Deep-learning-based reconstruction of undersampled MRI to reduce scan times: a multicentre, retrospective, cohort study.

BACKGROUND: The extended acquisition times required for MRI limit its availability in resource-constrained settings. Consequently, accelerating MRI by undersampling k-space data, which is necessary to reconstruct an image, has been a long-standing but important challenge. We aimed to develop a deep convolutional neural network (dCNN) optimisation method for MRI reconstruction and to reduce scan times and evaluate its effect on image quality and accuracy of oncological imaging biomarkers. METHODS: In this multicentre, retrospective, cohort study, MRI data from patients with glioblastoma treated at Heidelberg University Hospital (775 patients and 775 examinations) and from the phase 2 CORE trial (260 patients, 1083 examinations, and 58 institutions) and the phase 3 CENTRIC trial (505 patients, 3147 examinations, and 139 institutions) were used to develop, train, and test dCNN for reconstructing MRI from highly undersampled single-coil k-space data with various acceleration rates (R=2, 4, 6, 8, 10, and 15). Independent testing was performed with MRIs from the phase 2/3 EORTC-26101 trial (528 patients with glioblastoma, 1974 examinations, and 32 institutions). The similarity between undersampled dCNN-reconstructed and original MRIs was quantified with various image quality metrics, including structural similarity index measure (SSIM) and the accuracy of undersampled dCNN-reconstructed MRI on downstream radiological assessment of imaging biomarkers in oncology (automated artificial intelligence-based quantification of tumour burden and treatment response) was performed in the EORTC-26101 test dataset. The public NYU Langone Health fastMRI brain test dataset (558 patients and 558 examinations) was used to validate the generalisability and robustness of the dCNN for reconstructing MRIs from available multi-coil (parallel imaging) k-space data. FINDINGS: In the EORTC-26101 test dataset, the median SSIM of undersampled dCNN-reconstructed MRI ranged from 0·88 to 0·99 across different acceleration rates, with 0·92 (95% CI 0·92-0·93) for 10-times acceleration (R=10). The 10-times undersampled dCNN-reconstructed MRI yielded excellent agreement with original MRI when assessing volumes of contrast-enhancing tumour (median DICE for spatial agreement of 0·89 [95% CI 0·88 to 0·89]; median volume difference of 0·01 cm3 [95% CI 0·00 to 0·03] equalling 0·21%; p=0·0036 for equivalence) or non-enhancing tumour or oedema (median DICE of 0·94 [95% CI 0·94 to 0·95]; median volume difference of -0·79 cm3 [95% CI -0·87 to -0·72] equalling -1·77%; p=0·023 for equivalence) in the EORTC-26101 test dataset. Automated volumetric tumour response assessment in the EORTC-26101 test dataset yielded an identical median time to progression of 4·27 months (95% CI 4·14 to 4·57) when using 10-times-undersampled dCNN-reconstructed or original MRI (log-rank p=0·80) and agreement in the time to progression in 374 (95·2%) of 393 patients with data. The dCNN generalised well to the fastMRI brain dataset, with significant improvements in the median SSIM when using multi-coil compared with single-coil k-space data (p<0·0001). INTERPRETATION: Deep-learning-based reconstruction of undersampled MRI allows for a substantial reduction of scan times, with a 10-times acceleration demonstrating excellent image quality while preserving the accuracy of derived imaging biomarkers for the assessment of oncological treatment response. Our developments are available as open source software and hold considerable promise for increasing the accessibility to MRI, pending further prospective validation. FUNDING: Deutsche Forschungsgemeinschaft (German Research Foundation) and an Else Kröner Clinician Scientist Endowed Professorship by the Else Kröner Fresenius Foundation.

Phenotyping of COPD with MRI in comparison to same-day CT in a multi-centre trial.

OBJECTIVES: A prospective, multi-centre study to evaluate concordance of morphologic lung MRI and CT in chronic obstructive pulmonary disease (COPD) phenotyping for airway disease and emphysema. METHODS: A total of 601 participants with COPD from 15 sites underwent same-day morpho-functional chest MRI and paired inspiratory-expiratory CT. Two readers systematically scored bronchial wall thickening, bronchiectasis, centrilobular nodules, air trapping and lung parenchyma defects in each lung lobe and determined COPD phenotype. A third reader acted as adjudicator to establish consensus. Inter-modality and inter-reader agreement were assessed using Cohen's kappa (im-κ and ir-κ). RESULTS: The mean combined MRI score for bronchiectasis/bronchial wall thickening was 4.5/12 (CT scores, 2.2/12 for bronchiectasis and 6/12 for bronchial wall thickening; im-κ, 0.04-0.3). Expiratory right/left bronchial collapse was observed in 51 and 47/583 on MRI (62 and 57/599 on CT; im-κ, 0.49-0.52). Markers of small airways disease on MRI were 0.15/12 for centrilobular nodules (CT, 0.34/12), 0.94/12 for air trapping (CT, 0.9/12) and 7.6/12 for perfusion deficits (CT, 0.37/12 for mosaic attenuation; im-κ, 0.1-0.41). The mean lung defect score on MRI was 1.3/12 (CT emphysema score, 5.8/24; im-κ, 0.18-0.26). Airway-/emphysema/mixed COPD phenotypes were assigned in 370, 218 and 10 of 583 cases on MRI (347, 218 and 34 of 599 cases on CT; im-κ, 0.63). For all examined features, inter-reader agreement on MRI was lower than on CT. CONCLUSION: Concordance of MRI and CT for phenotyping of COPD in a multi-centre setting was substantial with variable inter-modality and inter-reader concordance for single diagnostic key features. CLINICAL RELEVANCE STATEMENT: MRI of lung morphology may well serve as a radiation-free imaging modality for COPD in scientific and clinical settings, given that its potential and limitations as shown here are carefully considered. KEY POINTS: • In a multi-centre setting, MRI and CT showed substantial concordance for phenotyping of COPD (airway-/emphysema-/mixed-type). • Individual features of COPD demonstrated variable inter-modality concordance with features of pulmonary hypertension showing the highest and bronchiectasis showing the lowest concordance. • For all single features of COPD, inter-reader agreement was lower on MRI than on CT.

Reliability and reproducibility of sciatic nerve magnetization transfer imaging and T2 relaxometry.

OBJECTIVES: To assess the interreader and test-retest reliability of magnetization transfer imaging (MTI) and T2 relaxometry in sciatic nerve MR neurography (MRN). MATERIALS AND METHODS: In this prospective study, 21 healthy volunteers were examined three times on separate days by a standardized MRN protocol at 3 Tesla, consisting of an MTI sequence, a multi-echo T2 relaxometry sequence, and a high-resolution T2-weighted sequence. Magnetization transfer ratio (MTR), T2 relaxation time, and proton spin density (PSD) of the sciatic nerve were assessed by two independent observers, and both interreader and test-retest reliability for all readout parameters were reported by intraclass correlation coefficients (ICCs) and standard error of measurement (SEM). RESULTS: For the sciatic nerve, overall mean ± standard deviation MTR was 26.75 ± 3.5%, T2 was 64.54 ± 8.2 ms, and PSD was 340.93 ± 78.8. ICCs ranged between 0.81 (MTR) and 0.94 (PSD) for interreader reliability and between 0.75 (MTR) and 0.94 (PSD) for test-retest reliability. SEM for interreader reliability was 1.7% for MTR, 2.67 ms for T2, and 21.3 for PSD. SEM for test-retest reliability was 1.7% for MTR, 2.66 ms for T2, and 20.1 for PSD. CONCLUSIONS: MTI and T2 relaxometry of the sciatic nerve are reliable and reproducible. The values of measurement imprecision reported here may serve as a guide for correct interpretation of quantitative MRN biomarkers in future studies. KEY POINTS: • Magnetization transfer imaging (MTI) and T2 relaxometry of the sciatic nerve are reliable and reproducible. • The imprecision that is unavoidably associated with different scans or different readers can be estimated by the here presented SEM values for the biomarkers T2, PSD, and MTR. • These values may serve as a guide for correct interpretation of quantitative MRN biomarkers in future studies and possible clinical applications.

Deep Learning-based Identification of Brain MRI Sequences Using a Model Trained on Large Multicentric Study Cohorts.

Purpose To develop a fully automated device- and sequence-independent convolutional neural network (CNN) for reliable and high-throughput labeling of heterogeneous, unstructured MRI data. Materials and Methods Retrospective, multicentric brain MRI data (2179 patients with glioblastoma, 8544 examinations, 63 327 sequences) from 249 hospitals and 29 scanner types were used to develop a network based on ResNet-18 architecture to differentiate nine MRI sequence types, including T1-weighted, postcontrast T1-weighted, T2-weighted, fluid-attenuated inversion recovery, susceptibility-weighted, apparent diffusion coefficient, diffusion-weighted (low and high b value), and gradient-recalled echo T2*-weighted and dynamic susceptibility contrast-related images. The two-dimensional-midsection images from each sequence were allocated to training or validation (approximately 80%) and testing (approximately 20%) using a stratified split to ensure balanced groups across institutions, patients, and MRI sequence types. The prediction accuracy was quantified for each sequence type, and subgroup comparison of model performance was performed using χ2 tests. Results On the test set, the overall accuracy of the CNN (ResNet-18) ensemble model among all sequence types was 97.9% (95% CI: 97.6, 98.1), ranging from 84.2% for susceptibility-weighted images (95% CI: 81.8, 86.6) to 99.8% for T2-weighted images (95% CI: 99.7, 99.9). The ResNet-18 model achieved significantly better accuracy compared with ResNet-50 despite its simpler architecture (97.9% vs 97.1%; P ≤ .001). The accuracy of the ResNet-18 model was not affected by the presence versus absence of tumor on the two-dimensional-midsection images for any sequence type (P > .05). Conclusion The developed CNN (www.github.com/neuroAI-HD/HD-SEQ-ID) reliably differentiates nine types of MRI sequences within multicenter and large-scale population neuroimaging data and may enhance the speed, accuracy, and efficiency of clinical and research neuroradiologic workflows. Keywords: MR-Imaging, Neural Networks, CNS, Brain/Brain Stem, Computer Applications-General (Informatics), Convolutional Neural Network (CNN), Deep Learning Algorithms, Machine Learning Algorithms Supplemental material is available for this article. © RSNA, 2023.

Assessing the added value of apparent diffusion coefficient, cerebral blood volume, and radiomic magnetic resonance features for differentiation of pseudoprogression versus true tumor progression in patients with glioblastoma.

Background: Pseudoprogression (PsPD) is a major diagnostic challenge in the follow-up of patients with glioblastoma (GB) after chemoradiotherapy (CRT). Conventional imaging signs and parameters derived from diffusion and perfusion-MRI have yet to prove their reliability in clinical practice for an accurate differential diagnosis. Here, we tested these parameters and combined them with radiomic features (RFs), clinical data, and MGMT promoter methylation status using machine- and deep-learning (DL) models to distinguish PsPD from Progressive disease. Methods: In a single-center analysis, 105 patients with GB who developed a suspected imaging PsPD in the first 7 months after standard CRT were identified retrospectively. Imaging data included standard MRI anatomical sequences, apparent diffusion coefficient (ADC), and normalized relative cerebral blood volume (nrCBV) maps. Median values (ADC, nrCBV) and RFs (all sequences) were calculated from DL-based tumor segmentations. Generalized linear models with LASSO feature-selection and DL models were built integrating clinical data, MGMT methylation status, median ADC and nrCBV values and RFs. Results: A model based on clinical data and MGMT methylation status yielded an areas under the receiver operating characteristic curve (AUC) = 0.69 (95% CI 0.55-0.83) for detecting PsPD, and the addition of median ADC and nrCBV values resulted in a nonsignificant increase in performance (AUC = 0.71, 95% CI 0.57-0.85, P = .416). Combining clinical/MGMT information with RFs derived from ADC, nrCBV, and from all available sequences both resulted in significantly (both P < .005) lower model performances, with AUC = 0.52 (0.38-0.66) and AUC = 0.54 (0.40-0.68), respectively. DL imaging models resulted in AUCs ≤ 0.56. Conclusion: Currently available imaging biomarkers could not reliably differentiate PsPD from true tumor progression in patients with glioblastoma; larger collaborative efforts are needed to build more reliable models.

Deep-learning based detection of vessel occlusions on CT-angiography in patients with suspected acute ischemic stroke.

Swift diagnosis and treatment play a decisive role in the clinical outcome of patients with acute ischemic stroke (AIS), and computer-aided diagnosis (CAD) systems can accelerate the underlying diagnostic processes. Here, we developed an artificial neural network (ANN) which allows automated detection of abnormal vessel findings without any a-priori restrictions and in <2 minutes. Pseudo-prospective external validation was performed in consecutive patients with suspected AIS from 4 different hospitals during a 6-month timeframe and demonstrated high sensitivity (≥87%) and negative predictive value (≥93%). Benchmarking against two CE- and FDA-approved software solutions showed significantly higher performance for our ANN with improvements of 25-45% for sensitivity and 4-11% for NPV (p ≤ 0.003 each). We provide an imaging platform ( https://stroke.neuroAI-HD.org ) for online processing of medical imaging data with the developed ANN, including provisions for data crowdsourcing, which will allow continuous refinements and serve as a blueprint to build robust and generalizable AI algorithms.

Artificial intelligence (AI)-based decision support improves reproducibility of tumor response assessment in neuro-oncology: An international multi-reader study.

BACKGROUND: To assess whether artificial intelligence (AI)-based decision support allows more reproducible and standardized assessment of treatment response on MRI in neuro-oncology as compared to manual 2-dimensional measurements of tumor burden using the Response Assessment in Neuro-Oncology (RANO) criteria. METHODS: A series of 30 patients (15 lower-grade gliomas, 15 glioblastoma) with availability of consecutive MRI scans was selected. The time to progression (TTP) on MRI was separately evaluated for each patient by 15 investigators over two rounds. In the first round the TTP was evaluated based on the RANO criteria, whereas in the second round the TTP was evaluated by incorporating additional information from AI-enhanced MRI sequences depicting the longitudinal changes in tumor volumes. The agreement of the TTP measurements between investigators was evaluated using concordance correlation coefficients (CCC) with confidence intervals (CI) and P-values obtained using bootstrap resampling. RESULTS: The CCC of TTP-measurements between investigators was 0.77 (95% CI = 0.69,0.88) with RANO alone and increased to 0.91 (95% CI = 0.82,0.95) with AI-based decision support (P = .005). This effect was significantly greater (P = .008) for patients with lower-grade gliomas (CCC = 0.70 [95% CI = 0.56,0.85] without vs. 0.90 [95% CI = 0.76,0.95] with AI-based decision support) as compared to glioblastoma (CCC = 0.83 [95% CI = 0.75,0.92] without vs. 0.86 [95% CI = 0.78,0.93] with AI-based decision support). Investigators with less years of experience judged the AI-based decision as more helpful (P = .02). CONCLUSIONS: AI-based decision support has the potential to yield more reproducible and standardized assessment of treatment response in neuro-oncology as compared to manual 2-dimensional measurements of tumor burden, particularly in patients with lower-grade gliomas. A fully-functional version of this AI-based processing pipeline is provided as open-source (https://github.com/NeuroAI-HD/HD-GLIO-XNAT).

Automated detection and quantification of brain metastases on clinical MRI data using artificial neural networks.

Background: Reliable detection and precise volumetric quantification of brain metastases (BM) on MRI are essential for guiding treatment decisions. Here we evaluate the potential of artificial neural networks (ANN) for automated detection and quantification of BM. Methods: A consecutive series of 308 patients with BM was used for developing an ANN (with a 4:1 split for training/testing) for automated volumetric assessment of contrast-enhancing tumors (CE) and non-enhancing FLAIR signal abnormality including edema (NEE). An independent consecutive series of 30 patients was used for external testing. Performance was assessed case-wise for CE and NEE and lesion-wise for CE using the case-wise/lesion-wise DICE-coefficient (C/L-DICE), positive predictive value (L-PPV) and sensitivity (C/L-Sensitivity). Results: The performance of detecting CE lesions on the validation dataset was not significantly affected when evaluating different volumetric thresholds (0.001-0.2 cm3; P = .2028). The median L-DICE and median C-DICE for CE lesions were 0.78 (IQR = 0.6-0.91) and 0.90 (IQR = 0.85-0.94) in the institutional as well as 0.79 (IQR = 0.67-0.82) and 0.84 (IQR = 0.76-0.89) in the external test dataset. The corresponding median L-Sensitivity and median L-PPV were 0.81 (IQR = 0.63-0.92) and 0.79 (IQR = 0.63-0.93) in the institutional test dataset, as compared to 0.85 (IQR = 0.76-0.94) and 0.76 (IQR = 0.68-0.88) in the external test dataset. The median C-DICE for NEE was 0.96 (IQR = 0.92-0.97) in the institutional test dataset as compared to 0.85 (IQR = 0.72-0.91) in the external test dataset. Conclusion: The developed ANN-based algorithm (publicly available at www.github.com/NeuroAI-HD/HD-BM) allows reliable detection and precise volumetric quantification of CE and NEE compartments in patients with BM.

Thunderclap Headache: A Primary Symptom of a Steroid-Responsive Encephalopathy with Autoimmune Thyroiditis.

Thunderclap headache is frequently associated with serious intracranial vascular disorders and a usual reason for emergency department admissions. Association of thunderclap headaches with autoimmune disorders, such as steroid-responsive encephalopathy with autoimmune thyroiditis (SREAT), is highly unusual. Here, we report a patient who presented with high-intensity headache of abrupt onset. Cerebrospinal fluid (CSF) analysis revealed moderate lymphocytic pleocytosis without evidence of infectious, neoplastic, or metabolic causes. Brain magnetic resonance imaging showed no specific pathologies, and examinations for neuronal antibodies in serum and CSF were negative. The medical history revealed that seven years before, an episode of an aseptic meningoencephalitis with remarkable response to steroids was present. Finally, increased levels of serum anti-TPO antibodies were identified, and against the background of a previous steroid-responsive aseptic meningoencephalitis, diagnosis of SREAT was highly probable. Methylprednisolone therapy was initiated, and the patient recovered completely. In particular, because most SREAT patients respond very well to steroids, this case underlines the importance of taking SREAT into consideration during the assessment of a high-intensity headache of abrupt onset.

Deep-learning-based synthesis of post-contrast T1-weighted MRI for tumour response assessment in neuro-oncology: a multicentre, retrospective cohort study.

BACKGROUND: Gadolinium-based contrast agents (GBCAs) are widely used to enhance tissue contrast during MRI scans and play a crucial role in the management of patients with cancer. However, studies have shown gadolinium deposition in the brain after repeated GBCA administration with yet unknown clinical significance. We aimed to assess the feasibility and diagnostic value of synthetic post-contrast T1-weighted MRI generated from pre-contrast MRI sequences through deep convolutional neural networks (dCNN) for tumour response assessment in neuro-oncology. METHODS: In this multicentre, retrospective cohort study, we used MRI examinations to train and validate a dCNN for synthesising post-contrast T1-weighted sequences from pre-contrast T1-weighted, T2-weighted, and fluid-attenuated inversion recovery sequences. We used MRI scans with availability of these sequences from 775 patients with glioblastoma treated at Heidelberg University Hospital, Heidelberg, Germany (775 MRI examinations); 260 patients who participated in the phase 2 CORE trial (1083 MRI examinations, 59 institutions); and 505 patients who participated in the phase 3 CENTRIC trial (3147 MRI examinations, 149 institutions). Separate training runs to rank the importance of individual sequences and (for a subset) diffusion-weighted imaging were conducted. Independent testing was performed on MRI data from the phase 2 and phase 3 EORTC-26101 trial (521 patients, 1924 MRI examinations, 32 institutions). The similarity between synthetic and true contrast enhancement on post-contrast T1-weighted MRI was quantified using the structural similarity index measure (SSIM). Automated tumour segmentation and volumetric tumour response assessment based on synthetic versus true post-contrast T1-weighted sequences was performed in the EORTC-26101 trial and agreement was assessed with Kaplan-Meier plots. FINDINGS: The median SSIM score for predicting contrast enhancement on synthetic post-contrast T1-weighted sequences in the EORTC-26101 test set was 0·818 (95% CI 0·817-0·820). Segmentation of the contrast-enhancing tumour from synthetic post-contrast T1-weighted sequences yielded a median tumour volume of 6·31 cm3 (5·60 to 7·14), thereby underestimating the true tumour volume by a median of -0·48 cm3 (-0·37 to -0·76) with the concordance correlation coefficient suggesting a strong linear association between tumour volumes derived from synthetic versus true post-contrast T1-weighted sequences (0·782, 0·751-0·807, p<0·0001). Volumetric tumour response assessment in the EORTC-26101 trial showed a median time to progression of 4·2 months (95% CI 4·1-5·2) with synthetic post-contrast T1-weighted and 4·3 months (4·1-5·5) with true post-contrast T1-weighted sequences (p=0·33). The strength of the association between the time to progression as a surrogate endpoint for predicting the patients' overall survival in the EORTC-26101 cohort was similar when derived from synthetic post-contrast T1-weighted sequences (hazard ratio of 1·749, 95% CI 1·282-2·387, p=0·0004) and model C-index (0·667, 0·622-0·708) versus true post-contrast T1-weighted MRI (1·799, 95% CI 1·314-2·464, p=0·0003) and model C-index (0·673, 95% CI 0·626-0·711). INTERPRETATION: Generating synthetic post-contrast T1-weighted MRI from pre-contrast MRI using dCNN is feasible and quantification of the contrast-enhancing tumour burden from synthetic post-contrast T1-weighted MRI allows assessment of the patient's response to treatment with no significant difference by comparison with true post-contrast T1-weighted sequences with administration of GBCAs. This finding could guide the application of dCNN in radiology to potentially reduce the necessity of GBCA administration. FUNDING: Deutsche Forschungsgemeinschaft.

Klippel-Trénaunay-Weber syndrome associated with abdominal aortic aneurysm in childhood.

Klippel-Trénaunay-Weber syndrome (KTWS), also known as angioosteohypertrophy syndrome, is a rare congenital malformation with unknown etiology characterized by the combination of capillary malformations (port-wine strain), venous varicosities, and a soft tissue or bony hypertrophy of the affected limb. It is known to be rarely associated with abdominal aortic aneurysm (AAA) in adults. We report the first published case of KTWS and a rapidly progressing symptomatic AAA undergoing open repair in a child. This underlines the importance of AAA screening and treatment rather than surveillance in patients with KTWS.

Hemodynamic assessment of partial mechanical circulatory support: data derived from computed tomography angiographic images and computational fluid dynamics.

Partial mechanical circulatory support represents a new concept for the treatment of advanced heart failure. The Circulite Synergy Micro Pump(®), where the inflow cannula is connected to the left atrium and the outflow cannula to the right subclavian artery, was one of the first devices to introduce this concept to the clinic. Using computational fluid dynamics (CFD) simulations, hemodynamics in the aortic tree was visualized and quantified from computed tomography angiographic (CTA) images in two patients. A realistic computational model was created by integrating flow information from the native heart and from the Circulite device. Diastolic flow augmentation in the descending aorta but competing/antagonizing flow patterns in the proximal innominate artery was observed. Velocity time curves in the ascending aorta correlated well with those in the left common carotid, the left subclavian and the descending aorta but poorly with the one in the innominate. Our results demonstrate that CFD may be useful in providing a better understanding of the main flow patterns in mechanical circulatory support devices.