Boundary-Aware Network for Kidney Parsing

<b>Objective:</b> To explore the preoperative whole perforator evaluation and intraoperative eccentric design of anterolateral thigh flap (ALTF) based on superficial fascial perforators by modified computed tomography angiography (CTA), and the clinical effects were observed. <b>Methods:</b> A prospective observational study was adopted. Twelve patients with oral and maxillofacial tumors and 10 patients with open injury of the upper limb with large soft tissue defects were hospitalized in the Department of Hand & Microsurgery and Department of Oral & Maxillofacial Surgery of Affiliated Hospital of Binzhou Medical University from January 2021 to July 2022, with 12 males and 10 females, aged from 33 to 75 years, an average age of 56.6 years. The wounds of the patients with oral and maxillofacial tumors were reconstructed by ALTF after the extensive tumor resection and radical cervical lymph node dissection in the same stage; the wounds of the patients with skin and soft tissue defect on the upper limb were covered by ALTF in stage Ⅱ after debridement in stage Ⅰ. After debridement, the area of wound was 3.5 cm×3.5 cm-25.0 cm×10.0 cm and the area of the required flap area was 4.0 cm×4.0 cm-23.0 cm×13.0 cm. Modified CTA scan was performed on the donor site of ALTF before the operation, with the parameters of modified CTA being set to mainly reduce the tube voltage and tube current, and increase the contrast dose and the dual phase scan. The acquired image data were sent to GE AW 4.7 workstation and adopted the volume reconstruction function for visual reconstruction and evaluation of the whole perforator. The information of perforator and source artery was marked on the body surface before operation according to the above evaluation. During the operation, an eccentric flap centered on the visible superficial fascia whole perforator was designed and cut according to the desired flap area and shape. The donor sites of the flap were repaired by direct sutures or full-thickness skin grafts. The total radiation dose was compared between the modified CTA scan and the traditional CTA scan. The distribution of outlet point of perforator of double thighs, the length and direction of superficial fascia perforators based modified CTA were recorded. The type, number, and origin of the target perforator, distribution of of outlet point of perforator, and the diameter, course, and branch of the source artery observed before the operation were compared with those observed during the operation. The healing of donor site wound and the survival of flaps in recipient site were observed after operation. The texture and appearance of flap, oral and upper limb functions, and the functions of femoral donor sites were followed up. <b>Results:</b> The total radiation dose of modified CTA scan was lower than that of the traditional CTA scan. A total of 48 perforators of double thighs were observed, among which, 31 (64.6%) perforators went outward and downward, 9 (18.8%) perforators went inward and downward, 6 (12.5%) perforators went outward and upward, and 2 (4.2%) perforators went inward and upward, and the average length of superficial fascia perforators was 19.94 mm. The preoperative observed type, number, and source of the perforator, the distribution of the outlet point of the perforator, diameter, course, and branches of the source artery were basically consistent with the intraoperative exploration. The types of 15 septocutaneous (including musculoseptocutaneous) perforators and 10 musculocutaneous perforators observed before the operation was consistent with intraoperative exploration. The distance between the mark of the surface perforator point and the actual exit point of the perforator during operation was (0.38±0.11) mm. All flaps survived without vascular crisis. The donor site wounds of 5 cases of skin grafting and 17 cases of direct suturing wounds healed well. The postoperative follow-up was 2 months to 1 year, with an average of 8.2 months, the flaps were soft and slightly bloated; the function of diet and mouth closing was accessible in patients with oral and maxillofacial tumors, the speech function was mildly impaired in patients with tongue cancer, but they could complete basic oral communication; the wrist and elbow joints and forearm rotation function were not significantly limited in patients with upper limb soft tissue injuries; there was no obvious tightness in the donor sites, and the function of the hip and knee joints was not limited. <b>Conclusions:</b> The whole perforator and even the subcutaneous perforator of the donor site of ALTF can be evaluated by modified CTA, and the flap can be used in oral or maxillofacial reconstruction and repair of skin and soft tissue defects of upper limbs to achieve good results. By clarifying the type, number, and source of the perforator, the distribution of the outlet point of the perforator, diameter, course, and branches of the source artery before the operation, the eccentric design of the ALTF based on the superficial fascia perforator was realized. This study has strong guiding value.

PurposeTo explore the feasibility of transcatheter aortic valve implantation (TAVI) planning computed tomography (CT) on single‐source 8‐cm detector scanners with proper dose control by using two deep‐learning reconstruction algorithms.MethodsReduced‐dose TAVI planning CT was simulated by replacing routine aortic CT angiography (CTA) with a reduced‐dose aortic CTA and a reduced‐dose coronary CTA (Group A, n = 82), while keeping the total dose unchanged. Each of the two CTA scans was processed with a different deep‐learning reconstruction algorithm. Routine‐dose coronary CTA (Group B, n = 86) and routine‐dose aortic CTA (Group C, n = 77) with hybrid iterative reconstruction were used as reference for evaluating the acceptability for surgical planning (A vs. B for aortic valve; A vs. C for access route) and for comparing both the diagnostic and objective image quality (A vs. B for coronary arteries; A vs. C for aortoiliac arteries).ResultsThe mean effective dose in Group A was 8.22 ± 0.83 mSv, representing a 57% reduction of the routine‐dose TAVI planning CT, that is, a routine‐dose coronary CTA plus a routine‐dose aortic CTA on the same scanner model. With respect to B and C, images in A were scored higher for evaluating the aortic valve (p = 0.045) and the access route (p = 0.014) and for diagnosing the thoracic aorta and iliac segments (p < 0.050), while the diagnostic confidence were comparable on the coronary arteries (p > 0.050), abdominal aorta (p = 0.276), and femoral segment (p = 0.816). The image noise in A was found to be 21%–55% lower, leading to a significant increase in contrast‐to‐noise ratio (CNR) by 63%–114% (p < 0.050).ConclusionReduced‐dose TAVI planning CT is feasible on 8‐cm detector scanners by using deep‐learning reconstruction algorithms, showing promise of implementing the examination in imaging settings that are more commonly accessible.

Fenestrated endovascular aortic aneurysm repair (FEVAR) is used in pararenal abdominal aortic aneurysms to achieve a durable proximal seal. This study investigated the mid-term course of the proximal fenestrated stent graft (FSG) sealing zone on the first and latest available post-FEVAR computed tomographic angiography (CTA) scan in a single-center series. In 61 elective FEVAR patients, the shortest length of circumferential apposition between the FSG and the aortic wall (shortest apposition length [SAL]) was retrospectively assessed on the first and last available postoperative CTA scans. Patient records were reviewed for FEVAR-related procedural details, complications, and reinterventions. The median (interquartile range) time between the FEVAR procedure and the first and last CTA scan was 35 (30-48) days and 2.6 (1.2-4.3) years, respectively. The median (interquartile range) SAL was 38 (29-48) mm, and 44 (34-59) mm on the first and last CTA scans, respectively. During follow-up, the SAL increased >5 mm in 32 patients (52%), and decreased >5 mm in six patients (10%). Reintervention was performed for a type 1a endoleak in one patient. Twelve other patients needed 17 reinterventions for other FEVAR-related complications. Good mid-term apposition of the FSG in the pararenal aorta was achieved post-FEVAR, and the occurrence of type 1a endoleaks was low. The number of reinterventions was substantial, however, but for reasons other than loss of proximal seal.

Research has shown that three-dimensional (3D) stereoscopic virtual anatomic models can help students understand the complex spatial relationships of human structures that are not easily accessible via dissection. For instance, the cerebral cortex is located within the cranial vault; however, it can be difficult to view the relationship between the cerebral cortex and skull via dissection. This project goes into discussing the creation of a 3D stereoscopic model of the cerebral cortex. The cerebral cortex model was segmented via Amira 5.6 software from computed tomography angiography (CTA) data. Amira 5.6 surface rendering methods were used to create the cerebral cortex, and volume rendering methods were used to create the skull. The segmentations were performed using the axial view and paintbrush tools in Amira 5.6 along with the Wacom pen and tablet. After completing the initial segmentation across 155 slides, the CTA scans were compiled in Amira 5.6 to create the 3D model of the cerebral cortex. A smoothing filter was then applied to the initial surface render of the cerebral cortex to smooth the transition from slide to slide. The cerebral cortex model generated can be viewed from any angle at any magnification level. In addition, the model can also be overlayed orthoslice CTA data to allow the user to have a stronger understanding of the relationship between each individual two-dimensional CTA image and the three-dimensional model. Moreover, the cerebral cortex virtual model can be created into video clips using the Amira 5.6 movie maker, which can be inserted into PowerPoint presentations. As a result, the cerebral cortex virtual model has the potential to be used for online distance anatomical learning, which has become the adopted method of teaching due to the COVID-19 pandemic. The flexibility of this model allows it to also be used in the classroom setting as a virtual learning tool where students may view the models via a 3D screen with 3D glasses.

Application and significance of precise computed tomography angiography (CTA) scanning technology in the assessment of lower extremity arterial diseases.

Abdominal Aortic Aneurysm (AAA) is still a socially relevant public health challenge, evidenced by an 82.1% increase in associated fatalities from 1990 to 2019 (with 172,427 deaths in 2019 alone). In a clinical setting, computed tomography angiography (CTA) is the imaging modality of choice for monitoring and/or presurgical planning of AAA patients. However, manual segmentation of CTA images is labor intensive and time consuming. Hence, there is a growing need for automated segmentation algorithms, particularly when these influence treatment planning. The deep-learning pipeline proposed in this work is designed to automatically segment AAA CTA images. The framework adapted a fully developed patch-based dilated modified U-Net model, which shows remarkable efficiency in accurately delineating AAA regions within the CTA scans. During the prediction phase, the deep learning architecture demonstrates exceptional speed, requiring 17 ± 0.02 milliseconds per frame to generate the final segmented output. Building upon this work, we included the application of Non-Uniform Rational B-Splines (NURBS) to enhance the segmentation process. This advancement is essential in addressing the critical need for clinical accuracy in medical image segmentation. NURBS enables the creation of continuous curves that seamlessly conform to the intricate contours of anatomical structures, offering a significant improvement in segmentation accuracy. Through the integration of advanced deep learning architectures and the precision of NURBS for segmentation refinement, coupled with the fast processing time and accurate segmentation, the the proposed model represents a promising clinical tool that can be used in the clinical management of AAAs.

Application value of iterative reconstruction with computed tomographic angiography (CTA) in the patients with intractable headache was investigated. One hundred and eighty patients with headache, who were admitted and treated in Cangzhou Central Hospital, were selected to undergo CTA scan. The patients were divided into group A, B and C according to different scanning conditions and data reconstruction techniques. In group A, the scanning parameters were 120 kV and 300 mA, and filtered back projection (FBP) algorithm was used for data reconstruction. In group B, the scan parameters were 100 kV and automatic milliamperes. Further, adaptive iterative dose reduction via three-dimensional processing (AIDR-3D) was used for data reconstruction. In group C, the scan parameters were 80 kV with automatic milliamperes, and AIDR-3D technique was utilized for data reconstruction. The CT value, noise, signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), subjective assessment score of image quality and radiation dose of the three groups of images were compared. There were significant differences in CT values, standard deviation (SD) values, SNRs and CNRs of different vessel segments and muscles among the three groups (P<0.05). The image assessment scores at the levels of the atlas and C7 vertebra as well as those of the brain parenchyma in the three groups had notable differences (P<0.05). However, they showed no differences at the level of the C4 vertebra (P>0.05). Further, significant differences were observed in volume computed tomography dose index (CTDIvol), dose-length product (DLP) and effective dose (ED) (P<0.05). In conclusion, for patients with intractable headache, the image quality of the CTA scan using AIDR-3D reconstruction method showed better results over FBP reconstruction method. Further, best results were observed when the scan parameters were 100 kV, automatic milliamperes and the data reconstruction was performed by AIDR-3D.

The aorta is the largest vessel of the human body and its pathological degenerations, such as dissections and aneurysms, can be life threatening. An automatic and fast segmentation of the aorta can therefore be a helpful tool to quickly identify an abnormal anatomy. The segmentation of the aortic vessel tree (AVT) typically requires extensive manual labor, but, in recent years, progress in deep learning techniques made the automation of this process viable. For this purpose, we tested different deep learning networks to segment the aortic vessel tree from computed tomography angiography (CTA) scans with a deep neural network consisting of an encoder-decoder architecture with skip connections and an optional self-attention block. The networks were trained on a dataset of 56 CTA scans from three different sources and resulted in Dice score similarities between 0.043−0.897. Generally, the classical U-Nets performed better than the ones containing a self-attention block, indicating that they might diminish performance for AVT segmentation. The quality of the resulting segmentations was highly dependent on the CTA image quality, especially on the contrast between the aorta and the surrounding tissues. However, the trained deep neural network can segment CTA scans well with limited computational resources and training data.

Introduction: Guidelines for ascending thoracic aortic aneurysm (ATAA) repair use ATAA diameter, with repair recommended at ≥5.5cm, but ATAA biomechanics may better predict acute type A dissection (ATAD) risk. However, little is known regarding changes in wall stresses among clinically followed patients with &lt;5.5cm ATAA over time. This information is important for patient risk stratification. Hypothesis: We hypothesized that peak ATAA wall stresses would change over time in a patient-specific fashion alongside diameter. Methods: 31 nonsurgical ATAA patients (&lt;5.5cm and growth &lt;0.5cm/year) with computed tomography angiography (CTA) scans taken 3 to 5 years apart were identified. Images were used to construct patient specific three-dimensional ATAA models. Peak diastolic circumferential stresses were determined along the ascending aorta (AA), sinotubular junction (STJ), and aortic sinuses using finite element analysis. Diameters at both time points were measured from CTA scans by a single radiologist blinded to stress results. Stress and diameter distributions were compared using paired t-tests. Results: In the overall population, ATAA diameter increased over time (4.39±0.4 cm vs. 4.43±0.4 cm, p=0.02), while diastolic circumferential stresses along the aorta did not significantly change. However, we found two distinct patient groups: one where wall stresses increased and one where stresses decreased over time. Separate analysis of these groups showed significant changes in circumferential stress in all three aortic regions (488 ± 120 vs. 340 ± 63 kPa for the sinuses, 472 ± 127 vs 345 ± 76 kPa for the STJ and 337 ± 54 vs 277 ± 28 kPa for AA, p&lt;0.001), and significant increase in diameter in the group with increasing stresses (p=0.02). Conclusions: In this nonsurgical group, there is no statically significant change of peak ATAA wall stresses at diastole over 3-5 years. The patients with increased stress were found to be associated with increases in diameter during the corresponding time period. More patient specific data is required to investigate the interaction between wall biomechanics and aortic remodeling. Our results lay the foundation for developing patient-specific ATAD risk predictors for ATAD using patient-specific wall stress changes.

This study evaluated the feasibility, safety, and efficacy of the suprarenal implantation of a retrievable filter in patients with renal cell carcinoma (RCC) and renal vein thrombosis (RVT) [extending or not extending to the inferior vena cava (IVC)] undergoing surgery. Between March 2005 and May 2010, 13 patients (eight men and five women; mean age 67.08 years, range 38-95) with RCC and RVT associated or not with IVC thrombosis underwent implantation of a retrievable suprarenal IVC filter. All patients underwent computed tomography angiography (CTA), which documented RVT and in some cases its extension to the IVC. The level of IVC involvement by the neoplastic thrombus was evaluated on the basis of the Oto classification. Cavography was performed before and after filter implantation. Surgical resection of RCC was performed in all patients. A CTA scan was performed 1 week before filter removal. The procedure had 100% feasibility. All filters were correctly deployed in the suprarenal tract of the IVC. There was no evidence of peri-or postprocedural complications. All patients were monitored for clinical symptoms of pulmonary embolism (PE). There was no evidence of PE in the 30 days after the procedure. All suprarenal IVC filters were removed from 30 to 60 days after surgery. Implantation of a temporary suprarenal IVC filter is an additional and feasible procedure that can prevent immediate and perioperative PE.

We introduce a cascade classification algorithm for bifurcation detection in Computed Tomography Angiography (CTA) scans of blood vessels. The proposed algorithm analyzes the vessel surrounding by a trained classifier first, followed by an accurate segmentation of the vessel outer wall by Morphological Active Contour Without Edges and finally extracts the boundary features of the segmented object and classifies its shape by Approximate K-nearest Neighbour classifier. The algorithm shows encouraging and competitive results for blood vessels from various parts of a human body including head, neck and legs.

Due to the low image contrast and high tortuosity of the small bowel on CT scans, it is difficult for even experienced radiologists to localize small bowel. To facilitate this, we propose a novel mesenteric vasculature-guided method for small bowel region segmentation on high-resolution contrast-enhanced CT angiography (CTA) scans. It is essential and useful for further localizing small bowel tumors. The mesenteric vasculature is first segmented using multi-view multi-scale vesselness enhancement filters on maximum intensity projection images. Second, the small bowel region is automatically segmented based on the map of mesenteric vasculature and its relationship to the small bowel. The method is applied to high-resolution contrast-enhanced abdominal CTA scans of patients suspected of having carcinoid tumors. The result, 79.3% volume overlap accuracy compared with the reference standard, shows it is feasible to segment the small bowel using the mesenteric vasculature as a roadmap on CTA scans.

cerebral vasospasm (CVS) is a devastating sequela of subarachnoid hemorrhage (SAH). Among the many factors that are associated with the pathogenesis of CVS, the cerebral blood flow (CBF) and underlying haemodynamics play an important role. In this paper we present an integrated clinical-engineering approach to CVS research. after an admission CT scan, CT angiography (CTA) and/or Digital Subtraction Angiography (DSA) scans are performed for SAH patients. The anatomy of cerebral vasculature and its geometric parameters are monitored and compared with follow-up CTA and/or DSA scans. The governing equations for blood flow are numerically solved for the arteries and the computational results are analysed. in the particular CVS case presented in this paper, the numerical results indicate that blood flow velocity increases in moderate and severely spastic vessels (A1, M1 segment) that perfuse brain tissues. However, decreased vessel diameters in A1 and M1 arteries create larger resistance to CBF and hence lead to reduced flow in the inner carotid artery (ICA). a numerical approach to patient-specific CVS analysis has been established, and some initial results are achieved via application to an actual spasm case. The undergoing and future work include applying the approach to more CVS cases and incorporating computational models of different scales into the current framework for CVS and SAH research.

Computed Tomography Angiography (CTA) is the first line of imaging in the diagnosis of Large Vessel Occlusion (LVO) strokes. We trained and independently validated end-to-end automated deep learning pipelines to predict 3-month outcomes after anterior circulation LVO thrombectomy based on admission CTAs. We split a dataset of 591 patients into training/cross-validation (n = 496) and independent test set (n = 95). We trained separate models for outcome prediction based on admission "CTA" images alone, "CTA + Treatment" (including time to thrombectomy and reperfusion success information), and "CTA + Treatment + Clinical" (including admission age, sex, and NIH stroke scale). A binary (favorable) outcome was defined based on a 3-month modified Rankin Scale ≤ 2. The model was trained on our dataset based on the pre-trained ResNet-50 3D Convolutional Neural Network ("MedicalNet") and included CTA preprocessing steps. We generated an ensemble model from the 5-fold cross-validation, and tested it in the independent test cohort, with receiver operating characteristic area under the curve (AUC, 95% confidence interval) of 70 (0.59-0.81) for "CTA," 0.79 (0.70-0.89) for "CTA + Treatment," and 0.86 (0.79-0.94) for "CTA + Treatment + Clinical" input models. A "Treatment + Clinical" logistic regression model achieved an AUC of 0.86 (0.79-0.93). Our results show the feasibility of an end-to-end automated model to predict outcomes from admission and post-thrombectomy reperfusion success. Such a model can facilitate prognostication in telehealth transfer and when a thorough neurological exam is not feasible due to language barrier or pre-existing morbidities.

Shading and streaking artifacts brought by beam hardening and photon starvation is commonly observed in lowkVp CT angiography (CTA) for carotid artery imaging. Image quality is thus significantly degraded and a faithful observation of carotid artery is impeded. In this paper, we propose a novel quantitative image postprocessing scheme to eliminate these artifacts. In shading correction, we follow general knowledge of the relatively uniform CT number distribution in one tissue component, and continuous and low-frequency shading artifact distribution in projection domain. Coarse image segmentation is first applied to construct an ideal template image where each structure is filled with the same CT number of that specific tissue. By forward projecting the difference between uncorrected CT image and the ideal template, we estimate the continuous and lowfrequency shading error signal in projection domain using lowpass filtering. An error map is then reconstructed using standard filtered back-projection algorithm from the error signal and added to the original image to correct for the shading artifacts. To suppress the increased noise and streaking artifacts, we first perform a texture extraction to estimate the noise distribution in the image and then incorporate the estimated noise variation into a nonlocal filtering method. The proposed scheme is evaluated in carotid CTA scan using a dual-source CT at 80 kVp, in which the shading and streaking artifacts can be successfully corrected by reducing the CT number error from 246 HU to 63 HU and spatial non-uniformity by a factor of 2.2, respectively. In the volume rendering generated from the corrected CT images, the visualization of carotid artery is improved substantially and comparable to that generated from a CTA scan at 140-kVp. The proposed method is implemented directly on the CT image without access to the raw projection data and is thus attractive for clinical application in low-dose CTA.KeywordsShading correctionCTABM3D de-noising