A Dual-Channel Deep Learning Approach for Lung Cavity Estimation From Hyperpolarized Gas and Proton MRI.

BACKGROUND: Hyperpolarized gas MRI can quantify regional lung ventilation via biomarkers, including the ventilation defect percentage (VDP). VDP is computed from segmentations derived from spatially co-registered functional hyperpolarized gas and structural proton (1 H)-MRI. Although acquired at similar lung inflation levels, they are frequently misaligned, requiring a lung cavity estimation (LCE). Recently, single-channel, mono-modal deep learning (DL)-based methods have shown promise for pulmonary image segmentation problems. Multichannel, multimodal approaches may outperform single-channel alternatives. PURPOSE: We hypothesized that a DL-based dual-channel approach, leveraging both 1 H-MRI and Xenon-129-MRI (129 Xe-MRI), can generate LCEs more accurately than single-channel alternatives. STUDY TYPE: Retrospective. POPULATION: A total of 480 corresponding 1 H-MRI and 129 Xe-MRI scans from 26 healthy participants (median age [range]: 11 [8-71]; 50% females) and 289 patients with pulmonary pathologies (median age [range]: 47 [6-83]; 51% females) were split into training (422 scans [88%]; 257 participants [82%]) and testing (58 scans [12%]; 58 participants [18%]) sets. FIELD STRENGTH/SEQUENCE: 1.5-T, three-dimensional (3D) spoiled gradient-recalled 1 H-MRI and 3D steady-state free-precession 129 Xe-MRI. ASSESSMENT: We developed a multimodal DL approach, integrating 129 Xe-MRI and 1 H-MRI, in a dual-channel convolutional neural network. We compared this approach to single-channel alternatives using manually edited LCEs as a benchmark. We further assessed a fully automatic DL-based framework to calculate VDPs and compared it to manually generated VDPs. STATISTICAL TESTS: Friedman tests with post hoc Bonferroni correction for multiple comparisons compared single-channel and dual-channel DL approaches using Dice similarity coefficient (DSC), average boundary Hausdorff distance (average HD), and relative error (XOR) metrics. Bland-Altman analysis and paired t-tests compared manual and DL-generated VDPs. A P value < 0.05 was considered statistically significant. RESULTS: The dual-channel approach significantly outperformed single-channel approaches, achieving a median (range) DSC, average HD, and XOR of 0.967 (0.867-0.978), 1.68 mm (37.0-0.778), and 0.066 (0.246-0.045), respectively. DL-generated VDPs were statistically indistinguishable from manually generated VDPs (P = 0.710). DATA CONCLUSION: Our dual-channel approach generated LCEs, which could be integrated with ventilated lung segmentations to produce biomarkers such as the VDP without manual intervention. EVIDENCE LEVEL: 4. TECHNICAL EFFICACY: Stage 1.

Implementable Deep Learning for Multi-sequence Proton MRI Lung Segmentation: A Multi-center, Multi-vendor, and Multi-disease Study.

BACKGROUND: Recently, deep learning via convolutional neural networks (CNNs) has largely superseded conventional methods for proton (1 H)-MRI lung segmentation. However, previous deep learning studies have utilized single-center data and limited acquisition parameters. PURPOSE: Develop a generalizable CNN for lung segmentation in 1 H-MRI, robust to pathology, acquisition protocol, vendor, and center. STUDY TYPE: Retrospective. POPULATION: A total of 809 1 H-MRI scans from 258 participants with various pulmonary pathologies (median age (range): 57 (6-85); 42% females) and 31 healthy participants (median age (range): 34 (23-76); 34% females) that were split into training (593 scans (74%); 157 participants (55%)), testing (50 scans (6%); 50 participants (17%)) and external validation (164 scans (20%); 82 participants (28%)) sets. FIELD STRENGTH/SEQUENCE: 1.5-T and 3-T/3D spoiled-gradient recalled and ultrashort echo-time 1 H-MRI. ASSESSMENT: 2D and 3D CNNs, trained on single-center, multi-sequence data, and the conventional spatial fuzzy c-means (SFCM) method were compared to manually delineated expert segmentations. Each method was validated on external data originating from several centers. Dice similarity coefficient (DSC), average boundary Hausdorff distance (Average HD), and relative error (XOR) metrics to assess segmentation performance. STATISTICAL TESTS: Kruskal-Wallis tests assessed significances of differences between acquisitions in the testing set. Friedman tests with post hoc multiple comparisons assessed differences between the 2D CNN, 3D CNN, and SFCM. Bland-Altman analyses assessed agreement with manually derived lung volumes. A P value of <0.05 was considered statistically significant. RESULTS: The 3D CNN significantly outperformed its 2D analog and SFCM, yielding a median (range) DSC of 0.961 (0.880-0.987), Average HD of 1.63 mm (0.65-5.45) and XOR of 0.079 (0.025-0.240) on the testing set and a DSC of 0.973 (0.866-0.987), Average HD of 1.11 mm (0.47-8.13) and XOR of 0.054 (0.026-0.255) on external validation data. DATA CONCLUSION: The 3D CNN generated accurate 1 H-MRI lung segmentations on a heterogenous dataset, demonstrating robustness to disease pathology, sequence, vendor, and center. EVIDENCE LEVEL: 4. TECHNICAL EFFICACY: Stage 1.

Single breath-held acquisition of coregistered 3D 129 Xe lung ventilation and anatomical proton images of the human lung with compressed sensing.

PURPOSE: To develop and assess a method for acquiring coregistered proton anatomical and hyperpolarized 129 Xe ventilation MR images of the lungs with compressed sensing (CS) in a single breath hold. METHODS: Retrospective CS simulations were performed on fully sampled ventilation images acquired from one healthy smoker to optimize reconstruction parameters. Prospective same-breath anatomical and ventilation images were also acquired in five ex-smokers with an acceleration factor of 3 for hyperpolarized 129 Xe images, and were compared to fully sampled images acquired during the same session. The following metrics were used to assess data fidelity: mean absolute error (MAE), root mean square error, and linear regression of the signal intensity between fully sampled and undersampled images. The effect of CS reconstruction on two quantitative imaging metrics routinely reported [percentage ventilated volume (%VV) and heterogeneity score] was also investigated. RESULTS: Retrospective simulations showed good agreement between fully sampled and CS-reconstructed (acceleration factor of 3) images with MAE (root mean square error) of 3.9% (4.5%). The prospective same-breath images showed a good match in ventilation distribution with an average R2 of 0.76 from signal intensity linear regression and a negligible systematic bias of +0.1% in %VV calculation. A bias of -1.8% in the heterogeneity score was obtained. CONCLUSION: With CS, high-quality 3D images of hyperpolarized 129 Xe ventilation (resolution 4.2 × 4.2 × 7.5 mm3 ) can be acquired with coregistered 1 H anatomical MRI in a 15-s breath hold. The accelerated acquisition time dispenses with the need for registration between separate breath-hold 129 Xe and 1 H MRI, enabling more accurate %VV calculation.

Impact of multidisciplinary foot care team on outcome of diabetic foot ulcer in term of lower extremity amputation at a tertiary care unit in Karachi, Pakistan.

To compare the outcomes of diabetic foot ulcers (DFU) in terms of healing and lower extremity amputation (LEA) rate before and after training of multidisciplinary foot care team (MDFCT). Subjects were categorised into two groups; Group-A cases seen between 1997 and 2006 (before upgrading of training and services of MDFCT) and Group-B cases seen between 2007 and 2016 (after upgrading of training and services of MDFCT). Baseline demographic characteristics, biochemical results, and outcomes of DFU in terms of healing or amputation were analysed by using statistical package social science (SPSS) version 20. Total 7994 DFU cases seen, 888 in group A and 7106 in group B. Mean age of patients was 53.80 ± 10.40 years and mean haemoglobin (HbA1c) was 10.12 ± 2.44. Overall, decreasing trends of amputations were observed from baseline 27.5% to 3.92% during the period of 20 years. In group A, 479 (78.8%) subjects healed completely compared with 3806 (89.1%) in group B. Significant reduction in toe amputations ([13.81%] vs [8.11%]) and below knee amputations [(5.26%) vs (1.82%)] were seen. Similarly, rates of above knee amputation ([1.80%] vs [0.35%] P-value 0.008) in two groups was also significant. Significant improvement was observed in outcomes of DFU in terms of amputation through multidisciplinary team approach.

Comparison of 3 He and 129 Xe MRI for evaluation of lung microstructure and ventilation at 1.5T.

BACKGROUND: To support translational lung MRI research with hyperpolarized 129 Xe gas, comprehensive evaluation of derived quantitative lung function measures against established measures from 3 He MRI is required. Few comparative studies have been performed to date, only at 3T, and multisession repeatability of 129 Xe functional metrics have not been reported. PURPOSE/HYPOTHESIS: To compare hyperpolarized 129 Xe and 3 He MRI-derived quantitative metrics of lung ventilation and microstructure, and their repeatability, at 1.5T. STUDY TYPE: Retrospective. POPULATION: Fourteen healthy nonsmokers (HN), five exsmokers (ES), five patients with chronic obstructive pulmonary disease (COPD), and 16 patients with nonsmall-cell lung cancer (NSCLC). FIELD STRENGTH/SEQUENCE: 1.5T. NSCLC, COPD patients and selected HN subjects underwent 3D balanced steady-state free-precession lung ventilation MRI using both 3 He and 129 Xe. Selected HN, all ES, and COPD patients underwent 2D multislice spoiled gradient-echo diffusion-weighted lung MRI using both hyperpolarized gas nuclei. ASSESSMENT: Ventilated volume percentages (VV%) and mean apparent diffusion coefficients (ADC) were derived from imaging. COPD patients performed the whole MR protocol in four separate scan sessions to assess repeatability. Same-day pulmonary function tests were performed. STATISTICAL TESTS: Intermetric correlations: Spearman's coefficient. Intergroup/internuclei differences: analysis of variance / Wilcoxon's signed rank. Repeatability: coefficient of variation (CV), intraclass correlation (ICC) coefficient. RESULTS: A significant positive correlation between 3 He and 129 Xe VV% was observed (r = 0.860, P < 0.001). VV% was larger for 3 He than 129 Xe (P = 0.001); average bias, 8.79%. A strong correlation between mean 3 He and 129 Xe ADC was obtained (r = 0.922, P < 0.001). MR parameters exhibited good correlations with pulmonary function tests. In COPD patients, mean CV of 3 He and 129 Xe VV% was 4.08% and 13.01%, respectively, with ICC coefficients of 0.541 (P = 0.061) and 0.458 (P = 0.095). Mean 3 He and 129 Xe ADC values were highly repeatable (mean CV: 2.98%, 2.77%, respectively; ICC: 0.995, P < 0.001; 0.936, P < 0.001). DATA CONCLUSION: 129 Xe lung MRI provides near-equivalent information to 3 He for quantitative lung ventilation and microstructural MRI at 1.5T. LEVEL OF EVIDENCE: 3 Technical Efficacy Stage 2 J. Magn. Reson. Imaging 2018.

The Value of Secretin-Enhanced MRCP in Patients With Recurrent Acute Pancreatitis.

OBJECTIVE: The purpose of this study is to assess the additional value of secretin-enhanced MRCP over conventional (non-secretin-enhanced) MRCP in diagnosing disease in patients with recurrent acute pancreatitis. MATERIALS AND METHODS: A retrospective review of a radiology database found 72 patients with recurrent acute pancreatitis who had secretin-enhanced MRCP and ERCP correlation within 3 months of each other between January 2007 and December 2011. Of these patients, 54 had no history of pancreatic tumor or surgery and underwent MRI more than 3 months after an episode of acute pancreatitis. In addition, 57 age- and sex-matched control subjects with secretin-enhanced MRCP and ERCP correlation and without a diagnosis of recurrent acute pancreatitis or chronic pancreatitis were enrolled as the control group. All studies were anonymized, and secretin-enhanced MRCP images (image set A) were separated from conventional 2D and 3D MRCP and T2-weighted images (image set B). Image sets A and B for each patient were assigned different and randomized case numbers. Two blinded reviewers independently assessed both image sets for ductal abnormalities and group A image sets for exocrine response to secretin. RESULTS: There were statistically significantly more patients with recurrent acute pancreatitis with reduced exocrine function compared with patients in the control group (32% vs 9%; p < 0.01) on secretin-enhanced images. Patients with recurrent acute pancreatitis were more likely to have side branch dilation (p = 0.02; odds ratio, 3.6), but not divisum, compared with the control group. Secretin-enhanced images were superior to non-secretin-enhanced images for detecting ductal abnormalities in patients with recurrent acute pancreatitis, with higher sensitivity (76% vs 56%; p = 0.01) and AUC values (0.983 vs 0.760; p < 0.01). CONCLUSION: Up to one-third of patients with recurrent acute pancreatitis showed exocrine functional abnormalities. Secretin-enhanced MRCP had a significantly higher yield for ductal abnormalities than did conventional MRI and should be part of the MRCP protocol for investigation of patients with recurrent acute pancreatitis.

Comparison of CT-based Lobar Ventilation with 3He MR Imaging Ventilation Measurements.

PURPOSE: To compare lobar lung ventilation computed from expiratory and inspiratory computed tomographic (CT) data with direct measurements of ventilation at hyperpolarized helium 3 ((3)He) magnetic resonance (MR) imaging by using same-breath hydrogen 1 ((1)H) MR imaging examinations to coregister the multimodality images. MATERIALS AND METHODS: The study was approved by the national research ethics committee, and written patient consent was obtained. Thirty patients with asthma underwent breath-hold CT at total lung capacity and functional residual capacity. (3)He and (1)H MR images were acquired during the same breath hold at a lung volume of functional residual capacity plus 1 L. Lobar segmentations delineated by major fissures on both CT scans were used to calculate the percentage of ventilation per lobe from the change in inspiratory and expiratory lobar volumes. CT-based ventilation was compared with (3)He MR imaging ventilation by using diffeomorphic image registration of (1)H MR imaging to CT, which enabled indirect registration of (3)He MR imaging to CT. Statistical analysis was performed by using the Wilcoxon signed-rank test, Pearson correlation coefficient, and Bland-Altman analysis. RESULTS: The mean ± standard deviation absolute difference between the CT and (3)He MR imaging percentage of ventilation volume in all lobes was 4.0% (right upper and right middle lobes, 5.4% ± 3.3; right lower lobe, 3.7% ± 3.9; left upper lobe, 2.8% ± 2.7; left lower lobe, 3.9% ± 2.6; Wilcoxon signed-rank test, P < .05). The Pearson correlation coefficient between the two techniques in all lobes was 0.65 (P < .001). Greater percentage of ventilation was seen in the upper lobes with (3)He MR imaging and in the lower lobes with CT. This was confirmed with Bland-Altman analysis, with 95% limits of agreement for right upper and middle lobes, -2.4, 12.7; right lower lobe, -11.7, 4.6; left upper lobe, -4.9, 8.7; and left lower lobe, -9.8, 2.8. CONCLUSION: The percentage of regional ventilation per lobe calculated at CT was comparable to a direct measurement of lung ventilation at hyperpolarized (3)He MR imaging. This work provides evidence for the validity of the CT model, and same-breath (1)H MR imaging enables regional interpretation of (3)He ventilation MR imaging on the underlying lung anatomy at thin-section CT.

The utility of secretin-enhanced MRCP in diagnosing congenital anomalies.

PURPOSE: To assess the additional value of secretin-enhanced MRCP (SMRCP) over conventional MRCP in diagnosing divisum. METHODS: Retrospective HIPAA-compliant and IRB-approved review found 140 patients with SMRCP and ERCP correlation within 6 months of each other. All studies were anonymized and the SMRCP images (SMRCP image set) were separated from 2D and 3D MRCP and axial and coronal T2-weighted images (conventional MRI image set). Each image set on each patient was assigned different and randomized case numbers. Two reviewers (R1 and R2) independently reviewed the image sets for divisum vs. no divisum, complete divisum vs. incomplete divisum, and the certainty of diagnosis (1 = definitely certain, 2 = moderately certain, and 3 = unsure). ERCP findings were taken as gold standard. RESULTS: There was no difference in age and gender between the divisum (n = 97, with 13 incomplete divisum) and no divisum (n = 43) groups. In diagnosing divisum anatomy, the sensitivity was higher for SMRCP compared to conventional MRI for R1 (84.5 vs. 72.2, p = 0.02) but not R2 (89.7 vs. 84.4, p = 0.25). The specificity was higher in SMRCP image set compared to conventional MRI (R1: 88.1 vs. 76.2, p = 0.01; R2: 81.4 vs. 65.1, p < 0.001). The mean area under ROC curve was higher for SMRCP image set (R1: 0.86 vs. 0.74, p = 0.01; R2: 0.87 vs. 0.74, p = 0.01). The certainty of diagnosis was higher in SMRCP image set compared to conventional MRI (p = 0.02 for both reviewers). SMRCP was not found to be superior in distinguishing incomplete from complete divisum. The main reasons for erroneous SMRCP diagnosis were the presence of an ansa loop in the main duct and ductal strictures due to chronic pancreatitis. CONCLUSION: Even though the reviewers had more sequences (axial and coronal) to evaluate in the non-secretin image set, there was some improvement in diagnosing divisum with SMRCP.

Streptococcal necrotizing myositis: a case report and clinical review.

BACKGROUND: Streptococcal necrotizing myositis, also known as gangrenous myositis, is a very rare and severe soft tissue infection that predominately involves skeletal muscle and, eventually, superficial fascia and surrounding tissues. The presentation is often nonspecific until the rapidly progressing clinical course becomes apparent. A high morbidity and mortality rate has been reported in the small number of cases since 1900. Despite several attempts to better define the different entities causing necrotizing myositis, no single definitive causal relationship has been defined. OBJECTIVES: A review of the literature is presented here to help clinicians distinguish those with necrotizing myositis from those with nonnecrotizing myositis when the clinician is at all confronted with the suspicion for such an infection. CASE REPORT: The case presented is that of a 48-year-old woman who had streptococcal necrotizing myositis. She died roughly 72 h after admission. After the patient's death, the clinical team sought consent for autopsy. Hospital staff made contact with family, and information was obtained from the family that the onset of the patient's symptoms was allegedly temporally related to her acquisition of a new tattoo on the right back, where the tattoo process allegedly included injection of cremated ashes of a pet dog. CONCLUSION: A high level of suspicion for necrotizing myositis must be maintained for a patient with unexplained severe muscle pain and soft tissue swelling accompanied by systemic inflammatory response syndrome.

Explainable deep learning-based survival prediction for non-small cell lung cancer patients undergoing radical radiotherapy.

BACKGROUND AND PURPOSE: Survival is frequently assessed using Cox proportional hazards (CPH) regression; however, CPH may be too simplistic as it assumes a linear relationship between covariables and the outcome. Alternative, non-linear machine learning (ML)-based approaches, such as random survival forests (RSFs) and, more recently, deep learning (DL) have been proposed; however, these techniques are largely black-box in nature, limiting explainability. We compared CPH, RSF and DL to predict overall survival (OS) of non-small cell lung cancer (NSCLC) patients receiving radiotherapy using pre-treatment covariables. We employed explainable techniques to provide insights into the contribution of each covariable on OS prediction. MATERIALS AND METHODS: The dataset contained 471 stage I-IV NSCLC patients treated with radiotherapy. We built CPH, RSF and DL OS prediction models using several baseline covariable combinations. 10-fold Monte-Carlo cross-validation was employed with a split of 70%:10%:20% for training, validation and testing, respectively. We primarily evaluated performance using the concordance index (C-index) and integrated Brier score (IBS). Local interpretable model-agnostic explanation (LIME) values, adapted for use in survival analysis, were computed for each model. RESULTS: The DL method exhibited a significantly improved C-index of 0.670 compared to the CPH and a significantly improved IBS of 0.121 compared to the CPH and RSF approaches. LIME values suggested that, for the DL method, the three most important covariables in OS prediction were stage, administration of chemotherapy and oesophageal mean radiation dose. CONCLUSION: We show that, using pre-treatment covariables, a DL approach demonstrates superior performance over CPH and RSF for OS prediction and use explainable techniques to provide transparency and interpretability.

Enhancing supercapacitor performance of Ni-Co-Mn metal-organic frameworks by compositing it with polyaniline and reduced graphene oxide.

Metal-organic frameworks (MOFs) are one of the most sought-after materials in the domain of supercapacitors and can be tailored to accommodate diverse compositions, making them amenable to facile functionalization. However, their intrinsic specific capacitance as well as energy density is minimal, which hinders their usage for advanced energy storage applications. Therefore, herein, we have prepared six electrodes, i.e., Ni-Co-Mn MOFs, polyaniline (PANI), and reduced graphene oxide (rGO) along with their novel nanocomposites, i.e., C1, C2, and C3, comprising MOFs : PANI : rGO in a mass ratio of 100 : 1 : 0.5, 100 : 1 : 1, and 100 : 1 : 10, respectively. The polyaniline conducting polymer and rGO enabled efficient electron transport, enhanced charge storage processes, substantial surface area facilitating higher loading of active materials, promoting electrochemical reactions, and ultimately enhanced nanocomposite system performance. As a result, scanning electron microscopy (SEM) and X-ray diffraction (XRD) techniques confirmed the successful synthesis and revealed distinct morphological features of the materials. Following electrochemical testing, it was observed that composition C2 exhibited the highest performance, demonstrating a groundbreaking specific capacitance of 1007 F g-1 at 1 A g-1. The device showed a good energy density of 25.11 W h kg-1 and a power density of 860 W kg-1. Remarkably, the device demonstrated a capacity retention of 115% after 1500 cycles, which is a clear indication of the wettability factor, according to the literature. The power law indicated b-values in a range of 0.58-0.64, verifying the hybrid-type behavior of supercapacitors.

Use of diffusion-weighted MRI to differentiate chronic pancreatitis from pancreatic cancer.

OBJECTIVE: The purpose of this study was to compare diffusion-weighted MRI (DWI) and conventional (non-DWI) MRI sequences in differentiating mass-forming chronic pancreatitis from pancreatic cancer. MATERIALS AND METHODS: A retrospective cohort study included 36 patients who underwent pancreatic resection for pancreatic cancer (n = 13) and chronic pancreatitis (n = 23) after preoperative MRI with DWI. Two independent reviewers assessed the DW images for signal intensity and apparent diffusion coefficient (ADC) values. Four weeks later, they reviewed the other MR images for size of mass, double-duct sign, pancreatic duct cutoff, and perivascular soft-tissue cuffing. A score for conventional MRI was given with 1 meaning definitely benign and 5 meaning definitely malignant. Univariate and multivariate analyses and receiver operating characteristic (ROC) curve analysis were performed with surgical pathologic examination as the reference standard. RESULTS: The only finding that differentiated the two groups was the presence of a well-defined mass, favoring the diagnosis of cancer (p = 0.02, p < 0.01). There was no significant difference between the two groups in signal intensity on DW images (p = 0.82, p = 0.85) or ADC (p = 0.51, p = 0.76). Double-duct sign, pancreatic duct cutoff, and perivascular soft-tissue cuffing were not useful in differentiating the two groups. The areas under the ROC curve were 0.873 and 0.878 for the conventional MRI scores, compared with 0.602 and 0.552 for ADC measurements (p = 0.02, p = 0.008). CONCLUSION: The addition of DWI to conventional MRI does not facilitate differentiation of pancreatic cancer from chronic pancreatitis.

Usefulness of conventional MRI sequences and diffusion-weighted imaging in differentiating malignant from benign portal vein thrombus in cirrhotic patients.

OBJECTIVE: The objective of our study was to determine the value of diffusion-weighted imaging (DWI) and conventional MRI (non-DWI sequences) in differentiating benign portal vein thrombus (PVT) from malignant PVT in cirrhotic patients. MATERIALS AND METHODS: A retrospective search of the department of radiology's MRI database of examinations performed from October 2006 through December 2010 for "portal vein thrombosis" and "cirrhosis" and "hepatocellular cancer" was performed. Patients who underwent diagnostic DWI and had thrombus shown to be rapidly (< 3 months) increasing in size despite anticoagulation therapy were considered to have malignant PVT (n = 16 cases) and patients with MRI findings showing stability or reduction in the extent of thrombus over a 12-month follow-up were considered to have benign PVT (n = 20 cases). Two blinded and independent reviewers analyzed the DW images and conventional MR images. RESULTS: There was no difference in the distribution of patients by age (p = 0.25) or sex (p = 0.68) between the benign and malignant PVT groups. On multivariate analysis, the only parameter to predict the type of PVT was the size of HCC (p = 0.05); other parameters were excluded from the model. There was substantial overlap in apparent diffusion coefficient (ADC) values and PVT/liver ADC ratios of benign PVT and malignant PVT. The presence of at least two of the three following MRI findings had a sensitivity of 100% and specificity of 90% for the diagnosis of malignant PVT: distance from tumor to PVT of less than 2 cm, HCC size of greater than 5 cm, and arterial enhancement of PVT. CONCLUSION: Signal-intensity characteristics on DWI and measured ADC values do not reliably differentiate benign PVT from malignant PVT. On the other hand, careful assessment of conventional MRI findings may allow this distinction, thus obviating biopsy.

Changes in the prevalence of diabetes, prediabetes and associated risk factors in rural Baluchistan; a secondary analysis from repeated surveys (2002-2017).

To observe trends of diabetes and its associated risk factors from health surveys 2002-2017 in rural areas of Baluchistan-Pakistan and a secondary analysis based on community based health surveys of Baluchistan conducted between 2001-02, 2009-10, and 2016-17. A total of 4250 participants were included in this combined analysis, 2515 from 2001-2002, 1377 from 2009-2010 and 358 from 2016-2017 survey year. In each survey, detailed information of baseline parameters were noted on a predesigned questionnaire. Fasting plasma glucose (FPG) was used for diagnosis of diabetes for comparative purposes in this analysis. Cardiovascular (CVD) risk factors including hypertension, obesity, dyslipidaemia, tobacco use, alcohol consumption, and physical activity were compared. Most subjects were aged 30-50 years and males were found higher in 2016-17 compared to 2001-02 and 2009-10. Pronounced increases in BMI, waist circumference, blood pressure, and family history of diabetes were observed in 2016-17. Diabetes prevalence was 4.2 (3.4-4.9), 7.8 (6.6-9.2) and 31.9 (26.9-37.4), whilst pre-diabetes was 1.7 (1.3-2.2), 3.6 (2.8-4.6) and 10.7 (7.6-14.9) in years 2001-02, 2009-10, and 2016-17, respectively. Among those aged 20-39years, prevalence of diabetes was stable from 2001-10 yet increased considerably between the ages of 30-39years in 2016-17. Throughout the observed period, rapid increases were observed in hypertension, obesity, and dyslipidaemia, however, addiction to tobacco use and alcohol intake decreased. Adjusted odd ratios showed age, marital status, education, hypertension, and family history of diabetes as associated risk factors for glycaemic dysregulation. The rural Baluchistan population is confronted with increasing trends of early onset diabetes due to highly associated CVD risk factors, especially central obesity and dyslipidaemia, raising a major public health challenge.

A hybrid model- and deep learning-based framework for functional lung image synthesis from multi-inflation CT and hyperpolarized gas MRI.

BACKGROUND: Hyperpolarized gas MRI is a functional lung imaging modality capable of visualizing regional lung ventilation with exceptional detail within a single breath. However, this modality requires specialized equipment and exogenous contrast, which limits widespread clinical adoption. CT ventilation imaging employs various metrics to model regional ventilation from non-contrast CT scans acquired at multiple inflation levels and has demonstrated moderate spatial correlation with hyperpolarized gas MRI. Recently, deep learning (DL)-based methods, utilizing convolutional neural networks (CNNs), have been leveraged for image synthesis applications. Hybrid approaches integrating computational modeling and data-driven methods have been utilized in cases where datasets are limited with the added benefit of maintaining physiological plausibility. PURPOSE: To develop and evaluate a multi-channel DL-based method that combines modeling and data-driven approaches to synthesize hyperpolarized gas MRI lung ventilation scans from multi-inflation, non-contrast CT and quantitatively compare these synthetic ventilation scans to conventional CT ventilation modeling. METHODS: In this study, we propose a hybrid DL configuration that integrates model- and data-driven methods to synthesize hyperpolarized gas MRI lung ventilation scans from a combination of non-contrast, multi-inflation CT and CT ventilation modeling. We used a diverse dataset comprising paired inspiratory and expiratory CT and helium-3 hyperpolarized gas MRI for 47 participants with a range of pulmonary pathologies. We performed six-fold cross-validation on the dataset and evaluated the spatial correlation between the synthetic ventilation and real hyperpolarized gas MRI scans; the proposed hybrid framework was compared to conventional CT ventilation modeling and other non-hybrid DL configurations. Synthetic ventilation scans were evaluated using voxel-wise evaluation metrics such as Spearman's correlation and mean square error (MSE), in addition to clinical biomarkers of lung function such as the ventilated lung percentage (VLP). Furthermore, regional localization of ventilated and defect lung regions was assessed via the Dice similarity coefficient (DSC). RESULTS: We showed that the proposed hybrid framework is capable of accurately replicating ventilation defects seen in the real hyperpolarized gas MRI scans, achieving a voxel-wise Spearman's correlation of 0.57 ± 0.17 and an MSE of 0.017 ± 0.01. The hybrid framework significantly outperformed CT ventilation modeling alone and all other DL configurations using Spearman's correlation. The proposed framework was capable of generating clinically relevant metrics such as the VLP without manual intervention, resulting in a Bland-Altman bias of 3.04%, significantly outperforming CT ventilation modeling. Relative to CT ventilation modeling, the hybrid framework yielded significantly more accurate delineations of ventilated and defect lung regions, achieving a DSC of 0.95 and 0.48 for ventilated and defect regions, respectively. CONCLUSION: The ability to generate realistic synthetic ventilation scans from CT has implications for several clinical applications, including functional lung avoidance radiotherapy and treatment response mapping. CT is an integral part of almost every clinical lung imaging workflow and hence is readily available for most patients; therefore, synthetic ventilation from non-contrast CT can provide patients with wider access to ventilation imaging worldwide.

PhysVENeT: a physiologically-informed deep learning-based framework for the synthesis of 3D hyperpolarized gas MRI ventilation.

Functional lung imaging modalities such as hyperpolarized gas MRI ventilation enable visualization and quantification of regional lung ventilation; however, these techniques require specialized equipment and exogenous contrast, limiting clinical adoption. Physiologically-informed techniques to map proton (1H)-MRI ventilation have been proposed. These approaches have demonstrated moderate correlation with hyperpolarized gas MRI. Recently, deep learning (DL) has been used for image synthesis applications, including functional lung image synthesis. Here, we propose a 3D multi-channel convolutional neural network that employs physiologically-informed ventilation mapping and multi-inflation structural 1H-MRI to synthesize 3D ventilation surrogates (PhysVENeT). The dataset comprised paired inspiratory and expiratory 1H-MRI scans and corresponding hyperpolarized gas MRI scans from 170 participants with various pulmonary pathologies. We performed fivefold cross-validation on 150 of these participants and used 20 participants with a previously unseen pathology (post COVID-19) for external validation. Synthetic ventilation surrogates were evaluated using voxel-wise correlation and structural similarity metrics; the proposed PhysVENeT framework significantly outperformed conventional 1H-MRI ventilation mapping and other DL approaches which did not utilize structural imaging and ventilation mapping. PhysVENeT can accurately reflect ventilation defects and exhibits minimal overfitting on external validation data compared to DL approaches that do not integrate physiologically-informed mapping.

Voxel-Wise Comparison of Co-Registered Quantitative CT and Hyperpolarised Gas Diffusion-Weighted MRI Measurements in IPF.

The patterns of idiopathic pulmonary fibrosis (IPF) lung disease that directly correspond to elevated hyperpolarised gas diffusion-weighted (DW) MRI metrics are currently unknown. This study aims to develop a spatial co-registration framework for a voxel-wise comparison of hyperpolarised gas DW-MRI and CALIPER quantitative CT patterns. Sixteen IPF patients underwent 3He DW-MRI and CT at baseline, and eleven patients had a 1-year follow-up DW-MRI. Six healthy volunteers underwent 129Xe DW-MRI at baseline only. Moreover, 3He DW-MRI was indirectly co-registered to CT via spatially aligned 3He ventilation and structural 1H MRI. A voxel-wise comparison of the overlapping 3He apparent diffusion coefficient (ADC) and mean acinar dimension (LmD) maps with CALIPER CT patterns was performed at baseline and after 1 year. The abnormal lung percentage classified with the LmD value, based on a healthy volunteer 129Xe LmD, and CALIPER was compared with a Bland-Altman analysis. The largest DW-MRI metrics were found in the regions classified as honeycombing, and longitudinal DW-MRI changes were observed in the baseline-classified reticular changes and ground-glass opacities regions. A mean bias of -15.3% (95% interval -56.8% to 26.2%) towards CALIPER was observed for the abnormal lung percentage. This suggests DW-MRI may detect microstructural changes in areas of the lung that are determined visibly and quantitatively normal by CT.

Long bone fracture detection in suspected child abuse: contribution of lateral views.

BACKGROUND: ACR guidelines for routine skeletal survey for child abuse recommend only AP radiographs of the long bones; however, many institutions add lateral radiographs. OBJECTIVES: To evaluate whether adding lateral radiographs for long bones changes the frequency and confidence of fracture detection in skeletal survey radiographs for suspected abuse. MATERIALS AND METHODS: We identified 100 children younger than 2 years of age who underwent skeletal survey for child abuse; 56 with multiple long bone fractures, 22 with a single fracture and 22 with no fractures. Four radiologists (two pediatric radiologists, one pediatric radiology fellow and one general radiologist) evaluated two randomized series (one series included only frontal, and the other series, frontal and lateral radiographs). Likert scale of 1-5 was used to score for detection of metaphyseal and diaphyseal fractures. RESULTS: For combined readers, significantly more metaphyseal fractures (P = 0.01) were detected with the two-views series of radiographs compared with the frontal-only view; there was no significant difference for diaphyseal fractures. Confidence was also significantly higher for the two-views series. Kappa improved (from 0.32 to 0.48) when the lateral view was added only for the metaphyseal fractures. CONCLUSION: Adding lateral radiographs resulted in increased detection and confidence levels of metaphyseal fractures.

Deep learning in structural and functional lung image analysis.

The recent resurgence of deep learning (DL) has dramatically influenced the medical imaging field. Medical image analysis applications have been at the forefront of DL research efforts applied to multiple diseases and organs, including those of the lungs. The aims of this review are twofold: (i) to briefly overview DL theory as it relates to lung image analysis; (ii) to systematically review the DL research literature relating to the lung image analysis applications of segmentation, reconstruction, registration and synthesis. The review was conducted following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. 479 studies were initially identified from the literature search with 82 studies meeting the eligibility criteria. Segmentation was the most common lung image analysis DL application (65.9% of papers reviewed). DL has shown impressive results when applied to segmentation of the whole lung and other pulmonary structures. DL has also shown great potential for applications in image registration, reconstruction and synthesis. However, the majority of published studies have been limited to structural lung imaging with only 12.9% of reviewed studies employing functional lung imaging modalities, thus highlighting significant opportunities for further research in this field. Although the field of DL in lung image analysis is rapidly expanding, concerns over inconsistent validation and evaluation strategies, intersite generalisability, transparency of methodological detail and interpretability need to be addressed before widespread adoption in clinical lung imaging workflow.

Glycemic status and general characteristics among individuals with undiagnosed diabetes; findings from second National Diabetes Survey of Pakistan 2016-2017 (NDSP 08).

BACKGROUND AND AIM: To observe the glycemic status among individuals with undiagnosed diabetes in urban and rural areas of all four provinces of Pakistan. METHODS: The findings of this study are obtained from the second National Diabetes Survey of Pakistan (NDSP) 2016-2017, a nationwide epidemiological survey. Out of 12,486 individuals approached, 10,834 participants agreed to be included in the second NDSP. An oral glucose tolerance test was used to assess undiagnosed diabetes individuals according to World Health Organization criteria. RESULTS: The overall weighted prevalence of undiagnosed diabetes was 7.1% (2.4% in urban and 4.7% in rural areas). Based on isolated fasting plasma glucose or 2-h post 75 gm glucose load or combining both, the weighted prevalence of undiagnosed diabetes was 43.5%, 17.6%, and 38.9%, respectively. Out of the 43.5% of individuals, 15.3% had fasting plasma glucose higher than 250 mg/dl at the time of presentation. Among all the individuals, 23.7% were found to be of less than 40 years of age, 29.2% had a positive family history of diabetes, 80.8% were abdominal obese, 53.8% were hypertensive, and 98% were dyslipidemic. In comparison to the elder group, poor glycemic control of ≥10% HbA1c was observed in most of the younger age groups (p < 0.05). CONCLUSION: A significant number of people remain undiagnosed in this part of the world. The glycemic status along with the other associated risk factors at the time of presentation is alarming. Thus, for the early detection of diabetes, awareness and education in the community are crucial. Hence, long-term complications of diabetes can be prevented.