Microvasculature segmentation of arterioles using deep CNN

Kassim, Yasmin M.; Prasath, V. B. Surya; Glinskii, Olga V.; Glinsky, Vladislav V.; Huxley, Virginia H.; Palaniappan, Kannappan

doi:10.1109/icip.2017.8296347

Cited by 16 publications

(16 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our architecture accepts patches with size 32 × 32 and predict pixel wise the whole image. This architecture has two advantages compared to our previous work [1]:…”

Section: Training and Testingmentioning

confidence: 98%

“…Our ovariectomized -ovary removed (OVX) -mice dura mater epifluorescence microscopy images characterized by several challenges such as contrast variations, different foreground and background configurations, depth occlusion, stain diffusion with no distinct boundaries for the venule part. Our previous work [1] characterized by good segmentation for the arteriole part, however it did not work well with venule part (not introduced in the paper). Our proposed algorithm works well for both of them with less time needed for the training and testing.…”

Section: Introductionmentioning

confidence: 96%

“…The training doesn't need any condition for the patches to be considered as foreground. In our previous work [1], the patch is considered as foreground if the vessel passes through the center of the patch, otherwise it is a background. In this architecture, there is no need for any condition as the network will learn the morphological features from the patches themselves using our semantic network.…”

mentioning

confidence: 99%

“…Our new architecture is faster to converge compared to [1] since it learns pixels attributes and their relations rather than classifying patches. See figure 2, the top part contains two sets of patches that considered as input for both networks (VNet [1]) and our proposed (SVNet), however, the training is different between the two. In A, the vessel is considered a vessel/foreground if the the vessel passes through the center of the patch otherwise, it is a non-vesel/background patch.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Patch-Based Semantic Segmentation for Detecting Arterioles and Venules in Epifluorescence Imagery

Kassim

Glinskii

Glinsky

et al. 2018

2018 IEEE Applied Imagery Pattern Recognition Workshop (AIPR)

View full text Add to dashboard Cite

Segmentation and quantification of microvasculature structures are the main steps toward studying microvasculature remodeling. The proposed patch based semantic architecture enables accurate segmentation for the challenging epifluorescence microscopy images. Our pixel-based fast semantic network trained on random patches from different epifluorescence images to learn how to discriminate between vessels versus nonvessels pixels. The proposed semantic vessel network (SVNet) relies on understanding the morphological structure of the thin vessels in the patches rather than considering the whole image as input to speed up the training process and to maintain the clarity of thin structures. Experimental results on our ovariectomized-ovary removed (OVX)mice dura mater epifluorescence microscopy images shows promising results in both arteriole and venule part. We compared our results with different segmentation methods such as local, global thresholding, matched based filter approaches and related state of the art deep learning networks. Our overall accuracy (> 98%) outperforms all the methods including our previous work (VNet). [1].

show abstract

“…Our architecture accepts patches with size 32 × 32 and predict pixel wise the whole image. This architecture has two advantages compared to our previous work [1]:…”

Section: Training and Testingmentioning

confidence: 98%

Section: Introductionmentioning

confidence: 96%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Patch-Based Semantic Segmentation for Detecting Arterioles and Venules in Epifluorescence Imagery

Kassim

Glinskii

Glinsky

et al. 2018

2018 IEEE Applied Imagery Pattern Recognition Workshop (AIPR)

View full text Add to dashboard Cite

show abstract

“…In the detection of lesion targets and diseases, there are cancerous tissue recognition [13], detecting cardiovascular disease [14], and melanoma recognition [15]. In the segmentation of organs and substructures, there are studies on skin lesion segmentation [16], microvasculature segmentation of arterioles [17], tumor segmentation [18]. In addition, there are many other applications, such as studies of visual attention of patients with Dementia [19], diagnosis of cirrhosis stage [20], constructing brain maps [21].…”

Section: Related Workmentioning

confidence: 99%

Convolutional herbal prescription building method from multi-scale facial features

Liao

Wen

et al. 2019

Multimed Tools Appl

View full text Add to dashboard Cite

In Traditional Chinese Medicine (TCM), facial features are important basis for diagnosis and treatment. A doctor of TCM can prescribe according to a patient's physical indicators such as face, tongue, voice, symptoms, pulse. Previous works analyze and generate prescription according to symptoms. However, research work to mine the association between facial features and prescriptions has not been found for the time being. In this work, we try to use deep learning methods to mine the relationship between the patient's face and herbal prescriptions (TCM prescriptions), and propose to construct convolutional neural networks that generate TCM prescriptions according to the patient's face image. It is a novel and challenging job. In order to mine features from different granularities of faces, we design a multi-scale convolutional neural network based on three-grained face, which mines the patient's face information from the organs, local regions, and the entire face. Our experiments show that convolutional neural networks can learn relevant information from face to prescribe, and the multi-scale convolutional neural networks based on three-grained face perform better.

show abstract

Image Analysis for Ophthalmology: Segmentation and Quantification of Retinal Vascular Systems

Palaniappan

Bunyak

Chaurasia

2019

Ocular Fluid Dynamics

View full text Add to dashboard Cite

Microvasculature segmentation of arterioles using deep CNN

Cited by 16 publications

References 15 publications

Patch-Based Semantic Segmentation for Detecting Arterioles and Venules in Epifluorescence Imagery

Patch-Based Semantic Segmentation for Detecting Arterioles and Venules in Epifluorescence Imagery

Convolutional herbal prescription building method from multi-scale facial features

Image Analysis for Ophthalmology: Segmentation and Quantification of Retinal Vascular Systems

Contact Info

Product

Resources

About