Three-dimensional Segmentation Research Articles

Unraveling Spatial Heterogeneity in Mass Spectrometry Imaging Data with GraphMSI.

Mass spectrometry imaging (MSI) provides valuable insights into metabolic heterogeneity by capturing in situ molecular profiles within organisms. One challenge of MSI heterogeneity analysis is performing an objective segmentation to differentiate the biological tissue into distinct regions with unique characteristics. However, current methods struggle due to the insufficient incorporation of biological context and high computational demand. To address these challenges, a novel deep learning-based approach is proposed, GraphMSI, which integrates metabolic profiles with spatial information to enhance MSI data analysis. Our comparative results demonstrate GraphMSI outperforms commonly used segmentation methods in both visual inspection and quantitative evaluation. Moreover, GraphMSI can incorporate partial or coarse biological contexts to improve segmentation results and enable more effective three-dimensional MSI segmentation with reduced computational requirements. These are facilitated by two optional enhanced modes: scribble-interactive and knowledge-transfer. Numerous results demonstrate the robustness of these two modes, ensuring that GraphMSI consistently retains its capability to identify biologically relevant sub-regions in complex practical applications. It is anticipated that GraphMSI will become a powerful tool for spatial heterogeneity analysis in MSI data.

Federated Learning with Privacy Preserving for Multi- Institutional Three-Dimensional Brain Tumor Segmentation.

Brain tumors are complex diseases that require careful diagnosis and treatment. A minor error in the diagnosis may easily lead to significant consequences. Thus, one must place a premium on accurately identifying brain tumors. However, deep learning (DL) models often face challenges in obtaining sufficient medical imaging data due to legal, privacy, and technical barriers hindering data sharing between institutions. This study aims to implement a federated learning (FL) approach with privacy-preserving techniques (PPTs) directed toward segmenting brain tumor lesions in a distributed and privacy-aware manner. The suggested approach employs a model of 3D U-Net, which is trained using federated learning on the BraTS 2020 dataset. PPTs, such as differential privacy, are included to ensure data confidentiality while managing privacy and heterogeneity challenges with minimal communication overhead. The efficiency of the model is measured in terms of Dice similarity coefficients (DSCs) and 95% Hausdorff distances (HD95) concerning the target areas concerned by tumors, which include the whole tumor (WT), tumor core (TC), and enhancing tumor core (ET). In the validation phase, the partial federated model achieved DSCs of 86.1%, 83.3%, and 79.8%, corresponding to 95% values of 25.3 mm, 8.61 mm, and 9.16 mm for WT, TC, and ET, respectively. On the final test set, the model demonstrated improved performance, achieving DSCs of 89.85%, 87.55%, and 86.6%, with HD95 values of 22.95 mm, 8.68 mm, and 8.32 mm for WT, TC, and ET, respectively, which indicates the effectiveness of the segmentation approach, and its privacy preservation. This study presents a highly competitive, collaborative federated learning model with PPTs that can successfully segment brain tumor lesions without compromising patient data confidentiality. Future work will improve model generalizability and extend the framework to other medical imaging tasks.

Semantic segmentation via fusing 2D image and 3D point cloud data with shared multi-layer perceptron

ABSTRACT Three-dimensional (3D) semantic segmentation based on point clouds has become a critical technology in the field of intelligent spatial perception and scene understanding. However, most existing methods cannot fully exploit the spatial feature of 3D point cloud data and the orderliness of two-dimensional (2D) image information, resulting in an inability to effectively improve segmentation accuracy. This study proposes a novel 2D image and 3D point cloud fusion method named shared multi-layer perceptron fusion semantic segmentation (SMFusionSeg) for semantic segmentation. The rich features of 2D image segmentation and spatial information of 3D point clouds are integrated by designing a fusion architecture that facilitates the transfer of 2D semantics to 3D semantics. Specifically, the fusion architecture concatenates the features from both 2D and 3D domains, which are then further integrated through a shared multi-layer perceptron (MLP) and optimized using an attention mechanism to enhance feature effectiveness and distinctiveness. Moreover, a knowledge distillation strategy is introduced to improve the learning capability and segmentation accuracy in parsing complex scenes. Experimental results on the SemanticKITTI dataset demonstrate that the proposed SMFusionSeg achieves a mean Intersection over Union ( mIoU ) of 65.4%, significantly outperforming traditional single-modal methods and many existing segmentation techniques, thereby effectively enhancing the precision and robustness of geographic feature recognition.

A lightweight multi-scale multi-angle dynamic interactive Transformer-CNN fusion model for 3D medical image segmentation

Combining Convolutional Neural Network(CNN) and Transformer has become one of the mainstream methods for three-dimensional (3D) medical image segmentation. However, the complexity and diversity of target forms in 3D medical images require models to capture complex feature information for segmentation, resulting in an excessive number of parameters which are not conducive to training and deployment. Therefore, we have developed a lightweight 3D multi-target semantic segmentation model. In order to enhance contextual texture connections and reinforce the expression of detailed feature information, we designed a multi-scale and multi-angle feature interaction module to enhance feature representation by interacting multi-scale features from different perspectives. To address the issue of attention collapse in Transformers, leading to the neglect of other detailed feature learning, we utilized local features as dynamic parameters to interact with global features, dynamically grouping and learning critical features from global features, thereby enhancing the model's ability to learn detailed features. While ensuring the segmentation capability of the model, we aimed to keep the model lightweight, resulting in a total of 9.63M parameters. Extensive experiments were conducted on public datasets ACDC and Brats2018, as well as a private dataset, Temporal Bone CT. The results indicate that our proposed model is more competitive compared to the latest techniques in 3D medical image segmentation.

Three-Dimensional Instance Segmentation Using the Generalized Hough Transform and the Adaptive n-Shifted Shuffle Attention.

The progress of 3D instance segmentation techniques has made it essential for several applications, such as augmented reality, autonomous driving, and robotics. Traditional methods usually have challenges with complex indoor scenes made of multiple objects with different occlusions and orientations. In this work, the authors present an innovative model that integrates a new adaptive n-shifted shuffle (ANSS) attention mechanism with the Generalized Hough Transform (GHT) for robust 3D instance segmentation of indoor scenes. The proposed technique leverages the n-shifted sigmoid activation function, which improves the adaptive shuffle attention mechanism, permitting the network to dynamically focus on relevant features across various regions. A learnable shuffling pattern is produced through the proposed ANSS attention mechanism to spatially rearrange the relevant features, thus augmenting the model's ability to capture the object boundaries and their fine-grained details. The integration of GHT furnishes a vigorous framework to localize and detect objects in the 3D space, even when heavy noise and partial occlusions are present. The authors evaluate the proposed method on the challenging Stanford 3D Indoor Spaces Dataset (S3DIS), where it establishes its superiority over existing methods. The proposed approach achieves state-of-the-art performance in both mean Intersection over Union (IoU) and overall accuracy, showcasing its potential for practical deployment in real-world scenarios. These results illustrate that the integration of the ANSS and the GHT yields a robust solution for 3D instance segmentation tasks.

Estimation of outer-wall length in optimizing cochlear implantation in malformed inner ears

Estimation of cochlear length is gaining attention in the field of cochlear implants (CIs), mainly for selecting of CI electrode lengths. The currently available tools to estimate the cochlear duct length (CDL) are only valid for normal inner anatomy. However, inner ear malformation (IEM) types are associated with different degrees of cystic apices, limiting the application of CDL equations of normal anatomy inner ear. Therefore, this study aimed to understand the degree to which the outer wall (OW) is observed in different malformation types and to formulate mathematical equations to estimate the OW length (OWL) from cochlear parameters, namely the basal turn diameter (A-value) and width (B-value). Three-dimensional (3D) segmentation of promontory and fluid parts of the inner ear was performed to understand the extent to which the OW is visible to measure the OWL manually. Enlarged vestibular aqueduct syndrome (EVAS) was diagnosed in 37 ears, which consistently showed the extent of the OW to an angular depth of 540°, beyond which the cystic apex starts. Incomplete partition (IP) type I was observed in 30 ears, with the OW extending to only 360° of angular depth. IP type II was observed in 35 ears, with the OW extending to 450° of angular depth. IP type III was identified in 24 ears, with the OW observed for 540° of angular depth. Cavity-type malformations were observed in 36 ears, and circumference was measured in the axial view. A strong positive linear correlation was observed between the manually measured OWL and cochlear parameters for all malformation types analyzed. A multiple linear regression model was applied to formulate mathematical equations, which was further used to create a software application for estimating OWLs in IEM types, using cochlear parameters as inputs.

Fully automated method for three-dimensional segmentation and fine classification of mixed dentition in cone-beam computed tomography using deep learning

ObjectiveTo establish a high-precision, automated model using deep learning for the fine classification and three-dimensional (3D) segmentation of mixed dentition in cone-beam computed tomography (CBCT) images. MethodsA high-precision, automated deep learning model was built based on modified nnU-Net and U-Net networks and was used to classify and segment mixed dentition. It was trained on a series of 336 CBCT scans and tested using 120 mixed dentition CBCT scans from three centers and 143 permanent dentition CBCT scans from a public dataset. The diagnostic performance of the model was assessed and compared with those of two observers with different seniority levels. ResultsThe model achieved accurate classification and segmentation of specific tooth positions in the internal and external mixed dentition datasets (Dice similarity coefficient: 0.964 vs. 0.951; Jaccard coefficient: 0.931 vs. 0.921; precision: 0.963 vs. 0.945; recall: 0.945 vs. 0.941; F-1 score: 0.954 vs. 0.943). These indices consistently exceeded 0.9 across multiple conditions, including fillings, malocclusion, and supernumerary tooth, with an average symmetric surface distance of 0.091 ± 0.029 mm. For permanent dentition, the Dice similarity and Jaccard coefficients exceeded 0.90, the average symmetric surface distance was 0.190 ± 0.092 mm, and precision and recall exceeded 0.94. With the aid of the model, the performance of junior dentists in mixed dentition classification and segmentation improved significantly; in contrast, there was no significant improvement in the performance of senior dentists. The speed of segmentation conducted by the dentists increased by 20.9–22.8 times. ConclusionThe artificial intelligence model has strong clinical applicability, robustness, and generalizability for mixed and permanent dentition. Clinical significanceThe precise classification and 3D segmentation of mixed dentition in dentofacial deformities, supernumerary teeth, and metal artifacts present challenges. This study developed a deep learning approach to analyze CBCT scans, enhancing diagnostic accuracy and efficacy. It facilitates detailed measurements of tooth morphology and movement as well as informed orthodontic planning and orthotic design. Additionally, this method supports dental education by assisting doctors in explaining CBCT images to the families of pediatric patients.

Predictive Value of Multi-Phase CT Radiomics in Delineating Early and Advanced T Staging of Colon Cancer

This study leveraged the power of multi-phase CT radiomics, which extracts detailed features from multi-phase images, to explore the distinction between early (T1-T2) and advanced (T3-T4) colon cancer stages in each of multiple phases, providing valuable insights to healthcare professionals and enhancing their decision-making capabilities. A total of 191 patients with surgically confirmed primary colon cancer were retrospectively included, and multi-phase CT scans (non-enhanced contrast phase, arterial phase, portal venous phase, and delayed phase) were conducted within one week before surgery. Three-dimensional segmentation of colonic tumors was performed on the images of the four phases, and radiomics features of each colonic tumor were automatically extracted. Minimum redundancy maximum relevance (mRMR) was applied to features selection in each of the four phases. The least absolute shrinkage and selection operator logistic regression was conducted to determine the association between radiomics features and early (T1-T2) and advanced (T3-T4) stages of colon cancer. Additionally, diagnostic performance comparison was carried out in four phases. The mean (±SD) age of the 191 individuals was 61.87±13.137 years, with females comprising 43.5% of the cohort. The selected features for the non-enhanced, arterial, portal venous, and delayed phases numbered 7, 11, 6, and 10, respectively. In the test set, the AUC values for the on-enhanced, arterial, portal venous, and delayed phases were 0.86 (0.76-0.96), 0.84 (0.73-0.94), 0.82 (0.71-0.93), and 0.86 (0.75-0.97), with corresponding accuracies of 0.84, 0.80, 0.75, and 0.88, sensitivities of 0.73, 0.64, 0.86, and 0.68, and specificities of 0.91, 0.91, 0.68, and 1.00, respectively. DeLong's test revealed no statistically significant differences in the AUC values between the four phases within the test sets (P = 0.3233~ 0.9912). Multi-phase CT radiomics demonstrated substantial value in differentiating between early (T1-T2) and advanced (T3-T4) stages of patients with colon cancer.

MG-Net: A fetal brain tissue segmentation method based on multiscale feature fusion and graph convolution attention mechanisms

Background and Objective:Fetal brain tissue segmentation provides foundational support for comprehensively understanding the neurodevelopment of normal and congenital disease-affected fetuses. Manual labeling is very time-consuming, and automated segmentation methods can greatly improve the efficiency of doctors. At the same time, fetal brain tissue undergoes various changes throughout the pregnancy, leading to a continuous change in tissue contrast, which greatly increases the difficulty of training segmentation methods. This study aims to develop an automated segmentation model that can efficiently and accurately segment fetal brain tissue, improving the workflow for medical professionals. Methods:We propose a novel deep learning-based segmentation model that incorporates three innovative components: Firstly, a new Dual Dilated Attention Block (DDAB) is proposed in the encoder part to enhance the feature extraction of local spatial and structural contextual information. Secondly, a Multi-scale Deformable Transformer (MSDT) is integrated into the bottleneck to improve the feature extraction of global information on local spatial and structural contextual information. Thirdly, we use a novel block based on Graph Convolution Attention (GCAB) in the decoder, which effectively enhances the features at the decoder.The code is available at https://github.com/unicoco7/MG-Net/. Results:We trained and tested on the FeTA 2021 and FeTA 2022 datasets, and evaluated using seven popular metrics, including Dice, IoU, MAE, BoundaryF, PRE, SEN, and SPE. Compared to the current state-of-the-art 3D segmentation models such as nnFormer, SwinUNETR, and 3DUX-net, our proposed method has surpassed all of them in metrics like Dice, IoU, and MAE. Specifically, on the FeTA 2021 dataset, our model achieved a Dice of 0.8666, an IoU of 0.7646, and an MAE of 0.0027; on the FeTA 2022 dataset, it achieved a Dice of 0.8552, an IoU of 0.7470, and an MAE of 0.0005. Conclusion:In this paper, we propose a model for three-dimensional fetal brain tissue segmentation based on multi-scale feature fusion and graph convolution attention mechanism, and conduct experimental evaluation on the FeTA 2021 and FeTA 2022 datasets. Understanding the boundaries of fetal brain tissue is crucial for doctors’ diagnosis, so the proposed model is expected to improve the speed and accuracy of doctors’ diagnoses.

Revealing in vivo broiler chicken growth state: Integrating CT imaging and deep learning for non-invasive reproductive phenotypic measurement

The measurement of body dimensions in broiler chickens has long been of great interest to the poultry industry, especially regarding reproductive phenotypes closely linked to breeding traits and the growth status of roosters. Existing measurement methods suffer from subjectivity, destructiveness, and various limitations. Therefore, we propose a novel method for the in vivo measurement of broiler chicken reproductive phenotype based on a three-dimensional medical imaging segmentation network. Leveraging our proposed FDTR medical imaging segmentation algorithm, this method achieves robust segmentation performance on a broiler chicken dataset. However, due to the morphological diversity and extreme class imbalance of broiler chicken reproductive phenotypes, we introduce a meta-learning paradigm and design a specialized decoder path. Ultimately, we establish relationships between the predicted results obtained from the segmentation network and the reproductive phenotypes to achieve phenotypic measurement. To evaluate this method, we collected and constructed the YF2023 broiler chicken reproductive phenotype dataset. Extensive cross-validation experiments demonstrate that the proposed method effectively measures the reproductive phenotypes of live roosters using computed tomography (CT) medical imaging. The proposed segmentation model achieves a mean fold dice similarity coefficient (DSC) of 0.6353, a mean fold Hausdorff distance (HD) of 11.84 mm, and a mean fold average volume distance (AVD) of 1.72 mm3. In addition, we evaluated our model’s generalization performance on unseen data, where the model achieved a DSC of 0.6825, an HD of 7.58 mm, and an AVD of 1.40 mm3. The predicted results exhibit a mean correlation coefficient of 66.18% with the weights of reproductive phenotype. This validates the enormous potential of the method in broiler chicken breeding and provides new insights and solutions for the accurate segmentation of broiler chicken reproductive phenotype. The code is available at https://github.com/Github-XKou/MetaFDTR.

Arkitekt: streaming analysis and real-time workflows for microscopy.

Quantitative microscopy workflows have evolved dramatically over the past years, progressively becoming more complex with the emergence of deep learning. Long-standing challenges such as three-dimensional segmentation of complex microscopy data can finally be addressed, and new imaging modalities are breaking records in both resolution and acquisition speed, generating gigabytes if not terabytes of data per day. With this shift in bioimage workflows comes an increasing need for efficient orchestration and data management, necessitating multitool interoperability and the ability to span dedicated computing resources. However, existing solutions are still limited in their flexibility and scalability and are usually restricted to offline analysis. Here we introduce Arkitekt, an open-source middleman between users and bioimage apps that enables complex quantitative microscopy workflows in real time. It allows the orchestration of popular bioimage software locally or remotely in a reliable and efficient manner. It includes visualization and analysis modules, but also mechanisms to execute source code and pilot acquisition software, making 'smart microscopy' a reality.

Intelligent diagnostic method for developmental hip dislocation

BackgroundDevelopmental dislocation of the hip joint (DDH) is a condition that severely threatens children’s healthy growth. Without timely and correct treatment, it will lead to osteoarthritis and hip dysfunction in the evolution of children.ObjectiveIt is essential to develop an intelligent model for diagnosing hip dislocation and performing accurate quantitative analysis.MethodsIn this paper, 46 cases of computed tomography (CT) images were retrospectively collected, including 19 cases of hip dislocation and 27 cases of healthy people. The experiment first uses ITK-SNAP to sketch the ilium and femoral head in the original image. Then, it uses 3D U-Net to send the label of the background, ilium, and femoral head into three channels, respectively, to realize the three-dimensional segmentation of the ilium and femoral head. Next, the extraction of the surface of the acetabulum and femoral head is performed. Subsequently, the erroneous points are eliminated, and the spherical surfaces of the acetabulum and femoral head are fitted using the least squares method. Ultimately, the spherical center distance is calculated quantitatively to predict whether the hip joint is dislocated.ResultsUnder the independent test set, the segmentation average dice coefficients of the ilium and femoral head are 89% and 93%, respectively. The spherical center distance between the acetabulum and femoral head is calculated quantitatively. If the value exceeds 10 mm, it is considered a hip dislocation. Compared with the doctor’s diagnosis, the accuracy result is 94.4%.ConclusionThis paper successfully implements a precise and automated intelligent diagnostic system for the identification of hip dislocation. Commencing with the development of a 3D segmentation algorithm for the ilium and femoral head, we further introduce a novel method that computes the spherical distance for the prediction of hip dislocation. This approach provides robust quantitative analysis, thereby facilitating more informed clinical decision-making.

Improved Cascade-RCNN for automatic detection of coronary artery plaque in multi-angle fusion CPR images

Coronary heart disease is a disease that seriously endangers human health and life which is caused by plaque formation due to coronary artery atherosclerosis or spasm. The detection of coronary plaques through medical imaging is a non-destructive and fast diagnostic method, which holds significant medical and clinical value for the diagnosis of coronary heart disease. In this paper, We proposed an automatic detecting method for coronary artery vulnerable plaque based on CTA image sequence. We collected CTA image sequences from 132 patients and obtained the coronary artery tree by performing three-dimensional (3D) segmentation. The coronary artery centerline was extracted using the skeleton thinning method. To address the issue of insufficient features in a single CPR image, we constructed Curved Planar Reconstructed (CPR) images from multiple directions perpendicular to the coronary artery, following the centerline. In total, we established 8797 images in the training dataset and 1553 images in the test dataset. We proposed an attentive detection method that fused a new Cascade RCNN ResNet50-FPN neural network model with a convolutional attention module (CBAM). This method achieved automatic recognition and detection of plaques on the two-dimensional multi-angle fused CPR images. The proposed ResNet50-FPN network performed feature extraction, and CBAM was added after the first and last convolutional layers to enhance the network’s attention to plaque features. Our experimental results demonstrate that deep learning neural networks can provide a feasible approach to automatically detecting coronary artery plaques. Our method achieved a plaque detection accuracy of 94.6%, outperforming the RCNN method proposed by Zriek.

Joint segmentation of sternocleidomastoid and skeletal muscles in computed tomography images using a multiclass learning approach

Deep-learning-based methods can improve robustness against individual variations in computed tomography (CT) images of the sternocleidomastoid muscle, which is a challenge when using conventional methods based on probabilistic atlases are used for automatic segmentation. Thus, this study proposes a novel multiclass learning approach for the joint segmentation of the sternocleidomastoid and skeletal muscles in CT images, and it employs a two-dimensional U-Net architecture. The proposed method concurrently learns and segmented segments the sternocleidomastoid muscle and the entire skeletal musculature. Consequently, three-dimensional segmentation results are generated for both muscle groups. Experiments conducted on a dataset of 30 body CT images demonstrated segmentation accuracies of 82.94% and 92.73% for the sternocleidomastoid muscle and entire skeletal muscle compartment, respectively. These results outperformed those of conventional methods, such as the single-region learning of a target muscle and multiclass learning of specific muscle pairs. Moreover, the multiclass learning paradigm facilitated a robust segmentation performance regardless of the input image range. This highlights the method’s potential for cases that present muscle atrophy or reduced muscle strength. The proposed method exhibits promising capabilities for the high-accuracy joint segmentation of the sternocleidomastoid and skeletal muscles and is effective in recognizing skeletal muscles, thus, it holds promise for integration into computer-aided diagnostic systems for comprehensive musculoskeletal analysis. These findings are expected to enhance medical image analysis techniques and their applications in clinical decision support systems.

Automated endometrial identification and volume calculation in normal uteri using a novel smart ERA technique

To evaluate the repeatability of a novel automated technique called Smart ERA (Smart Endometrial Receptivity Analysis) for the automated segmentation and volume calculation of the endometrium in patients with normal uteri,, and to compare the agreement of endometrial volume measurements between Smart ERA, the semi-automated Virtual Organ Computer-aided Analysis (VOCAL) technique and manual segmentation. This retrospective study evaluated endometrial volume measurement in infertile patients who underwent frozen-thawed embryo transfer (FET). Transvaginal three-dimensional ultrasound scans were performed using a Resona R9 ultrasound machine. Data was collected from patients between 2021 and 2022. Patients with normal uteri and optimal ultrasound images were included. Endometrial volumes were measured using Smart ERA, VOCAL at 15° rotation, and manual segmentation. Intra-observer repeatability and agreement between techniques were assessed using the intraclass correlation coefficient (ICC) and Bland–Altman analysis. A total of 407 female patients were evaluated (mean age 33.2 ± 4.7 years). The repeatability of Smart ERA showed an ICC of 0.983 (95% CI 0.984–0.991). The agreement between Smart ERA and the manual method, Smart ERA and VOCAL, and VOCAL and the manual method, as assessed by ICC, were 0.986 (95% CI 0.977–0.990), 0.943 (95% CI 0.934–0.963), and 0.951 (95% CI 0.918–0.969), respectively. The Smart ERA technique required approximately 3 s for endometrial volume calculation, while VOCAL took around 5 min and the manual segmentation method took approximately 50 min. The Smart-ERA software, which employs a novel three-dimensional segmentation algorithm, demonstrated excellent intra-observer repeatability and high agreement with both VOCAL and manual segmentation for endometrial volume measurement in women with normal uteri. However, these findings should be interpreted with caution, as the algorithm's performance may not be generalizable to populations with different uterine characteristic. Additionally, Smart ERA required significantly less time compared to VOCAL and manual segmentation.

Postmortem Computed Tomography – Based Body Weight Estimation in Korean Infants Using Volume and Multiplication Factors

Postmortem computed tomography (PMCT) is used in forensic medicine worldwide due to its ability to non-invasively visualize injuries, hemorrhage, and estimate volume. In the autopsy of infants, assessing nutritional conditions such as weight is crucial for identifying neglect. This study aims to evaluate the usefulness of retrospectively estimating the weight of Korean infants using PMCT-based volume and multiplication factors, even when the body has been cremated. A total of 44 cases of infant death (under 12 months) were analyzed. PMCT images were obtained before autopsy. Autopsy records and documentation provided by the police at the time of autopsy were reviewed to determine the weight (g) of the infant. PMCT-based infant volumes (mL) were estimated using a three-dimensional semi-automatic segmentation method. Multiplication factors (g/mL) were calculated by dividing the weight recorded at autopsy by the PMCT-based volume, yielding a mean of 1.047 g/mL, ranging from 1.014 g/mL to 1.085 g/mL. The mean absolute error compared to weights recorded at autopsy was 95 g. Significant discrepancies were observed between weights recorded at the scene or medical center and those measured at autopsy. This study demonstrates that PMCT-based weight estimation for Korean infants is a reliable method and has the potential for retrospectively validating incorrect weight measurements and addressing inconsistencies in recorded weight data.

Deep-learning-based method for the segmentation of ureter and renal pelvis on non-enhanced CT scans

This study aimed to develop a deep-learning (DL) based method for three-dimensional (3D) segmentation of the upper urinary tract (UUT), including ureter and renal pelvis, on non-enhanced computed tomography (NECT) scans. A total of 150 NECT scans with normal appearance of the left UUT were chosen for this study. The dataset was divided into training (n = 130) and validation sets (n = 20). The test set contained 29 randomly chosen cases with computed tomography urography (CTU) and NECT scans, all with normal appearance of the left UUT. An experienced radiologist marked out the left renal pelvis and ureter on each scan. Two types of frameworks (entire and sectional) with three types of DL models (basic UNet, UNet3 + and ViT-UNet) were developed, and evaluated. The sectional framework with basic UNet model achieved the highest mean precision (85.5%) and mean recall (71.9%) on the test set compared to all other tested methods. Compared with CTU scans, this method had higher axial UUT recall than CTU (82.5% vs 69.1%, P < 0.01). This method achieved similar or better visualization of UUT than CTU in many cases, however, in some cases, it exhibited a non-ignorable false-positive rate. The proposed DL method demonstrates promising potential in automated 3D UUT segmentation on NECT scans. The proposed DL models could remarkably improve the efficiency of UUT reconstruction, and have the potential to save many patients from invasive examinations such as CTU. DL models could also serve as a valuable complement to CTU.

7T-high resolution MRI-derived radiomic analysis for the identification of symptomatic intracranial atherosclerotic plaques.

High-resolution magnetic resonance imaging (HR-MRI) allows for detailed visualization of intracranial atherosclerotic plaques. Radiomics can be used as a tool for objective quantification of the plaque's characteristics. We analyzed the radiomics features (RFs) obtained from 7 T HR-MRI of patients with intracranial atherosclerotic disease (ICAD) to determine distinct characteristics of culprit and non-culprit plaques. Patients with stroke due to ICAD underwent HR-MRI. Culprit plaques in the vascular territory of the stroke were identified. Degree of stenosis, area degree of stenosis and plaque burden were calculated. A three-dimensional segmentation of the plaque was performed, and RFs were obtained. A machine learning model for prediction and identification of culprit plaques using significantly different RFs was evaluated. The study included 33 patients with ICAD as stroke etiology. Univariate analysis revealed 24 RFs in pre-contrast MRI, 21 in post-contrast MRI, 13 RFs that were different between pre and post contrast MRIs. Additionally, six shape-based RFs significantly differed from culprit and non-culprit plaques. The random forest model achieved an accuracy rate of 81% (88% sensitivity and 75% specificity) in identifying culprit plaques in the independent testing dataset. This model successfully identified the culprit plaques in all patients during the testing phase. Symptomatic plaques had a distinct signature RFs compared to other plaques within the same subject. A machine learning model built with RFs successfully identified the symptomatic atherosclerotic plaques in most cases. Radiomics is a promising tool for stratification of plaques in patients with ICAD.

Past, present, and future perspectives of ultrasound-guided ablation of liver tumors: Where could artificial intelligence lead interventional oncology?

The first ablation procedures for small hepatocellular carcinomas were percutaneous ethanol injection under ultrasound (US) guidance. Later, radiofrequency ablation was shown to achieve larger coagulation areas than percutaneous ethanol injection and became the most used ablation technique worldwide. In the past decade, microwave ablation systems have achieved larger ablation areas than radiofrequency ablation, suggesting that the 3-cm barrier could be broken in the treatment of liver tumors. Likewise, US techniques to guide percutaneous ablation have seen important progress. Contrast-enhanced US (CEUS) can define and target the tumor better than US and can assess the size of the ablation area after the procedure, which allows immediate retreatment of the residual tumor foci. Furthermore, fusion imaging fuses real-time US images with computed tomography or magnetic resonance imaging with significant improvements in detecting and targeting lesions with low conspicuity on CEUS. Recently, software powered by artificial intelligence has been developed to allow three-dimensional segmentation and reconstruction of the anatomical structures, aiding in procedure planning, assessing ablation completeness, and targeting the residual viable foci with greater precision than CEUS. Hopefully, this could lead to the ablation of tumors up to 5-7 cm in size.

Structural and molecular characterization of astrocyte and vasculature connectivity in the mouse hippocampus and cortex.

The relation of astrocytic endfeet to the vasculature plays a key functional role in the neuro-glia-vasculature unit. We characterize the spatial organization of astrocytes and the structural aspects that facilitate their involvement in molecular exchanges. Using double transgenic mice, we performed co-immunostaining, confocal microscopy, and three-dimensional digital segmentation to investigate the biophysical and molecular organization of astrocytes and their intricate endfoot network at the micrometer level in the isocortex and hippocampus. The results showed that hippocampal astrocytes had smaller territories, reduced endfoot dimensions, and fewer contacts with blood vessels compared with those in the isocortex. Additionally, we found that both connexins 43 and 30 have a higher density in the endfoot and the former is overexpressed relative to the latter. However, due to the limitations of the method, further studies are needed to determine the exact localization on the endfoot. The quantitative information obtained in this study will be useful for modeling the interactions of astrocytes with the vasculature.