RSRamandeep Singh

Ramandeep Singh

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Ramandeep Singh has a total of 48 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Imaging Infectious Disease of the Abdomen (Including COVID-19)

    by Rubal Rai, Ramandeep Singh, Peter F. Hahn, Avinash Kambadakone, Richard M. Gore

    Abdominal infections can prolong hospital stays and lead to high morbidity and mortality. In patients with pre-existing critical illness or other conditions such as cancer and immunosuppression, early diagnosis of abdominal infections can be challenging and are important considerations to prevent life-threatening sepsis and complications. The constellation of predisposing host factors, infectious agents, and site of involvement can lead to a variety of clinical and imaging manifestations. Based on organ system involvement, diverse imaging techniques can be utilized ranging from plain films to cross-sectional and advanced imaging modalities. The purpose of this chapter is to discuss uncommon and common etiologies and imaging manifestations of infections in the abdomen and pelvis with emphasis on the radiological features considering the relevant clinical background and risk factors.


  • Spectral segmentation and radiomic features predict carotid stenosis and ipsilateral ischemic burden from DECT angiography

    by Shadi Ebrahimian, Fatemeh Homayounieh, Ramandeep Singh, Andrew Primak, Malvern Siemens Healthcare Usa Inc., Mannudeep K. Kalra, Javier M. Romero

    The purpose of this study is to compare spectral segmentation, spectral radiomic, and single-energy radiomic features in the assessment of internal and common carotid artery (ICA/CCA) stenosis and prediction of surgical outcome. Our ethical committee–approved, Health Insurance Portability and Accountability Act (HIPAA)-compliant study included 85 patients (mean age, 73 ± 10 years; male : female, 56 : 29) who underwent contrast-enhanced, dual-source dual-energy CT angiography (DECTA) (Siemens Definition Flash) of the neck for assessing ICA/CCA stenosis. Patients with a prior surgical or interventional treatment of carotid stenosis were excluded. Two radiologists graded the severity of carotid stenosis on DECTA images as mild (70%) stenosis. Thin-section, low- and high-kV DICOM images from the arterial phase acquisition were processed with a dual-energy CT prototype (DTA, eXamine, Siemens Healthineers) to generate spectral segmentation and radiomic features over regions of interest along the entire length (volume) and separately at a single-section with maximum stenosis. Multiple logistic regressions and area under the receiver operating characteristic curve (AUC) were used for data analysis. Among 85 patients, 22 ICA/CCAs had normal luminal dimensions and 148 ICA/CCAs had luminal stenosis (mild stenosis: 51, moderate: 38, severe: 59). For differentiating non-severe and severe ICA/CCA stenosis, radiomic features (volume: AUC = 0.94, 95% CI 0.88-0.96; section: AUC = 0.92, 95% CI 0.86-0.93) were significantly better than spectral segmentation features (volume: AUC = 0.86, 95% CI 0.74-0.87; section: AUC = 0.68, 95% CI 0.66-0.78) (P < .001). Spectral radiomic features predicted revascularization procedure (AUC = 0.77) and the presence of ipsilateral intracranial ischemic changes (AUC = 0.76). Spectral segmentation and radiomic features from DECTA can differentiate patients with different luminal ICA/CCA stenosis grades.


  • Open Access

    Deep learning predicts cardiovascular disease risks from lung cancer screening low dose computed tomography

    by Hanqing Chao, Hongming Shan, Fatemeh Homayounieh, Ramandeep Singh, Ruhani Doda Khera, Hengtao Guo, Timothy Su, Ge Wang, Mannudeep K. Kalra, Pingkun Yan

    Cancer patients have a higher risk of cardiovascular disease (CVD) mortality than the general population. Low dose computed tomography (LDCT) for lung cancer screening offers an opportunity for simultaneous CVD risk estimation in at-risk patients. Our deep learning CVD risk prediction model, trained with 30,286 LDCTs from the National Lung Cancer Screening Trial, achieves an area under the curve (AUC) of 0.871 on a separate test set of 2,085 subjects and identifies patients with high CVD mortality risks (AUC of 0.768). We validate our model against ECG-gated cardiac CT based markers, including coronary artery calcification (CAC) score, CAD-RADS score, and MESA 10-year risk score from an independent dataset of 335 subjects. Our work shows that, in high-risk patients, deep learning can convert LDCT for lung cancer screening into a dual-screening quantitative tool for CVD risk estimation.


  • Accuracy of radiomics for differentiating diffuse liver diseases on non-contrast CT

    by Fatemeh Homayounieh, Sanjay Saini, Leila Mostafavi, Ruhani Doda Khera, Michael Sühling, Bernhard Schmidt, Ramandeep Singh, Thomas Flohr, Mannudeep K. Kalra

    Purpose Radiomics help move cross-sectional imaging into the domain of quantitative imaging to assess the lesions, their stoma as well as in their temporal monitoring. We applied and assessed the accuracy of radiomics for differentiating healthy liver from diffuse liver diseases (cirrhosis, steatosis, amiodarone deposition, and iron overload) on non-contrast abdomen CT images in an institutional-reviewed board-approved, retrospective study. Methods Our study included 300 adult patients (mean age 63 ± 16 years; 171 men, 129 women) who underwent non-contrast abdomen CT and had either a healthy liver (n = 100 patients) or an evidence of diffuse liver disease (n = 200). The diffuse liver diseases included steatosis (n = 50), cirrhosis (n = 50), hyperdense liver due to amiodarone deposition (n = 50), or iron overload (n = 50). We manually segmented the liver in one section at the level of the porta hepatis (all 300 patients) and then over the entire liver volume (50 patients). Radiomics were estimated for the liver, and statistical comparison was performed with multiple logistic regression and random forest classifier. Results With random forest classifier, the AUC for radiomics ranged between 0.72 (iron overload vs. healthy liver) and 0.98 (hepatic steatosis vs. healthy liver) for differentiating diffuse liver disease from the healthy liver. Combined root mean square and gray-level co-occurrence matrix had the highest AUC (AUC:0.99, p < 0.01) for differentiating healthy liver from steatosis. Radiomics were more accurate for differentiating healthy liver from amiodarone (AUC:0.93) than from iron overload (AUC:0.79). Conclusion Radiomics enable differentiation of healthy liver from hepatic steatosis, cirrhosis, amiodarone deposition, and iron overload from a single section of non-contrast abdominal CT. The high accuracy of radiomics coupled with rapid segmentation of the region of interest, radiomics estimation, and statistical analyses within the same prototype makes a compelling case for bringing radiomics to clinical use for improving reporting in evaluation of healthy liver and diffuse liver diseases.


  • Quantitative lobar pulmonary perfusion assessment on dual-energy CT pulmonary angiography: applications in pulmonary embolism

    by Ramandeep Singh, Ryan Zipan Nie, Fatemeh Homayounieh, Bernhard Schmidt, Thomas Flohr, Mannudeep K. Kalra

    Purpose To assess quantitative lobar pulmonary perfusion on DECT-PA in patients with and without pulmonary embolism (PE). Materials and methods Our retrospective study included 88 adult patients (mean age 56 ± 19 years; 38 men, 50 women) who underwent DECT-PA (40 PE present; 48 PE absent) on a 384-slice, third-generation, dual-source CT. All DECT-PA examinations were reviewed to record the presence and location of occlusive and non-occlusive PE. Transverse thin (1 mm) DECT images (80/150 kV) were de-identified and exported offline for processing on a stand-alone deep learning–based prototype for automatic lung lobe segmentation and to obtain the mean attenuation numbers (in HU), contrast amount (in mg), and normalized iodine concentration per lung and lobe. The zonal volumes and mean enhancement were obtained from the Lung Analysis™ application. Data were analyzed with receiver operating characteristics (ROC) and analysis of variance (ANOVA). Results The automatic lung lobe segmentation was accurate in all DECT-PA (88; 100%). Both lobar and zonal perfusions were significantly lower in patients with PE compared with those without PE (p < 0.0001). The mean attenuation numbers, contrast amounts, and normalized iodine concentrations in different lobes were significantly lower in the patients with PE compared with those in the patients without PE (AUC 0.70–0.78; p < 0.0001). Patients with occlusive PE had significantly lower quantitative perfusion compared with those without occlusive PE (p < 0.0001). Conclusion The deep learning–based prototype enables accurate lung lobe segmentation and assessment of quantitative lobar perfusion from DECT-PA. Key Points • Deep learning–based prototype enables accurate lung lobe segmentation and assessment of quantitative lobar perfusion from DECT-PA. • Quantitative lobar perfusion parameters (AUC up to 0.78) have a higher predicting presence of PE on DECT-PA examinations compared with the zonal perfusion parameters (AUC up to 0.72). • The lobar-normalized iodine concentration has the highest AUC for both presence of PE and for differentiating occlusive and non-occlusive PE.


  • Comparison of image quality and radiation doses between rapid kV-switching and dual-source DECT techniques in the chest

    by Ramandeep Singh, Amita Sharma, Shaunagh McDermott, Fatemeh Homayounieh, Shivam Rastogi, Efren J. Flores, Jo Anne O. Shepard, Matthew D. Gilman, Subba R. Digumarthy


  • Open Access

    Can fully iterative reconstruction technique enable routine abdominal CT at less than 1 mSv?

    by Azadeh Tabari, Ramandeep Singh, Ruhani Doda Khera, Yiemeng Hoi, Erin Angel, Mannudeep K. Kalra, Rachna Madan


  • Heterogeneous Pulmonary Perfusion on Dual-Energy Computed Tomography: Faulty Postprocessing or New Artifact?

    by Riddhi Borse, Fatemeh Homayounieh, Ramandeep Singh, Subba R. Digumarthy

    Iodine uptake in the lungs and intrathoracic lesions on postcontrast dual-energy computed tomography is used for evaluation of pulmonary embolism-related perfusion defects and pulmonary infarctions. It has been applied in characterization and treatment response assessment of lung and mediastinal abnormalities. We report a new imaging artifact or faulty image postprocessing in a commercially available rapid kV switching technique of dual-energy computed tomography, which can confound its clinical utility for evaluation of iodine uptake.


  • Open Access

    Deep learning in chest radiography: Detection of findings and presence of change

    by Ramandeep Singh, Mannudeep K Kalra, Chayanin Nitiwarangkul, John A Patti, Fatemeh Homayounieh, Atul Padole, Pooja Rao, Preetham Putha, Victorine V Muse, Amita Sharma, et al.

    Deep learning (DL) based solutions have been proposed for interpretation of several imaging modalities including radiography, CT, and MR. For chest radiographs, DL algorithms have found success in the evaluation of abnormalities such as lung nodules, pulmonary tuberculosis, cystic fibrosis, pneumoconiosis, and location of peripherally inserted central catheters. Chest radiography represents the most commonly performed radiological test for a multitude of non-emergent and emergent clinical indications. This study aims to assess accuracy of deep learning (DL) algorithm for detection of abnormalities on routine frontal chest radiographs (CXR), and assessment of stability or change in findings over serial radiographs. We processed 874 de-identified frontal CXR from 724 adult patients (> 18 years) with DL (Qure AI). Scores and prediction statistics from DL were generated and recorded for the presence of pulmonary opacities, pleural effusions, hilar prominence, and enlarged cardiac silhouette. To establish a standard of reference (SOR), two thoracic radiologists assessed all CXR for these abnormalities. Four other radiologists (test radiologists), unaware of SOR and DL findings, independently assessed the presence of radiographic abnormalities. A total 724 radiographs were assessed for detection of findings. A subset of 150 radiographs with follow up examinations was used to asses change over time. Data were analyzed with receiver operating characteristics analyses and post-hoc power analysis. About 42% (305/ 724) CXR had no findings according to SOR; single and multiple abnormalities were seen in 23% (168/724) and 35% (251/724) of CXR. There was no statistical difference between DL and SOR for all abnormalities (p = 0.2–0.8). The area under the curve (AUC) for DL and test radiologists ranged between 0.837–0.929 and 0.693–0.923, respectively. DL had lowest AUC (0.758) for assessing changes in pulmonary opacities over follow up CXR. Presence of chest wall implanted devices negatively affected the accuracy of DL algorithm for evaluation of pulmonary and hilar abnormalities. DL algorithm can aid in interpretation of CXR findings and their stability over follow up CXR. However, in its present version, it is unlikely to replace radiologists due to its limited specificity for categorizing specific findings.