Prenatal magnetic resonance imaging detection of temporal lobes and hippocampal anomalies in hypochondroplasia.

Hypochondroplasia (HCH) is a genetic skeletal dysplasia, inherited in an autosomal dominant fashion. About 50-70% of HCH patients have a mutation in FGFR3 gene and in the majority of cases it is a de novo mutation. Recent magnetic resonance imaging studies on relative large cohorts of HCH patients have showed a central nervous system involvement with a high incidence of characteristic temporal lobe and hippocampal abnormalities. To the best of our knowledge, this report shows the first magnetic resonance imaging prenatal detection of characteristic brain anomalies in a case of HCH, molecularly confirmed through postnatal FGFR3 analysis.

Autoimmune pancreatitis: multidetector-row computed tomography (MDCT) and magnetic resonance (MR) findings in the Italian experience.

Multidetector-row computed tomography (MDCT) and magnetic resonance (MR) imaging are currently the most frequently performed imaging modalities for the study of pancreatic disease. In cases of suspected autoimmune pancreatitis (AIP), a dynamic quadriphasic (precontrast, contrast-enhanced pancreatic, venous and late phases) study is recommended in both techniques. In the diffuse form of autoimmune pancreatitis (DAIP), the pancreatic parenchyma shows diffuse enlargement and appears, during the MDCT and MR contrast-enhanced pancreatic phase, diffusely hypodense and hypointense, respectively, compared to the spleen because of lymphoplasmacytic infiltration and pancreatic fibrosis. During the venous phase of MDCT and MR imaging, the parenchyma appears hyperdense and hyperintense, respectively, in comparison to the pancreatic phase. In the delayed phase of both imaging modalities, it shows retention of contrast media. A "capsule-like rim" may be recognised as a peripancreatic MDCT hyperdense and MR hypointense halo in the T2-weighted images, compared to the parenchyma. DAIP must be differentiated from non-necrotizing acute pancreatitis (NNAP) and lymphoma since both diseases show diffuse enlargement of the pancreatic parenchyma. The differential diagnosis is clinically difficult, and dynamic contrast-enhanced MDCT has an important role. In the focal form of autoimmune pancreatitis (FAIP), the parenchyma shows segmental enlargement involving the head, the body-tail or the tail, with the same contrast pattern as the diffuse form on both modalities. FAIP needs to be differentiated from pancreatic adenocarcinoma to avoid unnecessary surgical procedures, since both diseases have similar clinical and imaging presentation. The differential diagnosis is clinically difficult, and dynamic contrast-enhanced MDCT and MR imaging both have an important role. MR cholangiopancreatography helps in the differential diagnosis. Furthermore, MDCT and MR imaging can identify the extrapancreatic manifestations of AIP, most commonly biliary, renal and retroperitoneal. Finally, in all cases of uncertain diagnosis, MDCT and/or MR follow-up after short-term treatment (2-3 weeks) with high-dose steroids can identify a significant reduction in size of the pancreatic parenchyma and, in FAIP, normalisation of the calibre of the upstream main pancreatic duct.

Co-ordinate-based positional embedding that captures resolution to enhance transformer's performance in medical image analysis.

Vision transformers (ViTs) have revolutionized computer vision by employing self-attention instead of convolutional neural networks and demonstrated success due to their ability to capture global dependencies and remove spatial biases of locality. In medical imaging, where input data may differ in size and resolution, existing architectures require resampling or resizing during pre-processing, leading to potential spatial resolution loss and information degradation. This study proposes a co-ordinate-based embedding that encodes the geometry of medical images, capturing physical co-ordinate and resolution information without the need for resampling or resizing. The effectiveness of the proposed embedding is demonstrated through experiments with UNETR and SwinUNETR models for infarct segmentation on MRI dataset with AxTrace and AxADC contrasts. The dataset consists of 1142 training, 133 validation and 143 test subjects. Both models with the addition of co-ordinate based positional embedding achieved substantial improvements in mean Dice score by 6.5% and 7.6%. The proposed embedding showcased a statistically significant advantage p-value< 0.0001 over alternative approaches. In conclusion, the proposed co-ordinate-based pixel-wise positional embedding method offers a promising solution for Transformer-based models in medical image analysis. It effectively leverages physical co-ordinate information to enhance performance without compromising spatial resolution and provides a foundation for future advancements in positional embedding techniques for medical applications.

Extended nnU-Net for Brain Metastasis Detection and Segmentation in Contrast-Enhanced Magnetic Resonance Imaging With a Large Multi-Institutional Data Set.

PURPOSE: The purpose of this study was to investigate an extended self-adapting nnU-Net framework for detecting and segmenting brain metastases (BM) on magnetic resonance imaging (MRI). METHODS AND MATERIALS: Six different nnU-Net systems with adaptive data sampling, adaptive Dice loss, or different patch/batch sizes were trained and tested for detecting and segmenting intraparenchymal BM with a size ≥2 mm on 3 Dimensional (3D) post-Gd T1-weighted MRI volumes using 2092 patients from 7 institutions (1712, 195, and 185 patients for training, validation, and testing, respectively). Gross tumor volumes of BM delineated by physicians for stereotactic radiosurgery were collected retrospectively and curated at each institute. Additional centralized data curation was carried out to create gross tumor volumes of uncontoured BM by 2 radiologists to improve the accuracy of ground truth. The training data set was augmented with synthetic BMs of 1025 MRI volumes using a 3D generative pipeline. BM detection was evaluated by lesion-level sensitivity and false-positive (FP) rate. BM segmentation was assessed by lesion-level Dice similarity coefficient, 95-percentile Hausdorff distance, and average Hausdorff distance (HD). The performances were assessed across different BM sizes. Additional testing was performed using a second data set of 206 patients. RESULTS: Of the 6 nnU-Net systems, the nnU-Net with adaptive Dice loss achieved the best detection and segmentation performance on the first testing data set. At an FP rate of 0.65 ± 1.17, overall sensitivity was 0.904 for all sizes of BM, 0.966 for BM ≥0.1 cm3, and 0.824 for BM <0.1 cm3. Mean values of Dice similarity coefficient, 95-percentile Hausdorff distance, and average HD of all detected BMs were 0.758, 1.45, and 0.23 mm, respectively. Performances on the second testing data set achieved a sensitivity of 0.907 at an FP rate of 0.57 ± 0.85 for all BM sizes, and an average HD of 0.33 mm for all detected BM. CONCLUSIONS: Our proposed extension of the self-configuring nnU-Net framework substantially improved small BM detection sensitivity while maintaining a controlled FP rate. Clinical utility of the extended nnU-Net model for assisting early BM detection and stereotactic radiosurgery planning will be investigated.

Magnetic resonance neurography of peroneal palsy in crossed-legs habit: case report.

"Drop foot" palsy attributed to the prolonged and repetitive maintenance of the crossed-leg posture has been occasionally reported. We report, to the best of our knowledge, the first case of magnetic resonance imaging evidence of peroneal nerve abnormalities related to right drop-foot palsy in a tall healthy subject with habit of prolonged daily leg crossing.

Artificial Intelligence with Statistical Confidence Scores for Detection of Acute or Subacute Hemorrhage on Noncontrast CT Head Scans.

Purpose: To present a method that automatically detects, subtypes, and locates acute or subacute intracranial hemorrhage (ICH) on noncontrast CT (NCCT) head scans; generates detection confidence scores to identify high-confidence data subsets with higher accuracy; and improves radiology worklist prioritization. Such scores may enable clinicians to better use artificial intelligence (AI) tools. Materials and Methods: This retrospective study included 46 057 studies from seven "internal" centers for development (training, architecture selection, hyperparameter tuning, and operating-point calibration; n = 25 946) and evaluation (n = 2947) and three "external" centers for calibration (n = 400) and evaluation (n = 16 764). Internal centers contributed developmental data, whereas external centers did not. Deep neural networks predicted the presence of ICH and subtypes (intraparenchymal, intraventricular, subarachnoid, subdural, and/or epidural hemorrhage) and segmentations per case. Two ICH confidence scores are discussed: a calibrated classifier entropy score and a Dempster-Shafer score. Evaluation was completed by using receiver operating characteristic curve analysis and report turnaround time (RTAT) modeling on the evaluation set and on confidence score-defined subsets using bootstrapping. Results: The areas under the receiver operating characteristic curve for ICH were 0.97 (0.97, 0.98) and 0.95 (0.94, 0.95) on internal and external center data, respectively. On 80% of the data stratified by calibrated classifier and Dempster-Shafer scores, the system improved the Youden indexes, increasing them from 0.84 to 0.93 (calibrated classifier) and from 0.84 to 0.92 (Dempster-Shafer) for internal centers and increasing them from 0.78 to 0.88 (calibrated classifier) and from 0.78 to 0.89 (Dempster-Shafer) for external centers (P < .001). Models estimated shorter RTAT for AI-prioritized worklists with confidence measures than for AI-prioritized worklists without confidence measures, shortening RTAT by 27% (calibrated classifier) and 27% (Dempster-Shafer) for internal centers and shortening RTAT by 25% (calibrated classifier) and 27% (Dempster-Shafer) for external centers (P < .001). Conclusion: AI that provided statistical confidence measures for ICH detection on NCCT scans reliably detected and subtyped hemorrhages, identified high-confidence predictions, and improved worklist prioritization in simulation.Keywords: CT, Head/Neck, Hemorrhage, Convolutional Neural Network (CNN) Supplemental material is available for this article. © RSNA, 2022.

Enhancing pancreatic adenocarcinoma delineation in diffusion derived intravoxel incoherent motion f-maps through automatic vessel and duct segmentation.

Diffusion-based intravoxel incoherent motion imaging has recently gained interest as a method to detect and characterize pancreatic lesions, especially as it could provide a radiation- and contrast agent-free alternative to existing diagnostic methods. However, tumor delineation on intravoxel incoherent motion-derived parameter maps is impeded by poor lesion-to-pancreatic duct contrast in the f-maps and poor lesion-to-vessel contrast in the D-maps. The distribution of the diffusion and perfusion parameters within vessels, ducts, and tumors were extracted from a group of 42 patients with pancreatic adenocarcinoma. Clearly separable combinations of f and D were observed, and receiver operating characteristic analysis was used to determine the optimal cutoff values for an automated segmentation of vessels and ducts to improve lesion detection and delineation on the individual intravoxel incoherent motion-derived maps. Receiver operating characteristic analysis identified f = 0.28 as the cutoff for vessels (Area under the curve (AUC) = 0.901) versus tumor/duct and D = 1.85 µm(2) /ms for separating duct from tumor tissue (AUC = 0.988). These values were incorporated in an automatic segmentation algorithm and then applied to 42 patients. This yielded clearly improved tumor delineation compared to individual intravoxel incoherent motion-derived maps. Furthermore, previous findings that indicated that the f value in pancreatic cancer is strongly reduced compared to healthy pancreatic tissue were reconfirmed.

Evaluating deep learning methods in detecting and segmenting different sizes of brain metastases on 3D post-contrast T1-weighted images.

Purpose: We investigate the impact of various deep-learning-based methods for detecting and segmenting metastases with different lesion volume sizes on 3D brain MR images. Approach: A 2.5D U-Net and a 3D U-Net were selected. We also evaluated weak learner fusion of the prediction features generated by the 2.5D and the 3D networks. A 3D fully convolutional one-stage (FCOS) detector was selected as a representative of bounding-box regression-based detection methods. A total of 422 3D post-contrast T1-weighted scans from patients with brain metastases were used. Performances were analyzed based on lesion volume, total metastatic volume per patient, and number of lesions per patient. Results: The performance of detection of the 2.5D and 3D U-Net methods had recall of > 0.83 and precision of > 0.44 for lesion volume > 0.3 cm 3 but deteriorated as metastasis size decreased below 0.3 cm 3 to 0.58 to 0.74 in recall and 0.16 to 0.25 in precision. Compared the two U-Nets for detection capability, high precision was achieved by the 2.5D network, but high recall was achieved by the 3D network for all lesion sizes. The weak learner fusion achieved a balanced performance between the 2.5D and 3D U-Nets; particularly, it increased precision to 0.83 for lesion volumes of 0.1 to 0.3 cm 3 but decreased recall to 0.59. The 3D FCOS detector did not outperform the U-Net methods in detecting either the small or large metastases presumably because of the limited data size. Conclusions: Our study provides the performances of four deep learning methods in relationship to lesion size, total metastasis volume, and number of lesions per patient, providing insight into further development of the deep learning networks.

Automated detection of critical findings in multi-parametric brain MRI using a system of 3D neural networks.

With the rapid growth and increasing use of brain MRI, there is an interest in automated image classification to aid human interpretation and improve workflow. We aimed to train a deep convolutional neural network and assess its performance in identifying abnormal brain MRIs and critical intracranial findings including acute infarction, acute hemorrhage and mass effect. A total of 13,215 clinical brain MRI studies were categorized to training (74%), validation (9%), internal testing (8%) and external testing (8%) datasets. Up to eight contrasts were included from each brain MRI and each image volume was reformatted to common resolution to accommodate for differences between scanners. Following reviewing the radiology reports, three neuroradiologists assigned each study to abnormal vs normal, and identified three critical findings including acute infarction, acute hemorrhage, and mass effect. A deep convolutional neural network was constructed by a combination of localization feature extraction (LFE) modules and global classifiers to identify the presence of 4 variables in brain MRIs including abnormal, acute infarction, acute hemorrhage and mass effect. Training, validation and testing sets were randomly defined on a patient basis. Training was performed on 9845 studies using balanced sampling to address class imbalance. Receiver operating characteristic (ROC) analysis was performed. The ROC analysis of our models for 1050 studies within our internal test data showed AUC/sensitivity/specificity of 0.91/83%/86% for normal versus abnormal brain MRI, 0.95/92%/88% for acute infarction, 0.90/89%/81% for acute hemorrhage, and 0.93/93%/85% for mass effect. For 1072 studies within our external test data, it showed AUC/sensitivity/specificity of 0.88/80%/80% for normal versus abnormal brain MRI, 0.97/90%/97% for acute infarction, 0.83/72%/88% for acute hemorrhage, and 0.87/79%/81% for mass effect. Our proposed deep convolutional network can accurately identify abnormal and critical intracranial findings on individual brain MRIs, while addressing the fact that some MR contrasts might not be available in individual studies.

Aceruloplasminemia: a novel mutation in a family with marked phenotypic variability.

Hereditary aceruloplasminemia (HA) is a rare inherited disease characterized by anemia, iron overload, diabetes, and neurodegeneration. HA is caused by the homozygous mutation of the ceruloplasmin (CP) gene. We report two siblings with markedly different phenotypes carrying a novel mutation: a homozygous deletion of two nucleotides (1257-1258 TT del) causing the premature stop of the Cp protein translation (Y401X). An early diagnosis of iron overload was made in the female sibling who was subsequently treated with deferoxamine. At the age of 54, her neurologic symptoms were limited to mild akinetic signs and a history of seizures; moreover, her fasting blood glucose level never exceeded 120 mg/dL. The male sibling, who had not received any specific treatment for HA, developed severe diabetes at the age of 32 and at 48 manifested a progressively disabling neurologic disease. Possible physiopathological bases of these intrafamilial phenotypic variations are discussed.