Automatic Segmentation Technique Research Articles

3D Quantum Cuts for automatic segmentation of porous media in tomography images

Binary segmentation of volumetric images of porous media is a crucial step towards gaining a deeper understanding of the factors governing biogeochemical processes at minute scales. Contemporary work primarily revolves around primitive techniques based on global or local adaptive thresholding that have known common drawbacks in image segmentation. Moreover, the absence of a unified benchmark prohibits quantitative evaluation, which further undermines the impact of existing methodologies. In this study, we tackle the issue on both fronts. First, by drawing parallels with natural image segmentation, we propose a novel, and automatic segmentation technique, 3D Quantum Cuts (QCuts-3D) grounded on a state-of-the-art spectral clustering technique. Secondly, we curate and present a publicly available dataset of 68 multiphase volumetric images of porous media with diverse solid geometries, along with voxel-wise ground truth annotations for each constituting phase. We provide comparative evaluations between QCuts-3D and the current state-of-the-art over this dataset across a variety of evaluation metrics. The proposed systematic approach achieves a 26% increase in AUROC (Area Under Receiver Operating Characteristics) while achieving a substantial reduction of the computational complexity over state-of-the-art competitors. Moreover, statistical analysis reveals that the proposed method exhibits significant robustness against the compositional variations of porous media.

OL107 - Comparison of automated segmentation techniques for magnetic resonance images of the prostate

OL107 - Comparison of automated segmentation techniques for magnetic resonance images of the prostate

Brain stroke computed tomography images analysis using image processing: A Review

<span lang="EN-US">Stroke is the second-leading cause of death globally; therefore, it needs immediate treatment to prevent the brain from damage. Neuroimaging technique for stroke detection such as computed tomography (CT) has been widely used for emergency setting that can provide precise information on an obvious difference between white and gray matter. CT is the comprehensively utilized medical imaging technology for bone, soft tissue, and blood vessels imaging. A fully automatic segmentation became a significant contribution to help neuroradiologists achieve fast and accurate interpretation based on the region of interest (ROI). This review paper aims to identify, critically appraise, and summarize the evidence of the relevant studies needed by researchers. Systematic literature review (SLR) is the most efficient way to obtain reliable and valid conclusions as well as to reduce mistakes. Throughout the entire review process, it has been observed that the segmentation techniques such as fuzzy C-mean, thresholding, region growing, k-means, and watershed segmentation techniques were regularly used by researchers to segment CT scan images. This review is also impactful in identifying the best automated segmentation technique to evaluate brain stroke and is expected to contribute new information in the area of stroke research.</span>

Deep Learning-Based Computer-Aided Fetal Echocardiography: Application to Heart Standard View Segmentation for Congenital Heart Defects Detection.

Accurate segmentation of fetal heart in echocardiography images is essential for detecting the structural abnormalities such as congenital heart defects (CHDs). Due to the wide variations attributed to different factors, such as maternal obesity, abdominal scars, amniotic fluid volume, and great vessel connections, this process is still a challenging problem. CHDs detection with expertise in general are substandard; the accuracy of measurements remains highly dependent on humans’ training, skills, and experience. To make such a process automatic, this study proposes deep learning-based computer-aided fetal heart echocardiography examinations with an instance segmentation approach, which inherently segments the four standard heart views and detects the defect simultaneously. We conducted several experiments with 1149 fetal heart images for predicting 24 objects, including four shapes of fetal heart standard views, 17 objects of heart-chambers in each view, and three cases of congenital heart defect. The result showed that the proposed model performed satisfactory performance for standard views segmentation, with a 79.97% intersection over union and 89.70% Dice coefficient similarity. It also performed well in the CHDs detection, with mean average precision around 98.30% for intra-patient variation and 82.42% for inter-patient variation. We believe that automatic segmentation and detection techniques could make an important contribution toward improving congenital heart disease diagnosis rates.

Automatic quadriceps and patellae segmentation of MRI with cascaded U2 -Net and SASSNet deep learning model.

Automatic muscle segmentation is critical for advancing our understanding of human physiology, biomechanics, and musculoskeletal pathologies, as it allows for timely exploration of large multi-dimensional image sets. Segmentation models are rarely developed/validated for the pediatric model. As such, autosegmentation is not available to explore how muscle architectural changes during development and how disease/pathology affects the developing musculoskeletal system. Thus, we aimed to develop and validate an end-to-end, fully automated, deep learning model for accurate segmentation of the rectus femoris and vastus lateral, medialis, and intermedialis using a pediatric database. We developed a two-stage cascaded deep learning model in a coarse-to-fine manner. In the first stage, the U2 -Net roughly detects the muscle subcompartment region. Then, in the second stage, the shape-aware 3D semantic segmentation method SASSNet refines the cropped target regions to generate the more finer and accurate segmentation masks. We utilized multifeature image maps in both stages to stabilize performance and validated their use with an ablation study. The second-stage SASSNet was independently run and evaluated with three different cropped region resolutions: the original image resolution, and images downsampled 2× and 4× (high, mid, and low). The relationship between image resolution and segmentation accuracy was explored. In addition, the patella was included as a comparator to past work. We evaluated segmentation accuracy using leave-one-out testing on a database of 3D MR images (0.43×0.43×2mm) from 40 pediatric participants (age 15.3 ± 1.9 years, 55.8 ± 11.8kg, 164.2 ± 7.9cm, 38F/2M). The mid-resolution second stage produced the best results for the vastus medialis, rectus femoris, and patella (Dice similarity coefficient=95.0%, 95.1%, 93.7%), whereas the low-resolution second stage produced the best results for the vastus lateralis and vastus intermedialis (DSC=94.5% and 93.7%). In comparing the low- to mid-resolution cases, the vasti intermedialis, vastus medialis, rectus femoris, and patella produced significant differences (p=0.0015, p=0.0101, p<0.0001, p=0.0003) and the vasti lateralis did not (p=0.2177). The high-resolution stage 2 had significantly lower accuracy (1.0 to 4.4 dice percentage points) compared to both the mid- and low-resolution routines (p value ranged from<0.001 to 0.04). The one exception was the rectus femoris, where there was no difference between the low- and high-resolution cases. The ablation study demonstrated that the multifeature is more reliable than the single feature. Our successful implementation of this two-stage segmentation pipeline provides a critical tool for expanding pediatric muscle physiology and clinical research. With a relatively small and variable dataset, our fully automatic segmentation technique produces accuracies that matched or exceeded the current state of the art. The two-stage segmentation avoids memory issues and excessive run times by using a first stage focused on cropping out unnecessary data. The excellent Dice similarity coefficients improve upon previous template-based automatic and semiautomatic methodologies targeting the leg musculature. More importantly, with a naturally variable dataset (size, shape, etc.), the proposed model demonstrates slightly improved accuracies, compared to previous neural networks methods.

A Multidisciplinary Approach for the Mapping, Automatic Detection and Morphometric Analysis of Ancient Submerged Coastal Installations: The Case Study of the Ancient Aegina Harbour Complex

The documentation of underwater cultural heritage (UCH) is the basis for sustainable maritime development including its protection, preservation, and incorporation in coastal zone management plans. In this study, we present a multidisciplinary, non-intrusive downscale approach for the documentation of UCH implemented on the coastal area of Aegina Island, Greece, where a unique submerged harbour complex is preserved. This approach succeeded in obtaining information that serves both geomorphological and archaeological purposes in a time- and cost-effective way, while obtaining information of centimeters to millimeters scale. The geomorphology of the area was mapped in detail through marine geophysical means while ancient submerged conical rubble structures and breakwaters were documented using automatic seafloor segmentation techniques, revealing previously unknown sites of archaeological interest. The structures’ parameters were extracted from the acoustic data to analyze their morphometry, while photogrammetry was realized using a Remotely Operated Vehicle to expose their micro-structure. The spatial distribution of the structures revealed the construction of a well-planned harbour complex with multiple passages and different possible functionalities. Finally, through the structures’ morphometric analysis (geometry and terrain statistical parameters) their preservation status was revealed, demonstrating the anthropogenic impact on the submerged ancient structures due to the modern harbor activity.

Validation and accuracy evaluation of automatic segmentation for knee joint pre-planning

BackgroundProper use of three-dimensional (3D) models generated from medical imaging data in clinical preoperative planning, training and consultation is based on the preliminary proved accuracy of the replication of the patient anatomy. Therefore, this study investigated the dimensional accuracy of 3D reconstructions of the knee joint generated from computed tomography scans via automatic segmentation by comparing them with 3D models generated through manual segmentation. MethodsThree unpaired, fresh-frozen right legs were investigated. Three-dimensional models of the femur and the tibia of each leg were manually segmented using a commercial software and compared in terms of geometrical accuracy with the 3D models automatically segmented using proprietary software. Bony landmarks were identified and used to calculate clinically relevant distances: femoral epicondylar distance; posterior femoral epicondylar distance; femoral trochlear groove length; tibial knee center tubercle distance (TKCTD). Pearson's correlation coefficient and Bland and Altman plots were used to evaluate the level of agreement between measured distances. ResultsDifferences between parameters measured on 3D models manually and automatically segmented were below 1 mm (range: −0.06 to 0.72 mm), except for TKCTD (between 1.00 and 1.40 mm in two specimens). In addition, there was a significant strong correlation between measurements. ConclusionsThe results obtained are comparable to those reported in previous studies where accuracy of bone 3D reconstruction was investigated. Automatic segmentation techniques can be used to quickly reconstruct reliable 3D models of bone anatomy and these results may contribute to enhance the spread of this technology in preoperative and operative settings, where it has shown considerable potential.

Artificial intelligence and abdominal adipose tissue analysis: a literature review.

Body composition imaging relies on assessment of tissues composition and distribution. Quantitative data provided by body composition imaging analysis have been linked to pathogenesis, risk, and clinical outcomes of a wide spectrum of diseases, including cardiovascular and oncologic. Manual segmentation of imaging data allows to obtain information on abdominal adipose tissue; however, this procedure can be cumbersome and time-consuming. On the other hand, quantitative imaging analysis based on artificial intelligence (AI) has been proposed as a fast and reliable automatic technique for segmentation of abdominal adipose tissue compartments, possibly improving the current standard of care. AI holds the potential to extract quantitative data from computed tomography (CT) and magnetic resonance (MR) images, which in most of the cases are acquired for other purposes. This information is of great importance for physicians dealing with a wide spectrum of diseases, including cardiovascular and oncologic, for the assessment of risk, pathogenesis, clinical outcomes, response to treatments, and complications. In this review we summarize the available evidence on AI algorithms aimed to the segmentation of visceral and subcutaneous adipose tissue compartments on CT and MR images.

Non‐invasive assessment of knee osteoarthritis patients using thermal imaging

Radiography is a widely used method for grading and tracking the anatomical changes in knee osteoarthritis (OA) patients. The ease of thermography in mapping functional information via the skin temperature (Tsk) helps in the diagnosis of various musculoskeletal diseases. There is a significant involvement of soft tissues in knee OA due to the complex osteoligamentous degeneration, which may affect the knee Tsk. A total of 62 patients with knee OA were analysed using thermography. The mean Tsk was computed by extracting the region of interest from the acquired thermal images using an automatic segmentation technique for frontal, lateral, and medial views. The mean Tsk for grade 1, 2, 3 and 4 were 30.96 ± 0.59, 31.56 ± 0.79, 31.40 ± 1.22, 32.20 ± 0.70 ˚C respectively. A significant temperature difference was found between grade 2 and 4 (p = 0.02, p = 0.018), grade 3 and 4 (p = 0.03, p = 0.02) for frontal and lateral views; whereas no significant difference was found between grade 2 and 3. Further, 2-way ANOVA test showed that risk factors (like age, BMI and duration of disease) do affect the mean Tsk significantly with a p-value of 0.0003, 0.02, and 0.008.

Multiple Sclerosis Lesion Segmentation in Brain MRI Using Inception Modules Embedded in a Convolutional Neural Network.

Multiple sclerosis (MS) is a chronic and autoimmune disease that forms lesions in the central nervous system. Quantitative analysis of these lesions has proved to be very useful in clinical trials for therapies and assessing disease prognosis. However, the efficacy of these quantitative analyses greatly depends on how accurately the MS lesions have been identified and segmented in brain MRI. This is usually carried out by radiologists who label 3D MR images slice by slice using commonly available segmentation tools. However, such manual practices are time consuming and error prone. To circumvent this problem, several automatic segmentation techniques have been investigated in recent years. In this paper, we propose a new framework for automatic brain lesion segmentation that employs a novel convolutional neural network (CNN) architecture. In order to segment lesions of different sizes, we have to pick a specific filter or size 3 × 3 or 5 × 5. Sometimes, it is hard to decide which filter will work better to get the best results. Google Net has solved this problem by introducing an inception module. An inception module uses 3 × 3, 5 × 5, 1 × 1 and max pooling filters in parallel fashion. Results show that incorporating inception modules in a CNN has improved the performance of the network in the segmentation of MS lesions. We compared the results of the proposed CNN architecture for two loss functions: binary cross entropy (BCE) and structural similarity index measure (SSIM) using the publicly available ISBI-2015 challenge dataset. A score of 93.81 which is higher than the human rater with BCE loss function is achieved.

PD-0930 Comparison of automated segmentation techniques for magnetic resonance images of the prostate

PD-0930 Comparison of automated segmentation techniques for magnetic resonance images of the prostate

Review of Deep Learning Based Automatic Segmentation for Lung Cancer Radiotherapy.

Lung cancer is the leading cause of cancer-related mortality for males and females. Radiation therapy (RT) is one of the primary treatment modalities for lung cancer. While delivering the prescribed dose to tumor targets, it is essential to spare the tissues near the targets—the so-called organs-at-risk (OARs). An optimal RT planning benefits from the accurate segmentation of the gross tumor volume and surrounding OARs. Manual segmentation is a time-consuming and tedious task for radiation oncologists. Therefore, it is crucial to develop automatic image segmentation to relieve radiation oncologists of the tedious contouring work. Currently, the atlas-based automatic segmentation technique is commonly used in clinical routines. However, this technique depends heavily on the similarity between the atlas and the image segmented. With significant advances made in computer vision, deep learning as a part of artificial intelligence attracts increasing attention in medical image automatic segmentation. In this article, we reviewed deep learning based automatic segmentation techniques related to lung cancer and compared them with the atlas-based automatic segmentation technique. At present, the auto-segmentation of OARs with relatively large volume such as lung and heart etc. outperforms the organs with small volume such as esophagus. The average Dice similarity coefficient (DSC) of lung, heart and liver are over 0.9, and the best DSC of spinal cord reaches 0.9. However, the DSC of esophagus ranges between 0.71 and 0.87 with a ragged performance. In terms of the gross tumor volume, the average DSC is below 0.8. Although deep learning based automatic segmentation techniques indicate significant superiority in many aspects compared to manual segmentation, various issues still need to be solved. We discussed the potential issues in deep learning based automatic segmentation including low contrast, dataset size, consensus guidelines, and network design. Clinical limitations and future research directions of deep learning based automatic segmentation were discussed as well.

Efficient Cell Segmentation from Electroluminescent Images of Single-Crystalline Silicon Photovoltaic Modules and Cell-Based Defect Identification Using Deep Learning with Pseudo-Colorization.

Solar cells may possess defects during the manufacturing process in photovoltaic (PV) industries. To precisely evaluate the effectiveness of solar PV modules, manufacturing defects are required to be identified. Conventional defect inspection in industries mainly depends on manual defect inspection by highly skilled inspectors, which may still give inconsistent, subjective identification results. In order to automatize the visual defect inspection process, an automatic cell segmentation technique and a convolutional neural network (CNN)-based defect detection system with pseudo-colorization of defects is designed in this paper. High-resolution Electroluminescence (EL) images of single-crystalline silicon (sc-Si) solar PV modules are used in our study for the detection of defects and their quality inspection. Firstly, an automatic cell segmentation methodology is developed to extract cells from an EL image. Secondly, defect detection can be actualized by CNN-based defect detector and can be visualized with pseudo-colors. We used contour tracing to accurately localize the panel region and a probabilistic Hough transform to identify gridlines and busbars on the extracted panel region for cell segmentation. A cell-based defect identification system was developed using state-of-the-art deep learning in CNNs. The detected defects are imposed with pseudo-colors for enhancing defect visualization using K-means clustering. Our automatic cell segmentation methodology can segment cells from an EL image in about s. The average segmentation errors along the x-direction and y-direction are only pixels and pixels, respectively. The defect detection approach on segmented cells achieves accuracy. Along with defect detection, the defect regions on a cell are furnished with pseudo-colors to enhance the visualization.

Reference Values for Skeletal Muscle Mass at the Third Lumbar Vertebral Level Measured by Computed Tomography in a Healthy Korean Population.

BackgroundSarcopenia is defined as the loss of skeletal muscle mass and is associated with negative clinical outcomes. This study aimed to establish sex-specific cutoff values for the skeletal muscle area (SMA) and skeletal muscle index (SMI) at the third lumbar vertebral (L3) level using computed tomography (CT) imaging to identify sarcopenia in healthy Korean liver donors.MethodsThis retrospective study included 659 healthy liver donors (408 men and 251 women) aged 20 to 60 years who had undergone abdominal CT examinations between January 2017 and December 2018. Assessment of body composition was performed with an automated segmentation technique using a deep-learning system. Sex-specific SMA and SMI distributions were assessed, and cutoff values for determining sarcopenia were defined as values at either two standard deviations (SDs) below the mean reference value or below the fifth percentile.ResultsUsing the SD definition, cutoff values for SMA and SMI were 117.04 cm2 and 39.33 cm2/m2, respectively, in men and 71.39 cm2 and 27.77 cm2/m2, respectively, in women. Using the fifth percentile definition, cutoff values for SMA and SMI were 126.88 cm2 and 40.96 cm2/m2, respectively, in men and 78.85 cm2 and 30.60 cm2/m2, respectively, in women.ConclusionOur data provide sex-specific cutoff values for the SMA and SMI at the L3 level measured by CT imaging in a healthy Korean population, which may be applicable for identifying sarcopenia in this population.

3D Deep Learning for Anatomical Structure Segmentation in Multiple Imaging Modalities.

Accurate, quantitative segmentation of anatomical structures in radiological scans, such as Magnetic Resonance Imaging (MRI) and Computer Tomography (CT), can produce significant biomarkers and can be integrated into computer-aided assisted diagnosis (CADx) systems to support the interpretation of medical images from multi-protocol scanners. However, there are serious challenges towards developing robust automated segmentation techniques, including high variations in anatomical structure and size, the presence of edge-based artefacts, and heavy un-controlled breathing that can produce blurred motion-based artefacts. This paper presents a novel computing approach for automatic organ and muscle segmentation in medical images from multiple modalities by harnessing the advantages of deep learning techniques in a two-part process. (1) a 3D encoder-decoder, Rb-UNet, builds a localisation model and a 3D Tiramisu network generates a boundary-preserving segmentation model for each target structure; (2) the fully trained Rb-UNet predicts a 3D bounding box encapsulating the target structure of interest, after which the fully trained Tiramisu model performs segmentation to reveal detailed organ or muscle boundaries. The proposed approach is evaluated on six different datasets, including MRI, Dynamic Contrast Enhanced (DCE) MRI and CT scans targeting the pancreas, liver, kidneys and psoas-muscle and achieves quantitative measures of mean Dice similarity coefficient (DSC) that surpass or are comparable with the state-of-the-art. A qualitative evaluation performed by two independent radiologists verified the preservation of detailed organ and muscle boundaries.

Region-aware Global Context Modeling for Automatic Nerve Segmentation from Ultrasound Images

We present a novel deep learning model equipped with a new region-aware global context modeling technique for automatic nerve segmentation from ultrasound images, which is a challenging task due to (1) the large variation and blurred boundaries of targets, (2) the large amount of speckle noise in ultrasound images, and (3) the inherent real-time requirement of this task. It is essential to efficiently capture long-range dependencies by global context modeling for a segmentation network to overcome these challenges. Traditional global context modeling techniques usually explore pixel-aware correlations to establish long-range dependencies, which are usually computation-intensive and greatly degrade time performance. In addition, in this application, pixel-aware modeling may inevitably introduce much speckle noise in the computation and potentially degrade segmentation performance. In this paper, we propose a novel region-aware modeling technique to establish long-range dependencies based on different regions to improve segmentation accuracy while maintaining real-time performance; we call it region-aware pyramid aggregation (RPA) module. In order to adaptively divide the feature maps into a set of semantic-independent regions, we develop an attention mechanism and integrate it into the spatial pyramid network to evaluate the semantic similarity of different regions. We further develop an adaptive pyramid fusion (APF) module to dynamically fuse the multi-level features generated from the decoder to refining the segmentation results. We conducted extensive experiments on a famous public ultrasound nerve image segmentation dataset. Experimental results demonstrate that our method consistently outperforms our rivals in terms of segmentation accuracy. The code is available at https://github.com/jsonliu-szu/RAGCM.

A Two-Phase Approach using Mask R-CNN and 3D U-Net for High-Accuracy Automatic Segmentation of Pancreas in CT Imaging

Background and objectiveThe size, shape, and position of the pancreas are affected by the patient characteristics such as age, sex, adiposity. Owing to more complex anatomical structures (size, shape, and position) of the pancreas, specialists have some difficulties in the analysis of pancreatic diseases (diabetes, pancreatic cancer, pancreatitis). Therefore, the treatment of the disease requires enormous time and depends on the experience of specialists. In order to decrease the rate of pancreatic disease deaths and to assist the specialist in the analysis of pancreatic diseases, automatic pancreas segmentation techniques have been actively developed in the research article for many years. MethodsAlthough the rapid growth of deep learning and proving satisfactory performance in many medical image processing and computer vision applications, the maximum Dice Similarity Coefficients (DSC) value of these techniques related to automatic pancreas segmentation is only around 85% due to complex structure of the pancreas and other factors. Contrary to previous techniques which are required significantly higher computational power and memory, this paper suggests a novel two-phase approach for high-accuracy automatic pancreas segmentation in computed tomography (CT) imaging. The proposed approach consists of two phases; (1) Pancreas Localization, where the rough pancreas position is detected on the 2D CT slice by adopting Mask R-CNN model, (2) Pancreas Segmentation, where the segmented pancreas region is produced by refining the candidate pancreas region with 3D U-Net on the 2D sub-CT slices generated in the first phase. Both qualitative and quantitative assessments of the proposed approach are performed on the NIH data set. ResultsIn order to evaluate the achievement of the recommended approach, a total of 16 different automatic pancreas segmentation techniques reported in the literature are compared by utilizing performance assessment procedures which are Dice Similarity Coefficient (DSC), Jaccard Index (JI), Precision (PRE), Recall (REC), Pixel Accuracy (ACC), Specificity (SPE), Receiver Operating Characteristics (ROC) and Area under ROC curve (AUC). The average values of DSC, JI, REC and ACC are computed as 86.15%, 75.93%, 86.27%, 86.27% and 99.95% respectively, which are the best values among well-established studies for automatic pancreas segmentation. ConclusionIt is demonstrated with qualitative and quantitative results that our suggested two-phase approach creates more favorable results than other existing approaches.

Detection of brain tumor using CNN and ML

An automated neurological disorder identification system that uses computer vision on magnetic resonance imaging to locate brain tumors (MRI). The most common and dangerous form of brain cancer is gliomas. Gliomas are tumors that, at their most advanced stage, result in a much shorter life span. Preparing for therapy is an important step in maintaining a better quality of life for oncology patients. Magnetic resonance imaging (MRI) is a technique for examining the structures and components of the human body as well as for medical diagnosis, determining the stage of disease, and monitoring without the use of ionizing radiation. The significant spatial and structural changeability of brain tumors complicates segmentation. As a result, an automatic and consistent segmentation technique is used, based on Convolutional Neural Networks (CNN). Because of the relatively low number of network weights, the use of small kernels enables the development of a deeper architecture, with such a positive effect on over-fitting. It also explores the use of intensity normalization as a pre-processing phase, which is not widely used in segmentation techniques based on the Convolution Neural Network, but has been shown to be efficient in segmenting brain tumors using Magnetic Resonance Imaging (MRI) in conjunction with data augmentation.

Dual-task performance is associated with brain MRI Morphometry in individuals with mild cognitive impairment.

Cognitive impairment is a critical health problem in the elderly population. Research has shown that patients with mild cognitive impairment (MCI) may develop dementia in later years. Therefore, early identification of MCI could allow for interventions to help delay the progression of this devastating disease. Our objective in this study was to detect the early presence of MCI in elderly patients via neuroimaging and dual-task performance. Brain MRI scans from 21 older adult volunteers, including cognitively healthy adults (HA, n = 9, age = 68-79 years) and mild cognitively impaired (MCI, n = 12, age = 66-92 years) were analyzed using automatic segmentation techniques. Regional volume, surface area, and thickness measures were correlated with simultaneous performance of motor and cognitive tasks (dual-task) within a novel upper-extremity function (UEF) test, using multivariate analysis of variance models. We found significant associations of dual-task performance with volume of five cortical brain regions (P≤.048) and thickness of 13 regions (P≤.043) within the frontal, temporal, and parietal lobes. There was a significant interaction effect of cognitive group on dual-task score for the inferior temporal gyrus volume (P≤.034), and the inferior parietal lobule, inferior temporal gyrus, and middle temporal gyrus average thickness (P≤.037). This study highlighted the potential of dual-tasking and MRI morphometric changes as a simple and accurate tool for early detection of cognitive impairment among community-dwelling older adults. The strong interaction effects of cognitive group on UEF dual-task score suggest higher association between atrophy of these brain structures and compromised dual-task performance among the MCI group.

Hippocampal subfields atrophy contribute more to cognitive impairment in middle-aged patients with type 2 diabetes rather than microvascular lesions.

Neurodegeneration and microvascular lesions are related to cognitive impairment in type 2 diabetes mellitus (T2DM). We aimed to use the volume of hippocampal subfields and the burden of white matter hyperintensities (WMH) as neurodegeneration and microangiopathy markers, respectively, to investigate their potential associations with cognitive impairment in T2DM patients. A total of 76 T2DM patients and 45 neurologically unimpaired normal controls were enrolled between February 2016 to August 2018. All participants underwent structural magnetic resonance imaging (MRI) and Montreal Cognitive Assessment (MoCA). The T2DM patients were divided into the T2DM without mild cognitive impairment (T2noMCI) group (n = 44) and the T2DM with mild cognitive impairment (T2MCI) group (n = 32) according to MoCA scores. We used automatic brain segmentation and quantitative technique to assess the volume of twelve hippocampal subfields and WMH on MRI. We used age, sex, education, and total intracranial volume as our covariates and the Bonferroni method for multiple comparison correction. Both the T2MCI group and T2noMCI group showed significant hippocampal subfields atrophy compared to the controls, which were mainly in the left hippocampal tail, left CA1, bilateral molecular layer, bilateral dentate gyrus, and bilateral CA4 (all p < 0.0042). No significant differences in the volume of total WMH, deep-WMH, and periventricular-WMH were found among the three groups. The HbA1c levels were significantly negatively correlated with hippocampal atrophy, and the MoCA scores were positively correlated with bilateral hippocampal volume in T2DM patients and all samples. Mediation analyses demonstrated that the association of HbA1c levels with cognitive function was mediated by hippocampal subfields volume. Widespread hippocampal atrophies across the subfields have been found in middle-aged T2DM patients, which was positively correlated with the MoCA scores and negatively correlated with the HbA1c levels. The association of HbA1c levels with cognitive function was mediated by some crucial hippocampal subfields volume. In middle-aged patients with T2DM, the neurodegeneration is more strongly associated with cognitive impairment than microvascular lesions. Trail Registeration This study was registered on Clinical-Trails.gov (NCT02738671).