Severity grading of psoriatic plaques using deep CNN based multi-task learning

  title={Severity grading of psoriatic plaques using deep CNN based multi-task learning},
  author={Anabik Pal and Akshay Chaturvedi and Utpal Garain and Aditi Chandra and Raghunath Chatterjee},
  journal={2016 23rd International Conference on Pattern Recognition (ICPR)},
This paper addresses the problem of automatic machine analysis based severity scoring of psoriasis skin disease. [...] Key Method Apart from viewing this task as three different single task learning (STL) problems (i.e. three different classification problems), a new multi-task learning (MTL) is also presented where the three classification tasks are treated as interdependent and thereby the neural net is trained accordingly.Expand
Severity Assessment of Psoriatic Plaques Using Deep CNN Based Ordinal Classification
The Earth Mover’s Distance based loss function is proposed for training CNN since it takes into account the corresponding ordinal class relationships and shows that the proposed ordinal classification technique outperforms the traditional approaches. Expand
Severity gradation of psoriatic plaques using ensemble of deep convolutional neural networks
Five new methods for severity scoring are proposed in order to bring about improvement in accuracy from the baseline and other approaches like Texture CNN based classification have also been tried and depicted in the thesis. Expand
PSENet: Psoriasis Severity Evaluation Network
  • Y. Li, Zhe Wu, +8 authors Yong Wang
  • Computer Science
  • AAAI
  • 2020
PSENet is proposed which applies deep neural networks to estimate Psoriasis severity based on skin lesion images and relieves dermatologists from the dull PASI calculation but also enables patients to track PsOriasis severity in a much more convenient manner. Expand
Psoriasis skin biopsy image segmentation using Deep Convolutional Neural Network
The present research shows that practical system can be developed for machine assisted analysis of psoriasis disease and the CNN based approaches outperform the traditional hand-crafted feature based classification approaches. Expand
Classification of Skin Cancer Dermoscopy Images using Transfer Learning
This paper proposes an efficient way to classify skin cancer using deep learning using the pre-trained MobileNet convolution neural network and trained over the HAM1000 skin lesion dataset, which has shown remarkable categorical accuracy. Expand
CapsDeMM: Capsule network for Detection of Munro's Microabscess in skin biopsy images
This paper presents an approach for automatic detection of Munro’s Microabscess in stratum corneum (SC) of human skin biopsy in order to realize a machine assisted diagnosis of Psoriasis. TheExpand
Smart identification of psoriasis by images using convolutional neural networks: a case study in China
  • S. Zhao, B. Xie, +12 authors X. Chen
  • Medicine
  • Journal of the European Academy of Dermatology and Venereology : JEADV
  • 2019
A smart approach to identify psoriasis by pictures would be highly adaptable countrywide and could play a useful role in early diagnosis and regular treatment of Psoriasis in China. Expand
Derm-NN: Skin Diseases Detection Using Convolutional Neural Network
A prototype to detect skin diseases using neural networks using CNN which abbreviates as a convolutional neural network and has 73% precision by actualizing the framework on the dermnet dataset of 500 pictures of various diseases. Expand
Supervised CNN Strategies for Optical Image Segmentation and Classification in Interventional Medicine
An overview of some of the most recent approaches (up to 2018) in the field of interventional-image analysis, with a focus on Convolutional Neural Networks (CNNs) for both segmentation and classification tasks. Expand
Automatic psoriasis assessment methods: current scenario and perspectives from a metrologic point of view
The paper presents an overview of the limitations on psoriasis assessment by means of electronic instrumentation and the solutions proposed by research, in these last years. Expand


Automatic Segmentation of Scaling in 2-D Psoriasis Skin Images
The algorithm is shown to give reliable segmentation results when evaluated with images with different lighting conditions, skin types, and psoriasis types. Expand
Random forest based erythema grading for psoriasis
A novel colorimetric feature for erythema grading is proposed by extending the tissue-photon interaction model to make it skin tone independent and a random forest based technique is presented for classification of ery thema regions in Psoriasis into severe, moderate and slight categories. Expand
Mixture model based color clustering for psoriatic plaque segmentation
A mixture model based color clustering based on von Mises distribution is presented and this technique is applied for psoriatic plaque segmentation in skin images and shows that the clustering in Lch using SWGMM outperforms the other approaches. Expand
Multi-Instance Deep Learning: Discover Discriminative Local Anatomies for Bodypart Recognition
  • Z. Yan, Y. Zhan, +5 authors X. Zhou
  • Computer Science, Medicine
  • IEEE Transactions on Medical Imaging
  • 2016
A multi-stage deep learning framework for image classification and apply it on bodypart recognition achieves better performances than state-of-the-art approaches, including the standard deep CNN. Expand
Segmentation of psoriasis vulgaris images using multiresolution-based orthogonal subspace techniques
The results show that the proposed algorithm can effectively segment psoriasis images and can also be applied to general color texture segmentation applications. Expand
Automatic Detection of Cerebral Microbleeds From MR Images via 3D Convolutional Neural Networks
This paper proposes a novel automatic method to detect CMBs from magnetic resonance (MR) images by exploiting the 3D convolutional neural network (CNN), outperforming previous methods using low-level descriptors or 2D CNNs by a significant margin. Expand
Objective measurement of erythema in psoriasis using digital color photography with color calibration
Quantitative measures based on the digital color images are shown to correlate well with subjective assessment of psoriasis severity collected using a standard numerical scale by a panel of dermatologists. Expand
Severe psoriasis--oral therapy with a new retinoid.
Ro 10--9359 proved to be an extremely potent antipsoriatic drug and a more than 90% reduction of psoriatic lesions could be seen in 10 patients out of 20 after 4-8 weeks of treatment. Expand
Geoepidemiology and environmental factors of psoriasis and psoriatic arthritis.
The current literature on the epidemiology and genetics of psoriasis and PsA is reviewed, showing that both diseases have a strong genetic component and environmental risk factors including streptococcal pharyngitis, stressful life events, low humidity, drugs, HIV infection, trauma, smoking and obesity have been associated with them. Expand
ImageNet classification with deep convolutional neural networks
A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective. Expand