Iterative Motion Correction Technique with Deep Learning Reconstruction for Brain MRI: A Volunteer and Patient Study.

The aim of this study was to investigate the effect of iterative motion correction (IMC) on reducing artifacts in brain magnetic resonance imaging (MRI) with deep learning reconstruction (DLR). The study included 10 volunteers (between September 2023 and December 2023) and 30 patients (between June 2022 and July 2022) for quantitative and qualitative analyses, respectively. Volunteers were instructed to remain still during the first MRI with fluid-attenuated inversion recovery sequence (FLAIR) and to move during the second scan. IMCoff DLR images were reconstructed from the raw data of the former acquisition; IMCon and IMCoff DLR images were reconstructed from the latter acquisition. After registration of the motion images, the structural similarity index measure (SSIM) was calculated using motionless images as reference. For qualitative analyses, IMCon and IMCoff FLAIR DLR images of the patients were reconstructed and evaluated by three blinded readers in terms of motion artifacts, noise, and overall quality. SSIM for IMCon images was 0.952, higher than that for IMCoff images (0.949) (p < 0.001). In qualitative analyses, although noise in IMCon images was rated as increased by two of the three readers (both p < 0.001), all readers agreed that motion artifacts and overall quality were significantly better in IMCon images than in IMCoff images (all p < 0.001). In conclusion, IMC reduced motion artifacts in brain FLAIR DLR images while maintaining similarity to motionless images.

Super-resolution Deep Learning Reconstruction Cervical Spine 1.5T MRI: Improved Interobserver Agreement in Evaluations of Neuroforaminal Stenosis Compared to Conventional Deep Learning Reconstruction.

The aim of this study was to investigate whether super-resolution deep learning reconstruction (SR-DLR) is superior to conventional deep learning reconstruction (DLR) with respect to interobserver agreement in the evaluation of neuroforaminal stenosis using 1.5T cervical spine MRI. This retrospective study included 39 patients who underwent 1.5T cervical spine MRI. T2-weighted sagittal images were reconstructed with SR-DLR and DLR. Three blinded radiologists independently evaluated the images in terms of the degree of neuroforaminal stenosis, depictions of the vertebrae, spinal cord and neural foramina, sharpness, noise, artefacts and diagnostic acceptability. In quantitative image analyses, a fourth radiologist evaluated the signal-to-noise ratio (SNR) by placing a circular or ovoid region of interest on the spinal cord, and the edge slope based on a linear region of interest placed across the surface of the spinal cord. Interobserver agreement in the evaluations of neuroforaminal stenosis using SR-DLR and DLR was 0.422-0.571 and 0.410-0.542, respectively. The kappa values between reader 1 vs. reader 2 and reader 2 vs. reader 3 significantly differed. Two of the three readers rated depictions of the spinal cord, sharpness, and diagnostic acceptability as significantly better with SR-DLR than with DLR. Both SNR and edge slope (/mm) were also significantly better with SR-DLR (12.9 and 6031, respectively) than with DLR (11.5 and 3741, respectively) (p < 0.001 for both). In conclusion, compared to DLR, SR-DLR improved interobserver agreement in the evaluations of neuroforaminal stenosis using 1.5T cervical spine MRI.

The automatic diagnosis artificial intelligence system for preoperative magnetic resonance imaging of uterine sarcoma.

OBJECTIVE: Magnetic resonance imaging (MRI) is efficient for the diagnosis of preoperative uterine sarcoma; however, misdiagnoses may occur. In this study, we developed a new artificial intelligence (AI) system to overcome the limitations of requiring specialists to manually process datasets and a large amount of computer resources. METHODS: The AI system comprises a tumor image filter, which extracts MRI slices containing tumors, and sarcoma evaluator, which diagnoses uterine sarcomas. We used 15 types of MRI patient sequences to train deep neural network (DNN) models used by tumor filter and sarcoma evaluator with 8 cross-validation sets. We implemented tumor filter and sarcoma evaluator using ensemble prediction technique with 9 DNN models. Ten tumor filters and sarcoma evaluator sets were developed to evaluate fluctuation accuracy. Finally, AutoDiag-AI was used to evaluate the new validation dataset, including 8 cases of sarcomas and 24 leiomyomas. RESULTS: Tumor image filter and sarcoma evaluator accuracies were 92.68% and 90.50%, respectively. AutoDiag-AI with the original dataset accuracy was 89.32%, with 90.47% sensitivity and 88.95% specificity, whereas AutoDiag-AI with the new validation dataset accuracy was 92.44%, with 92.25% sensitivity and 92.50% specificity. CONCLUSION: Our newly established AI system automatically extracts tumor sites from MRI images and diagnoses them as uterine sarcomas without human intervention. Its accuracy is comparable to that of a radiologist. With further validation, the system could be applied for diagnosis of other diseases. Further improvement of the system's accuracy may enable its clinical application in the future.

White and Gray Matter Abnormality in Burning Mouth Syndrome Evaluated with Diffusion Tensor Imaging and Neurite Orientation Dispersion and Density Imaging.

PURPOSE: Burning mouth syndrome (BMS) is defined by a burning sensation or pain in the tongue or other oral sites despite the presence of normal mucosa on inspection. Both psychiatric and neuroimaging investigations have examined BMS; however, there have been no analyses using the neurite orientation dispersion and density imaging (NODDI) model, which provides detailed information of intra- and extracellular microstructures. Therefore, we performed voxel-wise analyses using both NODDI and diffusion tensor imaging (DTI) models and compared the results to better comprehend the pathology of BMS. METHODS: Fourteen patients with BMS and 11 age- and sex-matched healthy control subjects were prospectively scanned using a 3T-MRI machine using 2-shell diffusion imaging. Diffusion tensor metrics (fractional anisotropy [FA], mean diffusivity [MD], axial diffusivity [AD], and radial diffusivity [RD]) and neurite orientation and dispersion index metrics (intracellular volume fraction [ICVF], isotropic volume fraction [ISO], and orientation dispersion index [ODI]) were retrieved from diffusion MRI data. These data were analyzed using tract-based spatial statistics (TBSS) and gray matter-based spatial statistics (GBSS). RESULTS: TBSS analysis showed that patients with BMS had significantly higher FA and ICVF and lower MD and RD than the healthy control subjects (family-wise error [FWE] corrected P < 0.05). Changes in ICVF, MD, and RD were observed in widespread white matter areas. Fairly small areas with different FA were included. GBSS analysis showed that patients with BMS had significantly higher ISO and lower MD and RD than the healthy control subjects (FWE-corrected P < 0.05), mainly limited to the amygdala. CONCLUSION: The increased ICVF in the BMS group may represent myelination and/or astrocytic hypertrophy, and microstructural changes in the amygdala in GBSS analysis indicate the emotional-affective profile of BMS.

MR imaging features to predict the type of bone metastasis in prostate cancer.

Bone metastases (BMs) of prostate cancer (PCa) have been considered predominantly osteoblastic, but non-osteoblastic (osteolytic or mixed osteoblastic and osteolytic) BMs can occur. We investigated the differences in prostate MRI and clinical findings between patients with osteoblastic and non-osteoblastic BMs. Between 2014 and 2021, patients with pathologically proven PCa without a history of other malignancies were included in this study. Age, Gleason score, prostate-specific antigen (PSA) density, normalized mean apparent diffusion coefficient and normalized T2 signal intensity (nT2SI) of PCa, and Prostate Imaging Reporting and Data System category on MRI were compared between groups. A multivariate logistic regression analysis using factors with P-values < 0.2 was performed to detect the independent parameters for predicting non-osteoblastic BM group. Twenty-five (mean 73 ± 6.6 years) and seven (69 ± 13.1 years) patients were classified into the osteoblastic and non-osteoblastic groups, respectively. PSA density and nT2SI were significantly higher in the non-osteoblastic group than in the osteoblastic group. nT2SI was an independent predictive factor for non-osteoblastic BMs in the multivariate logistic regression analysis. These results indicated that PCa patients with high nT2SI and PSA density should be examined for osteolytic BMs.

Neuroimaging of hypophysitis: etiologies and imaging mimics.

Hypophysitis is an inflammatory disease affecting the pituitary gland. Hypophysitis can be classified into multiple types depending on the mechanisms (primary or secondary), histology (lymphocytic, granulomatous, xanthomatous, plasmacytic/IgG4 related, necrotizing, or mixed), and anatomy (adenohypophysitis, infundibulo-neurohypophysitis, or panhypophysitis). An appropriate diagnosis is vital for managing these potentially life-threatening conditions. However, physiological morphological alterations, remnants, and neoplastic and non-neoplastic lesions may masquerade as hypophysitis, both clinically and radiologically. Neuroimaging, as well as imaging findings of other sites of the body, plays a pivotal role in diagnosis. In this article, we will review the types of hypophysitis and summarize clinical and imaging features of both hypophysitis and its mimickers.

Computer-aided detection improves brain metastasis identification on non-enhanced CT in less experienced radiologists.

BACKGROUND: Brain metastases (BMs) are the most common intracranial tumors causing neurological complications associated with significant morbidity and mortality. PURPOSE: To evaluate the effect of computer-aided detection (CAD) on the performance of observers in detecting BMs on non-enhanced computed tomography (NECT). MATERIAL AND METHODS: Three less experienced and three experienced radiologists interpreted 30 NECT scans with 89 BMs in 25 cases to detect BMs with and without the assistance of CAD. The observers' sensitivity, number of false positives (FPs), positive predictive value (PPV), and reading time with and without CAD were compared using paired t-tests. The sensitivity of CAD and the observers were compared using a one-sample t-test. RESULTS: With CAD, less experienced radiologists' sensitivity significantly increased from 27.7% ± 4.6% to 32.6% ± 4.8% (P = 0.007), while the experienced radiologists' sensitivity did not show a significant difference (from 33.3% ± 3.5% to 31.9% ± 3.7%; P = 0.54). There was no significant difference between conditions with CAD and without CAD for FPs (less experienced radiologists: 23.0 ± 10.4 and 25.0 ± 9.3; P = 0.32; experienced radiologists: 18.3 ± 7.4 and 17.3 ± 6.7; P = 0.76) and PPVs (less experienced radiologists: 57.9% ± 8.3% and 50.9% ± 7.0%; P = 0.14; experienced radiologists: 61.8% ± 12.7% and 64.0% ± 12.1%; P = 0.69). There were no significant differences in reading time with and without CAD (85.0 ± 45.6 s and 73.7 ± 36.7 s; P = 0.09). The sensitivity of CAD was 47.2% (with a PPV of 8.9%), which was significantly higher than that of any radiologist (P < 0.001). CONCLUSION: CAD improved BM detection sensitivity on NECT without increasing FPs or reading time among less experienced radiologists, but this was not the case among experienced radiologists.

Osteolytic or mixed bone metastasis is not uncommon in patients with high-risk prostate cancer.

PURPOSE: Osteolytic or mixed bone metastases (BMs) are considered rare in prostate cancer (PCa). However, we hypothesized that they are not uncommon in high-risk PCa. This study aimed to compare the clinical and CT imaging characteristics of PCa by focusing on BMs among patients with Gleason score (GS) ≥ 8 (high-risk group) and those with GS ≤ 7 (intermediate-low-risk group). METHODS: Between 2014 and 2021, patients with pathologically proven PCa and no history of other malignancies were included. Clinical findings including age and prostate-specific antigen (PSA) were collected. CT imaging findings, including the types of BM and other metastases, were evaluated by two radiologists. The clinical and CT imaging findings were compared between the high- and intermediate-low-risk groups. RESULTS: Patients were classified into high-risk (n = 527) and intermediate-low-risk (n = 973) groups. Age at diagnosis (median: 71 [44-91] vs 69 [35-86] years, p < 0.0001), PSA (8.7 [0.01-15314.5] vs 5.8 [0.01-163.2] ng/mL, p < 0.0001), frequencies of BMs (osteoblastic: 47/527 [8.7%] vs 3/973 [0.3%]), osteolytic or mixed BM (19/527 [3.6%] vs 2/973 [0.2%]), lymph node metastases (76/527 [14.4%] vs 3/973 [0.3%]), and lung metastases (13/527 [2.5%] vs 0%) were significantly higher in the high-risk group than in the intermediate-low-risk group (all p < 0.0001). CONCLUSIONS: Age, PSA, and the frequencies of osteolytic or mixed BMs were significantly higher in the high-risk group than in the intermediate-low-risk group. This study highlights the importance of high-risk PCa in the differential diagnoses of osteolytic or mixed BMs.

Development of a deep learning method for improving diagnostic accuracy for uterine sarcoma cases.

Uterine sarcomas have very poor prognoses and are sometimes difficult to distinguish from uterine leiomyomas on preoperative examinations. Herein, we investigated whether deep neural network (DNN) models can improve the accuracy of preoperative MRI-based diagnosis in patients with uterine sarcomas. Fifteen sequences of MRI for patients (uterine sarcoma group: n = 63; uterine leiomyoma: n = 200) were used to train the models. Six radiologists (three specialists, three practitioners) interpreted the same images for validation. The most important individual sequences for diagnosis were axial T2-weighted imaging (T2WI), sagittal T2WI, and diffusion-weighted imaging. These sequences also represented the most accurate combination (accuracy: 91.3%), achieving diagnostic ability comparable to that of specialists (accuracy: 88.3%) and superior to that of practitioners (accuracy: 80.1%). Moreover, radiologists' diagnostic accuracy improved when provided with DNN results (specialists: 89.6%; practitioners: 92.3%). Our DNN models are valuable to improve diagnostic accuracy, especially in filling the gap of clinical skills between interpreters. This method can be a universal model for the use of deep learning in the diagnostic imaging of rare tumors.

The Usefulness of Computer-Aided Detection of Brain Metastases on Contrast-Enhanced Computed Tomography Using Single-Shot Multibox Detector: Observer Performance Study.

OBJECTIVE: This study aimed to test the usefulness of computer-aided detection (CAD) for the detection of brain metastasis (BM) on contrast-enhanced computed tomography. METHODS: The test data set included whole-brain axial contrast-enhanced computed tomography images of 25 cases with 62 BMs and 5 cases without BM. Six radiologists from 3 institutions with 2 to 4 years of experience independently reviewed the cases, both in conditions with and without CAD assistance. Sensitivity, positive predictive value, number of false positives, and reading time were compared between the conditions using paired t tests. Subanalysis was also performed for groups of lesions divided according to size. A P value <0.05 was considered statistically significant. RESULTS: With CAD, sensitivity significantly increased from 80.4% to 83.9% ( P = 0.04), whereas positive predictive value significantly decreased from 88.7% to 84.8% ( P = 0.03). Reading time with and without CAD was 112 and 107 seconds, respectively ( P = 0.38), and the number of false positives was 10.5 with CAD and 7.0 without CAD ( P = 0.053). Sensitivity significantly improved for 6- to 12-mm lesions, from 71.2% without CAD to 80.3% with CAD ( P = 0.02). The sensitivity of the CAD (95.2%) was significantly higher than that of any reader (with CAD: P = 0.01; without CAD: P = 0.005). CONCLUSIONS: Computer-aided detection significantly improved BM detection sensitivity without prolonging reading time while marginally increased the false positives.

Microstructural white matter abnormalities in multiple sclerosis and neuromyelitis optica spectrum disorders: Evaluation by advanced diffusion imaging.

INTRODUCTION: Despite differences in the pathogenesis and treatment of multiple sclerosis (MS) and neuromyelitis optica spectrum disorders (NMOSD), it remains difficult to distinguish them. In this study, we aimed to discriminate between MS and NMOSD using diffusion tensor imaging (DTI), free water (FW) imaging, and neurite orientation dispersion and density imaging (NODDI). METHODS: Thirty patients with relapsing-remitting (RR) MS, 18 NMOSD patients with positive anti-aquaporin-4 immunoglobulin G seroreactivity, and 20 age- and sex- matched currently healthy subjects underwent MRI. The differences in the DTI (fractional anisotropy [FA], axial diffusivity [AD], mean diffusivity [MD], and radial diffusivity [RD]), FW and FW-corrected DTI, and NODDI indices between the three groups were evaluated using tract-based spatial statistics (TBSS) and region-of-interest (ROI) analyses. RESULTS: The ROI analysis of lesions indicated that the RRMS group had significantly higher AD, MD, RD, ISO and FW-corrected AD, and MD; and lower intracellular volume fraction (ICVF) than the NMOSD group. TBSS analysis showed increased water content in RRMS patients compared to NMOSD patients. Compared with healthy controls (HCs) using TBSS and ROI analysis, the changes in FW imaging indices were more limited than those of in DTI in RRMS patients. CONCLUSION: FW imaging and NODDI were useful for identifying the etiology of neurodegeneration- and neuroinflammation-related microstructural changes in RRMS and NMOSD patients.

Multimodal magnetic resonance imaging quantification of gray matter alterations in relapsing-remitting multiple sclerosis and neuromyelitis optica spectrum disorder.

Herein, we combined neurite orientation dispersion and density imaging (NODDI) and synthetic magnetic resonance imaging (SyMRI) to evaluate the spatial distribution and extent of gray matter (GM) microstructural alterations in patients with relapsing-remitting multiple sclerosis (RRMS) and neuromyelitis optica spectrum disorder (NMOSD). The NODDI (neurite density index [NDI], orientation dispersion index [ODI], and isotropic volume fraction [ISOVF]) and SyMRI (myelin volume fraction [MVF]) measures were compared between age- and sex-matched groups of 30 patients with RRMS (6 males and 24 females; mean age, 51.43 ± 8.02 years), 18 patients with anti-aquaporin-4 antibody-positive NMOSD (2 males and 16 females; mean age, 52.67 ± 16.07 years), and 19 healthy controls (6 males and 13 females; mean age, 51.47 ± 9.25 years) using GM-based spatial statistical analysis. Patients with RRMS showed reduced NDI and MVF and increased ODI and ISOVF, predominantly in the limbic and paralimbic regions, when compared with healthy controls, while only increases in ODI and ISOVF were observed when compared with NMOSD. Compared to NDI and MVF, the changes in ODI and ISOVF were observed more widely, including in the cerebellar cortex. These abnormalities were associated with disease progression and disability. In contrast, patients with NMOSD only showed reduced NDI mainly in the cerebellar, limbic, and paralimbic cortices when compared with healthy controls and patients with RRMS. Taken together, our study supports the notion that GM pathologies in RRMS are distinct from those of NMOSD. However, owing to the limitations of the study, the results should be cautiously interpreted.

Radiomics with 3-dimensional magnetic resonance fingerprinting: influence of dictionary design on repeatability and reproducibility of radiomic features.

OBJECTIVES: We aimed to investigate the influence of magnetic resonance fingerprinting (MRF) dictionary design on radiomic features using in vivo human brain scans. METHODS: Scan-rescans of three-dimensional MRF and conventional T1-weighted imaging were performed on 21 healthy volunteers (9 males and 12 females; mean age, 41.3 ± 14.6 years; age range, 22-72 years). Five patients with multiple sclerosis (3 males and 2 females; mean age, 41.2 ± 7.3 years; age range, 32-53 years) were also included. MRF data were reconstructed using various dictionaries with different step sizes. First- and second-order radiomic features were extracted from each dataset. Intra-dictionary repeatability and inter-dictionary reproducibility were evaluated using intraclass correlation coefficients (ICCs). Features with ICCs > 0.90 were considered acceptable. Relative changes were calculated to assess inter-dictionary biases. RESULTS: The overall scan-rescan ICCs of MRF-based radiomics ranged from 0.86 to 0.95, depending on dictionary step size. No significant differences were observed in the overall scan-rescan repeatability of MRF-based radiomic features and conventional T1-weighted imaging (p = 1.00). Intra-dictionary repeatability was insensitive to dictionary step size differences. MRF-based radiomic features varied among dictionaries (overall ICC for inter-dictionary reproducibility, 0.62-0.99), especially when step sizes were large. First-order and gray level co-occurrence matrix features were the most reproducible feature classes among different step size dictionaries. T1 map-derived radiomic features provided higher repeatability and reproducibility among dictionaries than those obtained with T2 maps. CONCLUSION: MRF-based radiomic features are highly repeatable in various dictionary step sizes. Caution is warranted when performing MRF-based radiomics using datasets containing maps generated from different dictionaries. KEY POINTS: • MRF-based radiomic features are highly repeatable in various dictionary step sizes. • Use of different MRF dictionaries may result in variable radiomic features, even when the same MRF acquisition data are used. • Caution is needed when performing radiomic analysis using data reconstructed from different dictionaries.

Deep-learning 2.5-dimensional single-shot detector improves the performance of automated detection of brain metastases on contrast-enhanced CT.

PURPOSE: This study aims to develop a 2.5-dimensional (2.5D) deep-learning, object detection model for the automated detection of brain metastases, into which three consecutive slices were fed as the input for the prediction in the central slice, and to compare its performance with that of an ordinary 2-dimensional (2D) model. METHODS: We analyzed 696 brain metastases on 127 contrast-enhanced computed tomography (CT) scans from 127 patients with brain metastases. The scans were randomly divided into training (n = 79), validation (n = 18), and test (n = 30) datasets. Single-shot detector (SSD) models with a feature fusion module were constructed, trained, and compared using the lesion-based sensitivity, positive predictive value (PPV), and the number of false positives per patient at a confidence threshold of 50%. RESULTS: The 2.5D SSD model had a significantly higher PPV (t test, p < 0.001) and a significantly smaller number of false positives (t test, p < 0.001). The sensitivities of the 2D and 2.5D models were 88.1% (95% confidence interval [CI], 86.6-89.6%) and 88.7% (95% CI, 87.3-90.1%), respectively. The corresponding PPVs were 39.0% (95% CI, 36.5-41.4%) and 58.9% (95% CI, 55.2-62.7%), respectively. The numbers of false positives per patient were 11.9 (95% CI, 10.7-13.2) and 4.9 (95% CI, 4.2-5.7), respectively. CONCLUSION: Our results indicate that 2.5D deep-learning, object detection models, which use information about the continuity between adjacent slices, may reduce false positives and improve the performance of automated detection of brain metastases compared with ordinary 2D models.

Feature-fusion improves MRI single-shot deep learning detection of small brain metastases.

BACKGROUND AND PURPOSE: To examine whether feature-fusion (FF) method improves single-shot detector's (SSD's) detection of small brain metastases on contrast-enhanced (CE) T1-weighted MRI. METHODS: The study included 234 MRI scans from 234 patients (64.3 years±12.0; 126 men). The ground-truth annotation was performed semiautomatically. SSDs with and without an FF module were developed and trained using 178 scans. The detection performance was evaluated at the SSDs' 50% confidence threshold using sensitivity, positive-predictive value (PPV), and the false-positive (FP) per scan with the remaining 56 scans. RESULTS: FF-SSD achieved an overall sensitivity of 86.0% (95% confidence interval [CI]: [83.0%, 85.6%]; 196/228) and 46.8% PPV (95% CI: [42.0%, 46.3%]; 196/434), with 4.3 FP (95% CI: [4.3, 4.9]). Lesions smaller than 3 mm had 45.8% sensitivity (95% CI: [36.1%, 45.5%]; 22/48) with 2.0 FP (95% CI: [1.9, 2.1]). Lesions measuring 3-6 mm had 92.3% sensitivity (95% CI: [86.5%, 92.0%]; 48/52) with 1.8 FP (95% CI: [1.7, 2.2]). Lesions larger than 6 mm had 98.4% sensitivity (95% CI: [97.8%, 99.4%]; 126/128) 0.5 FP (95% CI: [0.5, 0.8]) per scan. FF-SSD had a significantly higher sensitivity for lesions < 3 mm (p = 0.008, t = 3.53) than the baseline SSD, while the overall PPV was similar (p = 0.06, t = -2.16). A similar trend was observed even when the detector's confidence threshold was varied as low as 0.2, for which the FF-SSD's sensitivity was 91.2% and the FP was 9.5. CONCLUSIONS: The FF-SSD algorithm identified brain metastases on CE T1-weighted MRI with high accuracy.

Deep-learning single-shot detector for automatic detection of brain metastases with the combined use of contrast-enhanced and non-enhanced computed tomography images.

PURPOSE: To develop a deep-learning object detection model for automatic detection of brain metastases that simultaneously uses contrast-enhanced and non-enhanced images as inputs, and to compare its performance with that of a model that uses only contrast-enhanced images. METHOD: A total of 116 computed tomography (CT) scans of 116 patients with brain metastases were included in this study. They showed a total of 659 metastases, 428 of which were used for training and validation (mean size, 11.3 ± 9.9 mm) and 231 were used for testing (mean size, 9.0 ± 7.0 mm). Single-shot detector (SSD) models were constructed with a feature fusion module, and their results were compared per lesion at a confidence threshold of 50%. RESULTS: The sensitivity was 88.7% for the model that used both contrast-enhanced and non-enhanced CT images (the CE + NECT model) and 87.6% for the model that used only contrast-enhanced CT images (the CECT model). The positive predictive value (PPV) was 44.0% for the CE + NECT model and 37.2% for the CECT model. The number of false positives per patient was 9.9 for the CE + NECT model and 13.6 for the CECT model. The CE + NECT model had a significantly higher PPV (t test, p < 0.001), significantly fewer false positives (t test, p < 0.001), and a tendency to be more sensitive (t test, p = 0.14). CONCLUSIONS: The results indicate that the information on true contrast enhancement obtained by comparing the contrast-enhanced and non-enhanced images may prevent the detection of pseudolesions, suppress false positives, and improve the performance of deep-learning object detection models.

Structural connectivity changes in the cerebral pain matrix in burning mouth syndrome: a multi-shell, multi-tissue-constrained spherical deconvolution model analysis.

PURPOSE: Burning mouth syndrome (BMS) is a chronic intraoral pain syndrome. Previous studies have attempted to determine the brain connectivity features in BMS using functional and structural magnetic resonance imaging. However, no study has investigated the structural connectivity using multi-shell, multi-tissue-constrained spherical deconvolution (MSMT-CSD), anatomically constrained tractography (ACT), and spherical deconvolution informed filtering of tractograms (SIFT). Therefore, this study aimed to assess the differences in brain structural connectivity of patients with BMS and healthy controls using probabilistic tractography with these methods, and graph analysis. METHODS: Fourteen patients with BMS and 11 age- and sex-matched healthy volunteers underwent 3-T magnetic resonance imaging. MSMT-CSD-based probabilistic structural connectivity was computed using the second-order integration over fiber orientation distributions algorithm based on nodes set in 84 anatomical cortical regions with ACT and SIFT. A t-test was performed for comparisons between the BMS and healthy control brain networks. RESULTS: The betweenness centrality was significantly higher in the left insula, right amygdala, and right lateral orbitofrontal cortex and significantly lower in the right inferotemporal cortex in the BMS group than that in healthy controls. However, no significant difference was found in the clustering coefficient, node degree, and small-worldness between the two groups. CONCLUSION: Graph analysis of brain probabilistic structural connectivity, based on diffusion imaging using an MSMT-CSD model with ACT and SIFT, revealed alterations in the regions comprising the pain matrix and medial pain ascending pathway. These results highlight the emotional-affective profile of BMS, which is a type of chronic pain syndrome.

Automated detection of brain metastases on non-enhanced CT using single-shot detectors.

PURPOSE: To develop and investigate deep learning-based detectors for brain metastases detection on non-enhanced (NE) CT. METHODS: The study included 116 NECTs from 116 patients (81 men, age 66.5 ± 10.6 years) to train and test single-shot detector (SSD) models using 89 and 27 cases, respectively. The annotation was performed by three radiologists using bounding-boxes defined on contrast-enhanced CT (CECT) images. NECTs were coregistered and resliced to CECTs. The detection performance was evaluated at the SSD's 50% confidence threshold using sensitivity, positive-predictive value (PPV), and the false-positive rate per scan (FPR). For false negatives and true positives, binary logistic regression was used to examine the possible contributing factors. RESULTS: For lesions 6 mm or larger, the SSD achieved a sensitivity of 35.4% (95% confidence interval (CI): [32.3%, 33.5%]); 51/144) with an FPR of 14.9 (95% CI [12.4, 13.9]). The overall sensitivity was 23.8% (95% CI: [21.3%, 22.8%]; 55/231) and PPV was 19.1% (95% CI: [18.5%, 20.4%]; 98/ of 513), with an FPR of 15.4 (95% CI [12.9, 14.5]). Ninety-five percent of the lesions that SSD failed to detect were also undetectable to radiologists (168/176). Twenty-four percent of the lesions (13/50) detected by the SSD were undetectable to radiologists. Logistic regression analysis indicated that density, necrosis, and size contributed to the lesions' visibility for radiologists, while for the SSD, the surrounding edema also enhanced the detection performance. CONCLUSION: The SSD model we developed could detect brain metastases larger than 6 mm to some extent, a quarter of which were even retrospectively unrecognizable to radiologists.

Differentiation between multiple sclerosis and neuromyelitis optica spectrum disorders by multiparametric quantitative MRI using convolutional neural network.

Multiple sclerosis and neuromyelitis optica spectrum disorders are both neuroinflammatory diseases and have overlapping clinical manifestations. We developed a convolutional neural network model that differentiates between the two based on magnetic resonance imaging data. Thirty-five patients with relapsing-remitting multiple sclerosis and eighteen age-, sex-, disease duration-, and Expanded Disease Status Scale-matched patients with anti-aquaporin-4 antibody-positive neuromyelitis optica spectrum disorders were included in this study. All patients were scanned on a 3-T scanner using a multi-dynamic multi-echo sequence that simultaneously measures R1 and R2 relaxation rates and proton density. R1, R2, and proton density maps were analyzed using our convolutional neural network model. To avoid overfitting on a small dataset, we aimed to separate features of images into those specific to an image and those common to the group, based on SqueezeNet. We used only common features for classification. Leave-one-out cross validation was performed to evaluate the performance of the model. The area under the receiver operating characteristic curve of the developed convolutional neural network model for differentiating between the two disorders was 0.859. The sensitivity to multiple sclerosis and neuromyelitis optica spectrum disorders, and accuracy were 80.0%, 83.3%, and 81.1%, respectively. In conclusion, we developed a convolutional neural network model that differentiates between multiple sclerosis and neuromyelitis optica spectrum disorders, and which is designed to avoid overfitting on small training datasets. Our proposed algorithm may facilitate a differential diagnosis of these diseases in clinical practice.

Automatic detection of brain metastases on contrast-enhanced CT with deep-learning feature-fused single-shot detectors.

PURPOSE: Despite the potential usefulness, no automatic detector is available for brain metastases on contrast-enhanced CT (CECT). The study aims to develop and investigate deep learning-based detectors for brain metastases detection on CECT. METHOD: The study included 127 CECTs from 127 patients (65.5 years±11.1; 87 men). The ground-truth annotation was performed semi-automatically by applying connected-component analysis to the binarized dataset by three radiologists. Single-shot detector (SSD) algorithms, with and without a feature-fusion module, were developed and trained using 97 scans. The performance was evaluated at the detector's 50 % confidence threshold with the remaining 30 scans using sensitivity, positive-predictive value (PPV), and the false-positive rate per scan (FPR). RESULTS: Feature-fused SSD achieved an overall sensitivity of 88.1 % (95 % confidence interval [CI]: [85.2 %,88.6 %]; 214/243) and PPV of 36.0 % (95 % CI: [33.7 %,37.1 %]; 233/648), with 13.8 FPR (95 % CI: [12.7,15.0]). Lesions < 3 mm had a sensitivity of 23.1 % (95 % CI: [21.2 %,40.0 %]; 3/13), with 0.2 FPR (95 % CI: [0.23,0.65]). Lesions measuring 3-6 mm had a sensitivity of 80.0 % (95 % CI: [76.0 %,79.8 %]); 60/75) with 5.8 FPR (95 % CI: [5.0,6.2]). Lesions > 6 mm had a sensitivity of 97.4 % (95 % CI: [94.1 %,97.4 %]); 151/155) with 7.9 FPR (95 % CI: [7.2,8.5]). Feature-fused SSD had a significantly higher overall sensitivity (p = 0.03, t = 2.75) or sensitivity for lesions < 3 mm (p = 0.002, t = 4.49) than baseline SSD, while the overall PPV was similar (p = 0.96, t = -0.02). CONCLUSIONS: The SSD algorithm identified brain metastases on CECT with reasonable accuracy for lesions > 3 mm without pre/post-processing.