lesions segmentation from dermoscopy images, DRIVE for retinal blood vessels segmentation from fundus images, and BraTS 2018 for brain gliomas segmentation from MR scans. The experimental results showed superior state-of-the-art performance with overall dice similarity coefficients of 85.78%, 80.27%, and 88.96% on the segmentation of skin lesions, retinal blood vessels, and brain tumors, respectively. The proposed CMM-Net is inherently general and could be efficiently applied as a robust tool for various medical image segmentations.

show abstract

An End-to-End Multi-Task Deep Learning Framework for Skin Lesion Analysis

Cited by 111 publications

References 23 publications

Machine Learning and Deep Learning Methods for Skin Lesion Classification and Diagnosis: A Systematic Review

Machine Learning and Deep Learning Methods for Skin Lesion Classification and Diagnosis: A Systematic Review

DermoExpert: Skin lesion classification using a hybrid convolutional neural network through segmentation, transfer learning, and augmentation

CMM-Net: Contextual Multi-Scale Multi-Level Network for Efficient Biomedical Image Segmentation

Contact Info

Product

Resources

About