Refine
Has Fulltext
- yes (23)
Is part of the Bibliography
- yes (23)
Year of publication
- 2021 (23) (remove)
Document Type
- Journal article (21)
- Doctoral Thesis (1)
- Preprint (1)
Language
- English (23) (remove)
Keywords
- deep learning (3)
- CT angiography (2)
- MRI (2)
- stroke (2)
- 7 T (1)
- 7T (1)
- B (1)
- BM (1)
- CMR (1)
- CRC (1)
- CT perfusion (1)
- CT-angiography (1)
- CTNNB1 (1)
- Cushing’s disease (1)
- Cushing’s syndrome (1)
- Deep learning (1)
- EVT (1)
- Flow (1)
- Fluss (1)
- GCA (1)
- Heart (1)
- Herz (1)
- L-arginine (1)
- Lung (1)
- Lunge (1)
- Magnetresonanztomographie (1)
- Myocardial infarction (1)
- NIHSS (1)
- NR3C1 (1)
- PET (1)
- PLAG1 rearrangement (1)
- PMR (1)
- PTA (1)
- Primary hyperparathyroidism (pHPT) (1)
- Scar (1)
- Segmentation (1)
- USP8 (1)
- [18F]FDG PET/CT (1)
- [18F]FDG-PET-CT (1)
- abdominal lymph node metastases (1)
- aneurysmal subarachnoid hemorrhage (1)
- aneurysms (1)
- arthrography (1)
- brain metastases (1)
- cardiac MRI (1)
- cardiac function (1)
- cardiac magnetic resonance (1)
- case report (1)
- cerebral metastases (1)
- cold pressor test (1)
- color-coded (1)
- colorectal cancer (1)
- cone-beamcomputed tomography (1)
- convolutional neural networks (1)
- coracohumeral distance (1)
- coracohumeral impingement (1)
- diagnostics (1)
- digital subtraction angiography (1)
- dual-energy (1)
- embolism/thrombosis (1)
- endothelium (1)
- endovascular (1)
- endovascular therapy (1)
- extremities (1)
- fibroblast activation protein (1)
- fractures, bone (1)
- giant cell arteritis (1)
- glucocorticoid excess (1)
- head and neck cancer (1)
- hypercortisolism (1)
- image segmentation (1)
- imaging (1)
- immune check inhibitor (1)
- inflammation (1)
- joint instability (1)
- large vessel occlusion (1)
- late thrombectomy (1)
- lipoblastoma (1)
- lung (1)
- magnetic resonance imaging (1)
- medical research (1)
- meta-analysis (1)
- molecular diagnostics (1)
- molecular imaging (1)
- multiparametric CT (1)
- myocardial perfusion (1)
- neural networks (1)
- neurology (1)
- neuroradiology (1)
- neurosurgery (1)
- nnU-net (1)
- outcome (1)
- parathyroid carcinoma (1)
- pediatric (1)
- pembrolizumab (1)
- polymyalgia rheumatica (1)
- preclinical research (1)
- preoperative localization (1)
- pulmonary arteries (1)
- radiography (1)
- renal artery (1)
- repeat surgery (1)
- repeated surgery (1)
- retroperitoneal tumor (1)
- rotator cuff tear (1)
- segmentation (1)
- shimming (1)
- smoking (1)
- subscapularis tear (1)
- systematic review (1)
- transfer learning (1)
- triangular fibrocartilage (1)
- ultrahigh field (1)
- ultrahigh-field (1)
- vascular (1)
- vasculature (1)
- vasculitis (1)
- wrist (1)
Institute
- Institut für diagnostische und interventionelle Radiologie (Institut für Röntgendiagnostik) (23) (remove)
Purpose
Artificial neural networks show promising performance in automatic segmentation of cardiac MRI. However, training requires large amounts of annotated data and generalization to different vendors, field strengths, sequence parameters, and pathologies is limited. Transfer learning addresses this challenge, but specific recommendations regarding type and amount of data required is lacking. In this study, we assess data requirements for transfer learning to experimental cardiac MRI at 7T where the segmentation task can be challenging. In addition, we provide guidelines, tools, and annotated data to enable transfer learning approaches by other researchers and clinicians.
Methods
A publicly available segmentation model was used to annotate a publicly available data set. This labeled data set was subsequently used to train a neural network for segmentation of left ventricle and myocardium in cardiac cine MRI. The network is used as starting point for transfer learning to 7T cine data of healthy volunteers (n = 22; 7873 images) by updating the pre-trained weights. Structured and random data subsets of different sizes were used to systematically assess data requirements for successful transfer learning.
Results
Inconsistencies in the publically available data set were corrected, labels created, and a neural network trained. On 7T cardiac cine images the model pre-trained on public imaging data, acquired at 1.5T and 3T, achieved DICE\(_{LV}\) = 0.835 and DICE\(_{MY}\) = 0.670. Transfer learning using 7T cine data and ImageNet weight initialization improved model performance to DICE\(_{LV}\) = 0.900 and DICE\(_{MY}\) = 0.791. Using only end-systolic and end-diastolic images reduced training data by 90%, with no negative impact on segmentation performance (DICE\(_{LV}\) = 0.908, DICE\(_{MY}\) = 0.805).
Conclusions
This work demonstrates and quantifies the benefits of transfer learning for cardiac cine image segmentation. We provide practical guidelines for researchers planning transfer learning projects in cardiac MRI and make data, models, and code publicly available.
Purpose
To fully automatically derive quantitative parameters from late gadolinium enhancement (LGE) cardiac MR (CMR) in patients with myocardial infarction and to investigate if phase sensitive or magnitude reconstructions or a combination of both results in best segmentation accuracy.
Methods
In this retrospective single center study, a convolutional neural network with a U-Net architecture with a self-configuring framework (“nnU-net”) was trained for segmentation of left ventricular myocardium and infarct zone in LGE-CMR. A database of 170 examinations from 78 patients with history of myocardial infarction was assembled. Separate fitting of the model was performed, using phase sensitive inversion recovery, the magnitude reconstruction or both contrasts as input channels.
Manual labelling served as ground truth. In a subset of 10 patients, the performance of the trained models was evaluated and quantitatively compared by determination of the Sørensen-Dice similarity coefficient (DSC) and volumes of the infarct zone compared with the manual ground truth using Pearson’s r correlation and Bland-Altman analysis.
Results
The model achieved high similarity coefficients for myocardium and scar tissue. No significant difference was observed between using PSIR, magnitude reconstruction or both contrasts as input (PSIR and MAG; mean DSC: 0.83 ± 0.03 for myocardium and 0.72 ± 0.08 for scars). A strong correlation for volumes of infarct zone was observed between manual and model-based approach (r = 0.96), with a significant underestimation of the volumes obtained from the neural network.
Conclusion
The self-configuring nnU-net achieves predictions with strong agreement compared to manual segmentation, proving the potential as a promising tool to provide fully automatic quantitative evaluation of LGE-CMR.
Objectives
Trauma evaluation of extremities can be challenging in conventional radiography. A multi-use x-ray system with cone-beam CT (CBCT) option facilitates ancillary 3-D imaging without repositioning. We assessed the clinical value of CBCT scans by analyzing the influence of additional findings on therapy.
Methods
Ninety-two patients underwent radiography and subsequent CBCT imaging with the twin robotic scanner (76 wrist/hand/finger and 16 ankle/foot/toe trauma scans). Reports by on-call radiologists before and after CBCT were compared regarding fracture detection, joint affliction, comminuted injuries, and diagnostic confidence. An orthopedic surgeon recommended therapy based on reported findings. Surgical reports (N = 52) and clinical follow-up (N = 85) were used as reference standard.
Results
CBCT detected more fractures (83/64 of 85), joint involvements (69/53 of 71), and multi-fragment situations (68/50 of 70) than radiography (all p < 0.001). Six fractures suspected in radiographs were ruled out by CBCT. Treatment changes based on additional information from CBCT were recommended in 29 patients (31.5%). While agreement between advised therapy before CBCT and actual treatment was moderate (κ = 0.41 [95% confidence interval 0.35–0.47]; p < 0.001), agreement after CBCT was almost perfect (κ = 0.88 [0.83–0.93]; p < 0.001). Diagnostic confidence increased considerably for CBCT studies (p < 0.001). Median effective dose for CBCT was 4.3 μSv [3.3–5.3 μSv] compared to 0.2 μSv [0.1–0.2 μSv] for radiography.
Conclusions
CBCT provides advantages for the evaluation of acute small bone and joint trauma by detecting and excluding extremity fractures and fracture-related findings more reliably than radiographs. Additional findings induced therapy change in one third of patients, suggesting substantial clinical impact.
Parathyroid carcinoma (PC) is an orphan malignancy accounting for only ~1% of all cases with primary hyperparathyroidism. The localization of recurrent PC is of critical importance and can be exceedingly difficult to diagnose and sometimes futile when common sites of recurrence in the neck and chest cannot be confirmed. Here, we present the diagnostic workup, molecular analysis and multimodal therapy of a 46-year old woman with the extraordinary manifestation of abdominal lymph node metastases 12 years after primary diagnosis of PC. The patient was referred to our endocrine tumor center in 2016 with the aim to localize the tumor causative of symptomatic biochemical recurrence. In view of the extensive previous workup we decided to perform [18F]FDG-PET-CT. A pathological lymph node in the liver hilus showed slightly increased FDG-uptake and hence was suspected as site of recurrence. Selective venous sampling confirmed increased parathyroid hormone concentration in liver veins. Abdominal lymph node metastasis was resected and histopathological examination confirmed PC. Within four months, the patient experienced biochemical recurrence and based on high tumor mutational burden detected in the surgical specimen by whole exome sequencing the patient received immunotherapy with pembrolizumab that led to a biochemical response. Subsequent to disease progression repeated abdominal lymph node resection was performed in 10/2018, 01/2019 and in 01/2020. Up to now (12/2020) the patient is biochemically free of disease. In conclusion, a multimodal diagnostic approach and therapy in an interdisciplinary setting is needed for patients with rare endocrine tumors. Molecular analyses may inform additional treatment options including checkpoint inhibitors such as pembrolizumab.
Purpose
Repeat surgery in patients with primary hyperparathyroidism (pHPT) is associated with an increased risk of complications and failure. This stresses the need for optimized strategies to accurately localize a parathyroid adenoma before repeat surgery is performed. However, evidence on the extent of required diagnostics for a structured approach is sparse.
Methods
A retrospective single-center evaluation of 28 patients with an indication for surgery due to pHPT and previous thyroid or parathyroid surgery was performed. Diagnostic workup, surgical approach, and outcome in terms of complications and successful removement of parathyroid adenoma with biochemical cure were evaluated.
Results
Neck ultrasound, sestamibi scintigraphy, C11-methionine PET-CT, and selective parathyroid hormone venous sampling, but not MRI imaging, effectively detected the presence of a parathyroid adenoma with high positive predictive values. Biochemical cure was revealed by normalization of calcium and parathormone levels 24-48h after surgery and was achieved in 26/28 patients (92.9%) with an overall low rate of complications. Concordant localization by at least two diagnostic modalities enabled focused surgery with success rates of 100%, whereas inconclusive localization significantly increased the rate of bilateral explorations and significantly reduced the rate of biochemical cure to 80%.
Conclusion
These findings suggest that two concordant diagnostic modalities are sufficient to accurately localize parathyroid adenoma before repeat surgery for pHPT. In cases of poor localization, extended diagnostic procedures are warranted to enhance surgical success rates. We suggest an algorithm for better orientation when repeat surgery is intended in patients with pHPT.
Background
Lipoblastoma is a rare benign mesenchymal neoplasm of infancy that most commonly occurs on the extremities and trunk but can arise at variable sites of the body. Retroperitoneal lipoblastomas are particularly rare but can grow to enormous size, and preoperative diagnosis is difficult with diverse, mostly malignant differential diagnoses that would lead to aggressive therapy. Since lipoblastoma is a benign tumor that has an excellent prognosis after resection, correct diagnosis is crucial.
Case presentation
A case of a large retroperitoneal tumor of a 24-month old infant that was clinically suspicious of a malignant tumor is presented. Due to proximity to the right kidney, clinically most probably a nephroblastoma or clear cell sarcoma of the kidney was suspected. Radiological findings were ambiguous. Therefore, the mass was biopsied, and histology revealed an adipocytic lesion. Although mostly composed of mature adipocytes, in view of the age of the patient, the differential diagnosis of a (maturing) lipoblastoma was raised, which was supported by molecular analysis demonstrating a HAS2-PLAG1 fusion. The tumor was completely resected, and further histopathological workup led to the final diagnosis of a 13 cm large retroperitoneal maturing lipoblastoma. The child recovered promptly from surgery and showed no evidence of recurrence so far.
Conclusion
Although rare, lipoblastoma should be included in the differential diagnoses of retroperitoneal tumors in infants and children, and molecular diagnostic approaches could be a helpful diagnostic adjunct in challenging cases.
Background: Neurologic symptom severity and deterioration at 24 hours (h) predict long-term outcomes in patients with acute large vessel occlusion (LVO) stroke of the anterior circulation. We aimed to examine the association of baseline multiparametric CT imaging and clinical factors with the course of neurologic symptom severity in the first 24 h after endovascular treatment (EVT). Methods: Patients with LVO stroke of the anterior circulation were selected from a prospectively acquired consecutive cohort of patients who underwent multiparametric CT, including non-contrast CT, CT angiography and CT perfusion before EVT. The symptom severity was assessed on admission and after 24 h using the 42-point National Institutes of Health Stroke Scale (NIHSS). Clinical and imaging data were compared between patients with and without early neurological deterioration (END). END was defined as an increase in ≥4 points, and a significant clinical improvement as a decrease in ≥4 points, compared to NIHSS on admission. Multivariate regression analyses were used to determine independent associations of imaging and clinical parameters with NIHSS score increase or decrease in the first 24 h. Results: A total of 211 patients were included, of whom 38 (18.0%) had an END. END was significantly associated with occlusion of the internal carotid artery (odds ratio (OR), 4.25; 95% CI, 1.90–9.47) and the carotid T (OR, 6.34; 95% CI, 2.56–15.71), clot burden score (OR, 0.79; 95% CI, 0.68–0.92) and total ischemic volume (OR, 1.01; 95% CI, 1.00–1.01). In a comprehensive multivariate analysis model including periprocedural parameters and complications after EVT, carotid T occlusion remained independently associated with END, next to reperfusion status and intracranial hemorrhage. Favorable reperfusion status and small ischemic core volume were associated with clinical improvement after 24 h. Conclusions: The use of imaging parameters as a surrogate for early NIHSS progression in an acute LVO stroke after EVT reached limited performance with only carotid T occlusion as an independent predictor of END. Reperfusion status and early complications in terms of intracranial hemorrhage are critical factors that influence patient outcome in the acute stroke phase after EVT.
Background
Diagnosis of subscapularis (SSC) tendon lesions on magnetic resonance imaging (MRI) can be challenging. A small coracohumeral distance (CHD) has been associated with SSC tears. This study was designed to define a specific threshold value for CHD to predict SSC tears on axial MRI scans.
Methods
This retrospective study included 172 shoulders of 168 patients who underwent arthroscopic surgery for rotator cuff tear or glenohumeral instability. Diagnostic arthroscopy confirmed an SSC tear in 62 cases (36.0%, test group a), rotator cuff tear tears other than SSC in 71 cases (41.3%, control group b) and glenohumeral instability without any rotator cuff tear in 39 cases (22.7%, zero-sample group c). All patients had a preoperative MRI of the shoulder (1.5T or 3T). Minimum CHD was measured on axial fat-suppressed proton density-, T2-, or T1-weigthed sequences. Receiver operating characteristics analysis was used to determine the threshold value for CHD, and sensitivity and specificity were calculated.
Results
CHD measurement had a good interobserver reliability (Intraclass correlation coefficient 0.799). Mean CHD was highly significantly (P < .001) less for test group a (mean 7.3 mm, standard deviation ± 2.2) compared with control group b (mean 11.1 mm, standard deviation ± 2.3) or zero-sample group c (mean 13.6 mm, standard deviation ± 2.9). A threshold value of CHD <9.5 mm had a sensitivity of 83.6% and a specificity of 83.9% to predict SSC tears.
Conclusion
A CHD <9.5 mm on MRI is predictive of SSC lesions and a valuable tool to diagnose SSC tears.
Purpose
Inhomogeneities of the static magnetic B\(_{0}\) field are a major limiting factor in cardiac MRI at ultrahigh field (≥ 7T), as they result in signal loss and image distortions. Different magnetic susceptibilities of the myocardium and surrounding tissue in combination with cardiac motion lead to strong spatio‐temporal B\(_{0}\)‐field inhomogeneities, and their homogenization (B0 shimming) is a prerequisite. Limitations of state‐of‐the‐art shimming are described, regional B\(_{0}\) variations are measured, and a methodology for spherical harmonics shimming of the B\(_{0}\) field within the human myocardium is proposed.
Methods
The spatial B\(_{0}\)‐field distribution in the heart was analyzed as well as temporal B\(_{0}\)‐field variations in the myocardium over the cardiac cycle. Different shim region‐of‐interest selections were compared, and hardware limitations of spherical harmonics B\(_{0}\) shimming were evaluated by calibration‐based B0‐field modeling. The role of third‐order spherical harmonics terms was analyzed as well as potential benefits from cardiac phase–specific shimming.
Results
The strongest B\(_{0}\)‐field inhomogeneities were observed in localized spots within the left‐ventricular and right‐ventricular myocardium and varied between systolic and diastolic cardiac phases. An anatomy‐driven shim region‐of‐interest selection allowed for improved B\(_{0}\)‐field homogeneity compared with a standard shim region‐of‐interest cuboid. Third‐order spherical harmonics terms were demonstrated to be beneficial for shimming of these myocardial B\(_{0}\)‐field inhomogeneities. Initial results from the in vivo implementation of a potential shim strategy were obtained. Simulated cardiac phase–specific shimming was performed, and a shim term‐by‐term analysis revealed periodic variations of required currents.
Conclusion
Challenges in state‐of‐the‐art B\(_{0}\) shimming of the human heart at 7 T were described. Cardiac phase–specific shimming strategies were found to be superior to vendor‐supplied shimming.
Cone-beam computed tomography is a powerful tool for 3D imaging of the appendicular skeleton, facilitating detailed visualization of bone microarchitecture. This study evaluated various combinations of acquisition and reconstruction parameters for the cone-beam CT mode of a twin robotic x-ray system in cadaveric wrist and elbow scans, aiming to define the best possible trade-off between image quality and radiation dose. Images were acquired with different combinations of tube voltage and tube current–time product, resulting in five scan protocols with varying volume CT dose indices: full-dose (FD; 17.4 mGy), low-dose (LD; 4.5 mGy), ultra-low-dose (ULD; 1.15 mGy), modulated low-dose (mLD; 0.6 mGy) and modulated ultra-low-dose (mULD; 0.29 mGy). Each set of projection data was reconstructed with three convolution kernels (very sharp [Ur77], sharp [Br69], intermediate [Br62]). Five radiologists subjectively assessed the image quality of cortical bone, cancellous bone and soft tissue using seven-point scales. Irrespective of the reconstruction kernel, overall image quality of every FD, LD and ULD scan was deemed suitable for diagnostic use in contrast to mLD (very sharp/sharp/intermediate: 60/55/70%) and mULD (0/3/5%). Superior depiction of cortical and cancellous bone was achieved in FD\(_{Ur77}\) and LD\(_{Ur77}\) examinations (p < 0.001) with LD\(_{Ur77}\) scans also providing favorable bone visualization compared to FD\(_{Br69}\) and FD\(_{Br62}\) (p < 0.001). Fleiss’ kappa was 0.618 (0.594–0.641; p < 0.001), indicating substantial interrater reliability. In this study, we demonstrate that considerable dose reduction can be realized while maintaining diagnostic image quality in upper extremity joint scans with the cone-beam CT mode of a twin robotic x-ray system. Application of sharper convolution kernels for image reconstruction facilitates superior display of bone microarchitecture.