.
  Automatic functional region annotation of liver should be very useful for preoperative planning of liver resection in the clinical domain. However, many traditional computer-aided annotation methods based on anatomical landmarks or the vascular tree often fail to extract accurate liver segments. Furthermore, these methods are difficult to fully automate and thus remain time-consuming. To address these issues, in this study we aim to develop a fully-automated approach for functional region annotation of liver using deep learning based on 2.5D class-aware deep neural networks with spatial adaptation.
 
  112 CT scans were fed into our 2.5D class-aware deep neural network with spatial adaptation for automatic functional region annotation of liver. The proposed model was built upon the ResU-net architecture, which adaptively selected a stack of adjacent CT slices as input and, generating masks corresponding to the center slice, automatically annotated the liver functional region from abdominal CT images. Furthermiver from CT images. The experimental results demonstrated that the proposed method can attain a high average dice score and low computational time. Therefore, this work should allow for improved liver surgical resection planning by our precise segmentation and simple fully-automated method.
  Left ventricle (LV) dysfunction always occurs at early heart-failure stages, producing variations in the LV flow patterns. Cardiac diagnostics may therefore benefit from flow-pattern analysis. Several visualization tools have been proposed that require ultrafast ultrasound acquisitions. However, ultrafast ultrasound is not standard in clinical scanners. Meanwhile techniques that can handle low frame rates are still lacking. As a result, the clinical translation of these techniques remains limited, especially for 3D acquisitions where the volume rates are intrinsically low.
 
  To overcome these limitations, we propose a novel technique for the estimation of LV blood velocity and relative-pressure fields from dynamic contrast-enhanced ultrasound (DCE-US) at low frame rates. Different from other methods, our method is based on the time-delays between time-intensity curves measured at neighbor pixels in the DCE-US loops. Using Navier-Stokes equation, we regularize the obtained velocity fields and derive relativerd ultrasound scanners. The clinical value of the method in the context of CRT is also shown.
 Using the proposed method, adequate visualization and quantification of blood flow patterns are successfully enabled based on low-rate DCE-US of the LV, facilitating the clinical adoption of the method using standard ultrasound scanners. The clinical value of the method in the context of CRT is also shown.
  Four tie wings brackets are widely used in orthodontics, while the Six Tie Wings Brackets (STWB) are recently emerging in fixed orthodontic appliances due to their claim for less friction and thus faster teeth movement. The aim of this work was to evaluate the stress distribution and deformation during simulated mesio-distal tipping forces in Stainless Steel (SS) six tie wings orthodontic bracket using Finite Element Analysis (FEA).
 
  A six tie wings bracket (Synergy®, RMO, USA) dimensions were measured using the Vision system and a 3D model of the bracket was constructed. A Finite Element (FE) model was developed and mesio-distal tipping forces of 1.22 N to 1.96 N (125 to 200 gm) in increments were applied on the gingival and incisal slot walls. The stress distribution and deformation were recorded at specific points in the bracket and analyzed.
 
  The maximum deformation and stress distribution for the mesial and distal tipping forces of 1.96 N were recorded as 0.137 µm and 10.60 MPa respectively. The stred minimal in the mid-tie wings. Clinicians should be aware of this behavior of STWB in making decisions to alter the tipping forces in the archwire to compensate for the tie wing deformation in refining the teeth position.
  The biomedical engineering must frequently develop sensor designs by including information from performance of bio-samples (cell cultures or tissues), technical specifications of transducers, and constrains from electronic circuits. A computer program for real-time cell culture monitoring system design is developed; analyzing, modelling and integrating into the program design flow the electrodes, cell culture and test circuit's influences.
 
  The computer tool, first, generates an equivalent electric circuit model for the cell-electrode bio-systems based on the area covered by cells, which also considers the cell culture dynamics. Second, proposes an Oscillation Based Test (OBT) parameterized circuit, for Electrical Cell-Substrate Sensing (ECIS) measurements of the cell culture system bioimpedance. Third, simulates electrically the full system to define the best system parameter values for the sensor.
 
  Reported experimental results are based on commercial gold electrodes and the AA8 cell line. Characteristis proposed a computer program for system design of biosensors applied to monitoring cell culture dynamics. The program allows obtaining confident system information by electrical stimulation. All system components (electrodes, cell culture and test circuits) are properly modelled. The employed procedure can be applied to any other 2D electrode layout or alternative circuit technique for ECIS test. Finally, deep insight information on cell size, number, and time-division can be extracted from the comparison with real cell culture assays in the future.
  Accurate and reliable segmentation of the prostate gland in MR images can support the clinical assessment of prostate cancer, as well as the planning and monitoring of focal and loco-regional therapeutic interventions. Despite the availability of multi-planar MR scans due to standardized protocols, the majority of segmentation approaches presented in the literature consider the axial scans only.  https://www.selleckchem.com/products/Eloxatin.html  In this work, we investigate whether a neural network processing anisotropic multi-planar images could work in the context of a semantic segmentation task, and if so, how this additional information would improve the segmentation quality.
 
  We propose an anisotropic 3D multi-stream CNN architecture, which processes additional scan directions to produce a high-resolution isotropic prostate segmentation. We investigate two variants of our architecture, which work on two (dual-plane) and three (triple-plane) image orientations, respectively. The influence of additional information used by these models is evaluated by comparing them with a single-plane baseline processing only axial images.