Comparison of manual and artificial intelligence-automated choroidal thickness segmentation of optical coherence tomography imaging in myopic adults.

BACKGROUND: Myopia affects 1.4 billion individuals worldwide. Notably, there is increasing evidence that choroidal thickness plays an important role in myopia and risk of developing myopia-related conditions. With the advancements in artificial intelligence (AI), choroidal thickness segmentation can now be automated, offering inherent advantages such as better repeatability, reduced grader variability, and less reliance for manpower. Hence, we aimed to evaluate the agreement between AI-automated and manual segmented measurements of subfoveal choroidal thickness (SFCT) using two swept-source optical coherence tomography (OCT) systems. METHODS: Subjects aged ≥ 16 years, with myopia of ≥ 0.50 diopters in both eyes, were recruited from the Prospective Myopia Cohort Study in Singapore (PROMYSE). OCT scans were acquired using Triton DRI-OCT and PLEX Elite 9000. OCT images were segmented both automatically with an established SA-Net architecture and manually using a standard technique with adjudication by two independent graders. SFCT was subsequently determined based on the segmentation. The Bland-Altman plot and intraclass correlation coefficient (ICC) were used to evaluate the agreement. RESULTS: A total of 229 subjects (456 eyes) with mean [± standard deviation (SD)] age of 34.1 (10.4) years were included. The overall SFCT (mean ± SD) based on manual segmentation was 216.9 ± 82.7 µm with Triton DRI-OCT and 239.3 ± 84.3 µm with PLEX Elite 9000. ICC values demonstrated excellent agreement between AI-automated and manual segmented SFCT measurements (PLEX Elite 9000: ICC = 0.937, 95% CI: 0.922 to 0.949, P < 0.001; Triton DRI-OCT: ICC = 0.887, 95% CI: 0.608 to 0.950, P < 0.001). For PLEX Elite 9000, manual segmented measurements were generally thicker when compared to AI-automated segmented measurements, with a fixed bias of 6.3 µm (95% CI: 3.8 to 8.9, P < 0.001) and proportional bias of 0.120 (P < 0.001). On the other hand, manual segmented measurements were comparatively thinner than AI-automated segmented measurements for Triton DRI-OCT, with a fixed bias of - 26.7 µm (95% CI: - 29.7 to - 23.7, P < 0.001) and proportional bias of - 0.090 (P < 0.001). CONCLUSION: We observed an excellent agreement in choroidal segmentation measurements when comparing manual with AI-automated techniques, using images from two SS-OCT systems. Given its edge over manual segmentation, automated segmentation may potentially emerge as the primary method of choroidal thickness measurement in the future.

The influence of manual segmentation strategies and different phases selection on machine learning-based computed tomography in renal tumors: a systematic review and meta-analysis.

BACKGROUND: Delineating the region/volume of interest (ROI/VOI) and selecting the phases are of importance in developing machine learning (ML). The results will change when choosing different methods of drawing the ROI/VOI and selecting different phases. However, there is no related standard for delineating the ROI/VOI and selecting the phases in renal tumors to develop ML based on computed tomography (CT). METHODS: The PubMed and Web of Science were searched for related studies published until March 1, 2023. Inclusion criteria were studies that developed ML models in renal tumors from CT images. And the binary diagnostic accuracy data were extracted to obtain the outcomes, such as sensitivity (SE), specificity (SP), accuracy (ACC), and area under the curve (AUC). RESULTS: Twenty-three papers were included in the meta-analysis with a pooled SE of 87% (95% CI 85-88%), SP of 82% (95% CI 79-85%), and AUC of 91% (95% CI 89-93%) in phases; a pooled SE of 82% (95% CI 80-84%), SP of 85% (95% CI 83-86%), and AUC of 90% (95% CI 88-93%) in phases combined with delineating strategies, respectively. In all different combinations, the contour-focused and single phase produce the highest AUC of 93% (95% CI 90-95%). In subgroup analyses (sample size, year of publication, and geographical distribution), the performance was acceptable on phases and phases combined strategies. CONCLUSIONS: To explore the effect of manual segmentation strategies and different phases selection on ML-based CT, we find that the method of single phase (CMP or NP) combined with contour-focused was considered a better strategy compared to the other strategies.

Manual segmentation of the paraventricular nucleus of the hypothalamus and the dorsal and ventral bed nucleus of stria terminalis using multimodal 7 Tesla structural MRI: probabilistic atlases for a stress-control triad.

The paraventricular nucleus of the hypothalamus (PVN) is uniquely capable of proximal control over autonomic and neuroendocrine stress responses, and the bed nucleus of the stria terminalis (BNST) directly modulates PVN function, as well as playing an important role in stress control itself. The dorsal BNST (dBNST) is predominantly preautonomic, while the ventral BNST (vBNST) is predominantly viscerosensory, receiving dense noradrenergic signaling. Distinguishing the dBNST and vBNST, along with the PVN, may facilitate our understanding of dynamic interactions among these regions. T1-weighted MPRAGE and high resolution gradient echo (GRE) modalities were acquired at 7T. GRE was coregistered to MPRAGE and segmentations were performed in MRIcroGL based on their Atlas of the Human Brain depictions. The dBNST, vBNST and PVN were manually segmented in 25 participants; 10 images were rated by 2 raters. These segmentations were normalized and probabilistic atlases for each region were generated in MNI space, now available as resources for future research. We found moderate-high inter-rater reliability [n = 10; Mean Dice (SD); PVN = 0.69 (0.04); dBNST = 0.77 (0.04); vBNST = 0.62 (0.04)]. Probabilistic atlases were reverse normalized into native space for six additional participants that were segmented but not included in the original 25. We also found moderate to moderate-high reliability between the probabilistic atlases and manual segmentations [n = 6; Mean Dice (SD); PVN = 0.55 (0.12); dBNST = 0.60 (0.10); vBNST = 0.47 (0.12 SD)]. By isolating these hypothalamic and BNST subregions using ultra-high field MRI modalities, more specific delineations of these regions can facilitate greater understanding of mechanisms underlying stress-related function and psychopathology.

Deep neural network-based segmentation of normal and abnormal pancreas on abdominal CT: evaluation of global and local accuracies.

PURPOSE: Delay in diagnosis can contribute to poor outcomes in pancreatic ductal adenocarcinoma (PDAC), and new tools for early detection are required. Recent application of artificial intelligence to cancer imaging has demonstrated great potential in detecting subtle early lesions. The aim of the study was to evaluate global and local accuracies of deep neural network (DNN) segmentation of normal and abnormal pancreas with pancreatic mass. METHODS: Our previously developed and reported residual deep supervision network for segmentation of PDAC was applied to segment pancreas using CT images of potential renal donors (normal pancreas) and patients with suspected PDAC (abnormal pancreas). Accuracy of DNN pancreas segmentation was assessed using DICE simulation coefficient (DSC), average symmetric surface distance (ASSD), and Hausdorff distance 95% percentile (HD95) as compared to manual segmentation. Furthermore, two radiologists semi-quantitatively assessed local accuracies and estimated volume of correctly segmented pancreas. RESULTS: Forty-two normal and 49 abnormal CTs were assessed. Average DSC was 87.4 ± 3.1% and 85.5 ± 3.2%, ASSD 0.97 ± 0.30 and 1.34 ± 0.65, HD95 4.28 ± 2.36 and 6.31 ± 6.31 for normal and abnormal pancreas, respectively. Semi-quantitatively, ≥95% of pancreas volume was correctly segmented in 95.2% and 53.1% of normal and abnormal pancreas by both radiologists, and 97.6% and 75.5% by at least one radiologist. Most common segmentation errors were made on pancreatic and duodenal borders in both groups, and related to pancreatic tumor including duct dilatation, atrophy, tumor infiltration and collateral vessels. CONCLUSION: Pancreas DNN segmentation is accurate in a majority of cases, however, minor manual editing may be necessary; particularly in abnormal pancreas.

PILLAR: ParaspInaL muscLe segmentAtion pRoject - a comprehensive online resource to guide manual segmentation of paraspinal muscles from magnetic resonance imaging.

BACKGROUND: There is an increasing interest in assessing paraspinal morphology and composition in relation to low back pain (LBP). However, variations in methods and segmentation protocols contribute to the inconsistent findings in the literature. We present an on-line resource, the ParaspInaL muscLe segmentAtion pRoject (PILLAR, https://projectpillar.github.io/ ), to provide a detailed description and visual guide of a segmentation protocol by using the publicly available ITK-SNAP software and discuss related challenges when performing paraspinal lumbar muscles segmentations from magnetic resonance imaging (MRI). METHODS: T2-weighted and corresponding fat-water IDEAL axial MRI from 3 males and 3 females (2 chronic LBP and 1 control for each sex) were used to demonstrate our segmentation protocol for each lumbar paraspinal muscle (erector spinae, lumbar multifidus, quadratus lumborum and psoas) and lumbar spinal level (L1-L5). RESULTS: Proper segmentation requires an understanding of the anatomy of paraspinal lumbar muscles and the variations in paraspinal muscle morphology and composition due to age, sex, and the presence of LBP or related spinal pathologies. Other challenges in segmentation includes the presence and variations of intramuscular and epimuscular fat, and side-to-side asymmetry. CONCLUSION: The growing interest to assess the lumbar musculature and its role in the development and recurrence of LBP prompted the need for comprehensive and easy-to-follow resources, such as the PILLAR project to reduce inconsistencies in segmentation protocols. Standardizing manual muscle measurements from MRI will facilitate comparisons between studies while the field is progressively moving towards the automatization of paraspinal muscle measurements for large cohort studies.

The Cross-Sectional Area Assessment of Pelvic Muscles Using the MRI Manual Segmentation among Patients with Low Back Pain and Healthy Subjects.

The pain pathomechanism of chronic low back pain (LBP) is complex and the available diagnostic methods are insufficient. Patients present morphological changes in volume and cross-sectional area (CSA) of lumbosacral region. The main objective of this study was to assess if CSA measurements of pelvic muscle will indicate muscle atrophy between asymptomatic and symptomatic sides in chronic LBP patients, as well as between right and left sides in healthy volunteers. In addition, inter-rater reliability for CSA measurements was examined. The study involved 71 chronic LBP patients and 29 healthy volunteers. The CSA of gluteus maximus, medius, minimus and piriformis were measured using the MRI manual segmentation method. Muscle atrophy was confirmed in gluteus maximus, gluteus minimus and piriformis muscle for over 50% of chronic LBP patients (p < 0.05). Gluteus medius showed atrophy in patients with left side pain occurrence (p < 0.001). Muscle atrophy occurred on the symptomatic side for all inspected muscles, except gluteus maximus in rater one assessment. The reliability of CSA measurements between raters calculated using CCC and ICC presented great inter-rater reproducibility for each muscle both in patients and healthy volunteers (p < 0.95). Therefore, there is the possibility of using CSA assessment in the diagnosis of patients with symptoms of chronic LBP.

Validating ASHS-T1 automated entorhinal and transentorhinal cortical segmentation in Alzheimer's disease.

The current study aimed to validate entorhinal and transentorhinal cortical volumes measured by the automated segmentation tool Automatic Segmentation of Hippocampal Subfields (ASHS-T1). The study sample comprised 34 healthy controls (HCs), 37 individuals with amnestic mild cognitive impairment (aMCI), and 29 individuals with Alzheimer's disease (AD) dementia from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. Entorhinal and transentorhinal cortical volumes were assessed using ASHS-T1, manual segmentation, as well as a widely used automated segmentation tool, FreeSurfer v6.0.1. Mean differences, intraclass correlation coefficients, and Bland-Altman plots were computed. ASHS-T1 tended to underestimate entorhinal and transentorhinal cortical volumes relative to manual segmentation and FreeSurfer. There was variable consistency and low agreement between ASHS-T1 and manual segmentation volumes. There was low-to-moderate consistency and low agreement between ASHS-T1 and FreeSurfer volumes. There was a trend toward higher consistency and agreement for the entorhinal cortex in the aMCI and AD groups compared to the HC group. Despite the differences in volume measurements, ASHS-T1 was sensitive to entorhinal and transentorhinal cortical atrophy in both early and late disease stages. Based on the current study, ASHS-T1 appears to be a promising tool for automated entorhinal and transentorhinal cortical volume measurement in individuals with likely underlying AD.

Is Hippocampal Volume a Relevant Early Marker of Dementia?

OBJECTIVE: Hippocampal volume (HV) is a key imaging marker to improve Alzheimer's disease risk prediction. However, longitudinal studies are rare, and hippocampus may also be implicated in the subtle aging-related cognitive decline observed in dementia-free individuals. Our aim was to determine whether HV, measured by manual or automatic segmentation, is associated with dementia risk and cognitive decline in participants with and without incident dementia. METHODS: At baseline, 510 dementia-free participants from the French longitudinal ESPRIT cohort underwent magnetic resonance imaging. HV was measured by manual and by automatic segmentation (FreeSurfer 6.0). The presence of dementia and cognitive functions were investigated at each follow-up (2, 4, 7, 10, 12, and 15 years). Cox proportional hazards models and linear mixed models were used to assess the association of HV with dementia risk and with cognitive decline, respectively. RESULTS: During the 15-years follow-up, 42 participants developed dementia. Reduced HV (regardless of the measurement method) was significantly associated with higher dementia risk and cognitive decline in the whole sample. However, only the automatically measured HV was associated with cognitive decline in dementia-free participants. CONCLUSION: These results suggest that HV can be used to predict the long-term risk of dementia but also cognitive decline in a dementia-free population. This raises the question of the relevance of HV measurement as an early marker of dementia in the general population.

Automatic Segmentation of Parkinson Disease Therapeutic Targets Using Nonlinear Registration and Clinical MR Imaging: Comparison of Methodology, Presence of Disease, and Quality Control.

INTRODUCTION: Accurate and precise delineation of the globus pallidus pars interna (GPi) and subthalamic nucleus (STN) is critical for the clinical treatment and research of Parkinson's disease (PD). Automated segmentation is a developing technology which addresses limitations of visualizing deep nuclei on MR imaging and standardizing their definition in research applications. We sought to compare manual segmentation with three workflows for template-to-patient nonlinear registration providing atlas-based automatic segmentation of deep nuclei. METHODS: Bilateral GPi, STN, and red nucleus (RN) were segmented for 20 PD and 20 healthy control (HC) subjects using 3T MRIs acquired for clinical purposes. The automated workflows used were an option available in clinical practice and two common research protocols. Quality control (QC) was performed on registered templates via visual inspection of readily discernible brain structures. Manual segmentation using T1, proton density, and T2 sequences was used as "ground truth" data for comparison. Dice similarity coefficient (DSC) was used to assess agreement between segmented nuclei. Further analysis was done to compare the influences of disease state and QC classifications on DSC. RESULTS: Automated segmentation workflows (CIT-S, CRV-AB, and DIST-S) had the highest DSC for the RN and lowest for the STN. Manual segmentations outperformed automated segmentation for all workflows and nuclei; however, for 3/9 workflows (CIT-S STN, CRV-AB STN, and CRV-AB GPi) the differences were not statically significant. HC and PD only showed significant differences in 1/9 comparisons (DIST-S GPi). QC classification only demonstrated significantly higher DSC in 2/9 comparisons (CRV-AB RN and GPi). CONCLUSION: Manual segmentations generally performed better than automated segmentations. Disease state does not appear to have a significant effect on the quality of automated segmentations via nonlinear template-to-patient registration. Notably, visual inspection of template registration is a poor indicator of the accuracy of deep nuclei segmentation. As automatic segmentation methods continue to evolve, efficient and reliable QC methods will be necessary to support safe and effective integration into clinical workflows.

Inter-observer and intra-observer reliability between manual segmentation and semi-automated segmentation for carotid vessel wall volume measurements on three-dimensional ultrasonography.

PURPOSE: Carotid vessel wall volume (VWV) measurement on three-dimensional ultrasonography (3DUS) outperforms conventional two-dimensional ultrasonography for carotid atherosclerosis evaluation. Although time-saving semi-automated algorithms have been introduced, their clinical availability remains limited due to a lack of validation, particularly an extensive reliability analysis. This study compared inter-observer and intra-observer reliability between manual segmentation and semi-automated segmentation for carotid VWV measurements on 3DUS. METHODS: Thirty-one 3DUS volume datasets were prospectively acquired from 20 healthy subjects, aged >18 years, without previous stroke, transient ischemic attack, or cardiovascular disease. Five observers segmented all volume datasets both manually and semi-automatically. The process was repeated five times. Reliability was expressed by the intraclass correlation coefficient, supplemented by the coefficient of variation. RESULTS: Carotid VWV measurements using the common carotid artery (CCA) were more reliable than those using the internal carotid artery (ICA) or external carotid artery (ECA) for both manual and semiautomated segmentation (manual segmentation, CCA: inter-observer, 0.935; intra-observer, 0.934 to 0.966; ICA: inter-observer, 0.784; intra-observer, 0.756 to 0.878; ECA: inter-observer, 0.732; intraobserver, 0.919 to 0.962; semi-automated segmentation, CCA: inter-observer, 0.986; intra-observer, 0.954 to 0.993; ICA: inter-observer, 0.977; intra-observer, 0.958 to 0.978; ECA: inter-observer, 0.966; intra-observer, 0.884 to 0.937). Total carotid VWV measurements by manual (inter-observer, 0.922; intra-observer, 0.927 to 0.961) and semi-automated segmentation (inter-observer, 0.987; intra-observer, 0.968 to 0.989) were highly reliable. Semi-automated segmentation showed higher reliability than manual segmentation for both individual and total carotid VWV measurements. CONCLUSION: 3DUS carotid VWV measurements of the CCA are more reliable than measurements of the ICA and ECA. Total carotid VWV measurements are highly reliable. Semi-automated segmentation has higher reliability than manual segmentation.

A preliminary choroid plexus volumetric study in individuals with psychosis.

The choroid plexus (ChP) is part of the blood-cerebrospinal fluid barrier, regulating brain homeostasis and the brain's response to peripheral events. Its upregulation and enlargement are considered essential in psychosis. However, the timing of the ChP enlargement has not been established. This study introduces a novel magnetic resonance imaging-based segmentation method to examine ChP volumes in two cohorts of individuals with psychosis. The first sample consists of 41 individuals with early course psychosis (mean duration of illness = 1.78 years) and 30 healthy individuals. The second sample consists of 30 individuals with chronic psychosis (mean duration of illness = 7.96 years) and 34 healthy individuals. We utilized manual segmentation to measure ChP volumes. We applied ANCOVAs to compare normalized ChP volumes between groups and partial correlations to investigate the relationship between ChP, LV volumes, and clinical characteristics. Our segmentation demonstrated good reliability (.87). We further showed a significant ChP volume increase in early psychosis (left: p < .00010, right: p < .00010) and a significant positive correlation between higher ChP and higher LV volumes in chronic psychosis (left: r = .54, p = .0030, right: r = .68; p < .0010). Our study suggests that ChP enlargement may be a marker of acute response around disease onset. It might also play a modulatory role in the chronic enlargement of lateral ventricles, often reported in psychosis. Future longitudinal studies should investigate the dynamics of ChP enlargement as a promising marker for novel therapeutic strategies.

Intra-operator Repeatability of Manual Segmentations of the Hip Muscles on Clinical Magnetic Resonance Images.

The manual segmentation of muscles on magnetic resonance images is the gold standard procedure to reconstruct muscle volumes from medical imaging data and extract critical information for clinical and research purposes. (Semi)automatic methods have been proposed to expedite the otherwise lengthy process. These, however, rely on manual segmentations. Nonetheless, the repeatability of manual muscle volume segmentations performed on clinical MRI data has not been thoroughly assessed. When conducted, volumetric assessments often disregard the hip muscles. Therefore, one trained operator performed repeated manual segmentations (n = 3) of the iliopsoas (n = 34) and gluteus medius (n = 40) muscles on coronal T1-weighted MRI scans, acquired on 1.5 T scanners on a clinical population of patients elected for hip replacement surgery. Reconstructed muscle volumes were divided in sub-volumes and compared in terms of volume variance (normalized variance of volumes - nVV), shape (Jaccard Index-JI) and surface similarity (maximal Hausdorff distance-HD), to quantify intra-operator repeatability. One-way repeated measures ANOVA (or equivalent) tests with Bonferroni corrections for multiple comparisons were conducted to assess statistical significance. For both muscles, repeated manual segmentations were highly similar to one another (nVV: 2-6%, JI > 0.78, HD < 15 mm). However, shape and surface similarity were significantly lower when muscle extremities were included in the segmentations (e.g., iliopsoas: HD -12.06 to 14.42 mm, P < 0.05). Our findings show that the manual segmentation of hip muscle volumes on clinical MRI scans provides repeatable results over time. Nonetheless, extreme care should be taken in the segmentation of muscle extremities.

Stability and Reproducibility of Radiomic Features Based on Various Segmentation Techniques on Cervical Cancer DWI-MRI.

Cervical cancer is the most common cancer and ranked as 4th in morbidity and mortality among Malaysian women. Currently, Magnetic Resonance Imaging (MRI) is considered as the gold standard imaging modality for tumours with a stage higher than IB2, due to its superiority in diagnostic assessment of tumour infiltration with excellent soft-tissue contrast. In this research, the robustness of semi-automatic segmentation has been evaluated using a flood-fill algorithm for quantitative feature extraction, using 30 diffusion weighted MRI images (DWI-MRI) of cervical cancer patients. The relevant features were extracted from DWI-MRI segmented images of cervical cancer. First order statistics, shape features, and textural features were extracted and analysed. The intra-class relation coefficient (ICC) was used to compare 662 radiomic features extracted from manual and semi-automatic segmentations. Notably, the features extracted from the semi-automatic segmentation and flood filling algorithm (average ICC = 0.952 0.009, p > 0.05) were significantly higher than the manual extracted features (average ICC = 0.897 0.011, p > 0.05). Henceforth, we demonstrate that the semi-automatic segmentation is slightly expanded to manual segmentation as it produces more robust and reproducible radiomic features.

Comparative Multicentric Evaluation of Inter-Observer Variability in Manual and Automatic Segmentation of Neuroblastic Tumors in Magnetic Resonance Images.

Tumor segmentation is one of the key steps in imaging processing. The goals of this study were to assess the inter-observer variability in manual segmentation of neuroblastic tumors and to analyze whether the state-of-the-art deep learning architecture nnU-Net can provide a robust solution to detect and segment tumors on MR images. A retrospective multicenter study of 132 patients with neuroblastic tumors was performed. Dice Similarity Coefficient (DSC) and Area Under the Receiver Operating Characteristic Curve (AUC ROC) were used to compare segmentation sets. Two more metrics were elaborated to understand the direction of the errors: the modified version of False Positive (FPRm) and False Negative (FNR) rates. Two radiologists manually segmented 46 tumors and a comparative study was performed. nnU-Net was trained-tuned with 106 cases divided into five balanced folds to perform cross-validation. The five resulting models were used as an ensemble solution to measure training (n = 106) and validation (n = 26) performance, independently. The time needed by the model to automatically segment 20 cases was compared to the time required for manual segmentation. The median DSC for manual segmentation sets was 0.969 (±0.032 IQR). The median DSC for the automatic tool was 0.965 (±0.018 IQR). The automatic segmentation model achieved a better performance regarding the FPRm. MR images segmentation variability is similar between radiologists and nnU-Net. Time leverage when using the automatic model with posterior visual validation and manual adjustment corresponds to 92.8%.

Towards defining muscular regions of interest from axial magnetic resonance imaging with anatomical cross-reference: a scoping review of lateral hip musculature.

BACKGROUND: Measures of hip muscle morphology and composition (e.g., muscle size and fatty infiltration) are possible with magnetic resonance imaging (MRI). Standardised protocols or guidelines do not exist for evaluation of hip muscle characteristics, hindering reliable and valid inter-study analysis. This scoping review aimed to collate and synthesise MRI methods for measuring lateral hip muscle size and fatty infiltration to inform the future development of standardised protocols. METHODS: Five electronic databases (Medline, CINAHL, Embase, SportsDISCUS and AMED) were searched. Healthy or musculoskeletal pain populations that used MRI to assess lateral hip muscle size and fatty infiltration were included. Lateral hip muscles of interest included tensor fascia late (TFL), gluteus maximus, gluteus medius, and gluteus minimus. Data on MRI parameters, axial slice location, muscle size and fatty infiltrate measures were collected and analysed. Cross referencing for anatomical locations were made between MRI axial slice and E-12 anatomical plastinate sections. RESULTS: From 2684 identified publications, 78 studies contributed data on volume (n = 31), cross sectional area (CSA) (n = 24), and fatty infiltration (n = 40). Heterogeneity was observed for MRI parameters and anatomical boundaries scrutinizing hip muscle size and fatty infiltration. Seven single level axial slices were identified that provided consistent CSA measurement, including three for both gluteus maximus and TFL, and four for both gluteus medius and minimus. For assessment of fatty infiltration, six axial slice locations were identified including two for TFL, and four for each of the gluteal muscles. CONCLUSIONS: Several consistent anatomical levels were identified for single axial MR slice to facilitate muscle size and fatty infiltration muscle measures at the hip, providing the basis for reliable and accurate data synthesis and improvements in the validity of future between studies analyses. This work establishes the platform for standardised methods for the MRI assessment of lateral hip musculature and will aid in the examination of musculoskeletal conditions around the hip joint. Further studies into whole muscle measures are required to further optimise methodological parameters for hip muscle assessment.

Volumetric White Matter Hyperintensity Ranges Correspond to Fazekas Scores on Brain MRI.

INTRODUCTION: White matter hyperintensity (WMH) is an abnormal T2 signal in the deep and subcortical white matter visualized on MRI associated with hypertension, cerebrovascular disease, and aging. The Fazekas (Fz) scoring system is a commonly used qualitative tool to assess the severity of WMH. While studies have compared Fazekas scores to other scoring methods, the comparison of Fazekas scores and volume of WMH using current semiautomated volumetric techniques has not been studied. METHODS: We reviewed MRI studies acquired at our institution between 2015 and 2017. Relative WMH was scored by one author trained in Fazekas scoring. A board certified neuroradiologist scored them independently for confirmation. Manual segmentations of WMH were completed using 3D Slicer 4.9. A 3D model was formed to quantify WMH in milliliters (mL). ANOVA tests were performed to determine the association of Fazekas scores with corresponding WMH volumes. RESULTS: Among the 198 patients in our study, WMH were visualized in 163 (Fz1: n=66; Fz2: n=49; Fz3: n=48). WMH volumes significantly differed according to Fazekas score (F = 141.1, p<0.001), with increasing WMHV associated with higher Fazekas scores: Fz1, range 0.1-8.3 mL (mean 3.7, SD 2.3); Fz2, range 6.0-17.7 mL (mean 10.8, SD 3.1); Fz3, range 14.2-77.2 mL (mean 35.2, SD 17.9); and Fz3 (excluding 11 outliers above 50 mL), 14.2-47.0 mL (mean 27.1, SD 8.9). CONCLUSION: Fazekas scores correspond with distinct ranges of WMH volume with relatively little overlap, but scores based on volumes are more efficacious. A modified Fazekas from 0-4 should be considered.

Computerized Characterization of Spinal Structures on MRI and Clinical Significance of 3D Reconstruction of Lumbosacral Intervertebral Foramen.

BACKGROUND: Segmentation of spinal structures is important in medical imaging analysis, which facilitates surgeons to plan a preoperative trajectory for the transforaminal approach. However, manual segmentation of spinal structures is time-consuming, and studies have not explored automatic segmentation of spinal structures at the L5/S1 level. OBJECTIVES: This study sought to develop a new method based on a deep learning algorithm for automatic segmentation of spinal structures. The resulting algorithm may be used to rapidly generate a precise 3D lumbosacral intervertebral foramen model to assist physicians in planning an ideal trajectory in L5/S1 lumbar transforaminal radiofrequency ablation (LTRFA). STUDY DESIGN: This was an observational study for developing a new technique on spinal structures segmentation. STUDY SITE: The study was carried out at the department of radiology and spine surgery at our hospital. METHODS: A total of 100 L5/S1 level data samples from 100 study patients were used in this study. Masks of vertebral bone structures (VBSs) and intervertebral discs (IVDs) for all data samples were segmented manually by a skilled surgeon and served as the "ground truth." After data preprocessing, a 3D-UNet model based on deep learning was used for automated segmentation of lumbar spine structures at L5/S1 level magnetic resonance imaging (MRI). Segmentation performances and morphometric measurement were used for 3D lumbosacral intervertebral foramen (LIVF) reconstruction  generated by either manual segmentation and automatic segmentation. RESULTS: The 3D-UNet model showed high performance in automatic segmentation of lumbar spinal structures (VBSs and IVDs). The corresponding mean Dice similarity coefficient (DSC) of 5-fold cross-validation scores for L5 vertebrae, IVDs, S1 vertebrae, and all L5/S1 level spinal structures were 93.46 ± 2.93%, 90.39 ± 6.22%, 93.32 ± 1.51%, and 92.39 ± 2.82%, respectively. Notably, the analysis showed no associated difference in morphometric measurements between the manual and automatic segmentation at the L5/S1 level. LIMITATIONS: Semantic segmentation of multiple spinal structures (such as VBSs, IVDs, blood vessels, muscles, and ligaments) was simultaneously not integrated into the deep-learning method in this study. In addition, large clinical experiments are needed to evaluate the clinical efficacy of the model. CONCLUSION: The 3D-UNet model developed in this study based on deep learning can effectively and simultaneously segment VBSs and IVDs at L5/S1 level formMR images, thereby enabling rapid and accurate 3D reconstruction of LIVF models. The method can be used to segment VBSs and IVDs of spinal structures on MR images within near-human expert performance; therefore, it is reliable for reconstructing LIVF for L5/S1 LTRFA.

Agreement Between Automated and Manual MRI Volumetry in Alzheimer's Disease: A Systematic Review and Meta-Analysis.

BACKGROUND: Automated magnetic resonance imaging (MRI) volumetry is a promising tool to evaluate regional brain volumes in dementia and especially Alzheimer's disease (AD). PURPOSE: To compare automated methods and the gold standard manual segmentation in measuring regional brain volumes on MRI across healthy controls, patients with mild cognitive impairment, and patients with dementia due to AD. STUDY TYPE: Systematic review and meta-analysis. DATA SOURCES: MEDLINE, Embase, and PsycINFO were searched through October 2021. FIELD STRENGTH: 1.0 T, 1.5 T, or 3.0 T. ASSESSMENT: Two review authors independently identified studies for inclusion and extracted data. Methodological quality was assessed using the Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2). STATISTICAL TESTS: Standardized mean differences (SMD; Hedges' g) were pooled using random-effects meta-analysis with robust variance estimation. Subgroup analyses were undertaken to explore potential sources of heterogeneity. Sensitivity analyses were conducted to examine the impact of the within-study correlation between effect estimates on the meta-analysis results. RESULTS: Seventeen studies provided sufficient data to evaluate the hippocampus, lateral ventricles, and parahippocampal gyrus. The pooled SMD for the hippocampus, lateral ventricles, and parahippocampal gyrus were 0.22 (95% CI -0.50 to 0.93), 0.12 (95% CI -0.13 to 0.37), and -0.48 (95% CI -1.37 to 0.41), respectively. For the hippocampal data, subgroup analyses suggested that the pooled SMD was invariant across clinical diagnosis and field strength. Subgroup analyses could not be conducted on the lateral ventricles data and the parahippocampal gyrus data due to insufficient data. The results were robust to the selected within-study correlation value. DATA CONCLUSION: While automated methods are generally comparable to manual segmentation for measuring hippocampal, lateral ventricle, and parahippocampal gyrus volumes, wide 95% CIs and large heterogeneity suggest that there is substantial uncontrolled variance. Thus, automated methods may be used to measure these regions in patients with AD but should be used with caution. EVIDENCE LEVEL: 3 TECHNICAL EFFICACY: Stage 3.

A standardized protocol for manually segmenting stroke lesions on high-resolution T1-weighted MR images.

Although automated methods for stroke lesion segmentation exist, many researchers still rely on manual segmentation as the gold standard. Our detailed, standardized protocol for stroke lesion tracing on high-resolution 3D T1-weighted (T1w) magnetic resonance imaging (MRI) has been used to trace over 1,300 stroke MRI. In the current study, we describe the protocol, including a step-by-step method utilized for training multiple individuals to trace lesions ("tracers") in a consistent manner and suggestions for distinguishing between lesioned and non-lesioned areas in stroke brains. Inter-rater and intra-rater reliability were calculated across six tracers trained using our protocol, resulting in an average intraclass correlation of 0.98 and 0.99, respectively, as well as a Dice similarity coefficient of 0.727 and 0.839, respectively. This protocol provides a standardized guideline for researchers performing manual lesion segmentation in stroke T1-weighted MRI, with detailed methods to promote reproducibility in stroke research.

Stability and Reproducibility of Radiomic Features Based Various Segmentation Technique on MR Images of Hepatocellular Carcinoma (HCC).

Hepatocellular carcinoma (HCC) is considered as a complex liver disease and ranked as the eighth-highest mortality rate with a prevalence of 2.4% in Malaysia. Magnetic resonance imaging (MRI) has been acknowledged for its advantages, a gold technique for diagnosing HCC, and yet the false-negative diagnosis from the examinations is inevitable. In this study, 30 MR images from patients diagnosed with HCC is used to evaluate the robustness of semi-automatic segmentation using the flood fill algorithm for quantitative features extraction. The relevant features were extracted from the segmented MR images of HCC. Four types of features extraction were used for this study, which are tumour intensity, shape feature, textural feature and wavelet feature. A total of 662 radiomic features were extracted from manual and semi-automatic segmentation and compared using intra-class relation coefficient (ICC). Radiomic features extracted using semi-automatic segmentation utilized flood filling algorithm from 3D-slicer had significantly higher reproducibility (average ICC = 0.952 ± 0.009, p < 0.05) compared with features extracted from manual segmentation (average ICC = 0.897 ± 0.011, p > 0.05). Moreover, features extracted from semi-automatic segmentation were more robust compared to manual segmentation. This study shows that semi-automatic segmentation from 3D-Slicer is a better alternative to the manual segmentation, as they can produce more robust and reproducible radiomic features.