Improved Positron Emission Tomography Quantification: Evaluation of a Maximum-Likelihood Scatter Scaling Algorithm.

Incorrect scatter scaling of positron emission tomography (PET) images can lead to halo artifacts, quantitative bias, or reconstruction failure. Tail-fitted scatter scaling (TFSS) possesses performance limitations in multiple cases. This study aims to investigate a novel method for scatter scaling: maximum-likelihood scatter scaling (MLSS) in scenarios where TFSS tends to induce artifacts or are observed to cause reconstruction abortion. [68Ga]Ga-RGD PET scans of nine patients were included in cohort 1 in the scope of investigating the reduction of halo artifacts relative to the scatter estimation method. PET scans of 30 patients administrated with [68Ga]Ga-uPAR were included in cohort 2, used for an evaluation of the robustness of MLSS in cases where TFSS-integrated reconstructions are observed to fail. A visual inspection of MLSS-corrected images scored higher than TFSS-corrected reconstructions of cohort 1. The quantitative investigation near the bladder showed a relative difference in tracer uptake of up to 94.7%. A reconstruction of scans included in cohort 2 resulted in failure in 23 cases when TFSS was used. The lesion uptake values of cohort 2 showed no significant difference. MLSS is suggested as an alternative scatter-scaling method relative to TFSS with the aim of reducing halo artifacts and a robust reconstruction process.

Potential Clinical Impact of LAFOV PET/CT: A Systematic Evaluation of Image Quality and Lesion Detection.

We performed a systematic evaluation of the diagnostic performance of LAFOV PET/CT with increasing acquisition time. The first 100 oncologic adult patients referred for 3 MBq/kg 2-[18F]fluoro-2-deoxy-D-glucose PET/CT on the Siemens Biograph Vision Quadra were included. A standard imaging protocol of 10 min was used and scans were reconstructed at 30 s, 60 s, 90 s, 180 s, 300 s, and 600 s. Paired comparisons of quantitative image noise, qualitative image quality, lesion detection, and lesion classification were performed. Image noise (n = 50, 34 women) was acceptable according to the current standard of care (coefficient-of-varianceref < 0.15) after 90 s and improved significantly with increasing acquisition time (PB < 0.001). The same was seen in observer rankings (PB < 0.001). Lesion detection (n = 100, 74 women) improved significantly from 30 s to 90 s (PB < 0.001), 90 s to 180 s (PB = 0.001), and 90 s to 300 s (PB = 0.002), while lesion classification improved from 90 s to 180 s (PB < 0.001), 180 s to 300 s (PB = 0.021), and 90 s to 300 s (PB < 0.001). We observed improved image quality, lesion detection, and lesion classification with increasing acquisition time while maintaining a total scan time of less than 5 min, which demonstrates a potential clinical benefit. Based on these results we recommend a standard imaging acquisition protocol for LAFOV PET/CT of minimum 180 s to maximum 300 s after injection of 3 MBq/kg 2-[18F]fluoro-2-deoxy-D-glucose.

Estimation of brain amyloid accumulation using deep learning in clinical [11C]PiB PET imaging.

INTRODUCTION: Estimation of brain amyloid accumulation is valuable for evaluation of patients with cognitive impairment in both research and clinical routine. The development of high throughput and accurate strategies for the determination of amyloid status could be an important tool in patient selection for clinical trials and amyloid directed treatment. Here, we propose the use of deep learning to quantify amyloid accumulation using standardized uptake value ratio (SUVR) and classify amyloid status based on their PET images. METHODS: A total of 1309 patients with cognitive impairment scanned with [11C]PIB PET/CT or PET/MRI were included. Two convolutional neural networks (CNNs) for reading-based amyloid status and SUVR prediction were trained using 75% of the PET/CT data. The remaining PET/CT (n = 300) and all PET/MRI (n = 100) data was used for evaluation. RESULTS: The prevalence of amyloid positive patients was 61%. The amyloid status classification model reproduced the expert reader's classification with 99% accuracy. There was a high correlation between reference and predicted SUVR (R2 = 0.96). Both reference and predicted SUVR had an accuracy of 97% compared to expert classification when applying a predetermined SUVR threshold of 1.35 for binary classification of amyloid status. CONCLUSION: The proposed CNN models reproduced both the expert classification and quantitative measure of amyloid accumulation in a large local dataset. This method has the potential to replace or simplify existing clinical routines and can facilitate fast and accurate classification well-suited for a high throughput pipeline.

Scanner agnostic large-scale evaluation of MS lesion delineation tool for clinical MRI.

Introduction: Patients with MS are MRI scanned continuously throughout their disease course resulting in a large manual workload for radiologists which includes lesion detection and size estimation. Though many models for automatic lesion segmentation have been published, few are used broadly in clinic today, as there is a lack of testing on clinical datasets. By collecting a large, heterogeneous training dataset directly from our MS clinic we aim to present a model which is robust to different scanner protocols and artefacts and which only uses MRI modalities present in routine clinical examinations. Methods: We retrospectively included 746 patients from routine examinations at our MS clinic. The inclusion criteria included acquisition at one of seven different scanners and an MRI protocol including 2D or 3D T2-w FLAIR, T2-w and T1-w images. Reference lesion masks on the training (n = 571) and validation (n = 70) datasets were generated using a preliminary segmentation model and subsequent manual correction. The test dataset (n = 100) was manually delineated. Our segmentation model https://github.com/CAAI/AIMS/ was based on the popular nnU-Net, which has won several biomedical segmentation challenges. We tested our model against the published segmentation models HD-MS-Lesions, which is also based on nnU-Net, trained with a more homogenous patient cohort. We furthermore tested model robustness to data from unseen scanners by performing a leave-one-scanner-out experiment. Results: We found that our model was able to segment MS white matter lesions with a performance comparable to literature: DSC = 0.68, precision = 0.90, recall = 0.70, f1 = 0.78. Furthermore, the model outperformed HD-MS-Lesions in all metrics except precision = 0.96. In the leave-one-scanner-out experiment there was no significant change in performance (p < 0.05) between any of the models which were only trained on part of the dataset and the full segmentation model. Conclusion: In conclusion we have seen, that by including a large, heterogeneous dataset emulating clinical reality, we have trained a segmentation model which maintains a high segmentation performance while being robust to data from unseen scanners. This broadens the applicability of the model in clinic and paves the way for clinical implementation.

DeepDixon synthetic CT for [18F]FET PET/MRI attenuation correction of post-surgery glioma patients with metal implants.

Purpose: Conventional magnetic resonance imaging (MRI) can for glioma assessment be supplemented by positron emission tomography (PET) imaging with radiolabeled amino acids such as O-(2-[18F]fluoroethyl)-L-tyrosine ([18F]FET), which provides additional information on metabolic properties. In neuro-oncology, patients often undergo brain and skull altering treatment, which is known to challenge MRI-based attenuation correction (MR-AC) methods and thereby impact the simplified semi-quantitative measures such as tumor-to-brain ratio (TBR) used in clinical routine. The aim of the present study was to examine the applicability of our deep learning method, DeepDixon, for MR-AC in [18F]FET PET/MRI scans of a post-surgery glioma cohort with metal implants. Methods: The MR-AC maps were assessed for all 194 included post-surgery glioma patients (318 studies). The subgroup of 147 patients (222 studies, 200 MBq [18F]FET PET/MRI) with tracer uptake above 1 ml were subsequently reconstructed with DeepDixon, vendor-default atlas-based method, and a low-dose computed tomography (CT) used as reference. The biological tumor volume (BTV) was delineated on each patient by isocontouring tracer uptake above a TBR threshold of 1.6. We evaluated the MR-AC methods using the recommended clinical metrics BTV and mean and maximum TBR on a patient-by-patient basis against the reference with CT-AC. Results: Ninety-seven percent of the studies (310/318) did not have any major artifacts using DeepDixon, which resulted in a Dice coefficient of 0.89/0.83 for tissue/bone, respectively, compared to 0.84/0.57 when using atlas. The average difference between DeepDixon and CT-AC was within 0.2% across all clinical metrics, and no statistically significant difference was found. When using DeepDixon, only 3 out of 222 studies (1%) exceeded our acceptance criteria compared to 72 of the 222 studies (32%) with the atlas method. Conclusion: We evaluated the performance of a state-of-the-art MR-AC method on the largest post-surgical glioma patient cohort to date. We found that DeepDixon could overcome most of the issues arising from irregular anatomy and metal artifacts present in the cohort resulting in clinical metrics within acceptable limits of the reference CT-AC in almost all cases. This is a significant improvement over the vendor-provided atlas method and of particular importance in response assessment.

Imaging modalities for pulmonary tuberculosis in children: A systematic review.

Purpose: The optimal choice of protocol for diagnostic imaging in children with tuberculosis (TB) is a contemporary challenge due to the war in Ukraine, which potentially can create a steep rise in TB cases in Western Europe. We aimed to gather all primary research comparing imaging modalities and their diagnostic accuracies for pulmonary findings in children with suspected or confirmed pulmonary tuberculosis (PTB). Method: We searched the databases PubMed and Embase using pre-specified search terms, for English- and non-English published and un-published reports from the period 1972 to 2022. We retrieved reports via citation search in excluded literature reviews and systematic reviews. Studies were eligible if most of the study population was between 0 and 18 years of age with confirmed or suspected PTB, and study participants had described diagnostic images from two or more different imaging modalities. Results: A total of 15 studies investigated conventional chest X-Ray (CXR) and computed tomography (CT) in diagnosing PTB in children. Nine studies investigated the number of participants in where CT or CXR confirmed the diagnosis of TB, and all of them, including a total of 1244 patients, reported that findings compatible with TB were more frequently detected on CT than CXR. Only two studies did not include radiological findings as part of their diagnostic criteria for PTB, and combined they showed that CT diagnosed 54/54 (100 %) children with confirmed PTB, while CXR diagnosed 42/54 (78 %). Two studies compared magnetic resonance imaging (MRI) with CXR and showed that MRI diagnosed more children with PTB than CXR. One study reported a higher positive predictive value (PPV), sensitivity and specificity for PTB findings for MRI than CXR. One study compared CXR with high-kilovolt (high-kV) CXR, finding compatible sensitivity and specificity regarding confirmation of PTB. Two studies compared ultrasound (US) with CXR and found that US had a higher diagnostic yield and more often correctly identified consolidations, mediastinal LAP, and pleural effusion. Conclusion: CT showed a higher diagnostic accuracy for PTB findings than CXR, MRI and US, and should be the imaging modality of first choice when available. MRI had a higher sensitivity and specificity than CXR for LAP, pleural effusion, and cavitation. US was complimentary in initial diagnostic work-up and follow up. A diagnostic strategy for PTB in children according to local availability and expertise is proposed, as no evidence from this systematic review shows otherwise, in acknowledgement of the expertise in high TB-burdened countries. CT can be performed when in doubt, due to the higher diagnostic yield.

A zero-dose synthetic baseline for the personalized analysis of [18F]FDG-PET: Application in Alzheimer's disease.

Purpose: Brain 2-Deoxy-2-[18F]fluoroglucose ([18F]FDG-PET) is widely used in the diagnostic workup of Alzheimer's disease (AD). Current tools for uptake analysis rely on non-personalized templates, which poses a challenge as decreased glucose uptake could reflect neuronal dysfunction, or heterogeneous brain morphology associated with normal aging. Overcoming this, we propose a deep learning method for synthesizing a personalized [18F]FDG-PET baseline from the patient's own MRI, and showcase its applicability in detecting AD pathology. Methods: We included [18F]FDG-PET/MRI data from 123 patients of a local cohort and 600 patients from ADNI. A supervised, adversarial model with two connected Generative Adversarial Networks (GANs) was trained on cognitive normal (CN) patients with transfer-learning to generate full synthetic baseline volumes (sbPET) (192 × 192 × 192) which reflect healthy uptake conditioned on brain anatomy. Synthetic accuracy was measured by absolute relative %-difference (Abs%), relative %-difference (RD%), and peak signal-to-noise ratio (PSNR). Lastly, we deployed the sbPET images in a fully personalized method for localizing metabolic abnormalities. Results: The model achieved a spatially uniform Abs% of 9.4%, RD% of 0.5%, and a PSNR of 26.3 for CN subjects. The sbPET images conformed to the anatomical information dictated by the MRI and proved robust in presence of atrophy. The personalized abnormality method correctly mapped the pathology of AD subjects while showing little to no anomalies for CN subjects. Conclusion: This work demonstrated the feasibility of synthesizing fully personalized, healthy-appearing [18F]FDG-PET images. Using these, we showcased a promising application in diagnosing AD, and theorized the potential value of sbPET images in other neuroimaging routines.

Deep learning based low-activity PET reconstruction of [11C]PiB and [18F]FE-PE2I in neurodegenerative disorders.

PURPOSE: Positron Emission Tomography (PET) can support a diagnosis of neurodegenerative disorder by identifying disease-specific pathologies. Our aim was to investigate the feasibility of using activity reduction in clinical [18F]FE-PE2I and [11C]PiB PET/CT scans, simulating low injected activity or scanning time reduction, in combination with AI-assisted denoising. METHODS: A total of 162 patients with clinically uncertain Alzheimer's disease underwent amyloid [11C]PiB PET/CT and 509 patients referred for clinically uncertain Parkinson's disease underwent dopamine transporter (DAT) [18F]FE-PE2I PET/CT. Simulated low-activity data were obtained by random sampling of 5% of the events from the list-mode file and a 5% time window extraction in the middle of the scan. A three-dimensional convolutional neural network (CNN) was trained to denoise the resulting PET images for each disease cohort. RESULTS: Noise reduction of low-activity PET images was successful for both cohorts using 5% of the original activity with improvement in visual quality and all similarity metrics with respect to the ground-truth images. Clinically relevant metrics extracted from the low-activity images deviated < 2% compared to ground-truth values, which were not significantly changed when extracting the metrics from the denoised images. CONCLUSION: The presented models were based on the same network architecture and proved to be a robust tool for denoising brain PET images with two widely different tracer distributions (delocalized, ([11C]PiB, and highly localized, [18F]FE-PE2I). This broad and robust application makes the presented network a good choice for improving the quality of brain images to the level of the standard-activity images without degrading clinical metric extraction. This will allow for reduced dose or scan time in PET/CT to be implemented clinically.

Assessment of Artificial Intelligence Automatic Multiple Sclerosis Lesion Delineation Tool for Clinical Use.

PURPOSE: To implement and validate an existing algorithm for automatic delineation of white matter lesions on magnetic resonance imaging (MRI) in patients with multiple sclerosis (MS) on a local single-center dataset. METHODS: We implemented a white matter hyperintensity segmentation model, based on a 2D convolutional neural network, using the conventional T2-weighted fluid attenuated inversion recovery (FLAIR) MRI sequence as input. The model was adapted for delineation of MS lesions by further training on a local dataset of 93 MS patients with a total of 3040 lesions. A quantitative evaluation was performed on ten test patients, in which model-generated masks were compared to manually delineated masks from two expert delineators. A subsequent qualitative evaluation of the implemented model was performed by two expert delineators, in which generated delineation masks on a clinical dataset of 53 patients were rated acceptable (< 10% errors) or unacceptable (> 10% errors) based on the total number of true lesions. RESULTS: The quantitative evaluation resulted in an average accuracy score (F1) of 0.71, recall of 0.77 and dice similarity coefficient of 0.62. Our implemented model obtained the highest scores in all three metrics, when compared to three out of the box lesion segmentation models. In the clinical evaluation an average of 94% of our 53 model-generated masks were rated acceptable. CONCLUSION: After adaptation to our local dataset, the implemented segmentation model was able to delineate MS lesions with a high clinical value as rated by delineation experts while outperforming popular out of the box applications. This serves as a promising step towards implementation of automatic lesion delineation in our MS clinic.

Comparison of prospective and retrospective motion correction in 3D-encoded neuroanatomical MRI.

PURPOSE: To compare prospective motion correction (PMC) and retrospective motion correction (RMC) in Cartesian 3D-encoded MPRAGE scans and to investigate the effects of correction frequency and parallel imaging on the performance of RMC. METHODS: Head motion was estimated using a markerless tracking system and sent to a modified MPRAGE sequence, which can continuously update the imaging FOV to perform PMC. The prospective correction was applied either before each echo train (before-ET) or at every sixth readout within the ET (within-ET). RMC was applied during image reconstruction by adjusting k-space trajectories according to the measured motion. The motion correction frequency was retrospectively increased with RMC or decreased with reverse RMC. Phantom and in vivo experiments were used to compare PMC and RMC, as well as to compare within-ET and before-ET correction frequency during continuous motion. The correction quality was quantitatively evaluated using the structural similarity index measure with a reference image without motion correction and without intentional motion. RESULTS: PMC resulted in superior image quality compared to RMC both visually and quantitatively. Increasing the correction frequency from before-ET to within-ET reduced the motion artifacts in RMC. A hybrid PMC and RMC correction, that is, retrospectively increasing the correction frequency of before-ET PMC to within-ET, also reduced motion artifacts. Inferior performance of RMC compared to PMC was shown with GRAPPA calibration data without intentional motion and without any GRAPPA acceleration. CONCLUSION: Reductions in local Nyquist violations with PMC resulted in superior image quality compared to RMC. Increasing the motion correction frequency to within-ET reduced the motion artifacts in both RMC and PMC.

Deep-learning-based attenuation correction in dynamic [15O]H2O studies using PET/MRI in healthy volunteers.

Quantitative [15O]H2O positron emission tomography (PET) is the accepted reference method for regional cerebral blood flow (rCBF) quantification. To perform reliable quantitative [15O]H2O-PET studies in PET/MRI scanners, MRI-based attenuation-correction (MRAC) is required. Our aim was to compare two MRAC methods (RESOLUTE and DeepUTE) based on ultrashort echo-time with computed tomography-based reference standard AC (CTAC) in dynamic and static [15O]H2O-PET. We compared rCBF from quantitative perfusion maps and activity concentration distribution from static images between AC methods in 25 resting [15O]H2O-PET scans from 14 healthy men at whole-brain, regions of interest and voxel-wise levels. Average whole-brain CBF was 39.9 ± 6.0, 39.0 ± 5.8 and 40.0 ± 5.6 ml/100 g/min for CTAC, RESOLUTE and DeepUTE corrected studies respectively. RESOLUTE underestimated whole-brain CBF by 2.1 ± 1.50% and rCBF in all regions of interest (range -2.4%- -1%) compared to CTAC. DeepUTE showed significant rCBF overestimation only in the occipital lobe (0.6 ± 1.1%). Both MRAC methods showed excellent correlation on rCBF and activity concentration with CTAC, with slopes of linear regression lines between 0.97 and 1.01 and R2 over 0.99. In conclusion, RESOLUTE and DeepUTE provide AC information comparable to CTAC in dynamic [15O]H2O-PET but RESOLUTE is associated with a small but systematic underestimation.

The effect of reduced scan time on response assessment FDG-PET/CT imaging using Deauville score in patients with lymphoma.

PURPOSE: [18F]Fluoro-deoxy-glucose positron emission tomography/computed tomography (FDG-PET/CT) is used for response assessment during therapy in Hodgkin lymphoma (HL) and non-Hodgkin lymphoma (NHL). Clinicians report the scans visually using Deauville criteria. Improved performance in modern PET/CT scanners could allow for a reduction in scan time without compromising diagnostic image quality. Additionally, patient throughput can be increased with increasing cost-effectiveness. We investigated the effects of reducing scan time of response assessment FDG-PET/CT in HL and NHL patients on Deauville score (DS) and image quality. METHODS: Twenty patients diagnosed with HL/NHL referred to a response assessment FDG-PET/CT were included. PET scans were performed in list-mode with an acquisition time of 120 s per bed position(s/bp). From PET list-mode data images with full acquisition time of 120 s/bp and shorter acquisition times (90, 60, 45, and 30 s/bp) were reconstructed. All images were assessed by two specialists and assigned a DS. We estimated the possible savings when reducing scan time using a simplified model based on assumed values/costs for our hospital. RESULTS: There were no significant changes in the visually assessed DS when reducing scan time to 90 s/bp, 60 s/bp, 45 s/bp, and 30 s/bp. Image quality of 90 s/bp images were rated equal to 120 s/bp images. Coefficient of variance values for 120 s/bp and 90 s/bp images was significantly < 15%. The estimated annual savings to the hospital when reducing scan time was 8000-16,000 €/scanner. CONCLUSION: Acquisition time can be reduced to 90 s/bp in response assessment FDG-PET/CT without compromising Deauville score or image quality. Reducing acquisition time can reduce costs to the clinic.

Diagnostic accuracy and clinical impact of [18F]FET PET in childhood CNS tumors.

BACKGROUND: Central nervous system (CNS) tumors cause the highest death rates among childhood cancers, and survivors frequently have severe late effects. Magnetic resonance imaging (MRI) is the imaging modality of choice, but its specificity can be challenged by treatment-induced signal changes. In adults, O-(2-[18F]fluoroethyl)-l-tyrosine ([18F]FET) PET can assist in interpreting MRI findings. We assessed the clinical impact and diagnostic accuracy of adding [18F]FET PET to MRI in children with CNS tumors. METHODS: A total of 169 [18F]FET PET scans were performed in 97 prospectively and consecutively included patients with known or suspected childhood CNS tumors. Scans were performed at primary diagnosis, before or after treatment, or at relapse. RESULTS: Adding [18F]FET PET to MRI impacted clinical management in 8% [95% confidence interval (CI): 4%-13%] of all scans (n = 151) and in 33% [CI: 17%-53%] of scans deemed clinically indicated due to difficult decision making on MRI alone (n = 30). Using pathology or follow-up as reference standard, the addition of [18F]FET PET increased specificity (1.00 [0.82-1.00] vs 0.48 [0.30-0.70], P = .0001) and accuracy (0.91 [CI: 0.87-0.96] vs 0.81 [CI: 0.75-0.89], P = .04) in 83 treated lesions and accuracy in 58 untreated lesions (0.96 [CI: 0.91-1.00] vs 0.90 [CI: 0.82-0.92], P < .001). Further, in a subset of patients (n = 15) [18F]FET uptake correlated positively with genomic proliferation index. CONCLUSIONS: The addition of [18F]FET PET to MRI helped discriminate tumor from non-tumor lesions in the largest consecutive cohort of pediatric CNS tumor patients presented to date.

Low-dose PET image noise reduction using deep learning: application to cardiac viability FDG imaging in patients with ischemic heart disease.

INTRODUCTION: Cardiac [18F]FDG-PET is widely used for viability testing in patients with chronic ischemic heart disease. Guidelines recommend injection of 200-350 MBq [18F]FDG, however, a reduction of radiation exposure has become increasingly important, but might come at the cost of reduced diagnostic accuracy due to the increased noise in the images. We aimed to explore the use of a common deep learning (DL) network for noise reduction in low-dose PET images, and to validate its accuracy using the clinical quantitative metrics used to determine cardiac viability in patients with ischemic heart disease. METHODS: We included 168 patients imaged with cardiac [18F]FDG-PET/CT. We simulated a reduced dose by keeping counts at thresholds 1% and 10%. 3D U-net with five blocks was trained to de-noise full PET volumes (128 × 128 × 111). The low-dose and de-noised images were compared in Corridor4DM to the full-dose PET images. We used the default segmentation of the left ventricle to extract the quantitative metrics end-diastolic volume (EDV), end-systolic volume (ESV), and left ventricular ejection fraction (LVEF) from the gated images, and FDG defect extent from the static images. RESULTS: Our de-noising models were able to recover the PET signal for both the static and gated images in either dose-reduction. For the 1% low-dose images, the error is most pronounced for EDV and ESV, where the average underestimation is 25%. No bias was observed using the proposed DL de-noising method. De-noising minimized the outliers found for the 1% and 10% low-dose measurements of LVEF and extent. Accuracy of differential diagnosis based on LVEF threshold was highly improved after de-noising. CONCLUSION: A significant dose reduction can be achieved for cardiac [18F]FDG images used for viability testing in patients with ischemic heart disease without significant loss of diagnostic accuracy when using our DL model for noise reduction. Both 1% and 10% dose reductions are possible with clinically quantitative metrics comparable to that obtained with a full dose.

AI-driven attenuation correction for brain PET/MRI: Clinical evaluation of a dementia cohort and importance of the training group size.

INTRODUCTION: Robust and reliable attenuation correction (AC) is a prerequisite for accurate quantification of activity concentration. In combined PET/MRI, AC is challenged by the lack of bone signal in the MRI from which the AC maps has to be derived. Deep learning-based image-to-image translation networks present itself as an optimal solution for MRI-derived AC (MR-AC). High robustness and generalizability of these networks are expected to be achieved through large training cohorts. In this study, we implemented an MR-AC method based on deep learning, and investigated how training cohort size, transfer learning, and MR input affected robustness, and subsequently evaluated the method in a clinical setup, with the overall aim to explore if this method could be implemented in clinical routine for PET/MRI examinations. METHODS: A total cohort of 1037 adult subjects from the Siemens Biograph mMR with two different software versions (VB20P and VE11P) was used. The software upgrade included updates to all MRI sequences. The impact of training group size was investigated by training a convolutional neural network (CNN) on an increasing training group size from 10 to 403. The ability to adapt to changes in the input images between software versions were evaluated using transfer learning from a large cohort to a smaller cohort, by varying training group size from 5 to 91 subjects. The impact of MRI sequence was evaluated by training three networks based on the Dixon VIBE sequence (DeepDixon), T1-weighted MPRAGE (DeepT1), and ultra-short echo time (UTE) sequence (DeepUTE). Blinded clinical evaluation relative to the reference low-dose CT (CT-AC) was performed for DeepDixon in 104 independent 2-[18F]fluoro-2-deoxy-d-glucose ([18F]FDG) PET patient studies performed for suspected neurodegenerative disorder using statistical surface projections. RESULTS: Robustness increased with group size in the training data set: 100 subjects were required to reduce the number of outliers compared to a state-of-the-art segmentation-based method, and a cohort >400 subjects further increased robustness in terms of reduced variation and number of outliers. When using transfer learning to adapt to changes in the MRI input, as few as five subjects were sufficient to minimize outliers. Full robustness was achieved at 20 subjects. Comparable robust and accurate results were obtained using all three types of MRI input with a bias below 1% relative to CT-AC in any brain region. The clinical PET evaluation using DeepDixon showed no clinically relevant differences compared to CT-AC. CONCLUSION: Deep learning based AC requires a large training cohort to achieve accurate and robust performance. Using transfer learning, only five subjects were needed to fine-tune the method to large changes to the input images. No clinically relevant differences were found compared to CT-AC, indicating that clinical implementation of our deep learning-based MR-AC method will be feasible across MRI system types using transfer learning and a limited number of subjects.

[Artificial intelligence for diagnostic imaging].

Artificial intelligence (AI) is a computer-based system, which in diagnostic imaging can improve patient flow, optimise image processing, shorten scan time, reduce radiation dose and be used as decision aid in image interpretation. In this review, we argue that AI algorithms should be based on evidence with initial hypothesis, then a choice of algorithm and development with training on the initial data set; afterwards the algorithms should be tested on a new representative dataset, and finally it should be tested in a prospective study. If the AI is evidence-based and can solve a task better or cheaper than the usual methodology, it can be implemented.

Quantifying the Financial Savings of Motion Correction in Brain MRI: A Model-Based Estimate of the Costs Arising From Patient Head Motion and Potential Savings From Implementation of Motion Correction.

BACKGROUND: Patient head motion is a major concern in clinical brain MRI, as it reduces the diagnostic image quality and may increase examination time and cost. PURPOSE: To investigate the prevalence of MR images with significant motion artifacts on a given clinical scanner and to estimate the potential financial cost savings of applying motion correction to clinical brain MRI examinations. STUDY TYPE: Retrospective. SUBJECTS: In all, 173 patients undergoing a PET/MRI dementia protocol and 55 pediatric patients undergoing a PET/MRI brain tumor protocol. The total scan time of the two protocols were 17 and 40 minutes, respectively. FIELD STRENGTH/SEQUENCES: 3 T, Siemens mMR Biograph, MPRAGE, DWI, T1 and T2 -weighted FLAIR, T2 -weighted 2D-FLASH, T2 -weighted TSE. ASSESSMENT: A retrospective review of image sequences from a given clinical MRI scanner was conducted to investigate the prevalence of motion-corrupted images. The review was performed by three radiologists with different levels of experience using a three-step semiquantitative scale to classify the quality of the images. A total of 1013 sequences distributed on 228 MRI examinations were reviewed. The potential cost savings of motion correction were estimated by a cost estimation for our country with assumptions. STATISTICAL TEST: The cost estimation was conducted with a 20% lower and upper bound on the model assumptions to include the uncertainty of the assumptions. RESULTS: 7.9% of the sequences had motion artifacts that decreased the interpretability, while 2.0% of the sequences had motion artifacts causing the images to be nondiagnostic. The estimated annual cost to the clinic/hospital due to patient head motion per scanner was $45,066 without pediatric examinations and $364,242 with pediatric examinations. DATA CONCLUSION: The prevalence of a motion-corrupted image was found in 2.0% of the reviewed sequences. Based on the model, repayment periods are presented as a function of the price for applying motion correction and its performance. EVIDENCE LEVEL: 4 TECHNICAL EFFICACY: Stage 6 J. Magn. Reson. Imaging 2020;52:731-738.

Early Postoperative 18F-FET PET/MRI for Pediatric Brain and Spinal Cord Tumors.

Complete resection is the treatment of choice for most pediatric brain tumors, but early postoperative MRI for detection of residual tumor may be misleading because of MRI signal changes caused by the operation. PET imaging with amino acid tracers in adults increases the diagnostic accuracy for brain tumors, but the literature in pediatric neurooncology is limited. A hybrid PET/MRI system is highly beneficial in children, reducing the number of scanning procedures, and this is to our knowledge the first larger study using PET/MRI in pediatric neurooncology. We evaluated if additional postoperative 18F-fluoro-ethyl-tyrosine (18F-FET) PET in children and adolescents would improve diagnostic accuracy for the detection of residual tumor as compared with MRI alone and would assist clinical management. Methods: Twenty-two patients (7 male; mean age, 9.5 y; range, 0-19 y) were included prospectively and consecutively in the study and had 27 early postoperative 18F-FET PET exams performed preferentially in a hybrid PET/MRI system (NCT03402425). Results: Using follow-up (93%) or reoperation (7%) as the reference standard, PET combined with MRI discriminated tumor from treatment effects with a lesion-based sensitivity/specificity/accuracy (95% confidence intervals) of 0.73 (0.50-1.00)/1.00 (0.74-1.00)/0.87 (0.73-1.00) compared with MRI alone: 0.80 (0.57-1.00)/0.75 (0.53-0.94)/0.77 (0.65-0.90); that is, the specificity for PET/MRI was 1.00 as compared with 0.75 for MRI alone (P = 0.13). In 11 of 27 cases (41%), results from the 18F-FET PET scans added relevant clinical information, including one scan that directly influenced clinical management because an additional residual tumor site was identified. 18F-FET uptake in reactive changes was frequent (52%), but correct interpretation was possible in all cases. Conclusion: The high specificity for detecting residual tumor suggests that supplementary 18F-FET PET is relevant in cases where reoperation for residual tumor is considered.

Hybrid PET/MRI imaging in healthy unsedated newborn infants with quantitative rCBF measurements using 15O-water PET.

In this study, a new hybrid PET/MRI method for quantitative regional cerebral blood flow (rCBF) measurements in healthy newborn infants was assessed and the low values of rCBF in white matter previously obtained by arterial spin labeling (ASL) were tested. Four healthy full-term newborn subjects were scanned in a PET/MRI scanner during natural sleep after median intravenous injection of 14 MBq 15O-water. Regional CBF was quantified using a one-tissue-compartment model employing an image-derived input function (IDIF) from the left ventricle. PET rCBF showed the highest values in the thalami, mesencephalon and brain stem and the lowest in cortex and unmyelinated white matter. The average global CBF was 17.8 ml/100 g/min. The average frontal and occipital unmyelinated white matter CBF was 10.3 ml/100 g/min and average thalamic CBF 31.3 ml/100 g/min. The average white matter/thalamic ratio CBF was 0.36, significantly higher than previous ASL data. The rCBF ASL measurements were all unsuccessful primarily owing to subject movement. In this study, we demonstrated for the first time, a minimally invasive PET/MRI method using low activity 15O-water PET for quantitative rCBF assessment in unsedated healthy newborn infants and found a white/grey matter CBF ratio similar to that of the adult human brain.