Predicting the apolipoprotein E ε4 allele carrier status based on gray matter volumes and cognitive function.

BACKGROUND: Apolipoprotein E (ApoE) ε4 carriers have a higher risk of developing Alzheimer's disease (AD) and show brain atrophy and cognitive decline even before diagnosis. OBJECTIVE: To predict ApoE ε4 status using gray matter volume (GMV) obtained from magnetic resonance imaging images and demographic data with machine learning (ML) methods. METHODS: We recruited 74 participants (25 probable AD, 24 amnestic mild cognitive impairment, and 25 cognitively normal older people) with known ApoE genotype (22 ApoE ε4 carriers and 52 noncarriers) and scanned them with three-dimensional (3D) T1-weighted (T1W) and 3D double inversion recovery (DIR) sequences. We extracted GMV from regions of interest related to AD pathology and used them as features along with age and mini-mental state examination (MMSE) scores to train different ML models. We performed both receiver operating characteristic curve analysis and the prediction analysis of the ApoE ε4 carrier with different ML models. RESULTS: The best model of ML analyses was a cubic support vector machine (SVM3) that used age, the MMSE score, and DIR GMVs at the amygdala, hippocampus, and precuneus as features (AUC = .88). This model outperformed models using T1W GMV or demographic data alone. CONCLUSION: Our results suggest that brain atrophy with DIR GMV and cognitive decline with aging can be useful biomarkers for predicting ApoE ε4 status and identifying individuals at risk of AD progression.

Deep-learning model for diagnostic clue: detecting the dural tail sign for meningiomas on contrast-enhanced T1 weighted images.

Background: Meningiomas are the most common primary central nervous system tumors, and magnetic resonance imaging (MRI), especially contrast-enhanced T1 weighted image (CE T1WI), is used as a fundamental imaging modality for the detection and analysis of the tumors. In this study, we propose an automated deep-learning model for meningioma detection using the dural tail sign. Methods: The dataset included 123 patients with 3,824 dural tail signs on sagittal CE T1WI. The dataset was divided into training and test datasets based on specific time point, and 78 and 45 patients were comprised for the training and test dataset, respectively. To compensate for the small sample size of the training dataset, 39 additional patients with 69 dural tail signs from the open dataset were appended to the training dataset. A You Only Look Once (YOLO) v4 network was trained with sagittal CE T1WI to detect dural tail signs. The normal group dataset, comprised of 51 patients with no abnormal finding on MRI, was employed to evaluate the specificity of the trained model. Results: The sensitivity and false positive average were 82.22% and 29.73, respectively, in the test dataset. The specificity and false positive average were 17.65% and 3.16, respectively, in the normal dataset. Most of the false-positive cases in the test dataset were enhancing vessels, misinterpreted as dural thickening. Conclusions: The proposed model demonstrates an automated detection system for the dural tail sign to identify meningioma in general screening MRI. Our model can facilitate and alleviate radiologists' reading process by notifying the possibility of incidental dural mass based on dural tail sign detection.

Developing and Evaluating Deep Learning Algorithms for Object Detection: Key Points for Achieving Superior Model Performance.

In recent years, artificial intelligence, especially object detection-based deep learning in computer vision, has made significant advancements, driven by the development of computing power and the widespread use of graphic processor units. Object detection-based deep learning techniques have been applied in various fields, including the medical imaging domain, where remarkable achievements have been reported in disease detection. However, the application of deep learning does not always guarantee satisfactory performance, and researchers have been employing trial-and-error to identify the factors contributing to performance degradation and enhance their models. Moreover, due to the black-box problem, the intermediate processes of a deep learning network cannot be comprehended by humans; as a result, identifying problems in a deep learning model that exhibits poor performance can be challenging. This article highlights potential issues that may cause performance degradation at each deep learning step in the medical imaging domain and discusses factors that must be considered to improve the performance of deep learning models. Researchers who wish to begin deep learning research can reduce the required amount of trial-and-error by understanding the issues discussed in this study.

Deep Learning Analysis of Mammography for Breast Cancer Risk Prediction in Asian Women.

The purpose of this study was to develop a mammography-based deep learning (DL) model for predicting the risk of breast cancer in Asian women. This retrospective study included 287 examinations in 153 women in the cancer group and 736 examinations in 447 women in the negative group, obtained from the databases of two tertiary hospitals between November 2012 and March 2022. All examinations were labeled as either dense breast or nondense breast, and then randomly assigned to either training, validation, or test sets. DL models, referred to as image-level and examination-level models, were developed. Both models were trained to predict whether or not the breast would develop breast cancer with two datasets: the whole dataset and the dense-only dataset. The performance of DL models was evaluated using the accuracy, precision, sensitivity, specificity, F1 score, and area under the receiver operating characteristic curve (AUC). On a test set, performance metrics for the four scenarios were obtained: image-level model with whole dataset, image-level model with dense-only dataset, examination-level model with whole dataset, and examination-level model with dense-only dataset with AUCs of 0.71, 0.75, 0.66, and 0.67, respectively. Our DL models using mammograms have the potential to predict breast cancer risk in Asian women.

Blood viscosity associated with stroke mechanism and early neurological deterioration in middle cerebral artery atherosclerosis.

Blood viscosity may affect the mechanisms of stroke and early neurological deterioration (END). We aimed to investigate the relationship between blood viscosity, stroke mechanisms, and END in patients with middle cerebral artery (MCA) infarction. Patients with symptomatic MCA atherosclerosis (≥ 50% stenosis) were recruited. Blood viscosity was compared across patients with different mechanisms of symptomatic MCA disease: in situ thrombo-occlusion (sMCA-IST), artery-to-artery embolism (sMCA-AAE), and local branch occlusion (sMCA-LBO). END was defined as four points increase in the National Institutes of Health Stroke Scale score from baseline during the first week. The association between blood viscosity and END was also evaluated. A total of 360 patients (76 with sMCA-IST, 216 with sMCA-AAE, and 68 with sMCA-LBO) were investigated. Blood viscosity was highest in patients with sMCA-IST, followed by sMCA-AAE and sMCA-LBO (P < 0.001). Blood viscosity was associated with END in patients with MCA disease. Low shear viscosity was associated with END in patients with sMCA- LBO (adjusted odds ratio, aOR 1.524; 95% confidence interval, CI 1.035-2.246), sMCA- IST (aOR 1.365; 95% CI 1.013-1.839), and sMCA- AAE (aOR 1.285; 95% CI 1.010-1.634). Blood viscosity was related to END in patients with stroke caused by MCA disease.

Wall Shear Stress Associated with Stroke Occurrence and Mechanisms in Middle Cerebral Artery Atherosclerosis.

BACKGROUND AND PURPOSE: Various mechanisms are involved in the etiology of stroke caused by atherosclerosis of the middle cerebral artery (MCA). Here, we compared differences in plaque nature and hemodynamic parameters according to stroke mechanism in patients with MCA atherosclerosis. METHODS: Consecutive patients with asymptomatic and symptomatic MCA atherosclerosis (≥50% stenosis) were enrolled. MCA plaque characteristics (location and plaque enhancement) and wall shear stress (WSS) were measured using high-resolution vessel wall and four-dimensional flow magnetic resonance imaging, respectively, at five points (initial, upstream, minimal lumen, downstream, and terminal). These parameters were compared between patients with asymptomatic and symptomatic MCA atherosclerosis with infarctions of different mechanisms (artery-to-artery embolism vs. local branch occlusion). RESULTS: In total, 110 patients (46 asymptomatic, 32 artery-to-artery embolisms, and 32 local branch occlusions) were investigated. Plaques were evenly distributed in the MCA of patients with asymptomatic MCA atherosclerosis, more commonly observed in the distal MCA of patients with artery-to-artery embolism, and in the middle MCA of patients with local branch occlusion. Maximum WSS and plaque enhancement were more prominent in the minimum lumen area of patients with asymptomatic MCA atherosclerosis or those with local branch occlusion, and were more prominent in the upstream area in those with artery-to-artery embolism. The elevated variability in the maximum WSS was related to stroke caused by artery-to-artery embolism. CONCLUSION: Stroke caused by artery-to-artery embolism was related to plaque enhancement and the highest maximum WSS at the upstream point of the plaque, and was associated with elevated variability of maximum WSS.

National trends in physical activity among adolescents in South Korea before and during the COVID-19 pandemic, 2009-2021.

With the ongoing COVID-19 pandemic, several previous studies from different countries showed that physical activity (PA) decreased during the COVID-19 outbreak. However, few studies have examined the recent tendency of PA in the adolescent population. Thus, we aimed to investigate the long-term trend of PA in Korean youth and the prevalence changes between before and during the COVID-19 pandemic. Data from Korea Youth Risk Behavior Web-Based Survey (KYRBS) was collected for consecutive years between 2009 and 2021. The period was separated into prepandemic (2009-2019), early-pandemic (2020), and mid-pandemic (2021). Self-reported amount of PA was categorized into four groups (insufficient, aerobic, muscle strengthening, and both physical activities) according to World Health Organization (WHO) PA guidelines. A total of 840 488 adolescents aged 12-18 who fully responded to the survey were selected (response rate: 95.2%). The 13-year trends in the proportion of adolescents who reported aerobic and muscle-strengthening activities met or exceeded 2020 WHO exercise guidelines for adolescents plateaued (11.9% from 2009 to 2011, 14.2% from 2018 to 2019, 14.4% from 2020, and 14.0% from 2021); however, the slope decreased during the pandemic (ßdiff , -0.076; 95% confidence interval [CI], -0.123 to -0.029). Proportion of sufficient aerobic exercise among adolescents sharply decreased midst the pandemic (28.0% from 2009 to 2011, 29.4% from 2018 to 2019, and 23.8% from 2020; ßdiff , -0.266; 95% CI, -0.306 to -0.226) but increased again in 2021 (26.0% from mid-COVID 19; 95% CI, 25.4-26.7). Similar patterns were observed in Metabolic Equivalent Task (MET) score (MET-min/week; 804.1 from 2018 to 2019, 720.9 from 2020, and 779.6 from 2021). The mean difference in MET score between pre-COVID and post-COVID was -55.4 MET-min/week (95% CI, -70.5 to -40.3). Through a nationwide representative study, there was no significant difference with regard to the number of Korean adolescents who achieved the PA guidelines (pre and postpandemic); however, the prevalence of recommended levels of PA needs to increase more based on the trend before the COVID-19 outbreak. The findings of this study suggest reinforcement of the importance of public health policies for Korean youths to be more physically active, especially during and after the pandemic.

An aptamer-based magnetic resonance imaging contrast agent for detecting oligomeric amyloid-ß in the brain of an Alzheimer's disease mouse model.

The oligomeric amyloid-ß (oAß) is a reliable feature for an early diagnosis of Alzheimer's disease (AD). Therefore, the objective of this study was to demonstrate imaging of oAß deposits using our developed DNA aptamer called ob5 conjugated with gadolinium (Gd)-dodecane tetraacetic acid (DOTA) as a contrast agent for early diagnosis of AD using MRI. An oAß-specific aptamer was developed by amide bond formation and conjugated to Gd-DOTA MRI contrast agent and/or cyanine5 (cy5). We verified the performance of our new contrast agent with an AD mouse model using in vivo and ex vivo fluorescent imaging and animal MRI experiments. The presence of soluble Aß in 3xTg AD mice was detected using GdDOTA-ob5-cy5 probe ex vivo. Fluorescence intensities of the GdDOTA-ob5-cy5 contrast agent were high in the brains of 3xTg-AD mice, but relatively low in the brains of control mice. The GdDOTA-ob5 contrast agent had higher relaxivity than a clinically available contrast agent. T1-weighted MRI signals in 5-month-old 3xTg AD mice increased at 5 min, were prolonged until 10 min, then decreased 15 min after injecting the GdDOTA-ob5 contrast agent. Our targeted DNA aptamer GdDOTA-ob5 contrast agent could be potentially useful for validating the efficacy of a novel diagnostic contrast agent for selectively targeting neurotoxic oAß. It could ultimately be used for early diagnosis of AD.

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.

Reliable quality assurance of X-ray mammography scanner by evaluation the standard mammography phantom image using an interpretable deep learning model.

OBJECTIVE: Mammography is the initial examination to detect breast cancer symptoms, and quality control of mammography devices is crucial to maintain accurate diagnosis and to safeguard against degradation of performance. The objective of this study was to assist radiologists in mammography phantom image evaluation by developing and validating an interpretable deep learning model capable of objectively evaluating the quality of standard phantom images for mammography. MATERIALS AND METHODS: A total of 2,208 mammography phantom images were collected for periodic accreditation of the scanner from 1,755 institutions. The dataset was randomly split into training (1,808 images) and testing (400 images) datasets with subgroups (76 images) for the multi-reader study. To develop an interpretable model that contains two deep learning networks in series, five processing steps were performed: mammography phantom detection, phantom object detection, post-processing, score evaluation, and a report with a comment about ambiguous results. RESULTS: For phantom detection, the accuracy and mean intersection over union (mIOU) were 1.00 and 0.938 in the test dataset, respectively. During phantom object detection, a total of 6,369 out of 6,400 objects were detected as the correct object class, and the accuracy and mIOU were 0.995 and 0.813, respectively. The predicted score for each object showed a consensus of 97.40% excluding ambiguous points and 59.10% for ambiguous points of the groups. CONCLUSIONS: The interpretable deep learning model using large-scale data from multiple centers shows high performance and reasonable object scoring, successfully validating the reliability and feasibility of mammography phantom image quality management.

Diagnostic Challenge in Rapidly Growing Langerhans Cell Histiocytosis with Aneurysmal Bone Cyst in the Maxilla: A Case Report.

Langerhans cell histiocytosis (LCH) is a rare neoplastic disorder characterized by the clonal proliferation of CD1a +/CD 207 + dendritic cells, whose features are similar to those of epidermal Langerhans cells. LCH is more common in children than in adults. Localized osteolytic lesions in the craniofacial bones are the most common manifestations of LCH. However, LCH can also present as a multifocal and multisystem disease with poor prognosis. Locally aggressive LCH needs to be differentiated from various diseases such as osteomyelitis, malignant bone tumors, and soft tissue sarcomas. However, it is difficult to diagnose, since the imaging findings are nonspecific. We report a case of a highly aggressive LCH in the maxilla accompanied by a fluid-fluid level.

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.

A prospective multi-centre study of susceptibility map-weighted MRI for the diagnosis of neurodegenerative parkinsonism.

OBJECTIVES: This study aimed to compare susceptibility map-weighted imaging (SMwI) using various MRI machines (three vendors) with N-3-fluoropropyl-2-ß-carbomethoxy-3-ß-(4-iodophe nyl)nortropane (18F-FP-CIT) PET in the diagnosis of neurodegenerative parkinsonism in a multi-centre setting. METHODS: We prospectively recruited 257 subjects, including 157 patients with neurodegenerative parkinsonism, 54 patients with non-neurodegenerative parkinsonism, and 46 healthy subjects from 10 hospitals between November 2019 and October 2020. All participants underwent both SMwI and 18F-FP-CIT PET. SMwI was interpreted by two independent reviewers for the presence or absence of abnormalities in nigrosome 1, and discrepancies were resolved by consensus. 18F-FP-CIT PET was used as the reference standard. Inter-observer agreement was tested using Cohen's kappa coefficient. McNemar's test was used to test the agreement between the interpretations of SMwI and 18F-FP-CIT PET per participant and substantia nigra (SN). RESULTS: The inter-observer agreement was 0.924 and 0.942 per SN and participant, respectively. The diagnostic sensitivity of SMwI was 97.9% and 99.4% per SN and participant, respectively; its specificity was 95.9% and 95.2%, respectively, and its accuracy was 97.1% and 97.7%, respectively. There was no significant difference between the results of SMwI and 18F-FP-CIT PET (p > 0.05, for both SN and participant). CONCLUSIONS: This study demonstrated that the high diagnostic performance of SMwI was maintained in a multi-centre setting with various MRI scanners, suggesting the generalisability of SMwI for determining nigrostriatal degeneration in patients with parkinsonism. KEY POINTS: • Susceptibility map-weighted imaging helps clinicians to predict nigrostriatal degeneration. • The protocol for susceptibility map-weighted imaging can be standardised across MRI vendors. • Susceptibility map-weighted imaging showed diagnostic performance comparable to that of dopamine transporter PET in a multi-centre setting with various MRI scanners.

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.

Association Between Plasma Amyloid-ß and Neuropsychological Performance in Patients With Cognitive Decline.

Objective: To investigate the association between plasma amyloid-ß (Aß) levels and neuropsychological performance in patients with cognitive decline using a highly sensitive nano-biosensing platform. Methods: We prospectively recruited 44 patients with cognitive decline who underwent plasma Aß analysis, amyloid positron emission tomography (PET) scanning, and detailed neuropsychological tests. Patients were classified into a normal control (NC, n = 25) or Alzheimer's disease (AD, n = 19) group based on amyloid PET positivity. Multiple linear regression was performed to determine whether plasma Aß (Aß40, Aß42, and Aß42/40) levels were associated with neuropsychological test results. Results: The plasma levels of Aß42/40 were significantly different between the NC and AD groups and were the best predictor of amyloid PET positivity by receiver operating characteristic curve analysis [area under the curve of 0.952 (95% confidence interval, 0.892-1.000)]. Although there were significant differences in the neuropsychological performance of cognitive domains (language, visuospatial, verbal/visual memory, and frontal/executive functions) between the NC and AD groups, higher levels of plasma Aß42/40 were negatively correlated only with verbal and visual memory performance. Conclusion: Our results demonstrated that plasma Aß analysis using a nano-biosensing platform could be a useful tool for diagnosing AD and assessing memory performance in patients with cognitive decline.

Screening for cerebral amyloid angiopathy based on serological biomarkers analysis using a dielectrophoretic force-driven biosensor platform.

We aimed to analyze plasma amyloid-ß (Aß)1-40 and Aß1-42 using a highly sensitive dielectrophoretic-driven biosensor platform to demonstrate the possibility of precise cerebral amyloid angiopathy (CAA) diagnosis in participants classified according to Aß-positron emission tomography (PET) positivity and the neuroimaging criteria for CAA. We prospectively recruited 25 people with non-Alzheimer's disease (non-AD) and 19 patients with Alzheimer's disease (AD), which were further classified into the CAA- and CAA+ (possible and probable CAA) groups according to the modified Boston criteria. Patients underwent plasma Aß analysis using a highly sensitive nano-biosensor platform, Aß-PET scanning, and detailed neuropsychological testing. As a result, the average signal levels of Aß1-42/1-40 differed significantly between the non-AD and AD groups, and the CAA+ group exhibited significantly higher Aß1-40 signal levels than the CAA- group in both non-AD and AD groups. The concordance between the Aß1-40 signal level and the neuroimaging criteria for CAA was nearly perfect, with areas under the curve of 0.954 (95% confidence interval (CI) 0.856-1.000), 0.969 (0.894-1.000), 0.867 (0.648-1.000), and 1.000 (1.000-1.000) in the non-AD/CAA- vs. non-AD/possible CAA, non-AD/CAA- vs. non-AD/probable CAA, AD/CAA- vs. AD/possible CAA, and AD/CAA- vs. AD/probable CAA groups, respectively. Higher Aß1-40 signal levels were significantly associated with the presence of CAA according to regression analyses, and the neuroimaging pattern analysis partly supported this result. Our findings suggest that measuring plasma Aß1-40 signal levels using a highly sensitive biosensor platform could be a useful non-invasive CAA diagnostic method.

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.

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.