Coronary computed tomographic angiography (CCTA) is a non-invasive imaging modality for the visualization of the heart and coronary arteries. To fully exploit the potential of the CCTA datasets and apply it in clinical practice, an automated coronary artery extraction approach is needed. The purpose of this paper is to present and validate a fully automatic centerline extraction algorithm for coronary arteries in CCTA images. The algorithm is based on an improved version of Frangi’s vesselness filter which removes unwanted step-edge responses at the boundaries of the cardiac chambers. Building upon this new vesselness filter, the coronary artery extraction pipeline extracts the centerlines of main branches as well as side-branches automatically. This algorithm was first evaluated with a standardized evaluation framework named Rotterdam Coronary Artery Algorithm Evaluation Framework used in the MICCAI Coronary Artery Tracking challenge 2008 (CAT08). It includes 128 reference centerlines which were manually delineated. The average overlap and accuracy measures of our method were 93.7% and 0.30 mm, respectively, which ranked at the 1st and 3rd place compared to five other automatic methods presented in the CAT08. Secondly, in 50 clinical datasets, a total of 100 reference centerlines were generated from lumen contours in the transversal planes which were manually corrected by an expert from the cardiology department. In this evaluation, the average overlap and accuracy were 96.1% and 0.33 mm, respectively. The entire processing time for one dataset is less than 2 min on a standard desktop computer. In conclusion, our newly developed automatic approach can extract coronary arteries in CCTA images with excellent performances in extraction ability and accuracy.

The x-ray exposure to patients has become a major concern in Computed Tomography (CT) and minimizing the radiation exposure has been one of the major efforts in CT field. Due to the plenty high-attenuation tissues in human chest, under low dose scan protocols, thoracic low-dose CT (LDCT) images tend to be severely degraded by excessive mottled noise and non-stationary streak artifacts. Their removal is rather a challenging task because the streak artifacts with directional prominence are often hard to be well discriminated from the attenuation information of normal tissues. This paper describes a two-step processing scheme called "Artifact Suppressed Large-scale Nonlocal Means" (AS-LNLM) for suppressing both noise and artifacts in thoracic LDCT images. Specific scale and direction properties were exploited to discriminate the noise and artifacts from image structures. Parallel implementation has been introduced to speed up the whole processing by more than 100 times. Phantom and patient CT images were both acquired for evaluation purpose. Comparative qualitative and quantitative analyses were both performed that allows concluding on the efficacy of our method in improving thoracic LDCT data.

A publicly available standardized framework for the evaluation of (semi)automatic methods for CAC identification in cardiac CT is described. An evaluation of five (semi)automatic methods within this framework shows that automatic per patient CVD risk categorization is feasible. CAC lesions at ambiguous locations such as the coronary ostia remain challenging, but their detection had limited impact on CVD risk determination.

Minimal path techniques can efficiently extract geometrically curve-like structures by finding the path with minimal accumulated cost between two given endpoints. Though having found wide practical applications (e.g., line identification, crack detection, and vascular centerline extraction), minimal path techniques suffer from some notable problems. The first one is that they require setting two endpoints for each line to be extracted (endpoint problem). The second one is that the connection might fail when the geodesic distance between the two points is much shorter than the desirable minimal path (shortcut problem). In addition, when connecting two distant points, the minimal path connection might become inefficient as the accumulated cost increases over the propagation and results in leakage into some non-feature regions near the starting point (accumulation problem). To address these problems, this paper proposes an approach termed minimal path propagation with backtracking. We found that the information in the process of backtracking from reached points can be well utilized to overcome the above problems and improve the extraction performance. The whole algorithm is robust to parameter setting and allows a coarse setting of the starting point. Extensive experiments with both simulated and realistic data are performed to validate the performance of the proposed method.

Background Accurate prediction of tumour response to neoadjuvant chemoradiotherapy enables personalised perioperative therapy for locally advanced rectal cancer. We aimed to develop and validate an artificial intelligence radiopathomics integrated model to predict pathological complete response in patients with locally advanced rectal cancer using pretreatment MRI and haematoxylin and eosin (H&E)-stained biopsy slides. MethodsIn this multicentre observational study, eligible participants who had undergone neoadjuvant chemoradiotherapy followed by radical surgery were recruited, with their pretreatment pelvic MRI (T2-weighted imaging, contrast-enhanced T1-weighted imaging, and diffusion-weighted imaging) and whole slide images of H&E-stained biopsy sections collected for annotation and feature extraction. The RAdioPathomics Integrated preDiction System (RAPIDS) was constructed by machine learning on the basis of three feature sets associated with pathological complete response: radiomics MRI features, pathomics nucleus features, and pathomics microenvironment features from a retrospective training cohort. The accuracy of RAPIDS for the prediction of pathological complete response in locally advanced rectal cancer was verified in two retrospective external validation cohorts and further validated in a multicentre, prospective observational study (ClinicalTrials.gov, NCT04271657). Model performances were evaluated using area under the curve (AUC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV).

The cerebral glymphatic system, particularly the Virchow-Robin Spaces (VRS), plays an important role in waste clearance from the brain. Idiopathic generalized epilepsy (IGE) is a common epilepsy type associated with blood-brain-barrier dysfunction, abnormal exchange of cerebrospinal fluid and interstitial fluid. These disorders may be reflected in the glymphatic system. Therefore, this study investigated the relationships between visible VRS on MRI and seizures, to detect changes in glymphatic function. Methods: We retrospectively included 32 children with newly diagnosed IGE and 30 controls aged 3-13 years. Visible VRS were identified using a custom-designed automated method. VRS counts and volume were quantified and compared between children with IGE and controls. Meanwhile, Correlations of VRS counts and volume with seizure duration and course after seizure onset were respectively explored via Spearman's coefficient (r). Results: In this study, visible VRS counts were higher in IGE than control group (VRS _epilepsy , 234.34 ± 113.88 vs. VRS _control , 111.83 ± 52.46; P < 0.001), as similar results were found in VRS volume (VRS _epilepsy , 1377.47 ± 778.79 mm 3 vs. VRS _control , 795.153 ± 452.49 mm 3 ; P = 0.001). Visible VRS counts and volume positively correlated with seizure duration (r _counts = 0.638, r _volume = 0.639; P < 0.001) and gradually decreased with time after seizure onset (r _counts = −0.559, r_ volume = −0.558; P < 0.001). Conclusion: Epileptic seizures can induce changes in VRS counts and volume, which were associated with seizure duration and post-onset course. Quantitative metrics of VRS visible on MRI might be potential biomarkers for monitoring glymphatic function.

Background: Simple febrile seizures (SFS) and epilepsy are common seizures in childhood. However, the mechanism underlying SFS is uncertain, and the presence of obvious variances in white matter (WM) integrity and glymphatic function between SFS and epilepsy remain unclear. Therefore, this study aimed to investigate the differences in WM integrity and glymphatic function between SFS and epilepsy.Material and Methods: We retrospectively included 26 children with SFS, 33 children with epilepsy, and 28 controls aged 6–60 months who underwent magnetic resonance imaging (MRI). Tract-based spatial statistics (TBSS) were used to compare the diffusion tensor imaging (DTI) metrics of WM among the above-mentioned groups. T2-weighted imaging (T2WI) was used to segment the visible Virchow-Robin space (VRS) through a custom-designed automated method. VRS counts and volume were quantified and compared among the SFS, epilepsy, and control groups. Correlations of the VRS metrics and seizure duration and VRS metrics and the time interval between seizure onset and MRI scan were also investigated.Results: In comparison with controls, children with SFS showed no significant changes in fractional anisotropy (FA), axial diffusivity (AD), or radial diffusivity (RD) in the WM (P &gt; 0.05). Decreased FA, unchanged AD, and increased RD were observed in the epilepsy group in comparison with the SFS and control groups (P &lt; 0.05). Meanwhile, VRS counts were higher in the SFS and epilepsy groups than in the control group (VRS_SFS, 442.42 ± 74.58, VRS_epilepsy, 629.94 ± 106.55, VRS_control, 354.14 ± 106.58; P &lt; 0.001), and similar results were found for VRS volume (VRS_SFS, 6,228.18 ± 570.74 mm3, VRS_epilepsy, 9,684.84 ± 7,292.66mm3, VRS_control, 4,007.22 ± 118.86 mm3; P &lt; 0.001). However, VRS metrics were lower in the SFS group than in the epilepsy group (P &lt; 0.001). In both SFS and epilepsy, VRS metrics positively correlated with seizure duration and negatively correlated with the course after seizure onset.Conclusion: SFS may not be associated with WM microstructural disruption; however, epilepsy is related to WM alterations. Seizures are associated with glymphatic dysfunction in either SFS or epilepsy.

Fine renal artery segmentation on abdominal CT angiography (CTA) image is one of the most important tasks for kidney disease diagnosis and pre-operative planning. It will help clinicians locate each interlobar artery's blood-feeding region via providing the complete 3D renal artery tree masks. However, it is still a task of great challenges due to the large intra-scale changes, large inter-anatomy variation, thin structures, small volume ratio and small labeled dataset of the fine renal artery. In this paper, we propose the first semi-supervised 3D fine renal artery segmentation framework, DPA-DenseBiasNet, which combines deep prior anatomy (DPA), dense biased network (DenseBiasNet) and hard region adaptation loss (HRA): 1) Based on our proposed dense biased connection, the DenseBiasNet fuses multi-receptive field and multi-resolution feature maps for large intra-scale changes. This dense biased connection also obtains a dense