Manual CT Research Articles

SCALED SIAMESE CNN-BASED AUTOMATIC CLASSIFICATION ALGORITHM FOR DETECTING PULMONARY EMBOLISM

The majority of patients today have vascular illness that could cause pulmonary hypertension and pulmonary emboli which can lead to serious conditions. To diagnose changes in veins and arteries, manual, semi-automatic and automatic examination of a individuals chest computed tomography image or CT Pulmonary Angiogram (CTPA) is performed. Manual CT scan analysis is more tedious, takes more time and is not standardized. Thus the separation of vascular trees in CTPA scans is now semi-automatic and automatic which enables doctors to precisely identify aberrant conditions. Recent research has focused on applying machine learning along with deep learning approaches to find and categorize pulmonary vascular disorders like pulmonary embolism and pulmonary hypertension. Here, a brand-new technique is put out for the automatically classifying pulmonary veins in order to more accurately diagnose lung illnesses related to Pulmonary Embolism (PE). The proposed method uses Scaled Siamese-based Convoutional Neural Network (CNN) for classifying Pulmonary Embolism images with an accuracy more than 90 while using two publicly available datasets FUMPE and RSNA. Finally, comparison of the proposed method with other pretrained CNN-based algorithms for detecting PE is done in terms of Area Under Curve (AUC), recall, precision, accuracy, [Formula: see text]1 score, etc. and values are tabulated and our proposed method shows good results. Comparison was also done using deep learning models like PENET, Inception [Formula: see text]3 and [Formula: see text] fold cross validation and our proposed method values are outstanding compared to other methods.

WS01.01 Clinical validation of automated vs manual PRAGMA-CF CT score in children with CF

WS01.01 Clinical validation of automated vs manual PRAGMA-CF CT score in children with CF

Local Assessment and Small Bowel Crohn’s Disease Severity Scoring using AI

We present a machine learning and computer vision approach for a localized, automated, and standardized scoring of Crohn's disease (CD) severity in the small bowel, overcoming the current limitations of manual measurements CT enterography (CTE) imaging and qualitative assessments, while also considering the complex anatomy and distribution of the disease. Two radiologists introduced a severity score and evaluated disease severity at 7.5mm intervals along the curved planar reconstruction of the distal and terminal ileum using 236 CTE scans. A hybrid model, combining deep-learning, 3-D CNN, and Random Forest model, was developed to classify disease severity at each mini-segment. Precision, sensitivity, weighted Cohen's score, and accuracy were evaluated on a 20% hold-out test set. The hybrid model achieved precision and sensitivity ranging from 42.4% to 84.1% for various severity categories (normal, mild, moderate, and severe) on the test set. The model's Cohen's score (κ=0.83) and accuracy (70.7%) were comparable to the inter-observer agreement between experienced radiologists (κ=0.87, accuracy = 76.3%). The model accurately predicted disease length, correlated with radiologist-reported disease length (r=0.83), and accurately identified the portion of total ileum containing moderate-to-severe disease with an accuracy of 91.51%. The proposed automated hybrid model offers a standardized, reproducible, and quantitative local assessment of small bowel CD severity and demonstrates its value in CD severity assessment.

Abstract 215: A Sweet Indicator: HbA1C and Thrombectomy Outcomes in Hispanics

Introduction There is a higher prevalence of diabetes mellitus type 2 in Hispanics as compared to other ethnic groups in the United States. Diabetes is a risk factor for acute ischemic stroke and also a poor predictor of outcome for many interventional surgeries. We performed this retrospective cohort analysis to assess the impact of poorly controlled diabetes, defined as HbA1C of 9.0% or greater, on the functional and procedural outcomes of Hispanic patients with acute ischemic stroke undergoing mechanical thrombectomy. Methods We conducted a retrospective review of a prospectively maintained patient database at a large volume comprehensive stroke center. Patients included were of Hispanic origin presenting between 2012 and 2022 who underwent thrombectomy for acute ischemic stroke. Baseline patient demographics and clinical characteristics recorded include age, gender, HbA1C level, National Institutes of Health Stroke Scale (NIHSS) at admission, manual CT ASPECTS and stroke risk factors (hypertension, atrial fibrillation, coronary artery disease, congestive heart failure, LDL, smoking, history of stroke/TIAs). Patients were separated into two groups depending on the presence poorly controlled diabetes defined as an HbA1C of 9.0% or greater. Outcomes evaluated include modified Rankin scale at 3 months, symptomatic intracranial hemorrhage, mass effect, 90‐day mortality, and whether any stenting or angioplasty was required during mechanical thrombectomy. Results 495 patients met the inclusion criteria out of which 69 had HbA1c of 9% or greater. Patients with poorly controlled diabetes were significantly younger (median age 63 vs 72, p <0.001), had a lower prevalence of atrial fibrillation (7.69% vs 29.8%, p <0.001) and a higher median LDL level (95.5 vs 72, p<0.001) compared to patients who did not have poorly controlled diabetes. Median NIHSS on admission was also lower in the poorly controlled diabetics group (13 vs 17, p = 0.02). There was a statistically significant lower rate of functional independence (mRS 0‐2) at 90 days in patients with poorly controlled diabetes (30.6% vs 45.3%, p=0.05) after adjusting for age, NIHSS, and atrial fibrillation. Patients with poorly controlled diabetes also were more likely to require angioplasty (31.3% vs. 20.5%; p = 0.048) and stenting (28.4% vs. 18.1%; p = 0.049) during mechanical thrombectomy. Conclusion High HbA1c levels upon admission may be used to predict poor functional outcomes of thrombectomy and may also be associated with a greater chance of patients requiring angioplasty and/or stenting during thrombectomy. This can assist the physician in deciding if thrombectomy should be done on a patient with poorly controlled diabetes.

METHOD FOR OPTIMIZING CT VOLUMETRY OF THE LIVER IN RELATED TRANSPLANTATION

Computed tomography volumetry is the standard method for preoperative estimation of liver volume. Despite the development of various software, the trend towards discrepancy in the calculation of liver volume compared with any of the methods and intraoperative graft weight remains. The aim of the study was to optimize the manual method of CT volumetry donor’ liver, determine its accuracy and compare it with the standard method. Material and methods. A single-center prospective study including data from 60 liver donors who underwent computed tomography, CT volumetry and liver transplantation at the National Scientific Surgery Center named after A.N. Syzganov for the period 2018-2022. Results. The Pearson correlation between the right liver lobe volume estimated by the standard method and the graft weight was 0.730 (p<0.01), the Pearson correlation between the liver volume calculated by the optimized method (-10 HU) and the graft was 0.757 (p<0.01), and the correlation between the optimized method (-20 HU) and graft weight – 0.860 (p<0.01). The Pearson correlation coefficient of the optimized method (-20 HU) is statistically significantly higher than the correlation coefficient of the standard manual method (p=0.026), the difference between the correlation coefficient of the optimized method (-10 HU) and the standard one is statistically insignificant (p=0.375). The degree of discrepancy between the optimized method (-20 HU) was 8.4%, manual method - 12.7%. There is a statistically significant difference between the degree of discrepancy between the standard manual and optimized method (-20 HU) (p=0.029). Conclusions. Optimization of the manual CT volumetry method with a decrease in the liver density threshold by 20 HU demonstrated a statistically significantly high correlation coefficient with the graft weight, and also significantly reduced the degree of discrepancy.

Computed Tomography Pulmonary Angiography Prediction of Adverse Long-Term Outcomes in Chronic Thromboembolic Pulmonary Hypertension: Correlation with Hemodynamic Measurements Pre- and Post-Pulmonary Endarterectomy.

CT pulmonary angiography is commonly used in diagnosing chronic thromboembolic pulmonary hypertension (CTEPH). This work was conducted to determine if cardiac chamber size on CTPA may also be useful for predicting the outcome of CTEPH treatment. A retrospective analysis of paired CTPA and right heart hemodynamics in 33 consecutive CTEPH cases before and after pulmonary thromboendarterectomy (PTE) was performed. Semiautomated and manual CT biatrial and biventricular size quantifications were correlated with mean pulmonary artery pressure (mPAP), pulmonary vascular resistance (PVR) and cardiac output. The baseline indexed right atrioventricular volumes were twice the left atrioventricular volumes, with significant (p < 0.001) augmentation of left heart filling following PTE. Except for the left atrial volume to cardiac index, all other chamber ratios significantly correlated with hemodynamics. Left to right ventricular ratio cut point <0.82 has high sensitivity (91% and 97%) and specificity (88% and 85%) for identifying significant elevations of mPAP and PVR, respectively (AUC 0.90 and 0.95), outperforming atrial ratios (sensitivity 78% and 79%, specificity 82% and 92%, and AUC 0.86 and 0.91). Manual LV:RV basal dimension ratio correlates strongly with semiautomated volume ratio (r 0.77, 95% CI 0.64-0.85) and is an expeditious alternative with comparable prognostic utility (AUC 0.90 and 0.95). LV:RV dimension ratio of <1.03 and ≤0.99 (alternatively expressed as RV:LV ratio of >0.97 and ≥1.01) is a simple metric that can be used for CTEPH outcome prediction.

Automated liver segmental volume ratio quantification on non-contrast T1–Vibe Dixon liver MRI using deep learning

PurposeTo evaluate the effectiveness of automated liver segmental volume quantification and calculation of the liver segmental volume ratio (LSVR) on a non-contrast T1-vibe Dixon liver MRI sequence using a deep learning segmentation pipeline. MethodA dataset of 200 liver MRI with a non-contrast 3 mm T1-vibe Dixon sequence was manually labeledslice-by-sliceby an expert for Couinaud liver segments, while portal and hepatic veins were labeled separately. A convolutional neural networkwas trainedusing 170 liver MRI for training and 30 for evaluation. Liver segmental volumes without liver vessels were retrieved and LSVR was calculated as the liver segmental volumes I-III divided by the liver segmental volumes IV-VIII. LSVR was compared with the expert manual LSVR calculation and the LSVR calculated on CT scans in 30 patients with CT and MRI within 6 months. ResultsTheconvolutional neural networkclassified the Couinaud segments I-VIII with an average Dice score of 0.770 ± 0.03, ranging between 0.726 ± 0.13 (segment IVb) and 0.810 ± 0.09 (segment V). The calculated mean LSVR with liver MRI unseen by the model was 0.32 ± 0.14, as compared with manually quantified LSVR of 0.33 ± 0.15, resulting in a mean absolute error (MAE) of 0.02. A comparable LSVR of 0.35 ± 0.14 with a MAE of 0.04 resulted with the LSRV retrieved from the CT scans. The automated LSVR showed significant correlation with the manual MRI LSVR (Spearman r = 0.97, p < 0.001) and CT LSVR (Spearman r = 0.95, p < 0.001). ConclusionsA convolutional neural network allowed for accurate automated liver segmental volume quantification and calculation of LSVR based on a non-contrast T1-vibe Dixon sequence.

Redefining Lobe-Wise Ground-Glass Opacity in COVID-19 Through Deep Learning and its Correlation With Biochemical Parameters

During COVID-19 pandemic qRT-PCR, CT scans and biochemical parameters were studied to understand the patients' physiological changes and disease progression. There is a lack of clear understanding of the correlation of lung inflammation with biochemical parameters available. Among the 1136 patients studied, C-reactive-protein (CRP) is the most critical parameter for classifying symptomatic and asymptomatic groups. Elevated CRP is corroborated with increased D-dimer, Gamma-glutamyl-transferase (GGT), and urea levels in COVID-19 patients. To overcome the limitations of manual chest CT scoring system, we segmented the lungs and detected ground-glass-opacity (GGO) in specific lobes from 2D CT images by 2D U-Net-based deep learning (DL) approach. Our method shows accuracy, compared to the manual method ( ∼80%), which is subjected to the radiologist's experience. We determined a positive correlation of GGO in the right upper-middle (0.34) and lower (0.26) lobe with D-dimer. However, a modest correlation was observed with CRP, ferritin and other studied parameters. The final Dice Coefficient (or the F1 score) and Intersection-Over-Union for testing accuracy are 95.44% and 91.95%, respectively. This study can help reduce the burden and manual bias besides increasing the accuracy of GGO scoring. Further study on geographically diverse large populations may help to understand the association of the biochemical parameters and pattern of GGO in lung lobes with different SARS-CoV-2 Variants of Concern's disease pathogenesis in these populations.

A novel hybrid deep learning method for early detection of lung cancer using neural networks

Lung cancer is a fatal disease with a high mortality rate in diseased patients. Early diagnosis of this disease and accurately identifying the lung cancer stage can save the patients’ lives. Several image processing, biomarker-based and machine automation approaches are used to identify lung cancer, but accuracy and early diagnosis are challenging for medical practitioners. The Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI) are utilized in this study to extract the CT scan images. In conventional methods, manual CT images are supplied to visualize whether the person has lung cancer. This research article proposes a novel method for an early and accurate diagnosis called Cancer Cell Detection using Hybrid Neural Network (CCDC-HNN). The features are extracted from the CT scan images using deep neural networks. The accuracy in feature extraction is very important to detect the cancerous cells at early stages to save the patient from this fatal disease. In this study, an advanced 3D-convolution neural network (3D-CNN) is also utilized to improve the accuracy of diagnosis. The suggested approach also enables the distinction between benign and malignant tumors. The results are evaluated using standard statistical techniques, and the results confirm the viability of the proposed hybrid deep learning (DL) technique for early diagnosis of the lung cancer.

Accuracy of preoperative liver volumetry in living donor liver transplantation—A systematic review and meta-analysis

BackgroundLiver volume measurement plays a critical role in the clinical success of living donor liver transplantation (LDLT). CT liver volumetry is used for volumetric assessment of the donor hepatectomy. However, the degree of accuracy of the preoperative predicted volumetric measurements remains unclear. PurposeThis systematic review will assess the accuracy of CT liver volumetry. Materials and MethodsA systematic literature search was conducted to evaluate the accuracy of the CT based liver volumetry. To assess the difference between the left and right liver lobe the ratio between preoperative estimated graft volume (EGV) and actual graft weight (AGW) was calculated. A meta-analysis was performed to compare the EGV to the AGW of the left and right lobe with automated and manual CT volume prediction. ResultsThirty-one studies met the inclusion criteria and 1336 patients were included in the meta-analysis. The EGV of the right liver is overestimated with a mean of 4.01% and 2.99% for automated and manual volumetry respectively. The left lobe is overestimated with 6.28% and 14.41% for automated and manual volumetry respectively. For a right lobe liver graft automated volume prediction showed a mean difference of 43.9 g (95% confidence interval (CI): 21.21–66.54, p<0.001) between EGV and AGW. For manual volume prediction this was 34.0 g (95% CI: 11.85–56.11, p = 0.003). For a left lobe with automated volume prediction the mean difference was 46.0 g (95% CI: 20.91–71.09, p<0.001) between EGV and AGW. For manual volume prediction this was 39.6 g (95% CI: 8.40–70.74, p = 0.01). ConclusionThe volumes of the right and left liver lobe seem to be overestimated with automated and manual CT volume prediction. Considering the larger estimation error in the prediction of the left liver lobe, special attention should be paid to the volume when performing a LDLT with a left liver lobe to prevent small for size syndrome.

Safe drilling zones for anteriorly, central, and posteriorly angulated syndesmotic stabilization devices

PurposeThe purposes of the study were to (1) analyze the shape of the distal fibula at the location of syndesmotic stabilization and to (2) define safe zones at the distal-lateral fibula for three different drilling tunnel orientations: anteriorly-, posteriorly angulated and center-center.MethodsPostoperative, bilateral CT images of adult patients that underwent syndesmotic stabilization (suture-button system) for an acute, unilateral ankle injury were analyzed. Manual axial CT reconstructions of the uninjured side were generated. First, the axial shape of the distal fibula was classified. The aspect ratio between the anterio-lateral and the posterior-lateral surfaces of the fibula was calculated to assess symmetry. Second, the same axial planes were used to define the safe zones. Each drilling-tunnel orientation (anterior, central, posterior) comprised a fixed medial tibial anchor point and a safe zone on the lateral fibula. For each of the three orientations, the most anteriorly and posteriorly drilling tunnel location was simulated. Next to a cumulative visual analysis, a quantitative analysis of the most anterior and posterior point on the anterio- and posterior-lateral surfaces was calculated.ResultsA total of 96 CT datasets were analyzed. (1) 81% of fibulae revealed a triangular convex-, 10% an irregular-, and 8% a quadrilateral shape. The lateral surface ratio was 1.0 ± 0.2 (range: 0.7–1.5), not differing between the fibula types (n.s.). (2) The safe corridor on the lateral surface of the fibula for an anteriorly angulated drilling tunnel was − 8% to − 41%, for a posteriorly angulated drilling tunnel was 0% to 46%, and for a center-center alignment − 7 ± 11% (range: − 28 to 18%).ConclusionThe meta-diaphyseal region of the distal fibula revealed a homogeneous crosssectional shape. The lateral apex of the fibula can serve as a landmark defining safe zones to place the drilling tunnels correctly. Applying these safe zones in clinical practice could help to avoid the misplacement of the syndesmotic fixation device.Level of evidenceLevel III, retrospective radiographic study.

Evaluation of fully automated commercial software for Agatston calcium scoring on non-ECG-gated low-dose chest CT with different slice thickness.

To evaluate commercial deep learning-based software for fully automated coronary artery calcium (CAC) scoring on non-electrocardiogram (ECG)-gated low-dose CT (LDCT) with different slice thicknesses compared with manual ECG-gated calcium-scoring CT (CSCT). This retrospective study included 567 patients who underwent both LDCT and CSCT. All LDCT images were reconstructed with a 2.5-mm slice thickness (LDCT2.5-mm), and 453 LDCT scans were reconstructed with a 1.0-mm slice thickness (LDCT1.0-mm). Automated CAC scoring was performed on CSCT (CSCTauto), LDCT1.0-mm, and LDCT2.5-mm images. The reliability of CSCTauto, LDCT1.0-mm, and LDCT2.5-mm was compared with manual CSCT scoring (CSCTmanual) using intraclass correlation coefficients (ICCs) and Bland-Altman analysis. Agreement, in CAC severity category, was analyzed using weighted kappa statistics. Diagnostic performance at various Agatston score cutoffs was also calculated. CSCTauto, LDCT1.0-mm, and LDCT2.5-mm demonstrated excellent agreement with CSCTmanual (ICC [95% confidence interval, CI]: 1.000 [1.000, 1.000], 0.937 [0.917, 0.952], and 0.955 [0.946, 0.963], respectively). The mean difference with 95% limits of agreement was lower with LDCT1.0-mm than with LDCT2.5-mm (19.94 [95% CI, -244.0, 283.9] vs. 45.26 [-248.2, 338.7]). Regarding CAC severity, LDCT1.0-mm achieved almost perfect agreement, and LDCT2.5-mm achieved substantial agreement (kappa [95% CI]: 0.809 [0.776, 0.838], 0.776 [0.740, 0.809], respectively). Diagnostic performance for detecting Agatston score ≥ 400 was also higher with LDCT1.0-mm than with LDCT2.5-mm (F1 score, 0.929 vs. 0.855). Fully automated CAC-scoring software with both CSCT and LDCT yielded excellent reliability and agreement with CSCTmanual. LDCT1.0-mm yielded more accurate Agatston scoring than LDCT2.5-mm using fully automated commercial software. • Total Agatston scores and all vessels of CSCTauto, LDCT1.0-mm, and LDCT2.5-mm demonstrated excellent agreement with CSCTmanual (all ICC > 0.85). • The diagnostic performance for detecting all Agatston score cutoffs was better with LDCT1.0-mm than with LDCT2.5-mm. • This automated software yielded a lower degree of underestimation compared with methods described in previous studies, and the degree of underestimation was lower with LDCT1.0-mm than with LDCT2.5-mm.

Three-dimensional reconstruction of the hand from biplanar X-rays: Assessment of accuracy and reliability

BackgroundFunctional disorders of the hand are generally investigated first using conventional radiographic imaging. However, X-rays (two-dimensional (2D)) provide limited information and the information may be reduced by overlapping bones and projection bias. This work presents a three-dimensional (3D) hand reconstruction method from biplanar X-rays. MethodThis approach consists of the deformation of a generic hand model on biplanar X-rays by manual and automatic processes. The reference examination being the manual CT segmentation, the precision of the method was evaluated by a comparison between the reconstructions from biplanar X-rays and the corresponding reconstructions from the CT scan (0.3mm section thickness). To assess the reproducibility of the method, 6 healthy hands (6 subjects, 3 left, 3 men) were considered. Two operators repeated each reconstruction from biplanar X-rays three times to study inter- and intra-operator variability. Three anatomical parameters that could be calculated automatically from the reconstructions were considered from the bone surfaces: the length of the scaphoid, the depth of the distal end of the radius and the height of the trapezius. ResultsDouble the root mean square error (2 Root Mean Square, 2RMS) at the point/area difference between biplanar X-rays and computed tomography reconstructions ranged from 0.46mm for the distal phalanges to 1.55mm for the bones of the distal carpals. The inter-intra-observer variability showed precision with a 95% confidence interval of less than 1.32mm for the anatomical parameters, and 2.12mm for the bone centroids. DiscussionThe current method allows to obtain an accurate 3D reconstruction of the hand and wrist compared to the traditional segmented CT scan. By improving the automation of the method, objective information about the position of the bones in space could be obtained quickly. The value of this method lies in the early diagnosis of certain ligament pathologies (carpal instability) and it also has implications for surgical planning and personalized finite element modeling. Level of proofBasic sciences.

Anatomic measurement of osseous parameters of the glenoid

The angle and position of the scapular glenoid are important in shoulder mechanics, the interpretation of diseases, and planning shoulder replacement surgery. In total shoulder replacement, understanding the bony parameters of the glenoid is also of considerable guiding significance for designing implant size and improving material adaptability. To compare glenoid parameters measured from skeletal scapula specimens with those measured by 3D modeling of CT scanning images, analyze correlations between these data, and draw conclusions to guide clinical treatment of shoulder joint injury and total shoulder joint replacement. The data of manual and CT measurements from the same Chinese dry glenoid was compared. Three-dimensional measurement data were collected from the Japanese population and compared with the Chinese population data generated in this study. There were no significant differences between manual measurement and CT measurement in the inclination angle, glenopolar angle, anteroposterior transverse diameter, upper to lower vertical diameter, and depth of the glenoid (P = 0.288, 0.524, 0.111, 0.194, and 0.055, respectively). Further, there were no significant differences between Japanese and Chinese glenoid bones in the upper and lower vertical diameters or anteroposterior transverse diameters (P > 0.05). There were no significant differences between CT and manual measurements, suggesting that the CT method may provide measurements very close to the actual specimen size. This result, however, indicated that the measurer should be careful when measuring the depth of the glenoid.

Automatic vs manual coronary CT angiography reconstruction for whole-heart coverage CT scanner: a comparison study in general patient population.

Due to the limited temporal resolution and cardiac motion, coronary computed tomography angiography (CCTA) exam is one of the most challenging CT protocols which may require operating radiologist to apply additional phase adjustment or motion correction for image reconstruction. To evaluate image quality between automatic and manual CCTA reconstruction in a 0.25 second rotation time, 16 cm coverage, single-beat, CT scanner with automated phase selection and AI-assisted motion correction. CCTA exams of 535 consecutive patients were included. All exams were first reconstructed with an automatically selected phase. If there was an unacceptable motion artifact, a manual reconstruction process was performed by radiologists. Additionally, automatic image series which consist of auto-phase selection and a follow-up motion correction were reconstructed. For these two manual and automatic image series, a four-point Likert scale rating system was used to evaluate image quality of the coronary artery segment by two experienced radiologists, according to the 18-segment model. Fifty-one patients (9.5%) did not have satisfactory image quality after auto-phase selection. In these patients, the heart rate during scanning was higher (78.3±18.4 bpm) than in the remaining 484 patients (68.9±13.1 bpm). Overall, 734 out of the 918 vessel segments were identified for quality evaluation among 51 patients. Automatic and manual image series were rated as having average Likert scores of 3.48±0.62 and 3.32±0.67 (P < 0.001), respectively. Using a 0.25 second rotation speed, 16 cm z-coverage, CT scanner installed with an AI-assisted motion correction algorithm, the automatic image reconstruction with scanner equipped auto-phase-selection and motion correction algorithm outperforms manually controlled image reconstruction by radiologists. This suggests that the traditional CCTA exam reconstruction workflow could be altered allowing less radiologist involvement and becoming more efficient.

Patient-specific 3D-printed shelf implant for the treatment of hip dysplasia tested in an experimental animal pilot in canines

The concept of a novel patient-specific 3D-printed shelf implant should be evaluated in a relevant large animal model with hip dysplasia. Therefore, three dogs with radiographic bilateral hip dysplasia and a positive subluxation test underwent unilateral acetabular augmentation with a 3D-printed dog-specific titanium implant. The contralateral side served as control. The implants were designed on CT-based pelvic bone segmentations and extended the dysplastic acetabular rim to increase the weight bearing surface without impairing the range of motion. Outcome was assessed by clinical observation, manual subluxation testing, radiography, CT, and gait analysis from 6 weeks preoperatively until termination at 26 weeks postoperatively. Thereafter, all hip joints underwent histopathological examination. The implantation and recovery from surgery was uneventful. Clinical subluxation tests at the intervention side became negative. Imaging showed medialization of the femoral head at the intervention side and the mean (range) CE-angle increased from 94° (84°–99°) preoperative to 119° (117°–120°) postoperative. Gait analysis parameters returned to pre-operative levels after an average follow-up of 6 weeks. Histology showed a thickened synovial capsule between the implant and the femoral head without any evidence of additional damage to the articular cartilage compared to the control side. The surgical implantation of the 3D shelf was safe and feasible. The patient-specific 3D-printed shelf implants restored the femoral head coverage and stability of dysplastic hips without complications. The presented approach holds promise to treat residual hip dysplasia justifying future veterinary clinical trials to establish clinical effectiveness in a larger cohort to prepare for translation to human clinic.

Use and effectiveness of Digital Contact Tracing during COVID-19 pandemic: a systematic review

Abstract Background Contact tracing (CT) is a pillar of infection control during outbreaks and its implementation has been great ally in the context of the COVID-19 pandemic that pressured national health systems. Digital CT (DCT) aids manual CT by logging proximity contacts and timely notifying contacts of positive cases, contributing to greater epidemic. We aim to systematically review and critically appraise the available evidence on adoption, effectiveness, acceptance and barriers to access of available CT apps. Methods We conducted a systematic literature review by means of Pubmed, Embase, Cochrane and Web of Science and applying the PRISMA guidelines. We classified studies according to selected characteristics (eg, original data, mathematical models, policy papers, overview of the experience with national CT apps) in order to better outline our results. Results Our queries yielded 1201 articles, of which 790 remained after duplicates' removal. After applying a priori selected inclusion criteria, 428 (54.17%) were eliminated after screening by title and abstract. 362 records were included in our study: of them 33.7% were original studies, 54.1% were opinion papers not reporting quantitative data, 14.91% were mathematical models, 6% were systematic reviews on DCT-related topics. Among original studies, 11.47% described national experiences and 25.40% discussed adoption dynamics. Conclusions DCT adoption still faces several cultural, normative and technical barriers, ranging from adoption mandates to privacy issues, to device compatibility. Overall, scant evidence is available on the impact of DCT in controlling infection spread and wide heterogeneity persists within studies in term of design and assessed outcomes Future research is needed based on shared evaluation frameworks. Key messages Digital contact tracing apps are a powerful but underestimated tool to counter epidemiological emergencies. Future epidemiological challenges will require a shared implementation and evaluation protocol for digital contact tracing apps.

Alcoholism via 6-layer customized deep convolution neural network

Background: Alcoholism is caused by excessive alcohol into the human body. Alcohol primarily damages the central nervous system of the human body and causes the nervous system function disorder and inhibition. Severe addiction can lead to respiratory circulation center inhibition, paralysis and even death. So far, the diagnosis of alcoholism is done by radiologist's manual CT examination. However, the diagnosis process is time-consuming, subjective and boring for doctors. External factors, such as extreme fatigue, lack of sleep and mental concentration, can easily affect the diagnosis process.Methods: In order to solve this problem, this paper proposed a new neural network based on computer vision, which used deep convolution neural network to diagnose alcoholism automatically. A total of 216 brain images were collected. In the 6-layer customized deep convolution neural network structure, there were four convolution layers and two fully connected layers, and each convolution layer was connected with a pooling layer.Results: The results showed that the accuracy, sensitivity, specificity, precision, F1, MCC and FMI were 95.96%±1.44%, 95.96%±1.66%, 95.95%±1.67%, 95.73%±1.72%, 95.84%±1.48%, 91.92%±2.87% and 95.84%±1.48% respectively.Conclusion: It can be concluded from comparison results that the proposed neural network structure is more effective than four state-of-the-art approaches. The proposed method has high accuracy and can be used as a diagnostic method for alcoholism.

Tooth wear, growth and height in rabbits (Oryctolagus cuniculus) fed pelleted or extruded diets with or without added abrasives.

Among the different factors thought to affect dental wear, dietary consistency is possibly the least investigated. To understand tooth wear of herbivorous animals consuming different dietary consistencies with different abrasive potential, we fed 14 rabbits (Oryctolagus cuniculus) exclusively with a timothy grassmeal-based diet in either pelleted or extruded form, or the same diets with an addition of 5% fine sand abrasives (mean size 130µm). First, we offered the rabbits the pelleted and extruded diets as well as the pelleted control and pelleted abrasive diet in a two-stage preference experiment. Then, the rabbits received each diet for 2weeks in a randomised serial feeding experiment, where each animal served as its own control. Tooth measurements for wear, growth and height were achieved using a manual calliper, endoscopic examination and CT scans. The analysis of the diets as fed showed almost identical mean particle size, but the extruded diet had a lower density (volume/mass) and softer consistency compared to the pelleted one and was favoured by most rabbits. The rabbits selected against the diet with sand during the preference experiment, possibly because it caused more tooth wear, especially on the teeth most exposed to wear along the upper tooth row (upper P4 and M1). The maxillary teeth also showed evidence of an increased chewing laterality by the end of the experiment. The extruded diet led to a significantly lower cheek teeth height than the pelleted diet, potentially due to the higher chewing effort needed for a similar dry matter intake. The results suggest that dietary hardness alone is a poor predictor of dental wear. The regrowth of the teeth matched wear consistently.

Computer-aided quantification of non-contrast 3D black blood MRI as an efficient alternative to reference standard manual CT angiography measurements of abdominal aortic aneurysms

BackgroundNon-contrast 3D black blood MRI is a promising tool for abdominal aortic aneurysm (AAA) surveillance, permitting accurate aneurysm diameter measurements needed for patient management. PurposeTo evaluate whether automated AAA volume and diameter measurements obtained from computer-aided segmentation of non-contrast 3D black blood MRI are accurate, and whether they can supplant reference standard manual measurements from contrast-enhanced CT angiography (CTA). Materials and MethodsThirty AAA patients (mean age, 71.9 ± 7.9 years) were recruited between 2014 and 2017. Participants underwent both non-contrast black blood MRI and CTA within 3 months of each other. Semi-automatic (computer-aided) MRI and CTA segmentations utilizing deformable registration methods were compared against manual segmentations of the same modality using the Dice similarity coefficient (DSC). AAA lumen and total aneurysm volumes and AAA maximum diameter, quantified automatically from these segmentations, were compared against manual measurements using Pearson correlation and Bland-Altman analyses. Finally, automated measurements from non-contrast 3D black blood MRI were evaluated against manual CTA measurements using the Wilcoxon test, Pearson correlation and Bland-Altman analyses. ResultsSemi-automatic segmentations had excellent agreement with manual segmentations (lumen DSC: 0.91 ± 0.03 and 0.94 ± 0.03; total aneurysm DSC: 0.92 ± 0.02 and 0.94 ± 0.03, for black blood MRI and CTA, respectively). Automated volume and maximum diameter measurements also had excellent correlation to their manual counterparts for both black blood MRI (volume: r = 0.99, P < 0.001; diameter: r = 0.97, P < 0.001) and CTA (volume: r = 0.99, P < 0.001; diameter: r = 0.97, P < 0.001). Compared to manual CTA measurements, bias and limits of agreement (LOA) for automated MRI measurements (lumen volume: 1.49, [−4.19 7.17] cm3; outer wall volume: −2.46, [−14.05 9.13] cm3; maximal diameter: 0.08, [−6.51 6.67] mm) were largely equivalent to those of manual MRI measurements, particularly for maximum AAA diameter (lumen volume: 0.73, [−6.47 7.93] cm3; outer wall volume: 0.98, [−10.54 12.5] cm3; maximal diameter: 0.08, [−3.67 3.83] mm). ConclusionSemi-automatic segmentation of non-contrast 3D black blood MRI efficiently provides reproducible morphologic AAA assessment yielding accurate AAA diameters and volumes with no clinically relevant differences compared to either automatic or manual measurements based on CTA.