Psoriasis skin biopsy image segmentation using Deep Convolutional Neural Network

@article{Pal2018PsoriasisSB,
  title={Psoriasis skin biopsy image segmentation using Deep Convolutional Neural Network},
  author={Anabik Pal and Utpal Garain and Aditi Chandra and Raghunath Chatterjee and Swapan Senapati},
  journal={Computer methods and programs in biomedicine},
  year={2018},
  volume={159},
  pages={
          59-69
        }
}
BACKGROUND AND OBJECTIVE Development of machine assisted tools for automatic analysis of psoriasis skin biopsy image plays an important role in clinical assistance. Development of automatic approach for accurate segmentation of psoriasis skin biopsy image is the initial prerequisite for developing such system. However, the complex cellular structure, presence of imaging artifacts, uneven staining variation make the task challenging. This paper presents a pioneering attempt for automatic… Expand
Diabetic Wound Segmentation using Convolutional Neural Networks
TLDR
In this work, a Deep Learning based method for accurate segmentation of wound regions is proposed, and experiments show that the method can achieve high performance in terms of segmentation accuracy and Dice index. Expand
Convolutional Neural Network Application for Analysis of Fundus Images
TLDR
CNN-aided segmentation of the input image conducted in this work has shown the CNN to be capable of identifying all training dataset classes with high accuracy, and it has been demonstrated the H channel to be most informative. Expand
Cell‐type based semantic segmentation of histopathological images using deep convolutional neural networks
TLDR
This study proposes automatic semantic segmentation based on cell type using novel deep convolutional networks structure (DCNN), which has the most important advantage in that it has the ability to generate automatic information about the cancer and also provides information that pathologists can quickly interpret. Expand
Application of convolution neural networks in eye fundus image analysis
TLDR
A new approach to analyzing eye fundus images that relies upon the use of a convolutional neural network (CNN) is proposed, and the HSL color system was found to be most informative, using which the segmentation error was reduced to 3%. Expand
Evaluation of psoriasis skin disease classification using convolutional neural network
TLDR
This paper showed the promising used of CNN with the accuracy rate of 82.9% and 72.4% for Plaque and Guttate Psoriasis skin disease, respectively. 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
Computer vision applied to dual-energy computed tomography images for precise calcinosis cutis quantification in patients with systemic sclerosis
TLDR
It is demonstrated that CNN quantification has a high degree of correlation with expert radiologist measurement of finger CC area measurements, and will include segmentation of 3-dimensional (3D) images for volumetric and density quantification, as well as validation in larger, independent cohorts. Expand
High-throughput quantitative histology in systemic sclerosis skin disease using computer vision
TLDR
DNN analysis of SSc biopsies is an unbiased, quantitative, and reproducible outcome that is associated with validated SSc outcomes and between Fibrosis Scores and longitudinal changes in mRSS on a per patient basis. Expand
Classification of Childhood Medulloblastoma and its subtypes using Transfer Learning features - A Comparative Study of Deep Convolutional Neural Networks
TLDR
This paper performs classification of CMB samples for two categories: binary ( to classify it from normal samples) and multiclass (to classify its different subtypes) and shows that the features extracted by the VGG-16 network are more considerable than Alexnet. Expand
Classification of Vitiligo Based on Convolutional Neural Network
TLDR
This paper proposes a method base on probability-average value of three convolutional neural network models which are same structures, and trained with three different color-space images for the same vitiligo dataset which outperforms the individual networks. Expand
...
1
2
3
...

References

SHOWING 1-10 OF 41 REFERENCES
Automated segmentation and analysis of the epidermis area in skin histopathological images
  • Cheng Lu, M. Mandal
  • Computer Science, Medicine
  • 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society
  • 2012
TLDR
A computer-aided technique for segmentation and analysis of the epidermis area in the whole slide skin histopathological images provides a superior performance, about 92% sensitivity rate, 93% precision and 97% specificity rate. Expand
Computer-aided diagnosis of psoriasis skin images with HOS, texture and color features: A first comparative study of its kind
TLDR
A first comparative performance study of its kind using principal component analysis (PCA) based CADx system for psoriasis risk stratification and image classification utilizing 11 higher order spectra (HOS) features, 60 texture features, and 86 color feature sets and their seven combinations is presented. Expand
A Bottom-Up Approach for Pancreas Segmentation Using Cascaded Superpixels and (Deep) Image Patch Labeling
TLDR
Under six-fold cross-validation, the bottom-up segmentation method significantly outperforms its MALF counterpart and the segmentation framework using deep patch labeling confidences is also more numerically stable, as reflected in the smaller performance metric standard deviations. Expand
MSFCN-multiple supervised fully convolutional networks for the osteosarcoma segmentation of CT images
TLDR
The results indicated that the proposed algorithm contributed to the fast and accurate delineation of tumor boundaries, which could potentially assist doctors in making more precise treatment plans. Expand
Gland segmentation in colon histology images using hand-crafted features and convolutional neural networks
TLDR
It is found that fine-tuned CNN outperforms HC-SVM in gland segmentation measured by pixel-wise Jaccard and Dice indices, and it is observed that training a second-level window classifier on the posterior probabilities can substantially improve the segmentation performance. Expand
Vessel extraction in X-ray angiograms using deep learning
  • E. Nasr-Esfahani, S. Samavi, +6 authors K. Najarian
  • Computer Science, Medicine
  • 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
  • 2016
TLDR
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. Expand
Segmentation of epidermal tissue with histopathological damage in images of haematoxylin and eosin stained human skin
TLDR
The proposed methodology is able to segment the epidermis with different levels of histopathological damage and could be applied to segmentation of other epithelial tissues. Expand
Computer-Aided Prostate Cancer Diagnosis From Digitized Histopathology: A Review on Texture-Based Systems
TLDR
This review aims at providing a detailed description of selected literature in the field of CAD of PCa, emphasizing the role of texture analysis methods in tissue description, as well as future directions in pursuit of better texture-based CAD systems. Expand
Severity grading of psoriatic plaques using deep CNN based multi-task learning
TLDR
A novel deep CNN based architecture for achieving the problem of automatic machine analysis based severity scoring of psoriasis skin disease is presented and shows that the deepCNN based architectures (both the STL and MTL) achieve promising performances. Expand
Superpixel-based automatic segmentation of villi in confocal endomicroscopy
TLDR
This work presents an automatic method for villi detection from confocal endoscopy images, whose appearance changes with mucosal alterations, and uses superpixel segmentation to identify and cluster together pixels belonging to uniform regions. Expand
...
1
2
3
4
5
...