Rectangular Region Of Interest Research Articles

Influence of oblique proximal ulnar osteotomy on humeral intracondylar fissures in 35 spaniel breed dogs.

To investigate the effects of oblique proximal ulnar osteotomy (PUO) on the healing of humeral intracondylar fissure (HIF) in spaniel breed dogs. Clinical retrospective study. A total of 51 elbows from 35 spaniel dogs. An oblique PUO was performed in dogs diagnosed with HIF. The degree of healing of HIF was subjectively and objectively assessed on preoperative and long-term follow-up CT imaging. Objective assessment was performed by measuring the bone density in Hounsfield units (HU) of a rectangular region of interest (ROI) encompassing the entire hypoattenuated humeral fissure. Major and minor complications were recorded. A total of 24 partial and 27 complete HIFs were diagnosed. The follow-up CT scan was performed at a median 18.5 months (range 10-49 months). Subjective assessment confirmed partial or complete healing of the HIF in 41 elbows (80.3%). Objective assessment confirmed a difference in mean HU of the HIF's ROI between preoperative (HU 640) and last follow-up CT images (HU 835) (p = .001). Young dogs (<14 months) had the highest increase in HU of the HIF's ROI. Major complications occurred in five dogs (6 limbs) of which four were related to the lack of healing of the fissure (7.8%). Oblique PUO resulted in partial or complete healing of HIF and pain resolution in the majority of dogs. This study introduces an innovative approach to achieve healing of the HIF in the dog, which may help reduce the high complication rate traditionally associated with the use of transcondylar screws.

Analysis of the Efficacy of Elastography in Comparison with Dynamic Renal Nuclear Scintigraphy in the Evaluation of Unilateral Pelvi–Ureteric Junction Obstruction

IntroductionIn hydronephrosis due to pelviureteric junction obstruction (PUJO), an obstruction to urine flow may lead to increased pelvic pressure, which may cause interstitial fibrosis and renal impairment. Recently, there have been reports on renal pelvic assessment using ultrasound elastography (USE). This study was conducted to see if USE can evaluate PUJO and if it can be correlated to the findings of the dynamic renal nuclear scan. Material and methodsIn this observational study, only patients with unilateral PUJO underwent acoustic radiation force impulse (ARFI) elastography. A rectangular region of interest (ROI) measuring 5 × 10 mm was positioned on the cortex region of the upper, mid, and lower poles of the affected kidney. Three valid measurements were obtained, from which a mean value was calculated. A dynamic renal nuclear scan using Technetium-99m ethylene dicysteine (EC or TC99 m EC) was obtained and split renal function (SRF) was used for comparison. ResultsIn the group of 20 patients, the mean age was 3.37 years. The mean SRF of the affected kidney was 26.65 %, and the corresponding USE value was 0.45 kpa. The Spearman's rho correlation coefficient for SRF and USE was 1 and 0.672, respectively (p = 0.001). Elastography was not feasible if SRF was less than 20 %. ConclusionUSE may be able to comment on the renal functional status of hydronephrosis. If USE is reported as non-feasible, it may suggest that renal function is grossly compromised. It may serve as an alternative diagnostic modality for renal functional evaluation. Level of evidenceLevel II, Prospective Cohort Study.

Interobserver variability in the determination of bone mineral density in Hounsfield units from differently configured fields of measurement in the cancellous bone of vertebral bodies from elderly body donors

BackgroundDue to the absence of suitable diagnostic procedures, osteoporosis (OP) is frequently detected late or not at all. Many elderly persons undergo computed tomographies (CT). The routine determination of Hounsfield units (HU) in bone as a part of these examinations could close a gap here. MethodsSpines were extracted from 22 body donors, fixed in a PVC water phantom, and subjected to a high-resolution CT investigation. Cancellous bone was examined and its bone mineral density measured in HU from cervical vertebra 3 to lumbar vertebra 5 (484 vertebral bodies). On sagittal sections, a circular and a rectangular region of interest (ROI) were defined in mid-vertebral cancellous bone, positioned manually, and the measurements were performed by three experienced radiologists. Bone mineral density (BMD), measured in mg/cm3, was used to determine the presence of OP. ResultsAll of the spines were osteoporotic. In the presence of a BMD below 60 mg/cm3 and HU values below 63.36 in lumbar vertebrae, there were significantly more vertebral body fractures in the thoracic and thoracolumbar spine. No difference was observed between the manually positioned circular and rectangular regions of interest (ROI) on the sagittal CT section (p > 0.05). Similar HU counts were obtained by the individual examiners (p > 0.05). The following formula was used to determine QCT values on a non-contrasted CT of the spine: QCT = 0.6 × HU + 13.7. ConclusionsMeasurement of the density of cancellous bone in HU can be used to determine BMD for estimating demineralization. Quantitative BMD values in mg/cm3, which can be calculated from the HU data, concur well with QCT values.

Tracking by segmentation with future motion estimation applied to person-following robots.

Person-following is a crucial capability for service robots, and the employment of vision technology is a leading trend in building environmental understanding. While most existing methodologies rely on a tracking-by-detection strategy, which necessitates extensive datasets for training and yet remains susceptible to environmental noise, we propose a novel approach: real-time tracking-by-segmentation with a future motion estimation framework. This framework facilitates pixel-level tracking of a target individual and predicts their future motion. Our strategy leverages a single-shot segmentation tracking neural network for precise foreground segmentation to track the target, overcoming the limitations of using a rectangular region of interest (ROI). Here we clarify that, while the ROI provides a broad context, the segmentation within this bounding box offers a detailed and more accurate position of the human subject. To further improve our approach, a classification-lock pre-trained layer is utilized to form a constraint that curbs feature outliers originating from the person being tracked. A discriminative correlation filter estimates the potential target region in the scene to prevent foreground misrecognition, while a motion estimation neural network anticipates the target's future motion for use in the control module. We validated our proposed methodology using the VOT, LaSot, YouTube-VOS, and Davis tracking datasets, demonstrating its effectiveness. Notably, our framework supports long-term person-following tasks in indoor environments, showing promise for practical implementation in service robots.

Utility of machine learning for identifying stapes fixation on ultra-high-resolution CT.

Imaging diagnosis of stapes fixation (SF) is challenging owing to a lack of definite evidence. We developed a comprehensive machine learning (ML) model to identify SF on ultra-high-resolution CT. We retrospectively enrolled 109 participants (143 ears) and divided them into the training set (115 ears) and test set (28 ears). Stapes mobility (SF or non-SF) was determined by surgical inspection. In the ML analysis, rectangular regions of interest were placed on consecutive axial slices in the training set. Radiomic features were extracted and fed into the training session. The test set was analyzed using 7 ML models (support vector machine, k nearest neighbor, decision tree, random forest, extra trees, eXtreme Gradient Boosting, and Light Gradient Boosting Machine) and by 2 dedicated neuroradiologists. Diagnostic performance (sensitivity, specificity and accuracy, with surgical findings as the reference) was compared between the radiologists and the optimal ML model by using the McNemar test. The mean age of the participants was 42.3 ± 17.5years. The Light Gradient Boosting Machine (LightGBM) model showed the highest sensitivity (0.83), specificity (0.81), accuracy (0.82) and area under the curve (0.88) for detecting SF among the 7 ML models. The neuroradiologists achieved good sensitivities (0.75 and 0.67), moderate-to-good specificities (0.63 and 0.56) and good accuracies (0.68 and 0.61). This model showed no statistical differences with the neuroradiologists (P values 0.289-1.000). Compared to the neuroradiologists, the LightGBM model achieved competitive diagnostic performance in identifying SF, and has the potential to be a supportive tool in clinical practice.

Rectangular and radial region of interests on the edge of cylindrical phantom for spatial resolution measurement

&lt;span lang="EN-US"&gt;The purpose of this study was to evaluate the effect of rectangular region of interest (ROI) size on modulation transfer function (MTF), to develop the radial ROI, and to compare both ROIs performances for MTF measurement using a cylindrical polymethyl methacrylate (PMMA) phantom. The PMMA phantom used in this study was rotated 45°. Four rectangular ROIs and a radial ROI were created to measure the MTF value. The rectangular ROI sizes were 3×41, 21×41, 41×41, and 61×41 pixels; each was placed at upper phantom edge. The radial ROI’s length was 41 pixels and placed at several points in phantom edge. The MTF calculation was automatically conducted using MATLAB. The MTFs from rectangular ROIs and radial ROI were then compared. The comparison of the MTF measurement was also conducted using three different filters. The MTF which used radial ROI was smoother than those of rectangular ROI for all filters. This indicated that radial ROI was more resistant to noise than rectangular ROI. Rectangular ROI with the 41×41 pixels had similar 50% and 10% MTF values with the radial ROI. The MTF value which was obtained using radial ROI is more accurate and robust than those obtained using rectangular ROI.&lt;/span&gt;

Deep Learning for Predicting Distant Metastasis in Patients with Nasopharyngeal Carcinoma Based on Pre-Radiotherapy Magnetic Resonance Imaging.

Accurate pre-treatment prediction of distant metastasis in patients with Nasopharyngeal Carcinoma (NPC) enables the implementation of appropriate treatment strategies for high-risk individuals. To develop and assess a Convolutional Neural Network (CNN) model using pre-therapy Magnetic Resonance (MR) imaging to predict distant metastasis in NPC patients. We retrospectively reviewed data of 441 pathologically diagnosed NPC patients who underwent complete radiotherapy and chemotherapy at Renmin Hospital of Wuhan University (Hubei, China) between February 2012 and March 2018. Using Adobe Photoshop, an experienced radiologist segmented MR images with rectangular regions of interest. To develop an accurate model according to the primary tumour, Cervical Metastatic Lymph Node (CMLN), the largest area of invasion of the primary tumour, and image segmentation methods, we constructed intratumoural and intra-peritumoural datasets that were used for training and test of the transfer learning models. Each model's precision was assessed according to its receiver operating characteristic curve and accuracy. Generated high-risk-related Grad-Cams demonstrated how the model captured the image features and further verified its reliability. Among the four models, all intra-peritumoural datasets performed better than the corresponding intratumoural datasets, with the CMLN intra-peritumoural dataset exhibiting the best performance (average area under the curves (AUCs) = 0.88). There was no significant difference between average AUCs of the Max and NPC tumour datasets. AUCs of the eight datasets for the four models were higher than those of the Tumour-Node-Metastasis staging system (AUC=0.67). In most datasets, the xception model had higher AUCs than other models. The efficientnet-b0 and xception models efficiently extracted high-risk features. The CNN model predicted distant metastasis in NPC patients with high accuracy. Compared to the primary tumour, the CMLN better predicted distant metastasis. In addition to intratumoural data, peritumoural information can facilitate the prediction of distant metastasis. With a larger sample size, datasets of the largest areas of tumour invasion may achieve meaningful accuracy. Among the models, xception had the best overall performance.

Deep-Learning-Enabled Computer-Aided Diagnosis in the Classification of Pancreatic Cystic Lesions on Confocal Laser Endomicroscopy.

Accurate classification of pancreatic cystic lesions (PCLs) is important to facilitate proper treatment and to improve patient outcomes. We utilized the convolutional neural network (CNN) of VGG19 to develop a computer-aided diagnosis (CAD) system in the classification of subtypes of PCLs in endoscopic ultrasound-guided needle-based confocal laser endomicroscopy (nCLE). From a retrospectively collected 22,424 nCLE video frames (50 videos) as the training/validation set and 11,047 nCLE video frames (18 videos) as the test set, we developed and compared the diagnostic performance of three CNNs with distinct methods of designating the region of interest. The diagnostic accuracy for subtypes of PCLs by CNNs with manual, maximal rectangular, and U-Net algorithm-designated ROIs was 100%, 38.9%, and 66.7% on a per-video basis and 88.99%, 73.94%, and 76.12% on a per-frame basis, respectively. Our per-frame analysis suggested differential levels of diagnostic accuracy among the five subtypes of PCLs, where non-mucinous PCLs (serous cystic neoplasm: 93.11%, cystic neuroendocrine tumor: 84.31%, and pseudocyst: 98%) had higher diagnostic accuracy than mucinous PCLs (intraductal papillary mucinous neoplasm: 84.43% and mucinous cystic neoplasm: 86.1%). Our CNN demonstrated superior specificity compared to the state-of-the-art for the classification of mucinous PCLs (IPMN and MCN), with high specificity (94.3% and 92.8%, respectively) but low sensitivity (46% and 45.2%, respectively). This suggests the complimentary role of CNN-enabled CAD systems, especially for clinically suspected mucinous PCLs.

Additive Manufacturing of Hard Magnetic Passive Shims to Increase Field Homogeneity of a Halbach Magnet

Obtaining a highly homogeneous magnetic field is desired for field‐controlled applications. For example, the resolution of magnetic analysis methods can be improved by generating a stronger and more homogeneous field over the region of interest (ROI). A set of 3D‐printed passive shims is fabricated using additive manufacturing to improve the magnetic field homogeneity of a Halbach magnet assembly. The feedstock is a custom acrylonitrile butadiene styrene (ABS)‐hard magnet composite filament filled with 60% wt. isotropic NdFeB. Additionally, a method for investigating the remanence is developed and validated. The result reveals a good agreement between the new method and existing measurement techniques for the remanence of permanent magnets. It is also shown that the additive manufacturing procedure has negligible effects on the magnetic properties. Performing a parametric study over a rectangular ROI, an optimized shim configuration is achieved. In the optimized and 3D‐printed configuration, the average norm of the magnetic flux density, Bnorm, is increased by 13% and, more importantly, a 43% increase in the magnetic uniformity is obtained. These results highlight the great potential of freeform manufacturing, namely, additive manufacturing, to tailor the properties of magnet structures.

Automated MRI Field of View Prescription from Region of Interest Prediction by Intra-Stack Attention Neural Network.

Manual prescription of the field of view (FOV) by MRI technologists is variable and prolongs the scanning process. Often, the FOV is too large or crops critical anatomy. We propose a deep learning framework, trained by radiologists' supervision, for automating FOV prescription. An intra-stack shared feature extraction network and an attention network are used to process a stack of 2D image inputs to generate scalars defining the location of a rectangular region of interest (ROI). The attention mechanism is used to make the model focus on a small number of informative slices in a stack. Then, the smallest FOV that makes the neural network predicted ROI free of aliasing is calculated by an algebraic operation derived from MR sampling theory. The framework's performance is examined quantitatively with intersection over union (IoU) and pixel error on position and qualitatively with a reader study. The proposed model achieves an average IoU of 0.867 and an average ROI position error of 9.06 out of 512 pixels on 80 test cases, significantly better than two baseline models and not significantly different from a radiologist. Finally, the FOV given by the proposed framework achieves an acceptance rate of 92% from an experienced radiologist.

Trajectory-Based 3D Point Cloud ROI Determination Methods for Autonomous Mobile Robot

With depth cameras and LiDAR improving and generating more data, their applications in 3D point clouds are growing rapidly. However, the vast amount of generated data increases the computational load and results in a shortage of storage space. Therefore, a preprocessing step to reduce the number of points is required before using the 3D point cloud. This study proposes region of interest (ROI) determination methods that sequentially construct circular and rectangular ROIs along the target trajectory of the robot to extract only crucial data for the target task. These two ROI determination methods have two benefits. First, they maintain the resolution of the raw data; second, they create two ROIs that match perfectly regardless of the complexity of the trajectory. To verify the high performance of these two ROI determination methods, we conducted simulations and experiments using various data; artificial frames, keyframes, and sequential frames. As a result, when the distance between the center points was small, 25% of the diameter or height of the circular and rectangular ROIs, the classification evaluation results were closer to 1 and the processing speed was faster than the raw data acquisition rate. However, we confirm that there is a trade-off relationship between the classification results and the processing time according to the distance parameter. In addition, through the qualitative comparison with the previous study, the long cuboid ROI determination method, we identified the limitations of the previous study and the advantages of the two proposed ROI determination methods.

Changes in echo intensity of the gastrocnemius muscle with passive ankle dorsiflexion: can echo intensity be used to assess muscle elongation?

Introduction: While shear modulus has been used as an index of muscle elongation, high costs prevent its general adoption. A more general indicator that can quantify muscle elongation non-invasively is needed to develop effective methods for stretching each muscle. The purpose of this study was to determine whether the echo intensity of the muscle changes with muscle elongation compared with the shear modulus. Methods: Sixteen healthy males (24.1 ± 2.8years) participated in the study. Shear modulus and echo intensity of the medial gastrocnemius were assessed at 20° and 10° of ankle plantar-flexion, and 0°, 10°, and 20° of ankle dorsiflexion (presented as -20°, -10°, and 0°, +10°, +20°, respectively). Shear modulus was measured using ultrasound shear wave elastography. The echo intensity was quantified using the average grayscale value of a given region of interest (RoI) in longitudinal and transverse B-mode images. Grayscale analysis was performed using two RoIs: one which included as much of the muscle as possible (maximum RoI), and a rectangular one whose size and depth was identical for all images (rectangular RoI). Pearson's correlation coefficients between either the shear modulus or echo intensity and the ankle angle and between the echo intensity and shear modulus were calculated separately for each participant. Results: Average Pearson's correlation coefficient between shear modulus and ankle angle of the participants was 0.904. The average Pearson's correlation coefficients between the echo intensity and ankle angle were estimated to be 0.797 and 0.222 for the maximum RoI and 0.698 and 0.323 for the rectangular RoI in the longitudinal and transverse images, respectively. The average Pearson's correlation coefficients between the echo intensity and shear modulus were 0.684 and 0.514 for the maximum RoI, and 0.611 and 0.409 for rectangular RoI in the longitudinal and transverse images, respectively. Discussion: The results indicate that the echo intensity in the longitudinal image of the gastrocnemius, especially when assessed using the maximum RoI, increased with muscle elongation by passive ankle dorsiflexion. Therefore, assessment of the echo intensity using the maximum RoI in the longitudinal image might be useful for quantifying the muscle elongation.

Infrared nondestructive detection of defective visible-reflective solder joints in solenoid coil connectors

Nondestructive infrared detection of solder defects in solenoid coil connectors was investigated. A detailed experimental setup and a meticulous and repeatable experimental procedure were developed. The experimental methods were firmly based on the application of heat transfer science. Time averaged excess temperature ([Formula: see text]) was the sole discrimination parameter, and a difference larger than 2°C between good and defective solders was conservatively considered for good discrimination. Analysis of variance determined the minimum differences in [Formula: see text] between good and defective solder joints. The effects in discriminability of heating time ( th), time integration interval length ( ti), region of interest (ROI) geometry, and solder radiative properties were investigated. A rectangular ROI tightly enclosing the good solder was found as the best discrimination ROI. Matte black paint increasing radiative emission of solder joints significantly reduced discriminability. The defects were discriminated from the good solder for a rectangular ROI, th = 78 s, and ti = 20 s. Moreover, an excellent total inspection time of 34 s per solenoid coil is obtained by considering a well-controlled inspection environment during manufacturing, severe defects detection, and a possible 1°C difference for discrimination. Several aspects of the novel inspection procedure developed can greatly benefit the thermal imaging scientific community.

Directionally Sensitive Fractal Radiomics Compatible With Irregularly Shaped Magnetic Resonance Tumor Regions of Interest: Association With Osteosarcoma Chemoresistance.

Computational analysis of routinely acquired MRI has potential to improve the tumor chemoresistance prediction and to provide decision support in precision medicine, which may extend patient survival. Most radiomic analytical methods are compatible only with rectangular regions of interest (ROIs) and irregular tumor shape is therefore an important limitation. Furthermore, the currently used analytical methods are not directionally sensitive. To implement a tumor analysis that is directionally sensitive and compatible with irregularly shaped ROIs. Retrospective. A total of 54 patients with histopathologic diagnosis of primary osteosarcoma on tubular long bones and with prechemotherapy MRI. A 1.5 T, T2-weighted-short-tau-inversion-recovery-fast-spin-echo. A model to explore associations with osteosarcoma chemo-responsiveness included MRI data obtained before OsteoSa MAP neoadjuvant cytotoxic chemotherapy. Osteosarcoma morphology was analyzed in the MRI data by calculation of the nondirectional two-dimensional (2D) and directional and nondirectional one-dimensional (1D) Higuchi dimensions (Dh). MAP chemotherapy response was assessed by histopathological necrosis. The area under the receiver operating characteristic (ROC) curve (AUC) evaluated the association of the calculated features with the actual chemoresponsiveness, using tumor histopathological necrosis (95%) as the endpoint. Least absolute shrinkage and selection operator (LASSO) machine learning and multivariable regression were used for feature selection. Significance was set at <0.05. The nondirectional 1D Dh reached an AUC of 0.88 in association with the 95% tumor necrosis, while the directional 1D analysis along 180 radial lines significantly improved this association according to the Hanley/McNeil test, reaching an AUC of 0.95. The model defined by variable selection using LASSO reached an AUC of 0.98. The directional analysis showed an optimal predictive range between 90° and 97° and revealed structural osteosarcoma anisotropy manifested by its directionally dependent textural properties. Directionally sensitive radiomics had superior predictive performance in comparison to the standard nondirectional image analysis algorithms with AUCs reaching 0.95 and full compatibility with irregularly shaped ROIs. 3 TECHNICAL EFFICACY: Stage 1.

Quantifying Thermal Patterns Across Canine Body and Limbs

Abnormal surface patterns revealed in thermal images may indicate the presence of injury, disease, or inflammation in canines. Despite the use of infrared thermography in a laboratory setting, clinical application cannot be fully utilized without understanding isothermic patterns of the canine body. The objective of this study was to identify the thermal pattern of the canine body (Canis lupus familiaris). Rectangular regions of interest (ROIs) were drawn to represent the lateral surface of the torso (ROI 1) and hindquarter (ROI 2). Circular ROIs were analyzed along the limbs to portray joints and its diaphyses. All ROIs were detected through mean surface temperatures (STs). To identify the effect of the coat type, mean STs were categorized by each dog's hair coat type: short coat (SC), curly coat (CC), long coat (LC), and double coat (DC). The interaction between the ST of the ROIs across the body and limbs and were then analyzed using two‐way analysis of variance repeated measures (two‐way RM ANOVA) and multiple pairwise comparisons. The warmest regions of the body were found ventrally and distally in the abdominal regions of the torso (30.46 °C). Higher ST were found in areas of the hindquarter caudally and distally at the sacral end (30.53 °C). Significant differences in median ST using one‐way RM ANOVA on Ranks were observed between body percentage divisions (P &lt; 0.001). In addition, significant interactions between location of the horizontal/vertical divisions and coat types were present (P &lt; 0.001). In general, all dogs exhibited a decrease in temperature distally from the appendicular skeleton. No significant differences were found between joint and diaphyses (P &gt; 0.05). Both SC and CC dogs showed that the decrease in mean ST from the shoulder becomes significant after the shoulder. DC dogs exhibited significant ST lower on the limbs whereas LC dogs did not exhibit a significant trend.

Deep learning for locally advanced nasopharyngeal carcinoma prognostication based on pre- and post-treatment MRI

PurposeWe aimed to predict the prognosis of advanced nasopharyngeal carcinoma (stage Ⅲ-Ⅳa) using Pre- and Post-treatment MR images based on deep learning (DL). MethodsA total of 206 patients with primary nasopharyngeal carcinoma who were diagnosed and treated at the Renmin Hospital of Wuhan University between June 2012 and January 2018 were retrospectively selected. A rectangular region of interest (ROI), which included the tumor area, surrounding tissues and organs, was delineated on each Pre- and Post-treatment MR image. Two Inception-Resnet-V2 based transfer learning models, named Pre-model and Post-model, were trained with the Pre-treatment images and the Post-treatment images, respectively. In addition, an ensemble learning model based on the Pre-model and Post-models was established. The three established models were evaluated by receiver operating characteristic curve (ROC), confusion matrix, and Harrell's concordance indices (C-index). High-risk-related gradient-weighted class activation mapping (Grad-CAM) images were developed according to the DL models. ResultsThe Pre-model, Post-model, and ensemble model displayed a C-index of 0.717 (95% CI: 0.639 to 0.795), 0.811 (95% CI: 0.745–0.877), 0.830 (95% CI: 0.767–0.893), and AUC of 0.741 (95% CI: 0.584–0.900), 0.806 (95% CI: 0.670–0.942), and 0.842 (95% CI: 0.718–0.967) for the test cohort, respectively. In comparison with the models, the performance of Post-model was better than the performance of Pre-model, which indicated the importance of Post-treatment images for prognosis prediction. All three DL models performed better than the TNM staging system (0.723, 95% CI: 0.567–0.879). The captured features presented on Grad-CAM images suggested that the areas around the tumor and lymph nodes were related to the prognosis of the tumor. ConclusionsThe three established DL models based on Pre- and Post-treatment MR images have a better performance than TNM staging. Post-treatment MR images are of great significance for prognosis prediction and could contribute to clinical decision-making.

Comparison of MRI T1, T2, and T2* mapping with histology for assessment of intervertebral disc degeneration in an ovine model

An easy, reliable, and time-efficient standardized approach for assessing lumbar intervertebral disc (IVD) degeneration with relaxation times measurements in pre-clinical and clinical studies is lacking. This prospective study aims to determine the most appropriate method for lumbar IVD degeneration (IDD) assessment in sheep by comparing three quantitative MRI sequences (variable-flip-angle T1 mapping, and multi-echo T2 and T2* mapping), correlating them with Pfirrmann grading and histology. Strong intra- and interrater agreements were found for Nucleus pulposus (NP) regions-of-interest (ROI). T1, T2, and T2* mapping correlated with Pfirrmann grading and histological scoring (p < 0.05) except for the most ventral rectangular ROI on T2 maps. Correlations were excellent for all of the T1 ROIs and the T2* NP ROIs. Highly significant differences in T1 values were found between all Pfirrmann grades except between grades I/II and between grades III/IV. Significant differences were identified in the T2 and the T2* values between all grades except between grades I/III. T1, T2, and T2* relaxation times measurements of the NP are an accurate and time-efficient tool to assess lumbar IDD in sheep. Variable-flip-angle T1 mapping may be further considered as a valuable method to investigate IDD and to assess the efficacy of regenerative treatments in longitudinal studies.

Diagnosis of Serosal Invasion in Gastric Adenocarcinoma by Dual-Energy CT Radiomics: Focusing on Localized Gastric Wall and Peritumoral Radiomics Features

ObjectivesTo build a radiomics model and combined model based on dual-energy CT (DECT) for diagnosing serosal invasion in gastric adenocarcinoma.Materials and methods231 gastric adenocarcinoma patients were enrolled and randomly divided into a training (n = 132), testing (n = 58), and independent validation (n = 41) cohort. Radiomics features were extracted from the rectangular ROI of the 120-kV equivalent mixed images and iodine map (IM) images in the venous phase of DECT, which was manually delineated perpendicularly to the gastric wall in the deepest location of tumor infiltration, including the peritumoral adipose tissue within 5 mm outside the serosa. The random forest algorithm was used for radiomics model construction. Traditional features were collected by two radiologists. Univariate and multivariate logistic regression was used to construct the clinical model and combined model. The diagnostic efficacy of the models was evaluated using ROC curve analysis and compared using the Delong’s test. The calibration curves were used to evaluate the calibration performance of the combined model.ResultsBoth the radiomics model and combined model showed high efficacy in diagnosing serosal invasion in the training, testing and independent validation cohort, with AUC of 0.90, 0.90, and 0.85 for radiomics model; 0.93, 0.93, and 0.89 for combined model. The combined model outperformed the clinical model (AUC: 0.76, 0.76 and 0.81).ConclusionThe radiomics model and combined model constructed based on tumoral and peritumoral radiomics features derived from DECT showed high diagnostic efficacy for serosal invasion in gastric adenocarcinoma.

A Simple Approach for Real Time Speed Estimation of On Road Vehicles Using Video Sequences

This paper provides an efficient and simple approach towards real-time speed estimation of on road vehicles for surveillance applications. In the presented method, videos are supposed to be captured with a stationary camera mounted on a two-lane road and there is no need for the camera to be calibrated. The algorithm has two main phases, in the first phase there is an interactive procedure in which lane borders and real world distances are defined just once at the beginning. Then, based on the already received information, two rectangular ROIs are defined for each lane. In the second phase, approximate binary mask of the foreground is created differencing the two consecutive frames. Eventually, calculating centroids and the norm values of the binary mask in the ROIs, algorithm can compute the time that it takes each vehicle to pass between the two aforementioned lines and thus, average speed can be computed. In short, although the algorithm of this paper is simple, it is real-time and efficient, and its implementation doesn’t require any specific hardware. The average error of speed estimation is ±3km/h and the detection accuracy is 83 %.

An optimal feature enriched region of interest (ROI) extraction for periocular biometric system.

With the onset of COVID-19 pandemic, wearing of face mask became essential and the face occlusion created by the masks deteriorated the performance of the face biometric systems. In this situation, the use of periocular region (region around the eye) as a biometric trait for authentication is gaining attention since it is the most visible region when masks are used. One important issue in periocular biometrics is the identification of an optimal size periocular ROI which contains enough features for authentication. The state of the art ROI extraction algorithms use fixed size rectangular ROI calculated based on some reference points like center of the iris or centre of the eye without considering the shape of the periocular region of an individual. This paper proposes a novel approach to extract optimum size periocular ROIs of two different shapes (polygon and rectangular) by using five reference points (inner and outer canthus points, two end points and the midpoint of eyebrow) in order to accommodate the complete shape of the periocular region of an individual. The performance analysis on UBIPr database using CNN models validated the fact that both the proposed ROIs contain enough information to identify a person wearing face mask.