CT Volume Research Articles

Correlation of Differential Function and Glomerular Filtration Rate Estimated from Computed Tomography based Renal Volume and Diuretic Renogram in Living Renal Donor

Introduction: In renal transplant, serum creatinine and isotope studies are used for determination of donor glomerular filtration rate (GFR). Studies have shown computed tomography measured renal volume can also be used. Our main objective was to assess the accuracy of volume based estimated GFR (vGFR) with diethylene triamine penta acetic acid (DTPA) measured GFR in living kidney donors. Methods: An observational analytical study was conducted from July 2018 to June 2019 in Department of Urology and Kidney Transplant Surgery and Department of Radiodiagnosis in Tribhuvan University Teaching Hospital where a total of 38 eligible potential donors were evaluated and serum creatinine level, computed tomography with contrast and DTPA renogram were used to measure GFR and differential function. Results: The mean age of the donors were 42.8±10.9 years with 70% of donors being females. Renal volume was not statistically different between male and female donors. There was moderate correlation between volume based and DTPA based GFR (r=0.76) and differential function (r=0.71). Compared to creatinine, volume based GFR estimate showed better correlation to DTPA renogram. There was no significant difference in differential function estimated by DTPA and volume based estimates (p = 0.96). The upper and lower limit of agreement between the volume based and DTPA based differential function was –4.7 and 4.6 respectively. Conclusion: GFR measurement by CT volume overestimates total GFR compared to DTPA renogram but it has better correlation than creatinine based estimates. It can be used to estimate the differential function of the donor kidney.

StrokeViT with AutoML for brain stroke classification

Stroke, categorized under cardiovascular and circulatory diseases, is considered the second foremost cause of death worldwide, causing approximately 11% of deaths annually. Stroke diagnosis using a Computed Tomography (CT) scan is considered ideal for identifying whether the stroke is hemorrhagic or ischemic. However, most methods for stroke classification are based on a single slice-level prediction mechanism, meaning that the most imperative CT slice has to be manually selected by the radiologist from the original CT volume. This paper proposes an integration of Convolutional Neural Network (CNN), Vision Transformers (ViT), and AutoML to obtain slice-level predictions as well as patient-wise prediction results. While the CNN with inductive bias captures local features, the transformer captures long-range dependencies between sequences. This collaborative local-global feature extractor improves upon the slice-wise predictions of the CT volume. We propose stroke-specific feature extraction from each slice-wise prediction to obtain the patient-wise prediction using AutoML. While the slice-wise predictions helps the radiologist to verify close and corner cases, the patient-wise predictions makes the outcome clinically relevant and closer to real-world scenario. The proposed architecture has achieved an accuracy of 87% for single slice-level prediction and an accuracy of 92% for patient-wise prediction. For comparative analysis of slice-level predictions, standalone architectures of VGG-16, VGG-19, ResNet50, and ViT were considered. The proposed architecture has outperformed the standalone architectures by 9% in terms of accuracy. For patient-wise predictions, AutoML considers 13 different ML algorithms, of which 3 achieve an accuracy of more than 90%. The proposed architecture helps in reducing the manual effort by the radiologist to manually select the most imperative CT from the original CT volume and shows improvement over other standalone architectures for classification tasks. The proposed architecture can be generalized for volumetric scans aiding in the patient diagnosis of head and neck, lungs, diseases of hepatobiliary tract, genitourinary diseases, women’s imaging including breast cancer and various musculoskeletal diseases. Code for proposed stroke-specific feature extraction with the pre-trained weights of the trained model is available at: https://github.com/rishiraj-cs/StrokeViT_With_AutoML.

Spinal Cord Delineation Based on Computed Tomography Myelogram Versus T2 Magnetic Resonance Imaging in Spinal Stereotactic Body Radiation Therapy

Spinal cord delineation is critical to the delivery of stereotactic body radiation therapy (SBRT). Although underestimating the spinal cord can lead to irreversible myelopathy, overestimating the spinal cord may compromise the planning target volume coverage. We compare spinal cord contours based on computed tomography (CT) simulation with a myelogram to spinal cord contours based on fused axial T2 magnetic resonance imaging (MRI). Eight patients with 9 spinal metastases treated with spinal SBRT were contoured by 8 radiation oncologists, neurosurgeons, and physicists, with spinal cord definition based on (1) fused axial T2 MRI and (2) CT-myelogram simulation images, yielding 72 sets of spinal cord contours. The spinal cord volume was contoured at the target vertebral body volume based on both images. The mixed-effect model assessed comparisons of T2 MRI- to myelogram-defined spinal cord in centroid deviations (deviations in the center point of the cord) through the vertebral body target volume, spinal cord volumes, and maximum doses (0.035 cc point) to the spinal cord applying the patient's SBRT treatment plan, in addition to in-between and within-subject variabilities. The estimate for the fixed effect from the mixed model showed that the mean difference between 72 CT volumes and 72 MRI volumes was 0.06 cc and was not statistically significant (95% confidence interval, -0.034, 0.153; P=.1832). The mixed model showed that the mean dose at 0.035 cc for CT-defined spinal cord contours was 1.24 Gy lower than that of MRI-defined spinal cord contours and was statistically significant (95% confidence interval, -2.292, -0.180; P=.0271). Also, the mixed model indicated no statistical significance for deviations in any of the axes between MRI-defined spinal cord contours and CT-defined spinal cord contours. CT myelogram may not be required when MRI imaging is feasible, although uncertainty at the cord-to-treatment volume interface may result in overcontouring and hence higher estimated cord dose-maximums with axial T2 MRI-based cord definition.

Lung Cancer Screening Using Clinical Photon-Counting Detector Computed Tomography and Energy-Integrating-Detector Computed Tomography: A Prospective Patient Study.

To evaluate the diagnostic quality of photon-counting detector (PCD) computed tomography (CT) in patients undergoing lung cancer screening compared with conventional energy-integrating detector (EID) CT in a prospective multireader study. Patients undergoing lung cancer screening with conventional EID-CT were prospectively enrolled and scanned on a PCD-CT system using similar automatic exposure control settings and reconstruction kernels. Three thoracic radiologists blinded to CT system compared PCD-CT and EID-CT images and scored examinations using a 5-point Likert comparison score (-2 [left image is worse] to +2 [left image is better]) for artifacts, sharpness, image noise, diagnostic image quality, emphysema visualization, and lung nodule evaluation focusing on the border. Post hoc correction of Likert scores was performed such that they reflected PCD-CT performance in comparison to EID-CT. A nonreader radiologist measured objective image noise. Thirty-three patients (mean, 66.9 ± 5.6 years; 11 female; body mass index; 30.1 ± 5.1 kg/m 2 ) were enrolled. Mean volume CT dose index for PCD-CT was lower (0.61 ± 0.21 vs 0.73 ± 0.22; P < 0.001). Pooled reader results showed significant differences between imaging modalities for all comparative rankings ( P < 0.001), with PCD-CT favored for sharpness, image noise, image quality, and emphysema visualization and lung nodule border, but not artifacts. Photon-counting detector CT had significantly lower image noise (74.4 ± 10.5 HU vs 80.1 ± 8.6 HU; P = 0.048). Photon-counting detector CT with similar acquisition and reconstruction settings demonstrated improved image quality and less noise despite lower radiation dose, with improved ability to depict pulmonary emphysema and lung nodule borders compared with EID-CT at low-dose lung cancer CT screening.

A Lightweight Deep Learning Approach for Liver Segmentation

Liver segmentation is a prerequisite for various hepatic interventions and is a time-consuming manual task performed by radiology experts. Recently, various computationally expensive deep learning architectures tackled this aspect without considering the resource limitations of a real-life clinical setup. In this paper, we investigated the capabilities of a lightweight model, UNeXt, in comparison with the U-Net model. Moreover, we conduct a broad analysis at the micro and macro levels of these architectures by using two training loss functions: soft dice loss and unified focal loss, and by substituting the commonly used ReLU activation function, with the novel Funnel activation function. An automatic post-processing step that increases the overall performance of the models is also proposed. Model training and evaluation were performed on a public database—LiTS. The results show that the UNeXt model (Funnel activation, soft dice loss, post-processing step) achieved a 0.9902 dice similarity coefficient on the whole CT volumes in the test set, with 15× fewer parameters in nearly 4× less inference time, compared to its counterpart, U-Net. Thus, lightweight models can become the new standard in medical segmentation, and when implemented thoroughly can alleviate the computational burden while preserving the capabilities of a parameter-heavy architecture.

Reinforcement Learning Based Vocal Fold Localization in Preoperative Neck CT for Injection Laryngoplasty

Transcutaneous injection laryngoplasty is a well-known procedure for treating a paralyzed vocal fold by injecting augmentation material to it. Hence, vocal fold localization plays a vital role in the preoperative planning, as the fold location is required to determine the optimal injection route. In this communication, we propose a mirror environment based reinforcement learning (RL) algorithm for localizing the right and left vocal folds in preoperative neck CT. RL-based methods commonly showed noteworthy outcomes in general anatomic landmark localization problems in recent years. However, such methods suggest training individual agents for localizing each fold, although the right and left vocal folds are located in close proximity and have high feature-similarity. Utilizing the lateral symmetry between the right and left vocal folds, the proposed mirror environment allows for a single agent for localizing both folds by treating the left fold as a flipped version of the right fold. Thus, localization of both folds can be trained using a single training session that utilizes the inter-fold correlation and avoids redundant feature learning. Experiments with 120 CT volumes showed improved localization performance and training efficiency of the proposed method compared with the standard RL method.

CT volumetry performs better than nuclear renography in predicting estimated renal function one year after living donation

The evaluation of split renal function (SRF) is a critical issue in living kidney donations and can be evaluated using nuclear renography (NR) or computerized tomography (CT), with unclear comparative advantages. We conducted this retrospective study in 193 donors to examine the correlation of SRF assessed by NR and CT volumetry and compared their ability to predict remaining donor renal function at 1 year, through multiple approaches. A weak correlation between imaging techniques for evaluating the percentage of the remaining kidney volume was found in the global cohort, with an R2 = 0.15. However, the Bland–Altman plot showed an acceptable agreement (95% of the difference between techniques falling within − 8.51 to 6.11%). The predicted and observed eGFR one year after donation were calculated using the CKD-EPI, and CG/BSA equations. CT volume showed a better correlation than NR for both formulas (adjusted R2 of 0.42. and 0.61 vs 0.37 and 0.61 for CKD-EPI and CG/ BSA equations, respectively). In non-nested modeling tests, CT volumetry was significantly superior to NR for both equations. CT volumetry performed better than NR in predicting the estimated renal function of living donors at 1-year, independently from the eGFR equation.

A dual branch and fine-grained enhancement network for pancreatic tumor segmentation in contrast enhanced CT images

Segmentation of pancreatic tumors in CT images is important for clinical diagnosis and treatment, but it faces challenges of small size, low contrast, and large position difference. To address these issues, the abnormal pancreas is first segmented based on a dual branch coding network (DB-Net) using a coarse-to-fine segmentation strategy. In the encoder part, one branch extracts the semantic features of the pancreas and its surroundings, and the other branch captures the complex pancreas through wide-channel convolution and few down-sampling operations. An aggregation layer is used to fuse the different feature maps obtained by the two branches, and a U-Net decoder is used to segment the abnormal pancreas in CT images with pancreatic tumors. DB-Net is further trained to obtain the accurate pancreatic segmentation. Then, pancreatic tumors are segmented in the pancreas based on the fine-grained enhancement network (FE-Net). The FE-Net integrates a contrast enhancement block with a reverse attention block to extract detailed features and excavate effective information from the feature maps of the encoder and decoder to segment pancreatic tumors. In order to segment the tumor more accurately, the pancreatic tumor is segmented in the cropped pancreas. Experiments on 116 contrast-enhanced abdominal CT volumes of pancreatic cancer and 42 contrast-enhanced abdominal CT volumes of normal pancreas verify the effectiveness of the proposed framework in pancreatic tumor segmentation by using the two-fold cross-validation strategy. Compared to state-of-the-art deep learning segmentation network, the proposed method can achieve better segmentation of pancreas and pancreatic tumors.

Incidental findings in cone beam computed tomography volumes: Calcified head-and-neck atheromas detected during dental evaluation.

Atheromas can be detected incidentally in routine dental cone beam computed tomography (CBCT) images. This study aims to assess prevalence and risk factors associated with these vascular lesions. The maxillofacial CBCTs of 458 subjects were evaluated and divided into 4 groups based on the presence of calcified atheroma: subjects with no calcified atheroma, subjects with intracranial calcified atheroma (ICA), subjects with extracranial calcified atheroma (ECA), and subjects exhibiting combined lesions. Age, sex, medical conditions, family history, and size were documented. Analysis of variance followed by a multiple comparison test was used for data satisfying parametric test assumptions. Chi-squared tests were used to assess categorical data. The Spearman Rho test was used to assess the correlation between the incidence of calcified atheroma and subjects' medical condition. Of the 458 CBCTs evaluated, 29.90% presented with calcified atheroma. Calcified atheroma prevalence was significantly higher in older patients versus younger patients (p=0.004) and in males compared to females (p=0.004). Males were more likely to have the combination of ICA and ECA, whereas females were more likely to have ICA alone (p≤0.040). Patients with calcified atheroma were significantly more likely to have a history of hyperlipidemia (p=0.001), hypertension (p=0.001), and myocardial infarction/coronary artery diseases (p=0.001). Overall, patients exhibiting both intracranial and extracranial lesions were more likely to have cardiovascular risk factors (p=0.001). Incidentally detected calcified atheromas in CBCTs are common. Subjects with combined atheroma lesions are at higher risk for cardiovascular disease. The diagnosis of incidental calcified atheromas in CBCT's warrants early referral to medical specialists, especially if there is no medical history of existing cardiovascular disease.

Database-driven patient-specific registration error compensation method for image-guided laparoscopic surgery

A surgical navigation system helps surgeons understand anatomical structures in the operative field during surgery. Patient-to-image registration, which aligns coordinate systems between the CT volume and a positional tracker, is vital for accurate surgical navigation. Although a point-based rigid registration method using fiducials on the body surface is often utilized for laparoscopic surgery navigation, precise registration is difficult due to such factors as soft tissue deformation. We propose a method that compensates a transformation matrix computed using fiducials on the body surface based on the analysis of positional information in the database. We built our database by measuring the positional information of the fiducials and the guidance targets in both the CT volume and positional tracker coordinate systems through previous surgeries. We computed two transformation matrices: using only the fiducials and using only the guidance targets in all the data in the database. We calculated the differences between the two transformation matrices in each piece of data. The compensation transformation matrix was computed by averaging these difference matrices. In this step, we selected the data from the database based on the similarity of the fiducials and the configuration of the guidance targets. We evaluated our proposed method using 20 pieces of data acquired during laparoscopic gastrectomy for gastric cancer. The locations of blood vessels were used as guidance targets for computing target registration error. The mean target registration errors significantly decreased from 33.0 to 17.1 mm before and after the compensation. This paper described a registration error compensation method using a database for image-guided laparoscopic surgery. Since our proposed method reduced registration error without additional intraoperative measurements during surgery, it increases the accuracy of surgical navigation for laparoscopic surgery.

A new approach to dose reference levels in pediatric CT: Age and size-specific dose estimation

BackgroundAlthough paediatrics' are more radio-sensitivity than adults, the number of requested paediatric CT examinations is increasing globally. Significant efforts have been focused on achieving the lowest possible radiation dose for paediatric patients, particularly adjusting for size differences. This study aims to establish Diagnostic Reference Levels (DRLs) for paediatric patients based on size-specific dose estimates (SSDE). MethodIn this retrospective national study, CT scans for brain, chest, abdominopelvic, and chest, abdomen, and pelvis (CAP) were collected from four hospitals in Jordan undergoing paediatric CT scans. A total of 1818 cases were randomly selected in four age categories (<1 year, 1–4 years, 5–10 years, 11–18 years). The SSDE values were determined by multiplying the volume CT dose index (CTDIvol) with the conversion factor extracted from the American Association of Physicists in Medicine Report 204. ResultsVariations exist between the DRLs between the different hospitals, age groups, and variations in protocols with different types of CT scanners. The DRL values (CTDIvol, dose-length product (DLP) and SSDE) for the four age categories were as follows; <1 year: brain (47.88 mGy, 741.67 mGy cm and 58.40 mGy), chest (5.65 mGy, 124 mGy cm and 13.91 mGy), abdominopelvic (12.65 mGy, 321.5 mGy cm and 28.72 mGy) and CAP (16.12 mGy, 507.72 mGy cm and 38.04 mGy). 1–4 years, brain (54.79 mGy, 979.12 mGy cm and 55.88 mGy), chest (7.37 mGy, 220.85 mGy cm and 14.68 mGy), abdominopelvic (16.16 mGy, 424.72 mGy cm and 32.68 mGy) and CAP (16.13 mGy, 742.1 mGy cm and 33.54 mGy). 5–10 years: brain (65.03 mGy, 1129.94 mGy cm and 55.92 mGy), chest (12.57 mGy, 383.9 mGy cm and 22.45 mGy), abdominopelvic (12.34 mGy, 450.75 mGy cm and 22.23 mGy) and CAP (13.46 mGy, 748.85 mGy cm and 25.69 mGy). 11–18 years, brain (60.7 mGy, 1207.9 mGy cm and 41.81 mGy), chest examination (12.94 mGy, 496.2 mGy cm and 20.49 mGy), abdominopelvic (16.13 mGy, 803.07 mGy cm and 23.06 mGy) and CAP (16.13 mGy, 1101.5 mGy cm and 23.85 mGy). ConclusionThere were increases in CTDIvol, DLP, and SSDE with ascending age groups. SSDE and age are closely matched to delivered radiation in paediatric CT; however, radiation dose levels remain high in Jordan. This work highlights the need for caution when administering radiation in the paediatric population.

High-pitch, high temporal resolution, multi-energy cardiac imaging on a dual-source photon-counting-detector CT.

To measure the accuracy of material decomposition using a dual-source photon-counting-detector (DS-PCD) CT operated in the high-pitch helical scanning mode and compare the results against dual-source energy-integrating-detector (DS-EID) CT, which requires use of a low-pitch value in dual-energy mode. A DS-PCD CT and a DS-EID CT were used to scan a cardiac motion phantom consisting of a 3-mm diameter iodine cylinder. Iodine maps were reconstructed using DS-PCD in high-pitch mode and DS-EID in low-pitch mode. Image-based circularity, diameter, and iodine concentration of the iodine cylinder were calculated and compared between the two scanners. With institutional review board approval, in vivo exams were performed with the DS-PCD CT in high-pitch mode. Images were qualitatively compared against patients with similar heart rates that were scanned with DS-EID CT in low-pitch dual-energy mode. On iodine maps, the mean circularity was 0.97±0.02 with DS-PCD in high-pitch mode and 0.95±0.06 with DS-EID in low-pitch mode. The mean diameter was 2.9±0.2mm with DS-PCD and 3.1±0.2mm with DS-EID, both of which are close to the 3mm ground truth. For DS-PCD, the mean iodine concentration was 9.6±0.8mg/ml and this was consistent with the 9.4±0.6mg/ml value obtained with the cardiac motion disabled. For DS-EID, the concentration was 12.7±1.2mg/ml with motion enabled and 11.7±0.5mg/ml disabled. The background noise in the iodine maps was 15.1 HU with DS-PCD and 14.4 HU with DS-EID, whereas the volume CT dose index (CTDIvol ) was 3 mGy with DS-PCD and 11 mGy with DS-EID. On comparison of six patients (three on PCD, three on EID) with similar heart rates, DS-PCD provided iodine maps with well-defined coronaries even at a high heart rate of 86 beats per minute. Meanwhile, there were substantial motion artifacts in iodine maps obtained with DS-EID for patients with similar heart rates. In a cardiac motion phantom, DS-PCD CT can perform accurate material decomposition in high-pitch mode, providing iodine maps with excellent geometric accuracy and robustness to motion at approximately 38% of the dose for similar noise as DS-EID CT.

Automatic Exposure Control Attains Radiation Dose Modulation Matched with the Head Size in Pediatric Brain CT.

We investigated the relationship between the head size and radiation dose in pediatric brain computed tomography (CT) to evaluate the validity of automatic exposure control (AEC). Phantom experiments were performed to assess image noise with and without AEC, and indicated that AEC decreased differences in noise between slices of different section sizes. Retrospective analysis was conducted on 980 pediatric brain CT scans where the tube current was determined using AEC. The water equivalent diameter (WED) was employed as an index of the head size, and mean WED for each image set (WEDmean) and WED for each slice (WEDslice) were used for analysis. For the image-set-based analysis, volume CT dose index (CTDIvol) was compared to WEDmean. For the slice-based analysis, the tube current was compared to WEDslice using 20 of the 980 sets. Additionally, CTDIvol and WEDmean were compared between male and female patients matched for age, weight, or WEDmean. CTDIvol increased with increasing WEDmean, and an exponential curve was closely fitted to the relationship. Tube current changed similarly to the change in WEDslice for each image set, and an exponential curve was well-fitted to the plots of tube current against WEDslice when data from the 20 sets were pooled together. Although CTDIvol and WEDmean were slightly but significantly larger for male than female patients after matching for age or weight, a sex-dependent difference in CTDIvol was not found after matching for WEDmean. This study indicated successful dose modulation using AEC according to the head size for each patient and each slice location. The application of AEC to pediatric brain CT is recommended for radiation dose optimization.

From 2D projections to the 3D rotation matrix: an attempt for finding a machine learning approach for the efficient evaluation of mechanical joining elements in X-ray computed tomography volume data

Destructive and predominantly manual procedures are commonly used in the automotive industry for the testing of mechanical joints, such as rivets or screws. Combining X-ray computed tomography (CT) and machine learning (ML) bears the potential of a non-destructive and largely automated methodology. Assuming the desired result is a comprehensible and documentable evaluation, three basic steps need to be automatized: First, a joint must be detected and identified as such in a CT scan of the joined parts. Second, the detected region containing the joint is rotated to a predefined orientation. Third, key measures in cross-sections from the newly oriented joint are dimensioned and documented. This work deals only with the second step, the rotation. On the one hand, we present a methodology for creating a well-curated data set for the contextual machine learning application. On the other, we evaluate its performance on the well-known ResNet50. More concretely, we investigate if it is possible for a deep convolutional neural network (CNN) to learn the respective rotation matrix from three volume projections that are perpendicular to each other. Two scenarios are investigated: In one scenario we assume that future data that is presented to the network has similar rivet demographics to historic data. We therefore do not employ hold-out sets for the network evaluation. In the other scenario we assume the opposite and therefore evaluating the networks performance with hold-out sets. We show that from a machine learning point of view, a CNN like ResNet50 is well able to learn this relationship with acceptable accuracy. In most cases the validation loss dropped below 0.1 after only a couple of epochs. In one particular case, we even reached both mean and median errors lower than 0.2 for approximately 80% of the entire test set of 1600 examples using our methodology. From an application point of view, however, these low test set errors should be treated with caution since small deviations from the intended rotation matrix can cause volume warping and translation. In another case, in which we used a hold-out set, only a fraction of the median errors were below 0.2.

Four-dimensional measurement of root system development using time-series three-dimensional volumetric data analysis by backward prediction.

Root system architecture (RSA) is an essential characteristic for efficient water and nutrient absorption in terrestrial plants; its plasticity enables plants to respond to different soil environments. Better understanding of root plasticity is important in developing stress-tolerant crops. Non-invasive techniques that can measure roots in soils nondestructively, such as X-ray computed tomography (CT), are useful to evaluate RSA plasticity. However, although RSA plasticity can be measured by tracking individual root growth, only a few methods are available for tracking individual roots from time-series three-dimensional (3D) images. We developed a semi-automatic workflow that tracks individual root growth by vectorizing RSA from time-series 3D images via two major steps. The first step involves 3D alignment of the time-series RSA images by iterative closest point registration with point clouds generated by high-intensity particles in potted soils. This alignment ensures that the time-series RSA images overlap. The second step consists of backward prediction of vectorization, which is based on the phenomenon that the root length of the RSA vector at the earlier time point is shorter than that at the last time point. In other words, when CT scanning is performed at time point A and again at time point B for the same pot, the CT data and RSA vectors at time points A and B will almost overlap, but not where the roots have grown. We assumed that given a manually created RSA vector at the last time point of the time series, all RSA vectors except those at the last time point could be automatically predicted by referring to the corresponding RSA images. Using 21 time-series CT volumes of a potted plant of upland rice (Oryza sativa), this workflow revealed that the root elongation speed increased with age. Compared with a workflow that does not use backward prediction, the workflow with backward prediction reduced the manual labor time by 95%. We developed a workflow to efficiently generate time-series RSA vectors from time-series X-ray CT volumes. We named this workflow 'RSAtrace4D' and are confident that it can be applied to the time-series analysis of RSA development and plasticity.

Combining exercise, protein supplementation and electric stimulation to mitigate muscle wasting and improve outcomes for survivors of critical illness—The ExPrES study

BackgroundNeuromuscular electrical stimulation (NMES) with high protein supplementation (HPRO) to preserve muscle mass and function has not been assessed in ICU patients. We compared the effects of combining NMES and HPRO with mobility and strength rehabilitation (NMES+HPRO+PT) to standardized ICU care. ObjectivesTo assess the effectiveness of combined NMES+HPRO+PT in mitigating sarcopenia as evidenced by CT volume and cross-sectional area when compared to usual ICU care. Additionally, we assessed the effects of the combined therapy on select clinical outcomes, including nutritional status, nitrogen balance, delirium and days on mechanical ventilation. MethodsParticipants were randomized by computer generated assignments to receive either NMES+HPRO+PT or standard care. Over 14 days the standardized ICU care group (N = 23) received usual critical care and rehabilitation while the NMES+HPRO+PT group (N = 16) received 30 min neuromuscular electrical stimulation of quadriceps and dorsiflexors twice-daily for 10 days and mean 1.3 ± 0.4 g/kg body weight of high protein supplementation in addition to standard care. Nonresponsive participants received passive exercises and, once responsive, were encouraged to exercise actively. Primary outcome measures were muscle volume and cross-sectional area measured using CT-imaging. Secondary outcomes included nutritional status, nitrogen balance, delirium and days on mechanical ventilation. ResultsThe NMES+HPRO+PT group (N = 16) lost less lower extremity muscle volume compared to the standard care group (N = 23) and had larger mean combined thigh cross-sectional area. The nitrogen balance remained negative in the standard care group, while positive on days 5, 9, and 14 in the NMES+HPRO+PT group. Standard care group participants experienced more delirium than the NMES+HPRO+PT group. No differences between groups when comparing length of stay or mechanical ventilation days. ConclusionsThe combination of neuromuscular electrical stimulation, high protein supplementation and mobility and strength rehabilitation resulted in mitigation of lower extremity muscle loss and less delirium in mechanically ventilated ICU patients.Trial Registration: Clinicaltrials.gov identifier: NCT02509520. Registered July 28, 2015

Establishment of CT diagnostic reference levels (DRLs) for a Singapore healthcare cluster

IntroductionThe use of computed tomography (CT) in healthcare institutions has increased rapidly in recent years. The Singapore Health Services (SingHealth) cluster of healthcare institutions has taken the first step in establishing a local cluster-wide CT Diagnostic Reference Levels (DRL) in Singapore. CT dose data from each institution were collected through two primary dosimetry metrics: volume CT dose index (CTDIvol measured in mGy) and dose-length product (DLP measured in mGy.cm). MethodsData from 19 CT scanners in seven institutions under one of Singapore healthcare cluster were retrospectively collected and analysed. The five common adult CT examinations analysed were CT Brain (non-contrast enhanced), CT Chest (IV contrast enhanced), CT Kidney-Ureter-Bladder (CT KUB, non-contrast enhanced), CT Pulmonary Angiogram (CT PA, IV contrast enhanced) and CT Abdomen-Pelvis (CT AP, IV contrast enhanced, single phase). Median CTDIvol and DLP values for the five CT examinations from each institution were derived, with the cluster DRLs determined as the 75th percentile of the distribution of the institution median dose values. ResultsA total of 2413 dose data points were collected over a six-month period from June to November 2020. The cluster CT DRLs for the five CT examinations were determined to be 47 mGy and 820 mGy.cm for CT Brain, 5.4 mGy and 225 mGy.cm for CT Chest, 6.7 mGy and 248 mGy.cm for CT PA, 4.6 mGy and 190 mGy.cm for CT KUB and 6.9 mGy and 349 mGy.cm for CT AP. ConclusionThe establishment of the cluster CT DRLs provided individual institutions with a better understanding if their CT doses are unusually high or low, while emphasising that these DRLs are not meant as hard dose limits or constraints to follow strictly.

A Unified Multi-Phase CT Synthesis and Classification Framework for Kidney Cancer Diagnosis With Incomplete Data.

Multi-phase computed tomography (CT) is widely adopted for the diagnosis of kidney cancer due to the complementary information among phases. However, the complete set of multi-phase CT is often not available in practical clinical applications. In recent years, there have been some studies to generate the missing modality image from the available data. Nevertheless, the generated images are not guaranteed to be effective for the diagnosis task. In this paper, we propose a unified framework for kidney cancer diagnosis with incomplete multi-phase CT, which simultaneously recovers missing CT images and classifies cancer subtypes using the completed set of images. The advantage of our framework is that it encourages a synthesis model to explicitly learn to generate missing CT phases that are helpful for classifying cancer subtypes. We further incorporate lesion segmentation network into our framework to exploit lesion-level features for effective cancer classification in the whole CT volumes. The proposed framework is based on fully 3D convolutional neural networks to jointly optimize both synthesis and classification of 3D CT volumes. Extensive experiments on both in-house and external datasets demonstrate the effectiveness of our framework for the diagnosis with incomplete data compared with state-of-the-art baselines. In particular, cancer subtype classification using the completed CT data by our method achieves higher performance than the classification using the given incomplete data.

Multi-scale random walk driven adaptive graph neural network with dual-head neighboring node attention for CT segmentation

Segmenting objects with indistinct boundaries and large variations from CT volumes is a challenging issue due to overlapping intensity distributions from neighboring tissues or long-distance semantic relations. We propose a multi-scale random walk (RW) driven graph neural network (GNN) to address this issue. A graph is first initialized to represent image regions and deep semantic features from the segmentation encoder by graph nodes and attributes. We then propose a multi-scale graph reasoning model where for each scale, graph node attribute embedding is obtained by an adaptive GNN with dual-head neighboring node attention, while graph topology is evolved by RW. The neighboring-node attention mechanism is designed to learn and incorporate the importance and influence of neighboring nodes on their connected nodes. Random walking to multi-order neighbors enhance the contextual information formulation and diffusion along graph edges. Finally, multi-scale knowledge learnt from graphs is adaptively fused by a new graph-wise attention fusion module before reshaping and feeding to the segmentation decoder. We evaluate the contributions of major innovations by ablation studies, comparison with other state-of-the-art models on public kidney and tumor segmentation dataset. The generalization ability of our model is validated by different segmentation backbones. Experimental results show that the novel multi-scale adaptive graph reasoning architecture and RW-enhanced GNN model improved the segmentation of objects from adjacent tissues.

U-NetCTS: U-Net deep neural network for fully automatic segmentation of 3D CT DICOM volume

The accurate segmentation of computed tomography (CT) scan volume is an essential step in radiomic analysis as well as in developing advanced surgical planning techniques with numerous medical applications. When this process is performed manually by a clinician, it is laborious, time consuming, prone to error, and its success depends to a large extent on the level of experience. In this work, we propose an automated deep learning (DL) segmentation framework for CT images called U-Net CT Segmentation (U-NetCTS) to combine the DL U-Net and CT images in the domain of automatic segmentation. Experimental results show that U-NetCTS framework can segment different CT DICOM image regions of interest in a range of random CT volumes. A statistical and qualitative comparison of the CT slices automatically segmented by U-NetCTS framework and ground-truth images indicates that U-NetCTS framework achieves a high level of accuracy, where the Tanimoto coefficient, dice similarity coefficient, and peak signal-to-noise ratio values are 99.06%, 99.52%, and 53.29 dB, respectively. The DC value is also higher than that of state-of-the-art DL techniques for automatic segmentation of CT images of various human organs. Furthermore, a total amount of 3595 CT slices is employed in this study with various CT region of interest to validate the results.