Advanced searches left 3/3

Abdominal - Astrophysics Data System

Summarized by Plex Scholar
Last Updated: 10 August 2022

* If you want to update the article please login/register

Driving Points Prediction For Abdominal Probabilistic Registration

Probabilistic displacement registration software estimated displacement distribution for a subset of points by comparing feature vectors of points from the two images as one of the many registration options were developed for this task. The driving points predictor is optimized in an end-to-end fashion to infer driving points that are tailored to a particular registration pipeline, relative to previously proposed methods. In particular, we compared the results of six different probabilistic displacement registration models when using a driving points forecaster or one of two other traditional driving point selection methods.

Source link: https://ui.adsabs.harvard.edu/abs/2022arXiv220803232J/abstract


A New Probabilistic V-Net Model with Hierarchical Spatial Feature Transform for Efficient Abdominal Multi-Organ Segmentation

Accurate and robust abdominal multi-organ segmentation from CT imaging of various modalities is a difficult challenge due to numerous abdominal organ shape and appearance variations among abdominal organs, as well as complex inter- and intra-organ configurations. We introduce a probabilistic multi-organ segmentation network with hierarchical spatial-wise feature modulation to capture flexible organ semantic variants and inject the learnedt variants of feature maps for guiding segmentation. Then by integrating these learned variations into the V-Net decoder hierarchically, with the ability to convert the variations into conditional Affine transformation parameters for spatially variable feature maps modulating and guiding the fine-scale segmentation.

Source link: https://ui.adsabs.harvard.edu/abs/2022arXiv220801382X/abstract


Cardiovascular disease and all-cause mortality risk prediction from abdominal CT using deep learning

Healthy patients aged 50-65, in this study, we investigated how anatomic neural network could predict cardiovascular disease risk from abdominal CT scans obtained for routine CT colonography. We find that adding a variant of the auto encoder to the CNN classifier improves the CNN classifier's accuracy for five-year survival prediction. Our five-year survival prediction model is more accurate than the Framingham Risk Score and shows nearly identical results to the one used in Pickhardt et al.

Source link: https://ui.adsabs.harvard.edu/abs/2022SPIE12033E..2NE/abstract


Automated segmentation of oblique abdominal muscle based on body cavity segmentation in torso CT images using U-Net

Organs are present in the body cavity region, and it is an important area for muscle segmentation. In terms of the average dice value, the segmentation accuracies of the body cavity and oblique abdominal muscle in 16 cases were 98. 5 percent and 84. 9 percent, respectively. In addition, body cavity knowledge reduced the number of over-extracted pixels by 36. 2 percent in the segmentation of the oblique abdominal muscles adjacent to the body cavity segmentation, thus increasing segmentation accuracy. It could be helpful to determine whether the proposed simplification of CT images by segmentation of body cavities is also efficient for abdominal musculoskeletal muscles adjacent to body cavities partitioned by tendon ends, such as the rectus abdominis.

Source link: https://ui.adsabs.harvard.edu/abs/2022SPIE12177E..1VK/abstract


Deep pancreas segmentation through quantification of pancreatic uncertainty on abdominal CT images

Accurate segmentation of the pancreas on abdominal CT photographs is a first step toward understanding the pancreas in pancreatic cancer diagnosis, surgery, and treatment planning. However, pancreas segmentation is especially difficult due to the pancreas' characteristics of high inside and outside patient variation, as well as poor comparison with surrounding organs. The purpose of this report is to enhance the results of pancreas segmentation by increasing the degree of certainty in areas with high variability due to the pancreas' characteristics.

Source link: https://ui.adsabs.harvard.edu/abs/2022SPIE12033E..3PY/abstract


Development of a novel airbag system of abdominal compression for reducing respiratory motion: preliminary results in healthy volunteers

The airbag system consists of a six-sided polygon inflatable airbag, a same shape plate, a rigid air supply tube, an air-supply pump, and a digital pressure load cell monitor. To measure compression pressure load changes, Piezoelectric sensors were embedded in the plate to detect compression pressure load variations; pressure load data was transferred to the digital pressure load cell monitor via Bluetooth; pressure load data was transferred to the digital pressure load cell monitor by Bluetooth. The maximum inspiration pressure load was 4. 48 u00b1 0. 86 kgf, while the minimum expiration pressure load was 3. 69 u00b1 0. 95 kgf. Significant movement reduction was seen in the coronal plane's left diaphragm, pancreas, and liver, as well as the right kidney and liver. This novel airbag abdominal compression system was found to be safe during the experiment and successful in reducing internal organ respiratory motion reduction, and it promises to be a quick and effective tool for clinical radiotherapy.

Source link: https://ui.adsabs.harvard.edu/abs/2022JRadR..63..699L/abstract


Ultrastructural changes in the crayfish abdominal ganglia after axotomy

We investigated ultrastructural changes in ganglia abdomibal neurons and glia cells of ganglia abdomibal 4 and 24 hours after transection of interganglionic connectives by electron microscopy. Experiments on such model organisms as ganglia of invertebrates provide insight into the physiological mechanisms of the nervous system's reactions to mechanical injury. The nuclear chromatin of neurons differed in the degree of condensation in the control samples, with neurons' bodies and nuclei having a rounded shape. The bodies of neurons or unmyelinated axons of the neuropil were surrounded by cells of Glial cells, resulting in a multilayer sheath closely attached to the neuron soma or axons. Although some of the identified ultrastructural changes in the abdominal nerve cord of crayfish's embryographic stage necrosis may have arisents, chromatin contraction and condensation should be attributed to a mixed type of cell death, some of the described cell death modifications should be attributed to a mixed pattern of cell death.

Source link: https://ui.adsabs.harvard.edu/abs/2022SPIE12192E..04P/abstract


Combining Hybrid Architecture and Pseudo-label for Semi-supervised Abdominal Organ Segmentation

Abdominal organ segmentation has numerous important scientific uses, including organ quantification, surgical planning, and disease diagnosis. However, manually annotating organs from CT scans is time-consuming and labor-intensive. We then tie the model's performance and generalization capabilities with lightweight PHTrans for training, which we integrate with label data together into a two-stage segmentation framework with lightweight PHTrans for training to extend the model's effectiveness and generalization capability while remaining cost-effective. The average inference time is 18. 62 s, the average maximum GPU memory is 1995. 04 MB, and the area under the CPU utilization curve are 23196. 68 and 319. 67.

Source link: https://ui.adsabs.harvard.edu/abs/2022arXiv220711512L/abstract


Data Adaptive Regularization for Abdominal Quantitative Susceptibility Mapping

Methods and Methods: An improved approach to estimation of magnetic susceptibility distribution is developed as a constrained reconstruction issue that includes estimates of the input data quality and anatomical priors obtained from chemical shift-encoded imaging. At 3T, the proposed procedure was compared to the state-of-the-art approach in liver QSM for two multi-echo SGRE protocols with different acquisition parameters. Conclusions: The data-adaptive technique yielded susceptibility maps with improved subjective quality as a result of reduced shading artifacts. Conclusions: The new data-adaptive QSM algorithm could help quantifying liver iron concentration with improved repeatability/reproducibility across a variety of acquisition conditions as 3T.

Source link: https://ui.adsabs.harvard.edu/abs/2022arXiv220711416V/abstract

* Please keep in mind that all text is summarized by machine, we do not bear any responsibility, and you should always check original source before taking any actions

* Please keep in mind that all text is summarized by machine, we do not bear any responsibility, and you should always check original source before taking any actions