Leonid Roshkovan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Leonid Roshkovan has a total of 161 co-authors. Here are the top co-authors by number of shared publications:
- Sharyn I. Katz
Department of Radiology, University of Pennsylvania, Philadelphia, PA
30 shared publications - Despina Kontos
Department of Radiology, Columbia University, 622 W. 168th St, Alianza Dominicana Cultural Center, 5th Fl, New York, NY 10032
23 shared publications - Walter C. Mankowski
Department of Radiology, Columbia University, 622 W. 168th St, Alianza Dominicana Cultural Center, 5th Fl, New York, NY 10032
18 shared publications - Andrew William Chen
24Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania
17 shared publications - Brandon W. Higgs
Translational Data Science, Genmab, Princeton, NJ
17 shared publications - Christian U. Blank
Leiden University Medical Center, Leiden, The Netherlands
17 shared publications
Latest Publications
- Open Access
Deep Learning Reconstruction for Ultra-High-Resolution Photon-Counting CT of the Lung: Image Quality and Texture Characterization
Objectives: To characterize image noise, lesion contrast, spatial resolution, and attenuation distribution for deep learning reconstruction (DLR) compared with hybrid iterative reconstruction (IR) in ultra-high-resolution (UHR) photon-counting CT (PCCT) of the lung, using a patient-derived 3D-printed phantom, and to apply the same analytical framework to patient examinations acquired on the same system. Materials and Methods: A patient CT scan-derived lung phantom containing three digitally inserted lesions of differing morphology was fabricated using PixelPrint 3D printing and imaged on a CZT-based PCCT prototype at four dose levels (CTDIvol 6, 4, 2, and 1 mGy). Images were reconstructed with hybrid iterative reconstruction at normal resolution (512 by 512) and UHR (1024 by 1024), and with DLR at UHR. Image noise, lesion contrast, and contrast-to-noise ratio (CNR) were measured within prespecified regions of interest replicated across reconstructions by coordinate transfer. Spatial resolution was assessed by the modulation transfer function (MTF) from a high-contrast edge at eight locations. Attenuation distribution and local texture were characterized using histograms and gray-level co-occurrence matrices (GLCMs) within a structured parenchymal region. Two patient examinations with part solid lung nodules acquired on the same prototype were analyzed as illustrative examples, with solid and ground-glass components segmented separately and their attenuation distributions compared. Results: In the phantom, DLR reduced image noise relative to UHR hybrid iterative reconstruction (7.8% at 6 mGy and 15.2% at 1 mGy). Lesion contrast was constant across reconstructions and dose levels, so CNR differences reflected differences in noise alone. MTF curves for DLR lay above those for hybrid iterative reconstruction across the evaluated spatial frequency range at both 6 and 1 mGy, averaged +0.4 lp/mm in MTF50. In a structured parenchymal region, the attenuation histogram mode became progressively narrower from hybrid iterative reconstruction at 1 mGy to DLR at 6 mGy (averaged -23%), while mode position and mean regional attenuation were preserved, consistent with reduced partial-volume mixing rather than altered attenuation. In the patient example, the attenuation distributions of solid and ground-glass components were more widely separated with UHR DLR (2.0) than with either hybrid iterative reconstruction (1.6). Conclusions: In UHR photon-counting CT of the lung, DLR reduced image noise while preserving lesion contrast and regional attenuation, increased measured MTF at a high-contrast edge, and produced attenuation distributions consistent with reduced partial-volume mixing at material boundaries. The same effect was observed in the separation of solid and ground-glass components in two patient examples.
Open AccessDeep Learning Reconstruction for Ultra-High-Resolution Photon-Counting CT of the Lung: Image Quality and Texture Characterization
Objectives: To characterize image noise, lesion contrast, spatial resolution, and attenuation distribution for deep learning reconstruction (DLR) compared with hybrid iterative reconstruction (IR) in ultra-high-resolution (UHR) photon-counting CT (PCCT) of the lung, using a patient-derived 3D-printed phantom, and to apply the same analytical framework to patient examinations acquired on the same system. Materials and Methods: A patient CT scan-derived lung phantom containing three digitally inserted lesions of differing morphology was fabricated using PixelPrint 3D printing and imaged on a CZT-based PCCT prototype at four dose levels (CTDIvol 6, 4, 2, and 1 mGy). Images were reconstructed with hybrid iterative reconstruction at normal resolution (512 by 512) and UHR (1024 by 1024), and with DLR at UHR. Image noise, lesion contrast, and contrast-to-noise ratio (CNR) were measured within prespecified regions of interest replicated across reconstructions by coordinate transfer. Spatial resolution was assessed by the modulation transfer function (MTF) from a high-contrast edge at eight locations. Attenuation distribution and local texture were characterized using histograms and gray-level co-occurrence matrices (GLCMs) within a structured parenchymal region. Two patient examinations with part solid lung nodules acquired on the same prototype were analyzed as illustrative examples, with solid and ground-glass components segmented separately and their attenuation distributions compared. Results: In the phantom, DLR reduced image noise relative to UHR hybrid iterative reconstruction (7.8% at 6 mGy and 15.2% at 1 mGy). Lesion contrast was constant across reconstructions and dose levels, so CNR differences reflected differences in noise alone. MTF curves for DLR lay above those for hybrid iterative reconstruction across the evaluated spatial frequency range at both 6 and 1 mGy, averaged +0.4 lp/mm in MTF50. In a structured parenchymal region, the attenuation histogram mode became progressively narrower from hybrid iterative reconstruction at 1 mGy to DLR at 6 mGy (averaged -23%), while mode position and mean regional attenuation were preserved, consistent with reduced partial-volume mixing rather than altered attenuation. In the patient example, the attenuation distributions of solid and ground-glass components were more widely separated with UHR DLR (2.0) than with either hybrid iterative reconstruction (1.6). Conclusions: In UHR photon-counting CT of the lung, DLR reduced image noise while preserving lesion contrast and regional attenuation, increased measured MTF at a high-contrast edge, and produced attenuation distributions consistent with reduced partial-volume mixing at material boundaries. The same effect was observed in the separation of solid and ground-glass components in two patient examples.
- 1 May 2026
- Published by Radiological Society of North America (RSNA) in Radiology: Artificial Intelligence
- Vol. 8 (3) , e240218
Transformer-based Fusion of Longitudinal Multimodal Radiomic Features from Chest Radiography and CT in COVID-19
A transformer-based framework integrating longitudinal multimodal medical data from chest radiographs and CT images achieved robust performance in clinical outcome prediction in patients with COVID-19.
- 1 May 2026
- Published by Radiological Society of North America (RSNA) in Radiology: Artificial Intelligence
- Vol. 8 (3) , e240218
Transformer-based Fusion of Longitudinal Multimodal Radiomic Features from Chest Radiography and CT in COVID-19
A transformer-based framework integrating longitudinal multimodal medical data from chest radiographs and CT images achieved robust performance in clinical outcome prediction in patients with COVID-19.
- Open Access
Evaluation of a CZT-based photon-counting detector CT prototype for low-dose lung cancer screening using patient-specific lung phantoms
Objectives: To evaluate the clinical performance of a cadmium-zinc-telluride-(CZT-) based photon-counting computed tomography (PCCT) system for low-dose lung cancer screening (LCS-LDCT) using patient-specific 3D-printed lung phantoms, and to compare its image quality and radiomics consistency with a conventional energy-integrating detector CT (EIDCT) system. Methods: Six 3D-printed lung phantoms, derived from patient CT datasets and representing various lesion types (solid, part-solid, and ground-glass), were imaged on PCCT and EIDCT scanners at matched dose levels (1.6 - 20.4 mGy). Quantitative image metrics, Hounsfield unit (HU) accuracy, image noise, and contrast-to-noise ratio (CNR), were assessed across dose levels. Radiomic features were extracted for each lesion and analyzed via principal component analysis to quantify feature consistency (within-cluster distance) and lesion type separability. Results: PCCT demonstrated significantly lower image noise and higher CNR compared with EIDCT, particularly at lower dose levels. HU values were consistent across doses for both systems, with reduced variability in PCCT (coefficient of variation < 0.004). Radiomics analysis revealed tighter clustering (reduced within-cluster distances) and comparable lesion type separability between PCCT and EIDCT, indicating enhanced feature stability and lesion differentiation. Qualitative review confirmed superior lesion conspicuity and margin delineation with PCCT. Conclusions: CZT-based PCCT outperforms conventional EIDCT in quantitative and qualitative imaging metrics for LCS-LDCT, enabling superior image quality and radiomics reproducibility at reduced radiation doses. These findings support the clinical translation of PCCT for lung cancer screening and radiomics-based lesion characterization. Key points: PCCT offers reduced image noise and improved CNR performance, especially at ultra-low doses. HU stability and radiomics reproducibility are enhanced with PCCT. Clinical relevance statement: PCCT may enable further dose reduction without compromising diagnostic accuracy in LCS-LDCT.
Open AccessEvaluation of a CZT-based photon-counting detector CT prototype for low-dose lung cancer screening using patient-specific lung phantoms
Objectives: To evaluate the clinical performance of a cadmium-zinc-telluride-(CZT-) based photon-counting computed tomography (PCCT) system for low-dose lung cancer screening (LCS-LDCT) using patient-specific 3D-printed lung phantoms, and to compare its image quality and radiomics consistency with a conventional energy-integrating detector CT (EIDCT) system. Methods: Six 3D-printed lung phantoms, derived from patient CT datasets and representing various lesion types (solid, part-solid, and ground-glass), were imaged on PCCT and EIDCT scanners at matched dose levels (1.6 - 20.4 mGy). Quantitative image metrics, Hounsfield unit (HU) accuracy, image noise, and contrast-to-noise ratio (CNR), were assessed across dose levels. Radiomic features were extracted for each lesion and analyzed via principal component analysis to quantify feature consistency (within-cluster distance) and lesion type separability. Results: PCCT demonstrated significantly lower image noise and higher CNR compared with EIDCT, particularly at lower dose levels. HU values were consistent across doses for both systems, with reduced variability in PCCT (coefficient of variation < 0.004). Radiomics analysis revealed tighter clustering (reduced within-cluster distances) and comparable lesion type separability between PCCT and EIDCT, indicating enhanced feature stability and lesion differentiation. Qualitative review confirmed superior lesion conspicuity and margin delineation with PCCT. Conclusions: CZT-based PCCT outperforms conventional EIDCT in quantitative and qualitative imaging metrics for LCS-LDCT, enabling superior image quality and radiomics reproducibility at reduced radiation doses. These findings support the clinical translation of PCCT for lung cancer screening and radiomics-based lesion characterization. Key points: PCCT offers reduced image noise and improved CNR performance, especially at ultra-low doses. HU stability and radiomics reproducibility are enhanced with PCCT. Clinical relevance statement: PCCT may enable further dose reduction without compromising diagnostic accuracy in LCS-LDCT.
- Open Access
Obese patient imaging: improved dose efficiency with photon-counting CT
Objective: To evaluate the dose efficiency of cadmium-zinc-telluride (CZT) based photon-counting CT (PCCT) compared to energy-integrating detector CT (EID-CT) across phantom sizes. Methods: A patient-specific 3D-printed pancreas phantom and a phantom with tissue mimicking inserts were placed in extension rings corresponding to the 50 th , 75 th , 85 th , and 95 th percentile adult waist circumferences. Phantoms were scanned on both PCCT and EID-CT with CTDI vol ranging from 0.5 to 19.4 mGy. Noise was measured in both phantoms to evaluate dose efficiency. Non-Poisson noise at low doses (th , 75 th , 85 th , and 95 th percentile phantoms, respectively. Noise reduction intensified at lower doses and larger phantom sizes, reaching 88 HU at 1 mGy for the 95 th percentile phantom. Non-Poisson noise decreased significantly with PCCT compared to EID-CT for all phantom sizes (p < 0.013). At matched noise levels, PCCT enabled dose reductions of 33% and 44% for the 50 th and 95 th percentile phantoms, respectively. Conclusions: PCCT exhibited superior dose efficiency compared to EID-CT across a range of phantom sizes. The enhanced dose efficiency enables both noise reduction and potential dose reduction for the imaging of obese patients and low-dose imaging applications. Key Points: Question: Photon-counting CT (PCCT) enables improved quantum detection and eliminates electronic noise, but its benefits have not been evaluated for obese patient sizes. Findings: Compared to EID-CT, PCCT enhanced dose efficiency with noise reduction and potential dose reduction across all phantom sizes and doses. Clinical Relevance: The improved dose efficiency of PCCT facilitates noise reduction that enables diagnostic image quality, and thereby the diagnostic accuracy, for obese patients.
Open AccessObese patient imaging: improved dose efficiency with photon-counting CT
Objective: To evaluate the dose efficiency of cadmium-zinc-telluride (CZT) based photon-counting CT (PCCT) compared to energy-integrating detector CT (EID-CT) across phantom sizes. Methods: A patient-specific 3D-printed pancreas phantom and a phantom with tissue mimicking inserts were placed in extension rings corresponding to the 50 th , 75 th , 85 th , and 95 th percentile adult waist circumferences. Phantoms were scanned on both PCCT and EID-CT with CTDI vol ranging from 0.5 to 19.4 mGy. Noise was measured in both phantoms to evaluate dose efficiency. Non-Poisson noise at low doses (th , 75 th , 85 th , and 95 th percentile phantoms, respectively. Noise reduction intensified at lower doses and larger phantom sizes, reaching 88 HU at 1 mGy for the 95 th percentile phantom. Non-Poisson noise decreased significantly with PCCT compared to EID-CT for all phantom sizes (p < 0.013). At matched noise levels, PCCT enabled dose reductions of 33% and 44% for the 50 th and 95 th percentile phantoms, respectively. Conclusions: PCCT exhibited superior dose efficiency compared to EID-CT across a range of phantom sizes. The enhanced dose efficiency enables both noise reduction and potential dose reduction for the imaging of obese patients and low-dose imaging applications. Key Points: Question: Photon-counting CT (PCCT) enables improved quantum detection and eliminates electronic noise, but its benefits have not been evaluated for obese patient sizes. Findings: Compared to EID-CT, PCCT enhanced dose efficiency with noise reduction and potential dose reduction across all phantom sizes and doses. Clinical Relevance: The improved dose efficiency of PCCT facilitates noise reduction that enables diagnostic image quality, and thereby the diagnostic accuracy, for obese patients.
- Open Access
- 26 November 2025
- Published by American Association for Cancer Research (AACR)
Table 2 from Phase I/II Study of AXL-Specific Antibody–Drug Conjugate Enapotamab Vedotin in Patients with Advanced Solid Tumors
Demographics and baseline characteristics of patients in the dose-expansion population by cohort.
- 26 November 2025
- Published by American Association for Cancer Research (AACR)
Open AccessTable 2 from Phase I/II Study of AXL-Specific Antibody–Drug Conjugate Enapotamab Vedotin in Patients with Advanced Solid Tumors
Demographics and baseline characteristics of patients in the dose-expansion population by cohort.
- Open Access
- 26 November 2025
- Published by American Association for Cancer Research (AACR)
Table S4 from Phase I/II Study of AXL-Specific Antibody–Drug Conjugate Enapotamab Vedotin in Patients with Advanced Solid Tumors
Safety summary: TEAEs in ≥5% of patients overall in dose-escalation phase (3Q4W schedule)
- 26 November 2025
- Published by American Association for Cancer Research (AACR)
Open AccessTable S4 from Phase I/II Study of AXL-Specific Antibody–Drug Conjugate Enapotamab Vedotin in Patients with Advanced Solid Tumors
Safety summary: TEAEs in ≥5% of patients overall in dose-escalation phase (3Q4W schedule)
- Open Access
- 26 November 2025
- Published by American Association for Cancer Research (AACR)
Table S5 from Phase I/II Study of AXL-Specific Antibody–Drug Conjugate Enapotamab Vedotin in Patients with Advanced Solid Tumors
Safety summary: TEAEs in ≥20% of patients in any cohort in dose-expansion phase
- 26 November 2025
- Published by American Association for Cancer Research (AACR)
Open AccessTable S5 from Phase I/II Study of AXL-Specific Antibody–Drug Conjugate Enapotamab Vedotin in Patients with Advanced Solid Tumors
Safety summary: TEAEs in ≥20% of patients in any cohort in dose-expansion phase
- Open Access
- 26 November 2025
- Published by American Association for Cancer Research (AACR)
Figure 1 from Phase I/II Study of AXL-Specific Antibody–Drug Conjugate Enapotamab Vedotin in Patients with Advanced Solid Tumors
Best change from baseline in sum of target lesions (investigator assessment) in the dose-expansion phase for the NSCLC cohorts (A, C, and E) and baseline tumor H-score levels for AXL positivity by investigator-assessed confirmed best overall response (B, D, and F). A and B, Cohort 1 (Q3W): NSCLC with sensitizing EGFR mutations and/or mutations targeted by third-generation TKIs (n = 22). C and D, Cohort 2 (2.2 mg/kg Q3W): NSCLC without activating EGFR mutations or ALK rearrangements (n = 55). E and F, Cohort 8 (3Q4W): NSCLC without activating EGFR mutations or ALK rearrangements (n = 26). NE, not evaluable; PD, progressive disease; PR, partial response.
- 26 November 2025
- Published by American Association for Cancer Research (AACR)
Open AccessFigure 1 from Phase I/II Study of AXL-Specific Antibody–Drug Conjugate Enapotamab Vedotin in Patients with Advanced Solid Tumors
Best change from baseline in sum of target lesions (investigator assessment) in the dose-expansion phase for the NSCLC cohorts (A, C, and E) and baseline tumor H-score levels for AXL positivity by investigator-assessed confirmed best overall response (B, D, and F). A and B, Cohort 1 (Q3W): NSCLC with sensitizing EGFR mutations and/or mutations targeted by third-generation TKIs (n = 22). C and D, Cohort 2 (2.2 mg/kg Q3W): NSCLC without activating EGFR mutations or ALK rearrangements (n = 55). E and F, Cohort 8 (3Q4W): NSCLC without activating EGFR mutations or ALK rearrangements (n = 26). NE, not evaluable; PD, progressive disease; PR, partial response.
- Open Access
- 26 November 2025
- Published by American Association for Cancer Research (AACR)
Table S3 from Phase I/II Study of AXL-Specific Antibody–Drug Conjugate Enapotamab Vedotin in Patients with Advanced Solid Tumors
Safety summary: TEAEs in ≥5% of patients overall and grade ≥3 TEAEs in dose-escalation phase (Q3W schedule)
- 26 November 2025
- Published by American Association for Cancer Research (AACR)
Open AccessTable S3 from Phase I/II Study of AXL-Specific Antibody–Drug Conjugate Enapotamab Vedotin in Patients with Advanced Solid Tumors
Safety summary: TEAEs in ≥5% of patients overall and grade ≥3 TEAEs in dose-escalation phase (Q3W schedule)