Automated Melanoma Recognition in Dermoscopy Images via Very Deep Residual Networks

By Lequan Yu, Hao Chen, Qi-Yan Dou, Jing Qin, P. Heng. 2017

1,025 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Oncology, Radiology, Nuclear Medicine and Imaging

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Oncology

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Opportunities and obstacles for deep learning in biology and medicine (2017, background): “Such features were also repurposed to detect melanoma, the deadliest form of skin cancer, from dermoscopic [47,48] and non-dermoscopic images of skin lesions [4,49,50] as well as age-related macular degeneration [51].”
Progressive Transfer Learning and Adversarial Domain Adaptation for Cross-Domain Skin Disease Classification (2020, background): “Although deep CNNs are promising for disease diagnosis from medical images [13], [14], it is pointed out that CNN models trained on a dataset acquired from one hospital does not work equally well in datasets collected from different hospitals.”
A fully integrated computer-aided diagnosis system for digital X-ray mammograms via deep learning detection, segmentation, and classification (2018, methodology): “Breast mass segmentation also plays a crucial role in accurately extracting discriminative shape features of speci ﬁ c mass regions, while excluding surrounding tissues [19,25].”
Automatic Skin Lesion Segmentation Using Deep Fully Convolutional Networks With Jaccard Distance (2017, background): “To the best of our knowledge, our work is among the first few attempts to use deep neural networks to tackle this challenging problem [31], [32].”
Deep Learning Techniques for Medical Image Segmentation: Achievements and Challenges (2019, background): “One solution is multi-scale networks [42, 77, 83], where input images were resized and fed to the network.”
Using Deep Learning to Detect Defects in Manufacturing: A Comprehensive Survey and Current Challenges (2020, background): “It mainly includes convolutional neural network (CNN) [75], autoencoder neural network [74,76], deep residual neural network [77], full convolution neural network [78], and recurrent neural network [79,80].”
Dermoscopic Image Segmentation via Multistage Fully Convolutional Networks (2017, methodology): “[37] used a 50-layer deep residual network for segmentation, where the residual blocks proposed by He et al.”
Artificial intelligence in oncology (2020, background): “20,21 AI was, thus, found to be able to annotate skin lesions (including melanoma) as precisely as were expert dermatologists (with an area under the curve [AUC] of 0.94-0.96).”
Skin lesion detection based on an ensemble of deep convolutional neural network (2017, methodology): “Considering this task, we can find many recommendations such as for thresholding [8], region [9] and edge-based approaches [10], soft computing techniques [11] and deformable models [12].”
Skin Lesion Analysis towards Melanoma Detection Using Deep Learning Network (2017, background): “applied a very deep residual network to distinguish melanoma from non-melanoma lesions [20].”
SV-RCNet: Workflow Recognition From Surgical Videos Using Recurrent Convolutional Network (2018, background): “The importance of network depth for extracting discriminative features has been manifested by both computational theories [22], [23] and practical applications [24]–[26].”
Attention Residual Learning for Skin Lesion Classification (2019, neutral): “Second, the accuracy of skin lesion classification suffers from the inter-class similarity and intra-class variation [7], [30].”
AI in Medical Imaging Informatics: Current Challenges and Future Directions (2020, neutral): “Learning lung nodule features using a 2D autoencoder [128]”
Seven-Point Checklist and Skin Lesion Classification Using Multitask Multimodal Neural Nets (2019, methodology): “[18] fine-tuned a Residual Neural Network [19] pretrained over ImageNet [20].”