Sonia Colombo Serra
Research Subjects
Sonia Colombo Serra has a total of 85 co-authors. Here are the top co-authors by number of shared publications:
Fabio Tedoldi
GR&D, Bracco Imaging SpA Milan Italy
7 shared publications- Alberto Fringuello Mingo
Bracco Research Centre, Bracco Imaging SpA Colleretto Giacosa TO Italy
5 shared publications - Giovanni Valbusa
Bracco Imaging SpA, Centro Ricerche Bracco, Colleretto Giacosa, TO, Italy
4 shared publications - Fabio Tedoldi
Bracco Imaging Spa, Bracco Research Centre, Via Ribes 5, 10010 Colleretto Giacosa, Italy
3 shared publications Roberta Napolitano
Bracco Research Centre Bracco Imaging SpA Via Ribes 5 Colleretto Giacosa 10010 TO Italy
3 shared publications- Silvio Aime
IRCCS SDN SynLab Via E. Gianturco 113 80143 Napoli Italy
3 shared publications
Latest Publications
- Open Access
- 28 September 2026
- Published by Elsevier in Research in Diagnostic and Interventional Imaging
- Vol. 17, 100066
Machine learning quantification of hepatobiliary lesion-to-liver contrast enhancement ratio in benign hepatocellular tumors: a feasibility study
- 28 September 2026
- Published by Elsevier in Research in Diagnostic and Interventional Imaging
- Vol. 17, 100066
Open AccessMachine learning quantification of hepatobiliary lesion-to-liver contrast enhancement ratio in benign hepatocellular tumors: a feasibility study
- Open Access
- 17 August 2026
- Published by Wiley in Journal of Magnetic Resonance Imaging
Deep‐Learning Based Contrast Boosting: A Multi‐Center Multi‐Reader Study on Clinical Performance With Standard Contrast Enhanced Brain MRI
Background: Gadolinium‐based contrast agents are used in brain MRI to improve the visualization of disorders and improve the delineation of lesions. Higher doses of GBCAs can improve lesion sensitivity but may have safety implications, particularly in light of recent findings on gadolinium retention and deposition. Purpose: To evaluate the clinical performance of an FDA‐cleared deep‐learning (DL)‐based contrast boosting algorithm in routine clinical brain MRI exams. Study Type: Retrospective. Population: One hundred ten patients (47 ± 22 years; 52 Females, 47 Males, 11 N/A) with clinical contrast‐enhanced brain MR studies. Field Strength and Sequences: T1 weighted pre‐contrast and post‐contrast brain MRI sequences at 0.3 T, 1.5 T, and 3 T. Assessment: A multi‐center database of contrast‐enhanced brain MR images was used to evaluate a DL‐based contrast boosting algorithm. Pre‐contrast and standard post‐contrast (SC) images were processed with the algorithm to obtain contrast boosted (CB) images. CB images were compared to SC images in terms of contrast‐to‐noise ratio (CNR), lesion‐to‐brain ratio (LBR), and contrast enhancement percentage (CEP). Three board‐certified radiologists with 9, 15, and 18 years of experience reviewed CB and SC images side‐by‐side for qualitative evaluation and rated them on a 4‐point Likert scale for lesion contrast enhancement, border delineation, internal morphology, overall image quality, presence of artifacts, and changes in vessel conspicuity. The presence, cause, and severity of any false lesions was recorded. Statistical Tests: Wilcoxon signed rank test. A p value < 0.05 was considered significant. Results: CB images had significantly superior quantitative performance than SC images in terms of CNR (729.17% ± 1576.92%), LBR (87.91% ± 72.12%), and CEP (165.81% ± 42%). In the qualitative assessment, CB images showed significantly better lesion visualization (3.73 vs. 3.16) and had significantly better image quality (3.55 vs. 3.07). Data Conclusion: In this multi‐center, multi‐reader study, deep learning–based contrast boosting demonstrates robust improvements in lesion visualization and image quality without increasing contrast dosage. Evidence Level: 4. Technical Efficacy: Stage 3.
- 17 August 2026
- Published by Wiley in Journal of Magnetic Resonance Imaging
Open AccessDeep‐Learning Based Contrast Boosting: A Multi‐Center Multi‐Reader Study on Clinical Performance With Standard Contrast Enhanced Brain MRI
Background: Gadolinium‐based contrast agents are used in brain MRI to improve the visualization of disorders and improve the delineation of lesions. Higher doses of GBCAs can improve lesion sensitivity but may have safety implications, particularly in light of recent findings on gadolinium retention and deposition. Purpose: To evaluate the clinical performance of an FDA‐cleared deep‐learning (DL)‐based contrast boosting algorithm in routine clinical brain MRI exams. Study Type: Retrospective. Population: One hundred ten patients (47 ± 22 years; 52 Females, 47 Males, 11 N/A) with clinical contrast‐enhanced brain MR studies. Field Strength and Sequences: T1 weighted pre‐contrast and post‐contrast brain MRI sequences at 0.3 T, 1.5 T, and 3 T. Assessment: A multi‐center database of contrast‐enhanced brain MR images was used to evaluate a DL‐based contrast boosting algorithm. Pre‐contrast and standard post‐contrast (SC) images were processed with the algorithm to obtain contrast boosted (CB) images. CB images were compared to SC images in terms of contrast‐to‐noise ratio (CNR), lesion‐to‐brain ratio (LBR), and contrast enhancement percentage (CEP). Three board‐certified radiologists with 9, 15, and 18 years of experience reviewed CB and SC images side‐by‐side for qualitative evaluation and rated them on a 4‐point Likert scale for lesion contrast enhancement, border delineation, internal morphology, overall image quality, presence of artifacts, and changes in vessel conspicuity. The presence, cause, and severity of any false lesions was recorded. Statistical Tests: Wilcoxon signed rank test. A p value < 0.05 was considered significant. Results: CB images had significantly superior quantitative performance than SC images in terms of CNR (729.17% ± 1576.92%), LBR (87.91% ± 72.12%), and CEP (165.81% ± 42%). In the qualitative assessment, CB images showed significantly better lesion visualization (3.73 vs. 3.16) and had significantly better image quality (3.55 vs. 3.07). Data Conclusion: In this multi‐center, multi‐reader study, deep learning–based contrast boosting demonstrates robust improvements in lesion visualization and image quality without increasing contrast dosage. Evidence Level: 4. Technical Efficacy: Stage 3.
- 20 September 2025
- Published by Springer Nature
- p. 369-379
LIP-CAR: A Learned Inverse Problem Approach for Medical Imaging with Contrast Agent Reduction
- 20 September 2025
- Published by Springer Nature
- p. 369-379
LIP-CAR: A Learned Inverse Problem Approach for Medical Imaging with Contrast Agent Reduction
- 19 May 2025
- Published by Wiley in NMR in Biomedicine
- Vol. 38 (6) , e70062
Exploring the Limitations of Virtual Contrast Prediction in Brain Tumor Imaging: A Study of Generalization Across Tumor Types and Patient Populations
Accurate and timely diagnosis of brain tumors is critical for patient management and treatment planning. Magnetic resonance imaging (MRI) is a widely used modality for brain tumor detection and characterization, often aided by the administration of gadolinium‐based contrast agents (GBCAs) to improve tumor visualization. Recently, deep learning models have shown remarkable success in predicting contrast‐enhancement in medical images, thereby reducing the need of GBCAs and potentially minimizing patient discomfort and risks. In this paper, we present a study aimed at investigating the generalization capabilities of a neural network trained to predict full contrast in brain tumor images from noncontrast MRI scans. While initial results exhibited promising performance on a specific tumor type at a certain stage using a specific dataset, our attempts to extend this success to other tumor types and diverse patient populations yielded unexpected challenges and limitations. Through a rigorous analysis of the factor contributing to these negative results, we aim to shed light on the complexities associated with generalizing contrast enhancement prediction in medical brain tumor imaging, offering valuable insights for future research and clinical applications.
- 19 May 2025
- Published by Wiley in NMR in Biomedicine
- Vol. 38 (6) , e70062
Exploring the Limitations of Virtual Contrast Prediction in Brain Tumor Imaging: A Study of Generalization Across Tumor Types and Patient Populations
Accurate and timely diagnosis of brain tumors is critical for patient management and treatment planning. Magnetic resonance imaging (MRI) is a widely used modality for brain tumor detection and characterization, often aided by the administration of gadolinium‐based contrast agents (GBCAs) to improve tumor visualization. Recently, deep learning models have shown remarkable success in predicting contrast‐enhancement in medical images, thereby reducing the need of GBCAs and potentially minimizing patient discomfort and risks. In this paper, we present a study aimed at investigating the generalization capabilities of a neural network trained to predict full contrast in brain tumor images from noncontrast MRI scans. While initial results exhibited promising performance on a specific tumor type at a certain stage using a specific dataset, our attempts to extend this success to other tumor types and diverse patient populations yielded unexpected challenges and limitations. Through a rigorous analysis of the factor contributing to these negative results, we aim to shed light on the complexities associated with generalizing contrast enhancement prediction in medical brain tumor imaging, offering valuable insights for future research and clinical applications.
- Open Access
- 17 February 2025
- Published by Wiley in Advanced Science
- Vol. 12 (14) , e2415321
Chiral Switch of Gadopiclenol: New Standards in MRI Probes
Magnetic Resonance Imaging (MRI) plays a vital role in the accurate diagnosis of numerous human diseases and disorders, with Gd(III)‐based contrast agents (GBCAs) being used in ≈30%–40% of procedures, resulting in ≈30 million doses administered annually worldwide. The careful design of a rigid macrocyclic chelator featuring a highly hydrophilic periphery leads to the development of gadopiclenol, the first bis‐hydrated Gd(III)‐based MRI contrast agent, recently approved for clinical use by both the FDA and EMA. The stereochemistry of the coordinating arms is found to play a crucial role in the remarkable thermodynamic stability and inertness of the Gd(III)‐complex with the RRR/SSS ‐stereoisomer of this heptadentate chelating agent, ensuring its safety in vivo. The exceptional stability of the most effective gadopiclenol enantiomeric pair ( RRR/SSS ), coupled with a relaxivity 2 to 3 times higher than that of currently used GBCAs, has enabled the use of reduced doses while ensuring non‐inferior image contrast.
- 17 February 2025
- Published by Wiley in Advanced Science
- Vol. 12 (14) , e2415321
Open AccessChiral Switch of Gadopiclenol: New Standards in MRI Probes
Magnetic Resonance Imaging (MRI) plays a vital role in the accurate diagnosis of numerous human diseases and disorders, with Gd(III)‐based contrast agents (GBCAs) being used in ≈30%–40% of procedures, resulting in ≈30 million doses administered annually worldwide. The careful design of a rigid macrocyclic chelator featuring a highly hydrophilic periphery leads to the development of gadopiclenol, the first bis‐hydrated Gd(III)‐based MRI contrast agent, recently approved for clinical use by both the FDA and EMA. The stereochemistry of the coordinating arms is found to play a crucial role in the remarkable thermodynamic stability and inertness of the Gd(III)‐complex with the RRR/SSS ‐stereoisomer of this heptadentate chelating agent, ensuring its safety in vivo. The exceptional stability of the most effective gadopiclenol enantiomeric pair ( RRR/SSS ), coupled with a relaxivity 2 to 3 times higher than that of currently used GBCAs, has enabled the use of reduced doses while ensuring non‐inferior image contrast.
- Open Access
LIP-CAR: contrast agent reduction by a deep learned inverse problem
The adoption of contrast agents in medical imaging protocols is crucial for accurate and timely diagnosis. While highly effective and characterized by an excellent safety profile, the use of contrast agents has its limitation, including rare risk of allergic reactions, potential environmental impact and economic burdens on patients and healthcare systems. In this work, we address the contrast agent reduction (CAR) problem, which involves reducing the administered dosage of contrast agent while preserving the visual enhancement. The current literature on the CAR task is based on deep learning techniques within a fully image processing framework. These techniques digitally simulate high-dose images from images acquired with a low dose of contrast agent. We investigate the feasibility of a ``learned inverse problem'' (LIP) approach, as opposed to the end-to-end paradigm in the state-of-the-art literature. Specifically, we learn the image-to-image operator that maps high-dose images to their corresponding low-dose counterparts, and we frame the CAR task as an inverse problem. We then solve this problem through a regularized optimization reformulation. Regularization methods are well-established mathematical techniques that offer robustness and explainability. Our approach combines these rigorous techniques with cutting-edge deep learning tools. Numerical experiments performed on pre-clinical medical images confirm the effectiveness of this strategy, showing improved stability and accuracy in the simulated high-dose images.
Open AccessLIP-CAR: contrast agent reduction by a deep learned inverse problem
The adoption of contrast agents in medical imaging protocols is crucial for accurate and timely diagnosis. While highly effective and characterized by an excellent safety profile, the use of contrast agents has its limitation, including rare risk of allergic reactions, potential environmental impact and economic burdens on patients and healthcare systems. In this work, we address the contrast agent reduction (CAR) problem, which involves reducing the administered dosage of contrast agent while preserving the visual enhancement. The current literature on the CAR task is based on deep learning techniques within a fully image processing framework. These techniques digitally simulate high-dose images from images acquired with a low dose of contrast agent. We investigate the feasibility of a ``learned inverse problem'' (LIP) approach, as opposed to the end-to-end paradigm in the state-of-the-art literature. Specifically, we learn the image-to-image operator that maps high-dose images to their corresponding low-dose counterparts, and we frame the CAR task as an inverse problem. We then solve this problem through a regularized optimization reformulation. Regularization methods are well-established mathematical techniques that offer robustness and explainability. Our approach combines these rigorous techniques with cutting-edge deep learning tools. Numerical experiments performed on pre-clinical medical images confirm the effectiveness of this strategy, showing improved stability and accuracy in the simulated high-dose images.
- 20 May 2024
- Published by Elsevier in Radiography
- Vol. 30 (4) , 1080-1084
Stability testing of iomeprol and iopamidol formulations subjected to X-ray radiation
- 20 May 2024
- Published by Elsevier in Radiography
- Vol. 30 (4) , 1080-1084
Stability testing of iomeprol and iopamidol formulations subjected to X-ray radiation
- Open Access
- 28 July 2023
- Published by Wolters Kluwer Health in Investigative Radiology
- Vol. 58 (12) , 853-864
Amplifying the Effects of Contrast Agents on Magnetic Resonance Images Using a Deep Learning Method Trained on Synthetic Data
Objectives: Artificial intelligence (AI) methods can be applied to enhance contrast in diagnostic images beyond that attainable with the standard doses of contrast agents (CAs) normally used in the clinic, thus potentially increasing diagnostic power and sensitivity. Deep learning–based AI relies on training data sets, which should be sufficiently large and diverse to effectively adjust network parameters, avoid biases, and enable generalization of the outcome. However, large sets of diagnostic images acquired at doses of CA outside the standard-of-care are not commonly available. Here, we propose a method to generate synthetic data sets to train an “AI agent” designed to amplify the effects of CAs in magnetic resonance (MR) images. The method was fine-tuned and validated in a preclinical study in a murine model of brain glioma, and extended to a large, retrospective clinical human data set. Materials and Methods: A physical model was applied to simulate different levels of MR contrast from a gadolinium-based CA. The simulated data were used to train a neural network that predicts image contrast at higher doses. A preclinical MR study at multiple CA doses in a rat model of glioma was performed to tune model parameters and to assess fidelity of the virtual contrast images against ground-truth MR and histological data. Two different scanners (3 T and 7 T, respectively) were used to assess the effects of field strength. The approach was then applied to a retrospective clinical study comprising 1990 examinations in patients affected by a variety of brain diseases, including glioma, multiple sclerosis, and metastatic cancer. Images were evaluated in terms of contrast-to-noise ratio and lesion-to-brain ratio, and qualitative scores. Results: In the preclinical study, virtual double-dose images showed high degrees of similarity to experimental double-dose images for both peak signal-to-noise ratio and structural similarity index (29.49 dB and 0.914 dB at 7 T, respectively, and 31.32 dB and 0.942 dB at 3 T) and significant improvement over standard contrast dose (ie, 0.1 mmol Gd/kg) images at both field strengths. In the clinical study, contrast-to-noise ratio and lesion-to-brain ratio increased by an average 155% and 34% in virtual contrast images compared with standard-dose images. Blind scoring of AI-enhanced images by 2 neuroradiologists showed significantly better sensitivity to small brain lesions compared with standard-dose images (4.46/5 vs 3.51/5). Conclusions: Synthetic data generated by a physical model of contrast enhancement provided effective training for a deep learning model for contrast amplification. Contrast above that attainable at standard doses of gadolinium-based CA can be generated through this approach, with significant advantages in the detection of small low-enhancing brain lesions.
- 28 July 2023
- Published by Wolters Kluwer Health in Investigative Radiology
- Vol. 58 (12) , 853-864
Open AccessAmplifying the Effects of Contrast Agents on Magnetic Resonance Images Using a Deep Learning Method Trained on Synthetic Data
Objectives: Artificial intelligence (AI) methods can be applied to enhance contrast in diagnostic images beyond that attainable with the standard doses of contrast agents (CAs) normally used in the clinic, thus potentially increasing diagnostic power and sensitivity. Deep learning–based AI relies on training data sets, which should be sufficiently large and diverse to effectively adjust network parameters, avoid biases, and enable generalization of the outcome. However, large sets of diagnostic images acquired at doses of CA outside the standard-of-care are not commonly available. Here, we propose a method to generate synthetic data sets to train an “AI agent” designed to amplify the effects of CAs in magnetic resonance (MR) images. The method was fine-tuned and validated in a preclinical study in a murine model of brain glioma, and extended to a large, retrospective clinical human data set. Materials and Methods: A physical model was applied to simulate different levels of MR contrast from a gadolinium-based CA. The simulated data were used to train a neural network that predicts image contrast at higher doses. A preclinical MR study at multiple CA doses in a rat model of glioma was performed to tune model parameters and to assess fidelity of the virtual contrast images against ground-truth MR and histological data. Two different scanners (3 T and 7 T, respectively) were used to assess the effects of field strength. The approach was then applied to a retrospective clinical study comprising 1990 examinations in patients affected by a variety of brain diseases, including glioma, multiple sclerosis, and metastatic cancer. Images were evaluated in terms of contrast-to-noise ratio and lesion-to-brain ratio, and qualitative scores. Results: In the preclinical study, virtual double-dose images showed high degrees of similarity to experimental double-dose images for both peak signal-to-noise ratio and structural similarity index (29.49 dB and 0.914 dB at 7 T, respectively, and 31.32 dB and 0.942 dB at 3 T) and significant improvement over standard contrast dose (ie, 0.1 mmol Gd/kg) images at both field strengths. In the clinical study, contrast-to-noise ratio and lesion-to-brain ratio increased by an average 155% and 34% in virtual contrast images compared with standard-dose images. Blind scoring of AI-enhanced images by 2 neuroradiologists showed significantly better sensitivity to small brain lesions compared with standard-dose images (4.46/5 vs 3.51/5). Conclusions: Synthetic data generated by a physical model of contrast enhancement provided effective training for a deep learning model for contrast amplification. Contrast above that attainable at standard doses of gadolinium-based CA can be generated through this approach, with significant advantages in the detection of small low-enhancing brain lesions.
- 1 December 2022
- Published by Oxford University Press (OUP) in British Journal of Radiology
- Vol. 95 (1140) , 20220619
Stability testing of gadoteridol and gadobenate dimeglumine formulations under exposure to high-intensity focused ultrasound
Objective: Contrast-enhanced MRI could be useful to guide high-intensity focused ultrasound treatment (HIFU), but the effects of HIFU on gadolinium-based agents is not known. Here, we tested in vitro the stability of gadoteridol and gadobenate dimeglumine, two widely used MR contrast agents, after exposure to HIFU at power levels typically applied in the clinical practice. Methods: 0.5 M (gadoteridol and gadobenate dimeglumine) and diluted formulations (1:10 gadoteridol in saline) were exposed to different HIFU sequences. Unexposed and exposed solutions were characterized by high-performance liquid chromatography in terms of concentration of gadolinium complex, free gadolinium and free ligand. Results: Gadoteridol formulation after treatment showed concentrations of the complex not significantly different from control. Free Gd and/or free ligand concentrations in the order of 0.002/0.004% w/w, were observed occasionally without significant correlation with intensity and duration of exposure to HIFU. Gadobenate dimeglumine formulation after treatment showed complex assay content values, by-products (0.24–0.26%) and free BOPTA levels (0.07%) comparable to control sample within the experimental error. Conclusion: In the range of conditions explored, HIFU exposure did not induce significant dissociations of gadoteridol and gadobenate dimeglumine, nor a detectable increase in the concentration of free species. Advances in knowledge: Our study strengthens the hypothesis that gadolinium-based contrast agents are stable during HIFU treatment for body applications (e.g. thermal ablation of uterine fibroids).
- 1 December 2022
- Published by Oxford University Press (OUP) in British Journal of Radiology
- Vol. 95 (1140) , 20220619
Stability testing of gadoteridol and gadobenate dimeglumine formulations under exposure to high-intensity focused ultrasound
Objective: Contrast-enhanced MRI could be useful to guide high-intensity focused ultrasound treatment (HIFU), but the effects of HIFU on gadolinium-based agents is not known. Here, we tested in vitro the stability of gadoteridol and gadobenate dimeglumine, two widely used MR contrast agents, after exposure to HIFU at power levels typically applied in the clinical practice. Methods: 0.5 M (gadoteridol and gadobenate dimeglumine) and diluted formulations (1:10 gadoteridol in saline) were exposed to different HIFU sequences. Unexposed and exposed solutions were characterized by high-performance liquid chromatography in terms of concentration of gadolinium complex, free gadolinium and free ligand. Results: Gadoteridol formulation after treatment showed concentrations of the complex not significantly different from control. Free Gd and/or free ligand concentrations in the order of 0.002/0.004% w/w, were observed occasionally without significant correlation with intensity and duration of exposure to HIFU. Gadobenate dimeglumine formulation after treatment showed complex assay content values, by-products (0.24–0.26%) and free BOPTA levels (0.07%) comparable to control sample within the experimental error. Conclusion: In the range of conditions explored, HIFU exposure did not induce significant dissociations of gadoteridol and gadobenate dimeglumine, nor a detectable increase in the concentration of free species. Advances in knowledge: Our study strengthens the hypothesis that gadolinium-based contrast agents are stable during HIFU treatment for body applications (e.g. thermal ablation of uterine fibroids).
- 22 August 2018
- Published by Royal Society of Chemistry (RSC) in Chemical Communications
- Vol. 54 (72) , 10056-10059
Exploring the intramolecular catalysis of the proton exchange process to modulate the relaxivity of Gd(iii)-complexes of HP-DO3A-like ligands
The GdIII complex of Ph-HP-DO3A shows the highest contribution to the relaxivity by the intramolecular proton exchange of the –OH group.
- 22 August 2018
- Published by Royal Society of Chemistry (RSC) in Chemical Communications
- Vol. 54 (72) , 10056-10059
Exploring the intramolecular catalysis of the proton exchange process to modulate the relaxivity of Gd(iii)-complexes of HP-DO3A-like ligands
The GdIII complex of Ph-HP-DO3A shows the highest contribution to the relaxivity by the intramolecular proton exchange of the –OH group.