ABSTRACT
Background The diagnostic abilities of multimodal large language models (LLMs) using direct image inputs and the impact of the temperature parameter of LLMs remain unexplored. Purpose To investigate the ability of GPT-4V and Gemini Pro Vision in generating differential diagnoses at different temperatures compared with radiologists using Radiology Diagnosis Please cases. Materials and Methods This retrospective study included Diagnosis Please cases published from January 2008 to October 2023. Input images included original images and captures of the textual patient history and figure legends (without imaging findings) from PDF files of each case. The LLMs were tasked with providing three differential diagnoses, repeated five times at temperatures 0, 0.5, and 1. Eight subspecialty-trained radiologists solved cases. An experienced radiologist compared generated and final diagnoses, considering the result correct if the generated diagnoses included the final diagnosis after five repetitions. Accuracy was assessed across models, temperatures, and radiology subspecialties, with statistical significance set at P < .007 after Bonferroni correction for multiple comparisons across the LLMs at the three temperatures and with radiologists. Results A total of 190 cases were included in neuroradiology (n = 53), multisystem (n = 27), gastrointestinal (n = 25), genitourinary (n = 23), musculoskeletal (n = 17), chest (n = 16), cardiovascular (n = 12), pediatric (n = 12), and breast (n = 5) subspecialties. Overall accuracy improved with increasing temperature settings (0, 0.5, 1) for both GPT-4V (41% [78 of 190 cases], 45% [86 of 190 cases], 49% [93 of 190 cases], respectively) and Gemini Pro Vision (29% [55 of 190 cases], 36% [69 of 190 cases], 39% [74 of 190 cases], respectively), although there was no evidence of a statistically significant difference after Bonferroni adjustment (GPT-4V, P = .12; Gemini Pro Vision, P = .04). The overall accuracy of radiologists (61% [115 of 190 cases]) was higher than that of Gemini Pro Vision at temperature 1 (T1) (P < .001), while no statistically significant difference was observed between radiologists and GPT-4V at T1 after Bonferroni adjustment (P = .02). Radiologists (range, 45%-88%) outperformed the LLMs at T1 (range, 24%-75%) in most subspecialties. Conclusion Using direct radiologic image inputs, GPT-4V and Gemini Pro Vision showed improved diagnostic accuracy with increasing temperature settings. Although GPT-4V slightly underperformed compared with radiologists, it nonetheless demonstrated promising potential as a supportive tool in diagnostic decision-making. © RSNA, 2024 See also the editorial by Nishino and Ballard in this issue.
Subject(s)
Radiologists , Humans , Retrospective Studies , Diagnosis, Differential , Image Interpretation, Computer-Assisted/methods , FemaleABSTRACT
This study aims to analyse the volumetric changes in brain MRI after cochlear implantation (CI), focusing on the speech perception in postlingually deaf adults. We conducted a prospective cohort study with 16 patients who had bilateral hearing loss and received unilateral CI. Based on the surgical side, patients were categorized into left and right CI groups. Volumetric T1-weighted brain MRI were obtained before and one year after the surgery. To overcome the artifact caused by the internal device in post-CI scan, image reconstruction method was newly devised and applied using the contralateral hemisphere of the pre-CI MRI data, to run FreeSurfer. We conducted within-subject template estimation for unbiased longitudinal image analysis, based on the linear mixed effect models. When analyzing the contralateral cerebral hemisphere before and after CI, a substantial increase in superior frontal gyrus and superior temporal gyrus (STG) volumes was observed in the left CI group. A positive correlation was observed in the STG and post-CI word recognition score in both groups. As far as we know, this is the first study attempting longitudinal brain volumetry based on post-CI MRI scans. We demonstrate that better auditory performance after CI is associated with structural restoration in central auditory structures.
Subject(s)
Cochlear Implantation , Deafness , Magnetic Resonance Imaging , Speech Perception , Humans , Male , Female , Cochlear Implantation/methods , Speech Perception/physiology , Magnetic Resonance Imaging/methods , Deafness/physiopathology , Deafness/surgery , Deafness/diagnostic imaging , Adult , Middle Aged , Prospective Studies , Aged , Cochlear ImplantsABSTRACT
PURPOSE: To determine the optimal angular range (AR) for digital breast tomosynthesis (DBT) systems that provides highest lesion visibility across various breast densities and thicknesses. METHOD: A modular DBT phantom, consisting of tissue-equivalent adipose and glandular modules, along with a module embedded with test objects (speckles, masses, fibers), was used to create combinations simulating different breast thicknesses, densities, and lesion locations. A prototype DBT system operated at four ARs (AR±7.5°, AR±12.5°, AR±19°, and AR±25°) to acquire 11 projection images for each combination, with separate fixed doses for thin and thick combinations. Three blinded radiologists independently assessed lesion visibility in reconstructed images; assessments were averaged and compared using linear mixed models. RESULTS: Speckle visibility was highest with AR±7.5° or AR±12.5°, decreasing with wider ARs in all density and thickness combinations. The difference between AR±7.5° and AR±12.5° was not statistically significant, except for the tube-side speckles in thin-fatty combinations (5.83 [AR±7.5°] vs. 5.39 [AR±12.5°], P = 0.019). Mass visibility was not affected by AR in thick combinations, while AR±12.5° exhibited the highest mass visibility for both thin-fatty and thin-dense combinations (P = 0.032 and 0.007, respectively). Different ARs provided highest fiber visibility for different combinations; however, AR±12.5° consistently provided highest or comparable visibility. AR±12.5° showed highest overall lesion visibility for all density and thickness combinations. CONCLUSIONS: AR±12.5° exhibited the highest overall lesion visibility across various phantom thicknesses and densities using a projection number of 11.
Subject(s)
Breast Density , Breast Neoplasms , Mammography , Phantoms, Imaging , Mammography/methods , Mammography/instrumentation , Humans , Breast Neoplasms/diagnostic imaging , Breast/diagnostic imaging , Image Processing, Computer-Assisted/methods , FemaleABSTRACT
OBJECTIVES: To evaluate the use of a commercial artificial intelligence (AI)-based mammography analysis software for improving the interpretations of breast ultrasound (US)-detected lesions. METHODS: A retrospective analysis was performed on 1109 breasts that underwent both mammography and US-guided breast biopsy. The AI software processed mammograms and provided an AI score ranging from 0 to 100 for each breast, indicating the likelihood of malignancy. The performance of the AI score in differentiating mammograms with benign outcomes from those revealing cancers following US-guided breast biopsy was evaluated. In addition, prediction models for benign outcomes were constructed based on clinical and imaging characteristics with and without AI scores, using logistic regression analysis. RESULTS: The AI software had an area under the receiver operating characteristics curve (AUROC) of 0.79 (95% CI, 0.79-0.82) in differentiating between benign and cancer cases. The prediction models that did not include AI scores (non-AI model), only used AI scores (AI-only model), and included AI scores (integrated model) had AUROCs of 0.79 (95% CI, 0.75-0.83), 0.78 (95% CI, 0.74-0.82), and 0.85 (95% CI, 0.81-0.88) in the development cohort, and 0.75 (95% CI, 0.68-0.81), 0.82 (95% CI, 0.76-0.88), and 0.84 (95% CI, 0.79-0.90) in the validation cohort, respectively. The integrated model outperformed the non-AI model in the development and validation cohorts (p < 0.001 for both). CONCLUSION: The commercial AI-based mammography analysis software could be a valuable adjunct to clinical decision-making for managing US-detected breast lesions. CLINICAL RELEVANCE STATEMENT: The commercial AI-based mammography analysis software could potentially reduce unnecessary biopsies and improve patient outcomes. KEY POINTS: ⢠Breast US has high rates of false-positive interpretations. ⢠A commercial AI-based mammography analysis software could distinguish mammograms having benign outcomes from those revealing cancers after US-guided breast biopsy. ⢠A commercial AI-based mammography analysis software may improve interpretations for breast US-detected lesions.
ABSTRACT
Quantification of diffusion restriction lesions in sporadic Creutzfeldt-Jakob disease (sCJD) may provide information of the disease burden. We aim to develop an automatic segmentation model for sCJD and to evaluate the volume of disease extent as a prognostic marker for overall survival. Fifty-six patients (mean age ± SD, 61.2 ± 9.9 years) were included from February 2000 to July 2020. A threshold-based segmentation was used to obtain abnormal signal intensity masks. Segmented volumes were compared with the visual grade. The Dice similarity coefficient was calculated to measure the similarity between the automatic vs. manual segmentation. Cox proportional hazards regression analysis was performed to evaluate the volume of disease extent as a prognostic marker. The automatic segmentation showed good correlation with the visual grading. The cortical lesion volumes significantly increased as the visual grade aggravated (extensive: 112.9 ± 73.2; moderate: 45.4 ± 30.4; minimal involvement: 29.6 ± 18.1 mm3) (P < 0.001). The deep gray matter lesion volumes were significantly higher for positive than for negative involvement of the deep gray matter (5.6 ± 4.6 mm3 vs. 1.0 ± 1.3 mm3, P < 0.001). The mean Dice similarity coefficients were 0.90 and 0.94 for cortical and deep gray matter lesions, respectively. However, the volume of disease extent was not associated with worse overall survival (cortical extent: P = 0.07; deep gray matter extent: P = 0.12).
Subject(s)
Creutzfeldt-Jakob Syndrome , Gray Matter , Humans , Gray Matter/diagnostic imaging , Gray Matter/pathology , Creutzfeldt-Jakob Syndrome/pathology , Diffusion Magnetic Resonance Imaging/methods , Algorithms , Magnetic Resonance Imaging/methodsABSTRACT
OBJECTIVE: To evaluate the diagnostic performance of susceptibility map-weighted imaging (SMwI) taken in different acquisition planes for discriminating patients with neurodegenerative parkinsonism from those without. MATERIALS AND METHODS: This retrospective, observational, single-institution study enrolled consecutive patients who visited movement disorder clinics and underwent brain MRI and 18F-FP-CIT PET between September 2021 and December 2021. SMwI images were acquired in both the oblique (perpendicular to the midbrain) and the anterior commissure-posterior commissure (AC-PC) planes. Hyperintensity in the substantia nigra was determined by two neuroradiologists. 18F-FP-CIT PET was used as the reference standard. Inter-rater agreement was assessed using Cohen's kappa coefficient. The diagnostic performance of SMwI in the two planes was analyzed separately for the right and left substantia nigra. Multivariable logistic regression analysis with generalized estimating equations was applied to compare the diagnostic performance of the two planes. RESULTS: In total, 194 patients were included, of whom 105 and 103 had positive results on 18F-FP-CIT PET in the left and right substantia nigra, respectively. Good inter-rater agreement in the oblique (κ = 0.772/0.658 for left/right) and AC-PC planes (0.730/0.741 for left/right) was confirmed. The pooled sensitivities for two readers were 86.4% (178/206, left) and 83.3% (175/210, right) in the oblique plane and 87.4% (180/206, left) and 87.6% (184/210, right) in the AC-PC plane. The pooled specificities for two readers were 83.5% (152/182, left) and 82.0% (146/178, right) in the oblique plane, and 83.5% (152/182, left) and 86.0% (153/178, right) in the AC-PC plane. There were no significant differences in the diagnostic performance between the two planes (P > 0.05). CONCLUSION: There are no significant difference in the diagnostic performance of SMwI performed in the oblique and AC-PC plane in discriminating patients with parkinsonism from those without. This finding affirms that each institution may choose the imaging plane for SMwI according to their clinical settings.
Subject(s)
Parkinsonian Disorders , Humans , Magnetic Resonance Imaging/methods , Parkinsonian Disorders/diagnostic imaging , Retrospective Studies , TropanesABSTRACT
Normal pressure hydrocephalus (NPH) patients had altered white matter tract integrities on diffusion tensor imaging (DTI). Previous studies suggested disproportionately enlarged subarachnoid space hydrocephalus (DESH) as a prognostic sign of NPH. We examined DTI indices in NPH subgroups by DESH severity and clinical symptoms. This retrospective case-control study included 33 NPH patients and 33 age-, sex-, and education-matched controls. The NPH grading scales (0-12) were used to rate neurological symptoms. Patients with NPH were categorized into two subgroups, high-DESH and low-DESH groups, by the average value of the DESH scale. DTI indices, including fractional anisotropy, were compared across 14 regions of interest (ROIs). The high-DESH group had increased axial diffusivity in the lateral side of corona radiata (1.43 ± 0.25 vs. 1.72 ± 0.25, p = 0.04), and showed decreased fractional anisotropy and increased mean, and radial diffusivity in the anterior and lateral sides of corona radiata and the periventricular white matter surrounding the anterior horn of lateral ventricle. In patients with a high NPH grading scale, fractional anisotropy in the white matter surrounding the anterior horn of the lateral ventricle was significantly reduced (0.36 ± 0.08 vs. 0.26 ± 0.06, p = 0.03). These data show that DESH may be a biomarker for DTI-detected microstructural alterations and clinical symptom severity.
Subject(s)
Hydrocephalus, Normal Pressure , Hydrocephalus , White Matter , Humans , Hydrocephalus, Normal Pressure/diagnostic imaging , Diffusion Tensor Imaging/methods , White Matter/diagnostic imaging , Case-Control Studies , Retrospective Studies , Anisotropy , Hydrocephalus/diagnostic imagingABSTRACT
[This corrects the article DOI: 10.3389/fneur.2023.1221892.].
ABSTRACT
OBJECTIVE: To develop a deep-learning-based bone age prediction model optimized for Korean children and adolescents and evaluate its feasibility by comparing it with a Greulich-Pyle-based deep-learning model. MATERIALS AND METHODS: A convolutional neural network was trained to predict age according to the bone development shown on a hand radiograph (bone age) using 21036 hand radiographs of Korean children and adolescents without known bone development-affecting diseases/conditions obtained between 1998 and 2019 (median age [interquartile range {IQR}], 9 [7-12] years; male:female, 11794:9242) and their chronological ages as labels (Korean model). We constructed 2 separate external datasets consisting of Korean children and adolescents with healthy bone development (Institution 1: n = 343; median age [IQR], 10 [4-15] years; male: female, 183:160; Institution 2: n = 321; median age [IQR], 9 [5-14] years; male: female, 164:157) to test the model performance. The mean absolute error (MAE), root mean square error (RMSE), and proportions of bone age predictions within 6, 12, 18, and 24 months of the reference age (chronological age) were compared between the Korean model and a commercial model (VUNO Med-BoneAge version 1.1; VUNO) trained with Greulich-Pyle-based age as the label (GP-based model). RESULTS: Compared with the GP-based model, the Korean model showed a lower RMSE (11.2 vs. 13.8 months; P = 0.004) and MAE (8.2 vs. 10.5 months; P = 0.002), a higher proportion of bone age predictions within 18 months of chronological age (88.3% vs. 82.2%; P = 0.031) for Institution 1, and a lower MAE (9.5 vs. 11.0 months; P = 0.022) and higher proportion of bone age predictions within 6 months (44.5% vs. 36.4%; P = 0.044) for Institution 2. CONCLUSION: The Korean model trained using the chronological ages of Korean children and adolescents without known bone development-affecting diseases/conditions as labels performed better in bone age assessment than the GP-based model in the Korean pediatric population. Further validation is required to confirm its accuracy.
Subject(s)
Artificial Intelligence , Deep Learning , Adolescent , Humans , Child , Male , Female , Infant , Age Determination by Skeleton , Radiography , Republic of KoreaABSTRACT
We aimed to investigate the detection rate of brain MR and MR angiography for neuroimaging abnormality in newly diagnosed left-sided infective endocarditis patients with/without neurological symptoms. This retrospective study included consecutive patients with definite or possible left-sided infective endocarditis according to the modified Duke criteria who underwent brain MRI and MR angiography between March 2015 and October 2020. The detection rate for neuroimaging abnormality on MRI was defined as the number of patients with positive brain MRI findings divided by the number of patients with left-sided infective endocarditis. Positive imaging findings included acute ischemic lesions, cerebral microbleeds, hemorrhagic lesions, and infectious aneurysms. In addition, aneurysm rupture rate and median period to aneurysm rupture were evaluated on follow-up studies. A total 115 patients (mean age: 55 years ± 19; 65 men) were included. The detection rate for neuroimaging abnormality was 77% (89/115). The detection rate in patients without neurological symptoms was 70% (56/80). Acute ischemic lesions, cerebral microbleeds, and hemorrhagic lesions including superficial siderosis and intracranial hemorrhage were detected on MRI in 56% (64/115), 57% (66/115), and 20% (23/115) of patients, respectively. In particular, infectious aneurysms were detected on MR angiography in 3% of patients (4/115), but MR angiography in 5 patients (4.3%) was insignificant for infectious aneurysm, which were detected using CT angiography (n = 3) and digital subtraction angiography (n = 2) during follow-up. Among the 9 infectious aneurysm patients, aneurysm rupture occurred in 4 (44%), with a median period of aneurysm rupture of 5 days. The detection rate of brain MRI for neuroimaging abnormality in newly diagnosed left-sided infective endocarditis patients was high (77%), even without neurological symptoms (70%).
Subject(s)
Aneurysm, Infected , Endocarditis , Intracranial Aneurysm , Male , Humans , Middle Aged , Retrospective Studies , Brain/diagnostic imaging , Brain/pathology , Magnetic Resonance Imaging/methods , Endocarditis/diagnostic imaging , Endocarditis/pathology , Neuroimaging , Aneurysm, Infected/diagnostic imaging , Angiography, Digital Subtraction , Cerebral Hemorrhage/pathology , Intracranial Aneurysm/pathology , Cerebral Angiography/methodsABSTRACT
Background and purpose: To develop and validate a deep learning-based automatic segmentation model for assessing intracranial volume (ICV) and to compare the accuracy determined by NeuroQuant (NQ), FreeSurfer (FS), and SynthSeg. Materials and methods: This retrospective study included 60 subjects [30 Alzheimer's disease (AD), 21 mild cognitive impairment (MCI), 9 cognitively normal (CN)] from a single tertiary hospital for the training and validation group (50:10). The test group included 40 subjects (20 AD, 10 MCI, 10 CN) from the ADNI dataset. We propose a robust ICV segmentation model based on the foundational 2D UNet architecture trained with four types of input images (both single and multimodality using scaled or unscaled T1-weighted and T2-FLAIR MR images). To compare with our model, NQ, FS, and SynthSeg were also utilized in the test group. We evaluated the model performance by measuring the Dice similarity coefficient (DSC) and average volume difference. Results: The single-modality model trained with scaled T1-weighted images showed excellent performance with a DSC of 0.989 ± 0.002 and an average volume difference of 0.46% ± 0.38%. Our multimodality model trained with both unscaled T1-weighted and T2-FLAIR images showed similar performance with a DSC of 0.988 ± 0.002 and an average volume difference of 0.47% ± 0.35%. The overall average volume difference with our model showed relatively higher accuracy than NQ (2.15% ± 1.72%), FS (3.69% ± 2.93%), and SynthSeg (1.88% ± 1.18%). Furthermore, our model outperformed the three others in each subgroup of patients with AD, MCI, and CN subjects. Conclusion: Our deep learning-based automatic ICV segmentation model showed excellent performance for the automatic evaluation of ICV.
ABSTRACT
Social hierarchy has a profound impact on social behavior, reward processing, and mental health. Moreover, lower social rank can lead to chronic stress and often more serious problems such as bullying victims of abuse, suicide, or attack to society. However, its underlying mechanisms, particularly their association with glial factors, are largely unknown. In this study, we report that astrocyte-derived amphiregulin plays a critical role in the determination of hierarchical ranks. We found that astrocytes-secreted amphiregulin is directly regulated by cAMP response element-binding (CREB)-regulated transcription coactivator 3 (CRTC3) and CREB. Mice with systemic and astrocyte-specific CRTC3 deficiency exhibited a lower social rank with reduced functional connectivity between the prefrontal cortex, a major social hierarchy center, and the parietal cortex. However, this effect was reversed by astrocyte-specific induction of amphiregulin expression, and the epidermal growth factor domain was critical for this action of amphiregulin. These results provide evidence of the involvement of novel glial factors in the regulation of social dominance and may shed light on the clinical application of amphiregulin in the treatment of various psychiatric disorders.
Subject(s)
Signal Transduction , Transcription Factors , Animals , Mice , Amphiregulin/genetics , Mice, Knockout , Social Dominance , Transcription Factors/metabolismABSTRACT
INTRODUCTION: The number of brain MRI with contrast media performed in patients with cognitive impairment has increased without universal agreement. We aimed to evaluate the detection rate of contrast-enhanced brain MRI in patients with cognitive impairment. MATERIALS AND METHODS: This single-institution, retrospective study included 4,838 patients who attended outpatient clinics for cognitive impairment evaluation and underwent brain MRI with or without contrast enhancement from December 2015 to February 2020. Patients who tested positive for cognitive impairment were followed-up to confirm whether the result was true-positive and provide follow-up management. Detection rate was defined as the proportion of patients with true-positive results and was compared between groups with and without contrast enhancement. Individual matching in a 1:2 ratio according to age, sex, and year of test was performed. RESULTS: The overall detection rates of brain MRI with and without contrast media were 4.7% (57/1,203; 95% CI: 3.6%-6.1%) and 1.8% (65/3,635; 95% CI: 1.4%-2.3%), respectively (P<0.001); individual matching demonstrated similar results (4.7% and 1.9%). Among 1,203 patients with contrast media, 3.6% was only detectable with the aid of contrast media. The proportion of patients who underwent follow-up imaging or treatment for the detected lesions were significantly higher in the group with contrast media (2.0% and 0.6%, P < .001). CONCLUSIONS: Detection rate of brain MRI for lesions only detectable with contrast media in patients with cognitive impairment was not high enough and further study is needed to identify whom would truly benefit with contrast media.
Subject(s)
Contrast Media , Magnetic Resonance Imaging , Humans , Retrospective Studies , Magnetic Resonance Imaging/methods , Brain/diagnostic imaging , Brain/pathology , CognitionABSTRACT
OBJECTIVES: To develop and validate an automatic classification algorithm for diagnosing Alzheimer's disease (AD) or mild cognitive impairment (MCI). METHODS AND MATERIALS: This study evaluated a high-performance interpretable network algorithm (TabNet) and compared its performance with that of XGBoost, a widely used classifier. Brain segmentation was performed using a commercially approved software. TabNet and XGBoost were trained on the volumes or radiomics features of 102 segmented regions for classifying subjects into AD, MCI, or cognitively normal (CN) groups. The diagnostic performances of the two algorithms were compared using areas under the curves (AUCs). Additionally, 20 deep learning-based AD signature areas were investigated. RESULTS: Between December 2014 and March 2017, 161 AD, 153 MCI, and 306 CN cases were enrolled. Another 120 AD, 90 MCI, and 141 CN cases were included for the internal validation. Public datasets were used for external validation. TabNet with volume features had an AUC of 0.951 (95% confidence interval [CI], 0.947-0.955) for AD vs CN, which was similar to that of XGBoost (0.953 [95% CI, 0.951-0.955], p = 0.41). External validation revealed the similar performances of two classifiers using volume features (0.871 vs. 0.871, p = 0.86). Likewise, two algorithms showed similar performances with one another in classifying MCI. The addition of radiomics data did not improve the performance of TabNet. TabNet and XGBoost focused on the same 13/20 regions of interest, including the hippocampus, inferior lateral ventricle, and entorhinal cortex. CONCLUSIONS: TabNet shows high performance in AD classification and detailed interpretation of the selected regions. CLINICAL RELEVANCE STATEMENT: Using a high-performance interpretable deep learning network, the automatic classification algorithm assisted in accurate Alzheimer's disease detection using 3D T1-weighted brain MRI and detailed interpretation of the selected regions. KEY POINTS: ⢠MR volumetry data revealed that TabNet had a high diagnostic performance in differentiating Alzheimer's disease (AD) from cognitive normal cases, which was comparable with that of XGBoost. ⢠The addition of radiomics data to the volume data did not improve the diagnostic performance of TabNet. ⢠Both TabNet and XGBoost selected the clinically meaningful regions of interest in AD, including the hippocampus, inferior lateral ventricle, and entorhinal cortex.
Subject(s)
Alzheimer Disease , Deep Learning , Humans , Alzheimer Disease/diagnostic imaging , Magnetic Resonance Imaging/methods , Algorithms , Hippocampus/diagnostic imagingABSTRACT
OBJECTIVES: To develop and validate a nomogram based on MRI features for predicting iNPH. METHODS: Patients aged ≥ 60 years (clinically diagnosed with iNPH, Parkinson's disease, or Alzheimer's disease or healthy controls) who underwent MRI including three-dimensional T1-weighted volumetric MRI were retrospectively identified from two tertiary referral hospitals (one hospital for derivation set and the other for validation set). Clinical and imaging features for iNPH were assessed. Deep learning-based brain segmentation software was used for 3D volumetry. A prediction model was developed using logistic regression and transformed into a nomogram. The performance of the nomogram was assessed with respect to discrimination and calibration abilities. The nomogram was internally and externally validated. RESULTS: A total of 452 patients (mean age ± SD, 73.2 ± 6.5 years; 200 men) were evaluated as the derivation set. One hundred eleven and 341 patients were categorized into the iNPH and non-iNPH groups, respectively. In multivariable analysis, high-convexity tightness (odds ratio [OR], 35.1; 95% CI: 4.5, 275.5), callosal angle < 90° (OR, 12.5; 95% CI: 3.1, 50.0), and normalized lateral ventricle volume (OR, 4.2; 95% CI: 2.7, 6.7) were associated with iNPH. The nomogram combining these three variables showed an area under the curve of 0.995 (95% CI: 0.991, 0.999) in the study sample, 0.994 (95% CI: 0.990, 0.998) in the internal validation sample, and 0.969 (95% CI: 0.940, 0.997) in the external validation sample. CONCLUSION: A brain morphometry-based nomogram including high-convexity tightness, callosal angle < 90°, and normalized lateral ventricle volume can help accurately estimate the probability of iNPH. KEY POINTS: ⢠The nomogram with MRI findings (high-convexity tightness, callosal angle, and normalized lateral ventricle volume) helped in predicting the probability of idiopathic normal-pressure hydrocephalus. ⢠The nomogram may facilitate the prediction of idiopathic normal-pressure hydrocephalus and consequently avoid unnecessary invasive procedures such as the cerebrospinal fluid tap test, drainage test, and cerebrospinal fluid shunt surgery.
Subject(s)
Alzheimer Disease , Hydrocephalus, Normal Pressure , Male , Humans , Aged , Nomograms , Retrospective Studies , Hydrocephalus, Normal Pressure/diagnostic imaging , Brain/diagnostic imaging , Magnetic Resonance Imaging/methodsABSTRACT
Purpose: We compared the feasibility of quantitative analysis methods using bone SPECT/CT with those using planar bone scans to assess active sacroiliitis. Methods: We retrospectively reviewed whole-body bone scans and pelvic bone SPECT/CTs of 8 patients who had clinically confirmed sacroiliitis and enrolled 24 patients without sacroiliitis as references. The volume of interest of each sacroiliac joint, including both the ilium and sacrum, was drawn. Active arthritis zone (AAZ) was defined as the zone of voxels with higher SUV than sacral mean SUV within the VOI of SI joint. Then, the following SPECT/CT quantitative parameters, SUVmax (maximum SUV), SUV50% (mean SUV in highest 50% of SUV), and SUV-AAZ, and the ratio of those values to sacral mean SUV (SUVmax/S, SUV50%/S, SUV-AAZ/S) were calculated. For the planar bone scan, the mean count ratio of SI joint/sacrum (SI/S) was conventionally measured. Results: Most of the SPECT/CT parameters of the sacroiliitis group were significantly higher than the normal group, whereas SI/S of the planar bone scan was not significantly different between the two groups. In receiver operating characteristic curve analysis, SUV-AAZ/S showed the highest AUC of 0.992, followed by SUV50%/S and SUVmax/S. All ratio parameters of the SPECT/CT showed higher AUC values than the SUV parameters of SI joint or SI/S of the planar scan. Conclusions: The quantitative analyses of bone SPECT/CT showed better performance in assessing active sacroiliitis than the planar bone scan. SPECT/CT parameters using the ratio of the SI joint to sacrum showed more favorable results than SUV parameters such as SUVmax, SUV50%, and SUV-AAZ.
ABSTRACT
The incidence of neurodegenerative diseases in the older population has increased in recent years. A considerable number of studies have been performed to characterize these diseases. Imaging analysis is an important biomarker for the diagnosis of neurodegenerative disease. Objective and reliable assessment and precise detection are important for the early diagnosis of neurodegenerative diseases. Artificial intelligence (AI) using brain MRI applied to the study of neurodegenerative diseases could promote early diagnosis and optimal decisions for treatment plans. MRI-based AI software have been developed and studied worldwide. Representatively, there are MRI-based volumetry and segmentation software. In this review, we present the development process of brain volumetry analysis software in neurodegenerative diseases, currently used and developed AI software for neurodegenerative disease in the Republic of Korea, probable uses of AI in the future, and AI software limitations.
ABSTRACT
The limited accessibility of medical specialists for Alzheimer's disease (AD) can make obtaining an accurate diagnosis in a timely manner challenging and may influence prognosis. We investigated whether VUNO Med-DeepBrain AD (DBAD) using a deep learning algorithm can be employed as a decision support service for the diagnosis of AD. This study included 98 elderly participants aged 60 years or older who visited the Seoul Asan Medical Center and the Korea Veterans Health Service. We administered a standard diagnostic assessment for diagnosing AD. DBAD and three panels of medical experts (ME) diagnosed participants with normal cognition (NC) or AD using T1-weighted magnetic resonance imaging. The accuracy (87.1% for DBAD and 84.3% for ME), sensitivity (93.3% for DBAD and 80.0% for ME), and specificity (85.5% for DBAD and 85.5% for ME) of both DBAD and ME for diagnosing AD were comparable; however, DBAD showed a higher trend in every analysis than ME diagnosis. DBAD may support the clinical decisions of physicians who are not specialized in AD; this may enhance the accessibility of AD diagnosis and treatment.
Subject(s)
Alzheimer Disease , Deep Learning , Aged , Humans , Alzheimer Disease/diagnostic imaging , Alzheimer Disease/pathology , Magnetic Resonance Imaging/methods , Brain/diagnostic imaging , Brain/pathology , AlgorithmsABSTRACT
OBJECTIVE: There is a paucity of large cohort-based evidence regarding the need and added value of diffusion-weighted imaging (DWI) in patients attending outpatient clinic for cognitive impairment. We aimed to evaluate the diagnostic yield of DWI in patients attending outpatient clinic for cognitive impairment. MATERIALS AND METHODS: This retrospective, observational, single-institution study included 3,298 consecutive patients (mean age ± SD, 71 years ± 10; 1,976 women) attending outpatient clinic for cognitive impairment with clinical dementia rating ≥ 0.5 who underwent brain MRI with DWI from January 2010 to February 2020. Diagnostic yield was defined as the proportion of patients in whom DWI supported the diagnosis that underlies cognitive impairment among all patients. Subgroup analyses were performed by age group and sex, and the Chi-square test was performed to compare the diagnostic yields between groups. RESULTS: The overall diagnostic yield of DWI in patients with cognitive impairment was 3.2% (106/3,298; 95% CI, 2.6-3.9%). The diagnostic yield was 2.5% (83/3,298) for acute or subacute infarct, which included recent small subcortical infarct for which the diagnostic yield was 1.6% (54/3,298). The diagnostic yield was 0.33% (11/3,298) for Creutzfeldt-Jakob disease (CJD), 0.15% (5/3,298) for transient global amnesia (TGA), 0.12% (4/3,298) for encephalitis and 0.09% (3/3,298) for lymphoma. There was a trend towards a higher diagnostic yield in the older age group with age ≥ 70 years old (3.6% vs 2.6%, P = .12). There was an incremental increase in the diagnostic yield from the age group 60-69 years (2.6%; 20/773) to 90-99 years (8.0%; 2/25). CONCLUSION: Despite its low overall diagnostic yield, DWI supported the diagnosis of acute or subacute infarct, CJD, TGA, encephalitis and lymphoma that underlie cognitive impairment, and there was a trend towards a higher diagnostic yield in the older age group.
Subject(s)
Amnesia, Transient Global , Cognitive Dysfunction , Creutzfeldt-Jakob Syndrome , Encephalitis , Aged , Brain/diagnostic imaging , Brain/pathology , Cognitive Dysfunction/diagnostic imaging , Cognitive Dysfunction/pathology , Cohort Studies , Creutzfeldt-Jakob Syndrome/diagnosis , Diffusion Magnetic Resonance Imaging/methods , Encephalitis/pathology , Female , Humans , Infarction/pathology , Magnetic Resonance Imaging , Middle Aged , Retrospective StudiesABSTRACT
PURPOSE: To validate the diagnostic performance of commercially available, deep learning-based automatic white matter hyperintensity (WMH) segmentation algorithm for classifying the grades of the Fazekas scale and differentiating subcortical vascular dementia. METHODS: This retrospective, observational, single-institution study investigated the diagnostic performance of a deep learning-based automatic WMH volume segmentation to classify the grades of the Fazekas scale and differentiate subcortical vascular dementia. The VUNO Med-DeepBrain was used for the WMH segmentation system. The system for segmentation of WMH was designed with convolutional neural networks, in which the input image was comprised of a pre-processed axial FLAIR image, and the output was a segmented WMH mask and its volume. Patients presented with memory complaint between March 2017 and June 2018 were included and were split into training (March 2017-March 2018, n = 596) and internal validation test set (April 2018-June 2018, n = 204). RESULTS: Optimal cut-off values to categorize WMH volume as normal vs. mild/moderate/severe, normal/mild vs. moderate/severe, and normal/mild/moderate vs. severe were 3.4 mL, 9.6 mL, and 17.1 mL, respectively, and the AUC were 0.921, 0.956 and 0.960, respectively. When differentiating normal/mild vs. moderate/severe using WMH volume in the test set, sensitivity, specificity, and accuracy were 96.4%, 89.9%, and 91.7%, respectively. For distinguishing subcortical vascular dementia from others using WMH volume, sensitivity, specificity, and accuracy were 83.3%, 84.3%, and 84.3%, respectively. CONCLUSION: Deep learning-based automatic WMH segmentation may be an accurate and promising method for classifying the grades of the Fazekas scale and differentiating subcortical vascular dementia.