Contrast Media Reduction in Computed Tomography With Deep Learning Using a Generative Adversarial Network in an Experimental Animal Study

Haubold, Johannes; Jošt, Gregor; Theysohn, Jens; Ludwig, Johannes; Li, Yan; Kleesiek, Jens; Schaarschmidt, Benedikt Michael; Forsting, Michael; Nensa, Felix; Pietsch, Hubertus; Hosch, René

doi:10.1097/rli.0000000000000875

Cited by 9 publications

(14 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The percentage is rather high, and it could be significantly reduced using more sophisticated coregistration techniques that are already part of the state of the art but are not object of the present study. A potential solution to work around the misalignment of images applied for training has been proposed by Haubold et al, 53 where the CycleGAN architecture is applied to abdominal computed tomography in a large animal model. Since CycleGAN loss does not contain any pixelwise computation, the training is not affected by coregistration imperfections.…”

Section: Discussionmentioning

confidence: 99%

Amplifying the Effects of Contrast Agents on Magnetic Resonance Images Using a Deep Learning Method Trained on Synthetic Data

Fringuello Mingo,

Colombo Serra,

Macula

et al. 2023

Invest Radiol

View full text Add to dashboard Cite

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.

show abstract

Section: Discussionmentioning

confidence: 99%

Amplifying the Effects of Contrast Agents on Magnetic Resonance Images Using a Deep Learning Method Trained on Synthetic Data

Fringuello Mingo,

Colombo Serra,

Macula

et al. 2023

Invest Radiol

View full text Add to dashboard Cite

show abstract

“…For each examination, it was possible to zoom and window without restrictions. Subsequently, the radiologists had to select the side on which the true normal-dose sequence is shown, and they had to evaluate whether the 2 representations have consistent findings according to the preliminary work of Haubold et al 13,14 This was an additional quality assurance step to ensure that the network does not change the image in an unexpected way. This includes changes in anatomy as well as image artifacts that can simulate a pathology.…”

Section: Qualitative Image Evaluationmentioning

confidence: 99%

“…Recently, however, a systematic intraindividual analysis in pigs has shown that a reduction of the GBCA dose of the venous phase by 40% and of up to 60% of the arterial phase in time-resolved magnetic resonance angiography (MRA) is possible while preserving the delineation of small vessels 12 . Furthermore, in recent years, due to technical progress in the field of machine learning, new methods for reducing the amount of contrast media in CT 13,14 or generating a synthetic MRA 15 have been demonstrated. In addition, various algorithms have been developed to generate a late contrast phase in MRI of the brain from noncontrast data 16 or from low-dose data using split-dose protocols 17,18 .…”

mentioning

confidence: 99%

Contrast Agent Dose Reduction in MRI Utilizing a Generative Adversarial Network in an Exploratory Animal Study

et al. 2023

Self Cite

View full text Add to dashboard Cite

Objectives: The aim of this study is to use virtual contrast enhancement to reduce the amount of hepatobiliary gadolinium-based contrast agent in magnetic resonance imaging with generative adversarial networks (GANs) in a large animal model. Methods: With 20 healthy Göttingen minipigs, a total of 120 magnetic resonance imaging examinations were performed on 6 different occasions, 50% with reduced (low-dose; 0.005 mmol/kg, gadoxetate) and 50% standard dose (normaldose; 0.025 mmol/kg). These included arterial, portal venous, venous, and hepatobiliary contrast phases (20 minutes, 30 minutes). Because of incomplete examinations, one animal had to be excluded. Randomly, 3 of 19 animals were selected and withheld for validation (18 examinations). Subsequently, a GAN was trained for imageto-image conversion from low-dose to normal-dose (virtual normal-dose) with the remaining 16 animals (96 examinations). For validation, vascular and parenchymal contrast-to-noise ratio (CNR) was calculated using region of interest measurements of the abdominal aorta, inferior vena cava, portal vein, hepatic parenchyma, and autochthonous back muscles. In parallel, a visual Turing test was performed by presenting the normal-dose and virtual normal-dose data to 3 consultant radiologists, blinded for the type of examination. They had to decide whether they would consider both data sets as consistent in findings and which images were from the normal-dose study. Results: The pooled dynamic phase vascular and parenchymal CNR increased significantly from low-dose to virtual normal-dose (pooled vascular: P < 0.0001, pooled parenchymal: P = 0.0002) and was found to be not significantly different between virtual normal-dose and normal-dose examinations (vascular CNR [mean ± SD]: low-dose 17.6 ± 6.0, virtual normal-dose 41.8 ± 9.7, and normal-dose 48.4 ± 12.2; parenchymal CNR [mean ± SD]: low-dose 20.2 ± 5.9, virtual normaldose 28.3 ± 6.9, and normal-dose 29.5 ± 7.2). The pooled parenchymal CNR of the hepatobiliary contrast phases revealed a significant increase from the low-dose (22.8 ± 6.2) to the virtual normal-dose (33.2 ± 6.1; P < 0.0001) and normal-dose sequence (37.0 ± 9.1; P < 0.0001). In addition, there was no significant difference between the virtual normal-dose and normal-dose sequence. In the visual Turing test, on the median, the consultant radiologist reported that the sequences of the normal-dose and virtual normal-dose are consistent in findings in 100% of the examinations. Moreover, the consultants were able to identify the normal-dose series as such in a median 54.5% of the cases. Conclusions:In this feasibility study in healthy Göttingen minipigs, it could be shown that GAN-based virtual contrast enhancement can be used to recreate the image impression of normal-dose imaging in terms of CNR and subjective image similarity in both dynamic and hepatobiliary contrast phases from low-dose data with an 80% reduction in gadolinium-based contrast agent dose. Before clinical implementation, further studies with pathologies are needed to...

show abstract

“…Since then, others have demonstrated the ability of GANs to synthesize realistic virtual contrast enhanced images, 24,25 potentially reducing the contrast media dose required for effective contrast enhanced imaging. 26,27 Beyond the previously described challenges associated with contrast enhanced imaging, there may be situations during imaging that result in poor contrast media uptake, either from compromised kidney function, degree of compliance with established scanning protocols, or other situation specific complications (e.g. corticomedullary and/or nephrogenic phase scanning occurs too early or too late and times of peak image contrast are missed) which could reduce CNN-based kidney segmentation performance if the CNN is trained only on high quality contrast enhanced images.…”

Section: Introductionmentioning

confidence: 99%

Using a GAN for CT contrast enhancement to improve CNN kidney segmentation accuracy

Welland¹,

Melendez-Corres

Teng

et al. 2023

Medical Imaging 2023: Image Processing

View full text Add to dashboard Cite

Kidneys are most easily segmented by convolutional neural networks (CNN) on contrast enhanced CT (CECT) images, but their segmentation accuracy may be reduced when only non-contrast CT (NCCT) images are available. The purpose of this work was to investigate the improvement in segmentation accuracy when implementing a generative adversarial network (GAN) to create virtual contrast enhanced (vCECT) images from non-contrast inputs. A 2D cycleGAN model, incorporating an additional idempotent loss function to restrict the GAN from making unnecessary modifications to data already in the translated domain, was trained to generate virtual contrast enhanced images on 286 paired non-contrast and contrast enhanced inputs. A 3D CNN trained on contrast enhanced images was applied to segment the kidneys in a test set of 20 paired non-contrast and contrast enhanced images. The non-contrast images were converted to virtual contrast enhanced images, then kidneys in both image conditions were segmented by the CNN. Segmentation results were compared to analyst annotations on non-contrast images visually and by Dice Coefficient (DC). Segmentation on virtual contrast enhanced images were more complete with fewer extraneous detections compared to non-contrast images in 16/20 cases. Mean(±SD) DC was 0.88(±0.80), 0.90(±0.03), and 0.95(±0.05) for non-contrast, virtual contrast enhanced, and real contrast enhanced, respectively. Virtual contrast enhancement visually improved segmentation quality, poor performing cases had their performance improved resulting in an overall reduction in DC variation, and the minimum DC increased from 0.65 to 0.85. This work provides preliminary results demonstrating the potential effectiveness of using a GAN for virtual contrast enhancement to improve CNN-based kidney segmentation on non-contrast images.

show abstract

Contrast Media Reduction in Computed Tomography With Deep Learning Using a Generative Adversarial Network in an Experimental Animal Study

Cited by 9 publications

References 26 publications

Amplifying the Effects of Contrast Agents on Magnetic Resonance Images Using a Deep Learning Method Trained on Synthetic Data

Amplifying the Effects of Contrast Agents on Magnetic Resonance Images Using a Deep Learning Method Trained on Synthetic Data

Contrast Agent Dose Reduction in MRI Utilizing a Generative Adversarial Network in an Exploratory Animal Study

Using a GAN for CT contrast enhancement to improve CNN kidney segmentation accuracy

Contact Info

Product

Resources

About