An official website of the United States government
For some images of a single stem cell, the boundary delineating the cell is discontinuous or blurry at some locations. If the statistical region merging (SRM) method is applied directly on such images, the image segmentation results may not be ideal. In this paper, for each such image, we add some gradient information into the image; then apply a discontinuous filter on the image so that the image is smoothed a bit and the edges of the image are kept well. Next, closing operations of morphology are applied on the filtered image; and the processed image is segmented using SRM. Finally, apply a threshold on the segmented image to obtain a binary image; apply a hole-filling function to the binary image; extract the biggest connected component in the hole-filled image; and apply a linear transform on the image of the biggest component to match the input image as well as possible in terms of the least squares fitting. This transformed image is the segmentation result. We have applied SRM using connectivity of 4 and 8 as well as a hexagonal lattice. The corresponding segmentation results are tabulated for convenient comparisons; and the results can show that the proposed method may be helpful for the segmentation of such images.
more »
« less
Image Segmentation for Hexagonally Sampled Images Using Statistical Region Merging
The statistical region merging (SRM) method for image segmentation is based on some solid probabilistic and statistical principles. It produces good segmentation results, and is efficient in term of the computational time. The original SRM algorithm is for Cartesian images sampled by square lattices (sqL). Because hexagonal lattices (hexL) have the advantage that each lattice point in a hexL has six equidistant adjacent lattice points, in this paper, we perform image segmentation for hexagonally sampled images using SRM. We first convert the SRM algorithm from sqLs to hexLs. Then we use some test images to compare the corresponding segmentation effect for hexLs versus sqLs. The experimental results have shown that a hexL exhibits evidently better image segmentation effect than the corresponding sqL (with the same spatial sampling rate as the hexL) using the usual 4-connectivity. Finally, we point out that CT image segmentation may benefit from using hexLs since they provide better image reconstruction effect than sqLs.
more »
« less
- Award ID(s):
- 2000158
- PAR ID:
- 10415028
- Date Published:
- Journal Name:
- 2022 6th International Conference on Imaging, Signal Processing and Communications (ICISPC)
- Volume:
- 2022
- Page Range / eLocation ID:
- 37 to 42
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Implicit neural representations (INR) have been recently proposed as deep learning (DL) based solutions for image compression. An image can be compressed by training an INR model with fewer weights than the number of image pixels to map the coordinates of the image to corresponding pixel values. While traditional training approaches for INRs are based on enforcing pixel-wise image consistency, we propose to further improve image quality by using a new structural regularizer. We present structural regularization for INR compression (SINCO) as a novel INR method for image compression. SINCO imposes structural consistency of the compressed images to the groundtruth by using a segmentation network to penalize the discrepancy of segmentation masks predicted from compressed images. We validate SINCO on brain MRI images by showing that it can achieve better performance than some recent INR methods.more » « less
-
Su, Ruidan (Ed.)In this paper, morphological operations on regular hexagonal structures are considered, where a regular hexagonal structure is a subset of a hexagonal lattice and consists of the sampled points for the discretization of a regular hexagonal region. First, a sequence of reasonable structure elements (SE) for hexagonal lattices are provided, and the decompositions of the SEs are shown. Second, based on the decompositions of the SEs, some efficient algorithms for morphological operations on the regular hexagonal structures are developed. Finally, the algorithms are tested using a computerized tomography (CT) image, and promising applications of such algorithms on CT image reconstruction and segmentation are pointed out.more » « less
-
Deep learning has been applied to magnetic resonance imaging (MRI) for a variety of purposes, ranging from the acceleration of image acquisition and image denoising to tissue segmentation and disease diagnosis. Convolutional neural networks have been particularly useful for analyzing MRI data due to the regularly sampled spatial and temporal nature of the data. However, advances in the field of brain imaging have led to network- and surface-based analyses that are often better represented in the graph domain. In this analysis, we propose a general purpose cortical segmentation method that, given resting-state connectivity features readily computed during conventional MRI pre-processing and a set of corresponding training labels, can generate cortical parcellations for new MRI data. We applied recent advances in the field of graph neural networks to the problem of cortical surface segmentation, using resting-state connectivity to learn discrete maps of the human neocortex. We found that graph neural networks accurately learn low-dimensional representations of functional brain connectivity that can be naturally extended to map the cortices of new datasets. After optimizing over algorithm type, network architecture, and training features, our approach yielded mean classification accuracies of 79.91% relative to a previously published parcellation. We describe how some hyperparameter choices including training and testing data duration, network architecture, and algorithm choice affect model performance.more » « less
-
This paper presents a tool-pose-informed variable center morphological polar transform to enhance segmentation of endoscopic images. The representation, while not loss-less, transforms rigid tool shapes into morphologies consistently more rectangular that may be more amenable to image segmentation networks. The proposed method was evaluated using the U-Net convolutional neural network, and the input images from endoscopy were represented in one of the four different coordinate formats (1) the original rectangular image representation, (2) the morphological polar coordinate transform, (3) the proposed variable center transform about the tool-tip pixel and (4) the proposed variable center transform about the tool vanishing point pixel. Previous work relied on the observations that endoscopic images typically exhibit unused border regions with content in the shape of a circle (since the image sensor is designed to be larger than the image circle to maximize available visual information in the constrained environment) and that the region of interest (ROI) was most ideally near the endoscopic image center. That work sought an intelligent method for, given an input image, carefully selecting between methods (1) and (2) for best image segmentation prediction. In this extension, the image center reference constraint for polar transformation in method (2) is relaxed via the development of a variable center morphological transformation. Transform center selection leads to different spatial distributions of image loss, and the transform-center location can be informed by robot kinematic model and endoscopic image data. In particular, this work is examined using the tool-tip and tool vanishing point on the image plane as candidate centers. The experiments were conducted for each of the four image representations using a data set of 8360 endoscopic images from real sinus surgery. The segmentation performance was evaluated with standard metrics, and some insight about loss and tool location effects on performance are provided. Overall, the results are promising, showing that selecting a transform center based on tool shape features using the proposed method can improve segmentation performance.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/ICISPC57208.2022.00015
