A Sensing-Based Visualization Method for Representing Pressure Distribution in a Multi-Zone Building by Floor.

Airflow in a multi-zone building can be a major cause of pollutant transfer, excessive energy consumption, and occupants discomfort. The key to monitoring airflows and mitigating related problems is to obtain a comprehensive understanding of pressure relationships within the buildings. This study proposes a visualization method for representing pressure distribution within a multi-zone building by using a novel pressure-sensing system. The system consists of a Master device and a couple of Slave devices that are connected with each other by a wireless sensor network. A 4-story office building and a 49-story residential building were installed with the system to detect pressure variations. The spatial and numerical mapping relationships of each zone were further determined through grid-forming and coordinate-establishing processes for the building floor plan. Lastly, 2D and 3D visualized pressure mappings of each floor were generated, illustrating the pressure difference and spatial relationship between adjacent zones. It is expected that the pressure mappings derived from this study will allow building operators to intuitively perceive the pressure variations and the spatial layouts of the zones. These mappings also make it possible for operators to diagnose the differences in pressure conditions between adjacent zones and plan a control scheme for the HVAC system more efficiently.

Novel Approaches to Detection of Cerebral Microbleeds: Single Deep Learning Model to Achieve a Balanced Performance.

PURPOSE: Cerebral microbleeds (CMBs) are considered essential indicators for the diagnosis of cerebrovascular disease and cognitive disorders. Traditionally, CMBs are manually interpreted based on criteria including the shape, diameter, and signal characteristics after an MR examination, such as susceptibility-weighted imaging or gradient echo imaging (GRE). In this paper, an efficient method for CMB detection in GRE scans is presented. MATERIALS AND METHODS: The proposed framework consists of the following phases: (1) pre-processing (skull extraction), (2) the first training with the ground truth labeled using CMB, (3) the second training with the ground truth labeled with CMB mimicking the same subjects, and (4) post-processing (cerebrospinal fluid (CSF) filtering). The proposed technique was validated on a dataset of 1133 CBMs that consisted of 5284 images for training and 1737 images for testing. We applied a two-stage approach using a region-based CNN method based on You Only Look Once (YOLO) to investigate a novel CMB detection technique. RESULTS: The sensitivity, precision, F1-score and false positive per person (FPavg) were evaluated as 80.96, 60.98, 69.57 and 6.57, 59.69, 62.70, 61.16 and 4.5, 66.90, 79.75, 72.76 and 2.15 for YOLO with a single label, YOLO with double labels, and YOLO + CSF filtering, respectively, and YOLO + CSF filtering showed the highest precision performance, F1-score and lowest FPavg. CONCLUSIONS: Using proposed framework, we developed an optimized CMB learning model with low false positives and a balanced performance in clinical practice.

Atherosclerotic plaque locations may be related to different ischemic lesion patterns.

BACKGROUND: Atherosclerosis of the internal carotid artery (ICA) is an important cause of ischemic stroke. Artery-to-artery embolism is the major stroke mechanism in patients with atherosclerotic carotid disease. This study hypothesized that the atherosclerotic ICA geometry and plaque location would be associated with lesion pattern in patients with acute ischemic stroke. METHODS: Ischemic stroke patients with symptomatic proximal ICA disease (> 50% diameter stenosis) were enrolled. The carotid plaque location was divided into high-apical and low-body types. The geometric parameters of the ICA (angles between arteries) were measured, and ischemic lesion patterns were classified according to the number, location, and size of the lesions. Factors associated with plaque location and lesion pattern, dichotomized by size, were investigated. RESULTS: Of the 93 acute ischemic stroke patients enrolled, 31 had high-apical and 62 had low-body plaques. Hyperlipidemia was more prevalent and the common carotid artery (CCA)-ICA angle was wider (167.7 ± 10.4° vs 162.3 ± 9.8°, p = 0.019) in patients with low-body than high-apical plaques. Low-body plaques were more frequently associated with small scattered or cortical lesions (54.8% vs. 32.3%, p = 0.040), whereas high-apical plaques were more frequently associated with large lesions having additional lesions (38.7% vs. 11.3%, p = 0.002). The presence of low-body plaques (odds ratio: 3.106, 95% confidence interval: 1.105-8.728, p = 0.032) was independently associated with the small lesion-only pattern. CONCLUSIONS: Low-body plaques are more frequently associated with small scattered lesions, whereas high-apical plaques are more frequently associated with large lesions having additional lesions. A wide CCA-ICA angle is associated with low-body plaque of the carotid artery.

Comparison of Computed Tomography, Magnetic Resonance Imaging, and Positron Emission Tomography and Computed Tomography for the Evaluation Bone Invasion in Upper and Lower Gingival Cancers.

PURPOSE: Preoperative detection of bone invasion is important in cases of gingival cancer. The aim of this study was to compare the diagnostic value of 3 imaging methods for the detection of bone invasion in upper and lower gingival cancer: computed tomography (CT), magnetic resonance imaging (MRI), and positron emission tomography (PET) and CT. MATERIALS AND METHODS: This retrospective cohort study enrolled patients who underwent a maxillectomy or a mandibulectomy for gingival cancer. Each preoperative image (CT, MRI, or PET/CT) was reviewed for the presence of bone invasion, and the possibility for bone invasion was graded. These results were verified with pathology reports. Sensitivity, specificity, positive predictive value, and negative predictive value for the detection of mandibular involvement in alveolar bone were calculated, and a receiver operating characteristics (ROC) curve analysis was performed. RESULTS: Forty patients (27 men and 13 women) were enrolled. Pathologic examination disclosed bone invasion in 25 of the 40 patients. Of these patients, 13 had maxillary and 12 had mandibular alveolus involvement. The diagnostic accuracy of CT (90.0%) was highest among the 3 modalities for the detection of bone invasion. In the ROC curve analysis, values for the area under the curve for upper gingival cancer were lower than those for lower gingival cancer. CONCLUSIONS: The 3 imaging methods were less sensitive for the detection of bone invasion in upper gingival cancer than in lower gingival cancer. Cases of upper gingival cancer should be evaluated more carefully for bone invasion before surgery.

Ultrasonographic features associated with false-negative and false-positive results of extrathyroidal extensions in papillary thyroid microcarcinoma.

PURPOSE: To assess the ultrasonographic features affect accuracy of extrathyroid extension (ETE) evaluation on preoperative ultrasonography (US) in papillary thyroid microcarcinoma (PTMC). METHODS: Of the total patients who underwent thyroid surgery, 516 patients with a tumor measuring less than 1 cm on preoperative US were enrolled in this study. One blinded head and neck radiologist reviewed the preoperative US images to evaluate the US features of PTMC, and the pathologic reports were reviewed. The diagnostic accuracy rates, including sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy, were calculated, and the factors associated with false-negative and false-positive results for ETE were analyzed. RESULTS: The sensitivity, specificity, PPV, NPV, and accuracy for predicting ETE according to sonographic criteria were 32.8%, 87.5%, 51.0%, 76.6%, and 71.7%, respectively. Non-adjacent to the trachea and unilateral lesion on US were significant factors associated with false-negative results. CONCLUSION: Size, shape, and location of PTMC on US are important factors that affect the US results in ETE evaluation.

Usefulness of contrast-enhanced 3-dimensional T1-VISTA in the diagnosis of facial neuritis: comparison with contrast-enhanced T1-TSE.

BACKGROUND AND PURPOSE: Compared with 2-dimensional imaging, 3D-reformatted imaging is a valuable technique that offers improved anatomic accuracy with minimal flow artifact and thinner sections without gaps between slices. Our aim was to evaluate the usefulness of CE 3D T1-VISTA with fat suppression sequences compared with CE T1-TSE with fat suppression sequences in patients with facial neuritis. MATERIAL AND METHODS: The study enrolled 32 consecutive patients who underwent IAC MR imaging for Bell's palsy. IAC MR scanning, including CE T1-VISTA and CE T1-TSE, was performed in all patients using a 3T scanner. The order of the scans was random. Signal intensity was measured at three segments (canalicular, labyrinthine, and anterior genu) of the facial nerve by drawing a ROI along the affected side and the normal side in each segment. We compared the quantitative CR of the two MR sequences with paired t-tests. RESULTS: In all three segments, the lesion-to-normal contrast ratios on CE 3D T1-VISTA (canalicular: 2.32; labyrinthine: 2.22; anterior genu: 1.97) were greater than those on CE T1-TSE (canalicular: 2.17; labyrinthine: 1.72; anterior genu: 1.68). The labyrinthine and anterior genu segments had significantly higher lesion-to-normal contrast ratios on CE 3D T1-VISTA in patients with facial neuritis (labyrinthine: P<0.001; anterior genu: P=0.002). CONCLUSION: CE 3D T1-VISTA was superior to CE T1-TSE in terms of image contrast between lesions and the normal facial nerve.

Intrathyroidal parathyroid carcinoma mimicking a thyroid nodule in a MEN type 1 patient.

A 59-year-old woman with classic manifestations of hyperparathyroidism associated with multiple endocrine neoplasia type 1 presented with a right adrenal mass and two pituitary microadenomas on imaging studies. For evaluation of hypercalcemia, (99m) Tc-MIBI scintigraphy was done and showed focal uptake at the thyroid level of the right anterior neck. Subsequent neck sonography showed several thyroid nodules, but there was no parathyroid tumor. Percutaneous fine-needle aspiration of the dominant thyroid nodule indicated a follicular nodule. After surgery, final histopathology revealed intrathyroidal parathyroid carcinoma. This case illustrates the difficulty in diagnosing parathyroid carcinoma via fine-needle aspiration.

Regional cerebral perfusion in patients with Alzheimer's disease and mild cognitive impairment: effect of APOE epsilon4 allele.

INTRODUCTION: The objective of this study was to evaluate the effect of apolipoprotein E (APOE) epsilon 4 allele on regional cerebral perfusion (rCBF) changes using arterial spin labeling (ASL) magnetic resonance imaging (MRI) in subjects who are carriers or noncarriers of this risk factor for Alzheimer disease (AD). METHODS: Twenty-five subjects with AD, 25 with amnestic mild cognitive impairment (MCI) and 25 cognitively normal (CN) subjects underwent isotropic volumetric T1-weighted imaging and pulsed ASL MRI. All subjects were divided into carrier or noncarriers of the epsilon4 allele. Voxel-based statistical analyses were performed among groups on rCBF by ANOVA tests. In each subject group, we also evaluated the rCBF change between carrier and noncarrier groups. RESULTS: rCBF was significantly reduced in AD subjects compared to other subjects. In CN and AD subjects, rCBF in the carrier group was significantly reduced in several areas of the brain compared with that of the noncarrier group. In the carrier group, rCBF was significantly increased in the right parahippocampal gyrus, the bilateral cingulate gyri and the right posterior cingulate on the MCI group in addition to the right superior frontal gyrus in the AD group. CONCLUSION: rCBF in the CN and AD groups were significantly reduced in the subjects with the carriers of the epsilon4 allele, which is a risk factor for Alzheimer's disease. In addition, rCBF in the MCI group was significantly increased in subjects who were carriers. Therefore, rCBF can be used as a biomarker to show disease progression in areas of the brain of MCI subjects.

Microstructural change of the brain in chronic obstructive pulmonary disease: a voxel-based investigation by MRI.

BACKGROUND: Cognitive deficit is a common problem in patients with chronic obstructive pulmonary disease (COPD). The aim of this study was to prospectively evaluate if MRI can demonstrate microstructural volume loss and the diffusion anisotropic change in subjects with COPD, compared with cognitively normal (CN) subjects. METHODS: Six subjects with severe COPD, 13 with moderate COPD, and 12 CN subjects underwent isotropic volumetric T1-weighted imaging and diffusion tensor imaging (DTI). Voxel-based statistical analyses among groups were performed on brain volumes, fractional anisotropy (FA) and trace. Cognitive function tests were performed in all subjects, and the Cognitive function tests (CFT) scores were compared among the three groups. RESULTS: No significant regional difference in volume was found in both the severe and moderate COPD groups relative to the CN group. Comparing between severe COPD and CN, FA was reduced in both the cerebral cortices, and in frontoparietal periventricular white matter. The trace value of the severe COPD group was significantly higher in the cerebral cortices, and in frontoparietal periventricular white matter, than that of the CN group. The severe COPD group showed significantly lower scores in the language-related, visuospatial, and frontal executive functions compared to those of the CN and moderate COPD group. CONCLUSION: This study demonstrated that COPD could affect the axonal integrity in multiple brain regions, and change in DTI might be related with the severity of the COPD.

Excessive Postoperative Nasal Bleeding Following Septoplasty Caused by a Branch of the Middle Meningeal Artery.

Septoplasty is a widely performed procedure globally to correct a deviated nasal septum and improve nasal breathing. Life-threatening nasal bleeding as a complication of septoplasty has been reported in a few cases in the literature. In cases of massive postoperative nasal bleeding, transarterial embolization using angiography was performed for the treatment. This article documents 1 case of excessive postoperative nasal bleeding following an uneventful septoplasty, which was successfully treated with embolization of the frontal branch of the middle meningeal artery. This case represents an extremely rare occurrence, and we present it in conjunction with a literature review.

Comparison of Safety and Diagnostic Efficacy of Iohexol 240 mgI/mL, Iopamidol 250 mgI/mL, and Iodixanol 270 mgI/mL in Cerebral Angiography: A Prospective, Multicenter Study.

PURPOSE: This multicenter prospective study aimed to evaluate the quality and diagnostic effectiveness of cerebral angiography images obtained using low-concentration iodinated contrast agents (iohexol 240 mgI/mL, iopamidol 250 mgI/mL, and iodixanol 270 mgI/mL) and to assess the safety thereof. The study addresses the need for safer contrast agent alternatives without compromising the diagnostic quality of identifying cerebrovascular disease. MATERIALS AND METHODS: Conducted in 5 medical centers in South Korea, we enrolled patients aged 19 years or older who were referred for diagnostic cerebral angiography under non-emergency conditions, excluding those with specific health conditions and sensitivities. The study design included a prospective, observational approach with a 1-way analysis of variance (ANOVA) for sample size calculation, aiming for a total sample of 231 participants for adequate power. Image quality was evaluated using a 4-level scale by 2 independent, blinded radiologists, and adverse reactions were monitored both immediately and up to 7 days post-procedure. Statistical analysis involved 1-way ANOVA and Kruskal-Wallis tests to assess the image quality and safety profiles of the contrast agents. RESULTS: Among 266 patients screened, 243 were included in the final analysis. The evaluation revealed no statistically significant differences in image quality among the 3 types of low-concentration contrast agents. Adverse events were observed in 28.8% of patients, with 27.2% experiencing acute reactions, primarily mild reactions, and 3.3% experiencing delayed reactions. The overall safety profile showed no significant changes in vital signs or electrocardiogram readings before and after contrast agent injection. CONCLUSION: Using low-concentration iodinated contrast agents for cerebral angiography provides image quality comparable to that of conventional high-concentration agents, with no significant increase in adverse events, suggesting a safer alternative for patients.

Diagnostic Performance of High-Resolution Vessel Wall Magnetic Resonance Imaging and Digital Subtraction Angiography in Intracranial Vertebral Artery Dissection.

PURPOSE: Intracranial vertebral artery dissection (VAD) is being increasingly recognized as a leading cause of Wallenberg syndrome and subarachnoid hemorrhage. Conventional angiography is considered the standard diagnostic modality, but the diagnosis of VAD remains challenging. This study aimed to compare the diagnostic performance of high-resolution vessel wall imaging (HR-VWI) with digital subtraction angiography (DSA) for intracranial VAD. MATERIALS AND METHODS: Twenty-four patients with 27 VADs, who underwent both HR-VWI and DSA within 2 weeks, were consecutively enrolled in the study from March 2016 to September 2020. HR-VWI and DSA were performed to diagnose VAD and to categorize its angiographic features as either definite dissection or suspicious dissection. Features of HR-VWI were used to evaluate direct arterial wall imaging. The reference standard was set from the clinicoradiologic diagnosis. Two independent raters evaluated the angiographic features, dissection signs, and interrater agreement. Each subject was also dichotomized into two groups (suspicious or definite VAD) in each modality, and diagnosis from HR-VWI and DSA was compared with the final diagnosis by consensus. RESULTS: HR-VWI had higher agreement (90.6% vs. 53.1%) with the final diagnosis and better interrater reliability (kappa value (κ) = 0.91; 95% confidence interval (CI) = 0.64-1.00) compared with DSA (κ = 0.58; 95% CI = 0.35-1.00). HR-VWI provided a more detailed identification of dissection signs (77.7% vs. 22.2%) and better reliability (κ = 0.88; 95% CI = 0.58-1.00 vs. κ = 0.75; 95% CI = 0.36-1.00), compared to DSA. HR-VWI was comparable to DSA for the depiction of angiographic features for VAD. CONCLUSIONS: HR-VWI may be useful to evaluate VAD, with better diagnostic confidence compared to DSA.

Deep learning-based detection algorithm for brain metastases on black blood imaging.

Brain metastases (BM) are the most common intracranial tumors, and their prevalence is increasing. High-resolution black-blood (BB) imaging was used to complement the conventional contrast-enhanced 3D gradient-echo imaging to detect BM. In this study, we propose an efficient deep learning algorithm (DLA) for BM detection in BB imaging with contrast enhancement scans, and assess the efficacy of an automatic detection algorithm for BM. A total of 113 BM participants with 585 metastases were included in the training cohort for five-fold cross-validation. The You Only Look Once (YOLO) V2 network was trained with 3D BB sampling perfection with application-optimized contrasts using different flip angle evolution (SPACE) images to investigate the BM detection. For the observer performance, two board-certified radiologists and two second-year radiology residents detected the BM and recorded the reading time. For the training cohort, the overall performance of the five-fold cross-validation was 87.95%, 24.82%, 19.35%, 14.48, and 18.40 for sensitivity, precision, F1-Score, the false positive average for the BM dataset, and the false positive average for the normal individual dataset, respectively. For the comparison of reading time with and without DLA, the average reading time was reduced by 20.86% in the range of 15.22-25.77%. The proposed method has the potential to detect BM with a high sensitivity and has a limited number of false positives using BB imaging.

Analysis of aneurysm rupture in relation to the geometric indices: aspect ratio, volume, and volume-to-neck ratio.

INTRODUCTION: Geometric indices of cerebral aneurysms have been widely studied to determine rupture risk. However, most of these parameters were evaluated based on two-dimensional (2D) images and could have a measurement bias. We propose a new three-dimensional geometric index, an aneurysm volume-to-neck area ratio (VNR). To determine whether the VNR of ruptured aneurysms is different from that of unruptured aneurysms, we compared VNR with other 2D geometric indices in discriminative capacity for aneurysm rupture status. METHODS: Two hundred fourteen aneurysms in 195 patients (mean age, 57.44 ± 11.21 years; males, 69; females, 126) were retrospectively evaluated. There were 105 ruptured and 109 unruptured aneurysms. The five geometric indices [aspect ratio (AR), bottleneck ratio (BR), height-width ratio (HWR), volume, and VNR] were calculated from angiographic data and assessed to determine correlation with aneurysm rupture (t test). Receiver operating characteristic (ROC) curve analysis was used for comparison of discriminative capacity between different indices. RESULTS: AR, BR, HWR, and VNR were correlated with rupture status. Areas under the ROC curve of the aspect ratio and VNR were significantly larger than that of the HWR, BR, and volume. However, AR and VNR did not show a significant difference. CONCLUSION: A larger aneurysm volume in proportion to the neck could be one of the geometric indices of aneurysms that indicate a higher rupture risk. This characteristic is represented by the aspect ratio.

A systematically designed study to investigate the effects of contrast medium on diffusion tensor MRI.

OBJECTIVE: This study investigated whether or not the effect of contrast medium on diffusion tensor magnetic resonance imaging (DTI) is time-related in patients with malignant brain tumours. PATIENTS AND METHODS: Twelve patients who only had malignant brain tumours were included in the study. DTI acquisitions were performed five times consecutively: twice before, once during, then twice after contrast injection. Diffusion indices were mapped and regions of interest (ROIs) were placed in the tumour, peritumoral edema and contralateral normal brain tissue. Repeated-measures ANOVA was used to investigate the effects of time on contrast medium in relation to diffusion indices. RESULTS: Precontrast DTI was redefined as "pre" by averaging the two before-contrast scans, as there were no statistically significant differences between them. There were statistically significant differences at four time points for only the edema ROI for fractional anisotropy and the first-largest eigenvalue, but not for trace and the second-largest eigenvalue. CONCLUSION: The effects of contrast medium on DTI were time-dependent for diffusion anisotropic indices. DTI obtained at>6 min after contrast injection does not cause significant changes in diffusion isotropic and anisotropic values.

Fulminant Course of Acute Necrotizing Encephalopathy Followed by Serial MRI: A Case Report.

Acute necrotizing encephalopathy (ANE) is a rare but distinctive type of influenza-associated encephalopathy characterized by symmetric multiple lesions with an invariable thalamic involvement. Although the exact pathogenesis of ANE remains unclear, the most prevalent hypothesis is the "cytokine storm," which results in blood-brain-barrier breakdown. We present the case of a 10-year-old boy with fulminant ANE confirmed with serial MRI studies, including diffusion-weighted imaging and susceptibility-weighted imaging. A comparison of these serial images demonstrated detailed and longitudinal changes in MRI findings during the clinical course corresponding to pathophysiological changes. Our case clarifies the pathogenesis of ANE brain lesions using serial imaging studies and suggests that early immunomodulatory therapy reduces brain damage.

Multiple myeloma with intractable lumbar pain and diagnostic challenge with MRI: A case report.

We present a 63-year-old male patient with intractable bone pain and rapidly progressive osteoporosis, who was diagnosed with multiple myeloma (MM) by CT despite normal magnetic resonance imaging (MRI) findings. The gold standard diagnostic modality for MM is MRI as it can be used to sensitively evaluate bone marrow, however, the current case highlights that MRI is not always accurate in evaluating MM. CT in combination with MRI could be used for secondary osteoporosis with intractable bone pain in order to determine the diagnosis, treatment, and prognosis.

The Clinical Significance of the Hyperintense Acute Reperfusion Marker Sign in Subacute Infarction Patients.

PURPOSE: The hyperintense acute reperfusion marker (HARM) is characterized by the delayed enhancement of the subarachnoid or subpial space observed on postcontrast fluid-attenuated inversion recovery (FLAIR) images, and is considered a cerebral reperfusion marker for various brain disorders, including infarction. In this study, we evaluated the cerebral distribution patterns of HARM for discriminating between an enhancing subacute infarction and an enhancing mass located in the cortex and subcortical white matter. MATERIALS AND METHODS: We analyzed consecutive patients who experienced a subacute ischemic stroke, were hospitalized, and underwent conventional brain magnetic resonance imaging including postcontrast FLAIR within 14 days from symptom onset, as well as those who had lesions corresponding to a clinical sign detected by diffusion-weighted imaging and postcontrast T1-weighted imaging between May 2019 and May 2021. A total of 199 patients were included in the study. Of them, 94 were finally included in the subacute infarction group. During the same period, 76 enhancing masses located in the cortex or subcortical white matter, which were subcategorized as metastasis, malignant glioma, and lymphoma, were analyzed. We analyzed the overall incidence of HARM in subacute ischemic stroke cases, and compared the enhancement patterns between cortical infarctions and cortical masses. RESULTS: Among 94 patients with subacute stroke, 78 patients (83%) presented HARM, and among 76 patients with subcortical masses, 48 patients (63%) presented peripheral rim enhancement. Of 170 subcortical enhancing lesions, 88 (51.8%) showed HARM, and 78 (88.6%) were determined to be subacute infarction. Among 94 patients with subacute stroke, 48 patients (51%) had diffusion restrictions, and HARM was found in 39 patients (81.2%). Of the 46 patients (49%) without diffusion restriction, 39 patients (84.8%) showed HARM. CONCLUSIONS: The presence of HARM was significantly associated with subacute infarctions. For the masses, a peripheral rim enhancement pattern was observed around the mass rather than the cerebral sulci on postcontrast FLAIR.

Added Value of Chemical Exchange-Dependent Saturation Transfer MRI for the Diagnosis of Dementia.

OBJECTIVE: Chemical exchange-dependent saturation transfer (CEST) MRI is sensitive for detecting solid-like proteins and may detect changes in the levels of mobile proteins and peptides in tissues. The objective of this study was to evaluate the characteristics of chemical exchange proton pools using the CEST MRI technique in patients with dementia. MATERIALS AND METHODS: Our institutional review board approved this cross-sectional prospective study and informed consent was obtained from all participants. This study included 41 subjects (19 with dementia and 22 without dementia). Complete CEST data of the brain were obtained using a three-dimensional gradient and spin-echo sequence to map CEST indices, such as amide, amine, hydroxyl, and magnetization transfer ratio asymmetry (MTRasym) values, using six-pool Lorentzian fitting. Statistical analyses of CEST indices were performed to evaluate group comparisons, their correlations with gray matter volume (GMV) and Mini-Mental State Examination (MMSE) scores, and receiver operating characteristic (ROC) curves. RESULTS: Amine signals (0.029 for non-dementia, 0.046 for dementia, p = 0.011 at hippocampus) and MTRasym values at 3 ppm (0.748 for non-dementia, 1.138 for dementia, p = 0.022 at hippocampus), and 3.5 ppm (0.463 for non-dementia, 0.875 for dementia, p = 0.029 at hippocampus) were significantly higher in the dementia group than in the non-dementia group. Most CEST indices were not significantly correlated with GMV; however, except amide, most indices were significantly correlated with the MMSE scores. The classification power of most CEST indices was lower than that of GMV but adding one of the CEST indices in GMV improved the classification between the subject groups. The largest improvement was seen in the MTRasym values at 2 ppm in the anterior cingulate (area under the ROC curve = 0.981), with a sensitivity of 100 and a specificity of 90.91. CONCLUSION: CEST MRI potentially allows noninvasive image alterations in the Alzheimer's disease brain without injecting isotopes for monitoring different disease states and may provide a new imaging biomarker in the future.

Effective End-to-End Deep Learning Process in Medical Imaging Using Independent Task Learning: Application for Diagnosis of Maxillary Sinusitis.

PURPOSE: This study aimed to propose an effective end-to-end process in medical imaging using an independent task learning (ITL) algorithm and to evaluate its performance in maxillary sinusitis applications. MATERIALS AND METHODS: For the internal dataset, 2122 Waters' view X-ray images, which included 1376 normal and 746 sinusitis images, were divided into training (n=1824) and test (n=298) datasets. For external validation, 700 images, including 379 normal and 321 sinusitis images, from three different institutions were evaluated. To develop the automatic diagnosis system algorithm, four processing steps were performed: 1) preprocessing for ITL, 2) facial patch detection, 3) maxillary sinusitis detection, and 4) a localization report with the sinusitis detector. RESULTS: The accuracy of facial patch detection, which was the first step in the end-to-end algorithm, was 100%, 100%, 99.5%, and 97.5% for the internal set and external validation sets #1, #2, and #3, respectively. The accuracy and area under the receiver operating characteristic curve (AUC) of maxillary sinusitis detection were 88.93% (0.89), 91.67% (0.90), 90.45% (0.86), and 85.13% (0.85) for the internal set and external validation sets #1, #2, and #3, respectively. The accuracy and AUC of the fully automatic sinusitis diagnosis system, including site localization, were 79.87% (0.80), 84.67% (0.82), 83.92% (0.82), and 73.85% (0.74) for the internal set and external validation sets #1, #2, and #3, respectively. CONCLUSION: ITL application for maxillary sinusitis showed reasonable performance in internal and external validation tests, compared with applications used in previous studies.