Generative Pre-trained Transformer 4 analysis of cardiovascular magnetic resonance reports in suspected myocarditis: A multicenter study.

BACKGROUND: Diagnosing myocarditis relies on multimodal data, including cardiovascular magnetic resonance (CMR), clinical symptoms, and blood values. The correct interpretation and integration of CMR findings require radiological expertise and knowledge. We aimed to investigate the performance of Generative Pre-trained Transformer 4 (GPT-4), a large language model, for report-based medical decision-making in the context of cardiac MRI for suspected myocarditis. METHODS: This retrospective study includes CMR reports from 396 patients with suspected myocarditis and eight centers, respectively. CMR reports and patient data including blood values, age, and further clinical information were provided to GPT-4 and radiologists with 1 (resident 1), 2 (resident 2), and 4 years (resident 3) of experience in CMR and knowledge of the 2018 Lake Louise Criteria. The final impression of the report regarding the radiological assessment of whether myocarditis is present or not was not provided. The performance of Generative pre-trained transformer 4 (GPT-4) and the human readers were compared to a consensus reading (two board-certified radiologists with 8 and 10 years of experience in CMR). Sensitivity, specificity, and accuracy were calculated. RESULTS: GPT-4 yielded an accuracy of 83%, sensitivity of 90%, and specificity of 78%, which was comparable to the physician with 1 year of experience (R1: 86%, 90%, 84%, p = 0.14) and lower than that of more experienced physicians (R2: 89%, 86%, 91%, p = 0.007 and R3: 91%, 85%, 96%, p < 0.001). GPT-4 and human readers showed a higher diagnostic performance when results from T1- and T2-mapping sequences were part of the reports, for residents 1 and 3 with statistical significance (p = 0.004 and p = 0.02, respectively). CONCLUSION: GPT-4 yielded good accuracy for diagnosing myocarditis based on CMR reports in a large dataset from multiple centers and therefore holds the potential to serve as a diagnostic decision-supporting tool in this capacity, particularly for less experienced physicians. Further studies are required to explore the full potential and elucidate educational aspects of the integration of large language models in medical decision-making.

Applicability of Magnetic Resonance Imaging of the Knee in Forensic Age Estimation.

ABSTRACT: Age estimation in forensic medicine practice is of particular importance to the legal systems, and it is one of the current research topics in forensic medicine. Age determination is most frequently performed by radiological methods, but recently, nonionized methods are preferred for nonmedical indications. Therefore, we aimed to examine feasibility of MRI imaging, which provides nonionized, noninvasive, and detailed images, in forensic age estimation and to expand the database on this subject. The MRI images of the patients between the ages of 10 and 25 years, who visited Cukurova University Faculty of Medicine between January 2012 and April 2018 for any reason, were retrospectively analyzed according to the staging method described by Dedouit et al. The stage 5 ossification in distal femoral epiphysis indicated an age over 18 years in both sexes (except for 2 cases of 14 and 15 years). The stage 5 ossification in proximal tibial epiphysis indicated an age older than 18 years (except for 1 male case at the age of 15 years and 2 female cases at the age of 14 and 17 years, respectively). It was determined that stage 1 and stage 2 in both distal femur and proximal tibial epiphysis were last seen in younger than 18 years in both sexes. Our study data show that MRI imaging is a nonionized method that can be used in addition to other radiological methods in determining the age limit of 18 years.

Feasibility, Safety, and Efficacy of Endovascular vs. Surgical Treatment of Unruptured Multi-Sac Intracranial Aneurysms in a Single-Center Retrospective Series.

PURPOSE: Multi-sac aneurysms (MSAs) are not uncommon, but studies on their management are scarce. This study aims to evaluate and compare the feasibility, safety, and efficacy of MSAs treated with either clipping or coiling after interdisciplinary case discussion at our center. MATERIALS AND METHODS: We retrospectively analyzed MSAs treated by microsurgical clipping, coiling, or stent-assisted coiling (SAC). Treatment modalities, complications, angiographic results, and clinical outcomes were evaluated. Major neurological events were defined as a safety endpoint and complete occlusion as an efficacy endpoint. RESULTS: Ninety patients (mean age, 53.2±11.0 years; 73 [81.1%] females) with MSAs met our inclusion criteria (clipping, 50; coiling, 19; SAC, 21). Most aneurysms were located in the middle cerebral artery (48.9%). All clipping procedures were technically successful, but endovascular treatment failed in 1 coiling case, and a switch from coiling to SAC was required in 2 cases. The major event rates were 4.0% after clipping (1 major stroke and 1 intracranial hemorrhage) and 0% after endovascular therapy (P=0.667). At mid-term angiographic follow-up (mean 12.0±8.9 months), all 37 followed clipped aneurysms were completely occluded, compared to 8/17 (41.7%) after coiling and 11/15 (73.3%) after SAC (P<0.001). Coiling was significantly associated with incomplete occlusion in the adjusted analysis (odds ratio, 11.7; 95% confidence interval, 2.7-52.6; P=0.001). CONCLUSION: Both endovascular and surgical treatment were feasible and safe for MSAs. As coiling was associated with comparatively high recanalization rates, endovascular treatment may be preferred with stent support.

Non-contrast-enhanced MR-angiography of the abdominal arteries: intraindividual comparison between relaxation-enhanced angiography without contrast and triggering (REACT) and 4D contrast-enhanced MR-angiography.

PURPOSE: To evaluate Relaxation-Enhanced Angiography without Contrast and Triggering (REACT), a novel 3D isotropic flow-independent non-contrast-enhanced magnetic resonance angiography (non-CE-MRA) for imaging of the abdominal arteries, by comparing image quality and assessment of vessel stenosis intraindidually with 4D CE-MRA. METHODS: Thirty patients (mean age 35.7 ± 16.8 years; 20 females) referred for the assessment of the arterial abdominal vasculature at 3 T were included in this retrospective, single-centre study. The protocol comprised both 4D CE-MRA and REACT (navigator-triggering, Compressed SENSE factor 10, nominal scan time 02:54 min, and reconstructed voxel size 0.78 × 0.78 × 0.85  mm3). Two radiologists independently evaluated 14 abdominal artery segments for stenoses, anatomical variants, and vascular findings (aortic dissection, abdominal aorta aneurysms and its branches). Subjective image quality was assessed using a 4-point Likert scale (1 = non-diagnostic, 4 = excellent). RESULTS: REACT had a total acquisition time of 5:36 ± 00:40 min, while 4D CE-MRA showed a total acquisition time (including the native scan and bolus tracking sequence) of 3:45 ± 00:59 min (p = 0.001). Considering 4D CE-MRA as the reference standard, REACT achieved a sensitivity of 87.5% and specificity of 100.0% for relevant (≥ 50%) stenosis while detecting 89.5% of all vascular findings other than stenosis. For all vessels combined, subjective vessel quality was slightly higher in 4D CE-MRA (3.0 [IQR: 2.0; 4.0.]; P = 0.040), although comparable to REACT (3.0 [IQR: 2.0; 3.5]). CONCLUSION: In a short scan time of about 5 min, REACT provides good diagnostic performance for detection of relevant stenoses, variants, and vascular findings of the abdominal arteries, while yielding to 4D CE-MRA comparable image quality.

Highly compressed SENSE accelerated relaxation-enhanced angiography without contrast and triggering (REACT) for fast non-contrast enhanced magnetic resonance angiography of the neck: Clinical evaluation in patients with acute ischemic stroke at 3 tesla.

BACKGROUND AND PURPOSE: Long acquisition times limit the feasibility of established non-contrast-enhanced MRA (non-CE-MRA) techniques. The purpose of this study was to evaluate a highly accelerated flow-independent sequence (Relaxation-Enhanced Angiography without Contrast and Triggering [REACT]) for imaging of the extracranial arteries in acute ischemic stroke (AIS). MATERIALS AND METHODS: Compressed SENSE (CS) accelerated (factor 7) 3D isotropic REACT (fixed scan time: 01:22 min, reconstructed voxel size 0.625 × 0.625 × 0.75 mm3) and CE-MRA (CS factor 6, scan time: 1:08 min, reconstructed voxel size 0.5 mm3) were acquired in 76 AIS patients (69.4 ± 14.3 years, 33 females) at 3 Tesla. Two radiologists assessed scans for the presence of internal carotid artery (ICA) stenosis and stated their diagnostic confidence using a 5-point scale (5 = excellent). Vessel quality of cervical arteries as well as the impact of artifacts and image noise were scored on 5-point scales (5 = excellent/none). Apparent signal- and contrast-to-noise ratios (aSNR/aCNR) were measured for the common carotid artery (CCA) and ICA (C1-segment). RESULTS: REACT provided a sensitivity of 88.5% and specificity of 100% for clinically relevant (≥50%) ICA stenosis with substantial concordance to CE-MRA regarding stenosis grading (Cohen's kappa 0.778) and similar diagnostic confidence (REACT: mean 4.5 ± 0.4 vs. CE-MRA: 4.5 ± 0.6; P = 0.674). Presence of artifacts (3.6 ± 0.5 vs. 3.5 ± 0.7; P = 0.985) and vessel quality (all segments: 3.6 ± 0.7 vs. 3.8 ± 0.7; P = 0.004) were comparable between both techniques with REACT showing higher scores at the CCA (4.3 ± 0.6 vs. 3.8 ± 0.9; P < 0.001) and CE-MRA at V2- (3.3 ± 0.5 vs. 3.9 ± 0.8; P < 0.001) and V3-segments (3.3 ± 0.5 vs. 4.0 ± 0.8; P < 0.001). For all vessels, REACT showed a lower impact of image noise (3.8 ± 0.6 vs. 3.6 ± 0.7; P = 0.024) while yielding higher aSNR (52.5 ± 15.1 vs. 37.9 ± 12.5; P < 0.001) and aCNR (49.4 ± 15.0 vs. 34.7 ± 12.3; P < 0.001) for all vessels combined. CONCLUSIONS: In patients with acute ischemic stroke, highly accelerated REACT provides an accurate detection of ICA stenosis with vessel quality and scan time comparable to CE-MRA.

Non-contrast-enhanced MR-angiography of Extracranial Arteries in Acute Ischemic Stroke at 1.5 Tesla Using Relaxation-Enhanced Angiography Without Contrast and Triggering (REACT).

PURPOSE: To evaluate a novel flow-independent sequence (Relaxation-Enhanced Angiography without Contrast and Triggering (REACT)) for imaging of the extracranial arteries in acute ischemic stroke (AIS) at 1.5 T. METHODS: This retrospective single-center study included 47 AIS patients who received REACT (scan time: 3:01 min) and contrast-enhanced MRA (CE-MRA) of the extracranial arteries at 1.5 T in clinical routine. Two radiologists assessed scans for proximal internal carotid artery (ICA) stenosis, stated their diagnostic confidence and rated the image quality of cervical arteries, impact of artifacts and image noise. Apparent signal- and contrast-to-noise ratios (aSNR/aCNR) were measured for the common carotid artery and ICA. RESULTS: REACT achieved a sensitivity of 95.0% and a specificity of 97.3% for ICA stenoses in high agreement with CE-MRA (κ = 0.83) with equal diagnostic confidence (p = 0.22). Image quality was rated higher for CE-MRA at the aortic arch (p = 0.002) and vertebral arteries (p < 0.001), whereas REACT provided superior results for the extracranial ICA (p = 0.008). Both sequences were only slightly affected by artifacts (p = 0.60), while image noise was more pronounced in CE-MRA (p < 0.001) in line with higher aSNR (p < 0.001) and aCNR (p < 0.001) values in REACT for all vessels. CONCLUSION: Given its good diagnostic performance while yielding comparable image quality and scan time to CE-MRA, REACT may be suitable for the imaging of the extracranial arteries in acute ischemic stroke at 1.5 T.

Deep Learning Virtual Contrast-Enhanced T1 Mapping for Contrast-Free Myocardial Extracellular Volume Assessment.

BACKGROUND: The acquisition of contrast-enhanced T1 maps to calculate extracellular volume (ECV) requires contrast agent administration and is time consuming. This study investigates generative adversarial networks for contrast-free, virtual extracellular volume (vECV) by generating virtual contrast-enhanced T1 maps. METHODS AND RESULTS: This retrospective study includes 2518 registered native and contrast-enhanced T1 maps from 1000 patients who underwent cardiovascular magnetic resonance at 1.5 Tesla. Recent hematocrit values of 123 patients (hold-out test) and 96 patients from a different institution (external evaluation) allowed for calculation of conventional ECV. A generative adversarial network was trained to generate virtual contrast-enhanced T1 maps from native T1 maps for vECV creation. Mean and SD of the difference per patient (ΔECV) were calculated and compared by permutation of the 2-sided t test with 10 000 resamples. For ECV and vECV, differences in area under the receiver operating characteristic curve (AUC) for discriminating hold-out test patients with normal cardiovascular magnetic resonance versus myocarditis or amyloidosis were tested with Delong's test. ECV and vECV showed a high agreement in patients with myocarditis (ΔECV: hold-out test, 2.0%±1.5%; external evaluation, 1.9%±1.7%) and normal cardiovascular magnetic resonance (ΔECV: hold-out test, 1.9%±1.4%; external evaluation, 1.5%±1.2%), but variations in amyloidosis were higher (ΔECV: hold-out test, 6.2%±6.0%; external evaluation, 15.5%±6.4%). In the hold-out test, ECV and vECV had a comparable AUC for the diagnosis of myocarditis (ECV AUC, 0.77 versus vECV AUC, 0.76; P=0.76) and amyloidosis (ECV AUC, 0.99 versus vECV AUC, 0.96; P=0.52). CONCLUSIONS: Generation of vECV on the basis of native T1 maps is feasible. Multicenter training data are required to further enhance generalizability of vECV in amyloidosis.

Forensic age estimation with ankle MRI: Evaluating distal tibial and calcaneal epiphyseal fusion.

Forensic authorities often request age estimation from forensic experts, particularly in cases related to sexual abuse, child pornography, illegal migration, marriage, etc. The most commonly used method in this regard is radiological methods. Because of the potential dangers of radiation exposure outside of clinical indications, new researches are focusing on non-ionizing and non-invasive technologies. This study aimed to demonstrate the applicability of age estimation in living individuals from ankle magnetic resonance images as a non-ionizing method, and to determine whether it is compatible with individuals' real ages and to establish a database. Ankle MRI images of patients aged between 7 and 26 years who applied to the Cukurova University Faculty of Medicine Balcali Hospital between January 2011 and December 2020 were retrospectively evaluated. A six-stage staging method proposed by Lu et al. was applied to the distal tibial and calcaneal epiphyseal ossification points by examining ankle MRI images of a total of 331 patients, 197 males and 134 females. In the study, images obtained from a sagittal section fast spin echo T1-weighted sequence, with a section thickness of 3-4 mm, were evaluated. As a result of the study, Stage 1 in both distal tibial and calcaneal epiphysis was observed only in patients under 18 years of age in both sex. In males, stage 2 in distal tibial epiphyseal ossification was observed under 18 years of age, except for one case, and stage 5 in both distal tibial and calcaneal epiphyseal ossification was observed in almost all cases over 18 years of age in males. According to the results of our study, magnetic resonance imaging was found to be a non-ionizing method that could be used in addition to other radiological methods aimed at determining the 18-year age limit in age estimation. Multicenter, comparative, and prospective studies conducted by experienced researchers are needed to enable the routine use of MRI in age estimation.

Compressed SENSE accelerated 3D single-breath-hold late gadolinium enhancement cardiovascular magnetic resonance with isotropic resolution: clinical evaluation.

Aim: The purpose of this study was to investigate the clinical application of Compressed SENSE accelerated single-breath-hold LGE with 3D isotropic resolution compared to conventional LGE imaging acquired in multiple breath-holds. Material & Methods: This was a retrospective, single-center study including 105 examinations of 101 patients (48.2 ± 16.8 years, 47 females). All patients underwent conventional breath-hold and 3D single-breath-hold (0.96 × 0.96 × 1.1 mm3 reconstructed voxel size, Compressed SENSE factor 6.5) LGE sequences at 1.5 T in clinical routine for the evaluation of ischemic or non-ischemic cardiomyopathies. Two radiologists independently evaluated the left ventricle (LV) for the presence of hyperenhancing lesions in each sequence, including localization and transmural extent, while assessing their scar edge sharpness (SES). Confidence of LGE assessment, image quality (IQ), and artifacts were also rated. The impact of LV ejection fraction (LVEF), heart rate, body mass index (BMI), and gender as possible confounders on IQ, artifacts, and confidence of LGE assessment was evaluated employing ordinal logistic regression analysis. Results: Using 3D single-breath-hold LGE readers detected more hyperenhancing lesions compared to conventional breath-hold LGE (n = 246 vs. n = 216 of 1,785 analyzed segments, 13.8% vs. 12.1%; p < 0.0001), pronounced at subendocardial, midmyocardial, and subepicardial localizations and for 1%-50% of transmural extent. SES was rated superior in 3D single-breath-hold LGE (4.1 ± 0.8 vs. 3.3 ± 0.8; p < 0.001). 3D single-breath-hold LGE yielded more artifacts (3.8 ± 1.0 vs. 4.0 ± 3.8; p = 0.002) whereas IQ (4.1 ± 1.0 vs. 4.2 ± 0.9; p = 0.122) and confidence of LGE assessment (4.3 ± 0.9 vs. 4.3 ± 0.8; p = 0.374) were comparable between both techniques. Female gender negatively influenced artifacts in 3D single-breath-hold LGE (p = 0.0028) while increased heart rate led to decreased IQ in conventional breath-hold LGE (p = 0.0029). Conclusions: In clinical routine, Compressed SENSE accelerated 3D single-breath-hold LGE yields image quality and confidence of LGE assessment comparable to conventional breath-hold LGE while providing improved delineation of smaller LGE lesions with superior scar edge sharpness. Given the fast acquisition of 3D single-breath-hold LGE, the technique holds potential to drastically reduce the examination time of CMR.