3D U-Net Research Articles

Clinical Use of Hematoma Volume Based On Automated Segmentation of Chronic Subdural Hematoma Using 3D U-Net.

To propose amethod for calculating hematoma volume based on automatic segmentation of chronic subdural hematoma (CSDH) using 3D U‑net and investigate whether it can be used clinically to predict recurrence. Hematoma volumes manually measured from pre- and postoperative computed tomography (CT) images were used as ground truth data to train 3D U‑net in 200 patients (400 CT scans). Atotal of 215 patients (430 CT scans) were used as test data to output segmentation results from the trained 3D U‑net model. The similarity with the ground truth data was evaluated using Dice scores for pre and postoperative separately. The recurrence prediction accuracy was evaluated by obtaining receiver operating characteristic (ROC) curves for the segmentation results. Using atypical mobile PC, the computation time per case was measured and the average time was calculated. The median Dice score of the test data were preoperative hematoma volume (Pre-HV): 0.764 and postoperative subdural cavity volume (Post-SCV): 0.741. In ROC analyses assessing recurrence prediction, the area under the curve (AUC) of the manual was 0.755 in Pre-HV, whereas the 3D U‑net was 0.735. In Post-SCV, the manual AUC was 0.779; the 3D U‑net was 0.736. No significant differences were found between manual and 3D U‑net for all results. Using amobile PC, the average time taken to output the test data results was 30 s per case. The proposed method is asimple, accurate, and clinically applicable; it can contribute to the widespread use of recurrence prediction scoring systems for CSDH.

Evaluation of an automated clinical decision system with deep learning dose prediction and NTCP model for prostate cancer proton therapy

Objective. To evaluate the feasibility of using a deep learning dose prediction approach to identify patients who could benefit most from proton therapy based on the normal tissue complication probability (NTCP) model. Approach. Two 3D UNets were established to predict photon and proton doses. A dataset of 95 patients with localized prostate cancer was randomly partitioned into 55, 10, and 30 for training, validation, and testing, respectively. We selected NTCP models for late rectum bleeding and acute urinary urgency of grade 2 or higher to quantify the benefit of proton therapy. Propagated uncertainties of predicted ΔNTCPs resulting from the dose prediction errors were calculated. Patient selection accuracies for a single endpoint and a composite evaluation were assessed under different ΔNTCP thresholds. Main results. Our deep learning-based dose prediction technique can reduce the time spent on plan comparison from approximately 2 days to as little as 5 seconds. The expanded uncertainty of predicted ΔNTCPs for rectum and bladder endpoints propagated from the dose prediction error were 0.0042 and 0.0016, respectively, which is less than one-third of the acceptable tolerance. The averaged selection accuracies for rectum bleeding, urinary urgency, and composite evaluation were 90%, 93.5%, and 93.5%, respectively. Significance. Our study demonstrates that deep learning dose prediction and NTCP evaluation scheme could distinguish the NTCP differences between photon and proton treatment modalities. In addition, the dose prediction uncertainty does not significantly influence the decision accuracy of NTCP-based patient selection for proton therapy. Therefore, automated deep learning dose prediction and NTCP evaluation schemes can potentially be used to screen large patient populations and to avoid unnecessary delays in the start of prostate cancer radiotherapy in the future.

Uncertainty estimation- and attention-based semi-supervised models for automatically delineate clinical target volume in CBCT images of breast cancer

ObjectivesAccurate segmentation of the clinical target volume (CTV) of CBCT images can observe the changes of CTV during patients' radiotherapy, and lay a foundation for the subsequent implementation of adaptive radiotherapy (ART). However, segmentation is challenging due to the poor quality of CBCT images and difficulty in obtaining target volumes. An uncertainty estimation- and attention-based semi-supervised model called residual convolutional block attention-uncertainty aware mean teacher (RCBA-UAMT) was proposed to delineate the CTV in cone-beam computed tomography (CBCT) images of breast cancer automatically.MethodsA total of 60 patients who undergone radiotherapy after breast-conserving surgery were enrolled in this study, which involved 60 planning CTs and 380 CBCTs. RCBA-UAMT was proposed by integrating residual and attention modules in the backbone network 3D UNet. The attention module can adjust channel and spatial weights of the extracted image features. The proposed design can train the model and segment CBCT images with a small amount of labeled data (5%, 10%, and 20%) and a large amount of unlabeled data. Four types of evaluation metrics, namely, dice similarity coefficient (DSC), Jaccard, average surface distance (ASD), and 95% Hausdorff distance (95HD), are used to assess the model segmentation performance quantitatively.ResultsThe proposed method achieved average DSC, Jaccard, 95HD, and ASD of 82%, 70%, 8.93, and 1.49 mm for CTV delineation on CBCT images of breast cancer, respectively. Compared with the three classical methods of mean teacher, uncertainty-aware mean-teacher and uncertainty rectified pyramid consistency, DSC and Jaccard increased by 7.89–9.33% and 14.75–16.67%, respectively, while 95HD and ASD decreased by 33.16–67.81% and 36.05–75.57%, respectively. The comparative experiment results of the labeled data with different proportions (5%, 10% and 20%) showed significant differences in the DSC, Jaccard, and 95HD evaluation indexes in the labeled data with 5% versus 10% and 5% versus 20%. Moreover, no significant differences were observed in the labeled data with 10% versus 20% among all evaluation indexes. Therefore, we can use only 10% labeled data to achieve the experimental objective.ConclusionsUsing the proposed RCBA-UAMT, the CTV of breast cancer CBCT images can be delineated reliably with a small amount of labeled data. These delineated images can be used to observe the changes in CTV and lay the foundation for the follow-up implementation of ART.

Patient-specific cerebral 3D vessel model reconstruction using deep learning

Three-dimensional vessel model reconstruction from patient-specific magnetic resonance angiography (MRA) images often requires some manual maneuvers. This study aimed to establish the deep learning (DL)-based method for vessel model reconstruction. Time of flight MRA of 40 patients with internal carotid artery aneurysms was prepared, and three-dimensional vessel models were constructed using the threshold and region-growing method. Using those datasets, supervised deep learning using 2D U-net was performed to reconstruct 3D vessel models. The accuracy of the DL-based vessel segmentations was assessed using 20 MRA images outside the training dataset. The dice coefficient was used as the indicator of the model accuracy, and the blood flow simulation was performed using the DL-based vessel model. The created DL model could successfully reconstruct a three-dimensional model in all 60 cases. The dice coefficient in the test dataset was 0.859. Of note, the DL-generated model proved its efficacy even for large aneurysms (> 10 mm in their diameter). The reconstructed model was feasible in performing blood flow simulation to assist clinical decision-making. Our DL-based method could successfully reconstruct a three-dimensional vessel model with moderate accuracy. Future studies are warranted to exhibit that DL-based technology can promote medical image processing.Graphical

Enhancing Precision in Cardiac Segmentation for Magnetic Resonance-Guided Radiation Therapy Through Deep Learning

IntroductionCardiac substructure dose metrics are more strongly linked to late cardiac morbidities than whole-heart metrics. MR-guided radiation therapy (MRgRT) enables substructure visualization during daily localization, allowing potential for enhanced cardiac sparing. We extend a publicly available state-of-the-art deep learning (DL) framework, nnU-Net, to incorporate self-distillation (nnU-Net.wSD) for substructure segmentation for MRgRT. MethodsEighteen (Institute A) patients who underwent thoracic or abdominal radiation therapy on a 0.35 T MR-guided linac were retrospectively evaluated. On each image, one of two radiation oncologists delineated reference contours of 12 cardiac substructures (chambers, great vessels, and coronary arteries) used to train (n=10), validate (n=3), and test (n=5) nnU-Net.wSD leveraging a teacher-student network and comparing to standard 3D U-Net. The impact of using simulation data or including 3-4 daily images for augmentation during training was evaluated for nnU-Net.wSD. Geometric metrics (Dice similarity coefficient (DSC), mean distance to agreement (MDA), and 95% Hausdorff distance (HD95)), visual inspection, and clinical dose volume histograms (DVHs) were evaluated. To determine generalizability, Institute A's model was tested on an unlabeled dataset from Institute B (n=22) and evaluated via consensus scoring and volume comparisons. ResultsnnU-Net.wSD yielded a DSC (reported mean ± standard deviation) of 0.65±0.25 across the 12 substructures (Chambers: 0.85±0.05, Great Vessels: 0.67±0.19, and Coronary Arteries 0.33±0.16, mean MDA <3 mm, and mean HD95 <9 mm) while outperforming the 3D U-Net (0.583±0.28, p<0.01). Leveraging fractionated data for augmentation improved over a single MR-SIM timepoint (0.579±0.29, p<0.01). Predicted contours yielded DVHs that closely matched the clinical treatment plans where mean and D0.03cc doses deviated by 0.32±0.5 Gy and 1.42±2.6 Gy respectively. No statistically significant differences between Institute A and B volumes (p>0.05) for 11 of 12 substructures with larger volumes requiring minor changes and coronary arteries exhibiting more variability. ConclusionsThis work is a critical step to rapid and reliable cardiac substructure segmentation to improve cardiac sparing in low-field MRgRT.

Real-time segmentation of short videos under VR technology in dynamic scenes

Abstract This work addresses the challenges of scene segmentation and low segmentation accuracy in short videos by employing virtual reality (VR) technology alongside a 3D DenseNet model for real-time segmentation in dynamic scenes. First, this work extracted short videos by frame and removed redundant background information. Then, the volume rendering algorithm in VR technology was used to reconstruct short videos in dynamic scenes in 3D. It enriched the detailed information of short videos, and finally used the 3D DenseNet model for real-time segmentation of short videos in dynamic scenes, improving the accuracy of segmentation. The experiment compared the performance of High resolution network, Mask region based convolutional neural network, 3D U-Net, Efficient neural network models on the Densely annotation video segmentation dataset. The experimental results showed that the segmentation accuracy of the 3D DenseNet model has reached 99.03%, which was 15.11% higher than that of the ENet model. The precision rate reached 98.33%, and the average segmentation time reached 0.64 s, improving the segmentation accuracy and precision rate. It can adapt to various scene situations and has strong robustness. The significance of this research lies in its innovative approach in tackling these issues. By integrating VR technology with advanced deep learning models, we can achieve more precise segmentation of dynamic scenes in short videos, enabling real-time processing. This has significant practical implications for fields such as video editing, VR applications, and intelligent surveillance. Furthermore, the outcomes of this research contribute to advancing computer vision in video processing, providing valuable insights for the development of future intelligent video processing systems.

Enhancement of the Consistency and Connectivity of the Ant-tracking Algorithm via 3D U-Net with Dual-Threshold Iteration

Abstract The ant-tracking algorithm is commonly used to extract faults in geological structures. However, obtaining 3D ant-tracking data requires the calculation of various volume attributes. To obtain satisfactory data, it is necessary to iterate through the parameters of these attributes to achieve reasonable continuity. Moreover, due to the numerous parameters involved, the algorithm can produce different outputs with each execution. In this study, we aimed to enhance the performance of the ant-tracking algorithm by combining it with a basic U-Net structure. The input and corresponding labels to the model are "cubic shaped" 3D data segmented from the original 3D seismic volume to facilitate cross-validation with distinct regions. We used the label data as the single ant-tracking result to minimize the operator’s bias by executing the ant-tracking with several different parameters and executors and then taking the average. An evaluative comparison of three different loss functions (MAE, RMSE, and MSE) was conducted to identify the optimal function for training the model. Across five out of the six metrics, MSE function demonstrated predominant performance, leading to its adoption. Apart from this, a significant number of misinterpreted faults led us to propose the post-processing algorithm named "Dual-Threshold Iteration." It was initially used to extract fine blood vessels branching out from large vessels in medical image segmentation and adapted in our work to ensure a high level of continuity while ignoring worthless noise. Comparison with the F1 score and the number of 3D-connected components confirmed that the proposed method could generate reduced bias and smoothly connected fault structures.

GMAlignNet: multi-scale lightweight brain tumor image segmentation with enhanced semantic information consistency

Although the U-shaped architecture, represented by UNet, has become a major network model for brain tumor segmentation, the repeated convolution and sampling operations can easily lead to the loss of crucial information. Additionally, directly fusing features from different levels without distinction can easily result in feature misalignment, affecting segmentation accuracy. On the other hand, traditional convolutional blocks used for feature extraction cannot capture the abundant multi-scale information present in brain tumor images. This paper proposes a multi-scale feature-aligned segmentation model called GMAlignNet that fully utilizes Ghost convolution to solve these problems. Ghost hierarchical decoupled fusion unit and Ghost hierarchical decoupled unit are used instead of standard convolutions in the encoding and decoding paths. This transformation replaces the holistic learning of volume structures by traditional convolutional blocks with multi-level learning on a specific view, facilitating the acquisition of abundant multi-scale contextual information through low-cost operations. Furthermore, a feature alignment unit is proposed that can utilize semantic information flow to guide the recovery of upsampled features. It performs pixel-level semantic information correction on misaligned features due to feature fusion. The proposed method is also employed to optimize three classic networks, namely DMFNet, HDCNet, and 3D UNet, demonstrating its effectiveness in automatic brain tumor segmentation. The proposed network model was applied to the BraTS 2018 dataset, and the results indicate that the proposed GMAlignNet achieved Dice coefficients of 81.65%, 90.07%, and 85.16% for enhancing tumor, whole tumor, and tumor core segmentation, respectively. Moreover, with only 0.29 M parameters and 26.88G FLOPs, it demonstrates better potential in terms of computational efficiency and possesses the advantages of lightweight. Extensive experiments on the BraTS 2018, BraTS 2019, and BraTS 2020 datasets suggest that the proposed model exhibits better potential in handling edge details and contour recognition.

Training deep learning based dynamic MR image reconstruction using open-source natural videos

To develop and assess a deep learning (DL) pipeline to learn dynamic MR image reconstruction from publicly available natural videos (Inter4K). Learning was performed for a range of DL architectures (VarNet, 3D UNet, FastDVDNet) and corresponding sampling patterns (Cartesian, radial, spiral) either from true multi-coil cardiac MR data (N = 692) or from synthetic MR data simulated from Inter4K natural videos (N = 588). Real-time undersampled dynamic MR images were reconstructed using DL networks trained with cardiac data and natural videos, and compressed sensing (CS). Differences were assessed in simulations (N = 104 datasets) in terms of MSE, PSNR, and SSIM and prospectively for cardiac cine (short axis, four chambers, N = 20) and speech cine (N = 10) data in terms of subjective image quality ranking, SNR and Edge sharpness. Friedman Chi Square tests with post-hoc Nemenyi analysis were performed to assess statistical significance. In simulated data, DL networks trained with cardiac data outperformed DL networks trained with natural videos, both of which outperformed CS (p < 0.05). However, in prospective experiments DL reconstructions using both training datasets were ranked similarly (and higher than CS) and presented no statistical differences in SNR and Edge Sharpness for most conditions.The developed pipeline enabled learning dynamic MR reconstruction from natural videos preserving DL reconstruction advantages such as high quality fast and ultra-fast reconstructions while overcoming some limitations (data scarcity or sharing). The natural video dataset, code and pre-trained networks are made readily available on github.

Deformable registration of magnetic resonance images using unsupervised deep learning in neuro-/radiation oncology

PurposeAccurate deformable registration of magnetic resonance imaging (MRI) scans containing pathologies is challenging due to changes in tissue appearance. In this paper, we developed a novel automated three-dimensional (3D) convolutional U-Net based deformable image registration (ConvUNet-DIR) method using unsupervised learning to establish correspondence between baseline pre-operative and follow-up MRI scans of patients with brain glioma.MethodsThis study involved multi-parametric brain MRI scans (T1, T1-contrast enhanced, T2, FLAIR) acquired at pre-operative and follow-up time for 160 patients diagnosed with glioma, representing the BraTS-Reg 2022 challenge dataset. ConvUNet-DIR, a deep learning-based deformable registration workflow using 3D U-Net style architecture as a core, was developed to establish correspondence between the MRI scans. The workflow consists of three components: (1) the U-Net learns features from pairs of MRI scans and estimates a mapping between them, (2) the grid generator computes the sampling grid based on the derived transformation parameters, and (3) the spatial transformation layer generates a warped image by applying the sampling operation using interpolation. A similarity measure was used as a loss function for the network with a regularization parameter limiting the deformation. The model was trained via unsupervised learning using pairs of MRI scans on a training data set (n = 102) and validated on a validation data set (n = 26) to assess its generalizability. Its performance was evaluated on a test set (n = 32) by computing the Dice score and structural similarity index (SSIM) quantitative metrics. The model’s performance also was compared with the baseline state-of-the-art VoxelMorph (VM1 and VM2) learning-based algorithms.ResultsThe ConvUNet-DIR model showed promising competency in performing accurate 3D deformable registration. It achieved a mean Dice score of 0.975 ± 0.003 and SSIM of 0.908 ± 0.011 on the test set (n = 32). Experimental results also demonstrated that ConvUNet-DIR outperformed the VoxelMorph algorithms concerning Dice (VM1: 0.969 ± 0.006 and VM2: 0.957 ± 0.008) and SSIM (VM1: 0.893 ± 0.012 and VM2: 0.857 ± 0.017) metrics. The time required to perform a registration for a pair of MRI scans is about 1 s on the CPU.ConclusionsThe developed deep learning-based model can perform an end-to-end deformable registration of a pair of 3D MRI scans for glioma patients without human intervention. The model could provide accurate, efficient, and robust deformable registration without needing pre-alignment and labeling. It outperformed the state-of-the-art VoxelMorph learning-based deformable registration algorithms and other supervised/unsupervised deep learning-based methods reported in the literature.

Deep Learning Analysis of 3D Volume of Brain Anomaly Using MRI

In this study, we present a comprehensive investigation into the efficacy of two state-of-the-art deep learning architectures, 3D UNet and VNet, for brain tumor detection and segmentation in volumetric medical images.

NoiseNet, a fully automatic noise assessment tool that can identify non-diagnostic CCTA examinations

Image noise and vascular attenuation are important factors affecting image quality and diagnostic accuracy of coronary computed tomography angiography (CCTA). The aim of this study was to develop an algorithm that automatically performs noise and attenuation measurements in CCTA and to evaluate the ability of the algorithm to identify non-diagnostic examinations. The algorithm, “NoiseNet”, was trained and tested on 244 CCTA studies from the Swedish CArdioPulmonary BioImage Study. The model is a 3D U-Net that automatically segments the aortic root and measures attenuation (Hounsfield Units, HU), noise (standard deviation of HU, HUsd) and signal-to-noise ratio (SNR, HU/HUsd) in the aortic lumen, close to the left coronary ostium. NoiseNet was then applied to 529 CCTA studies previously categorized into three subgroups: fully diagnostic, diagnostic with excluded parts and non-diagnostic. There was excellent correlation between NoiseNet and manual measurements of noise (r = 0.948; p < 0.001) and SNR (r = 0.948; <0.001). There was a significant difference in noise levels between the image quality subgroups: fully diagnostic 33.1 (29.8–37.9); diagnostic with excluded parts 36.1 (31.5–40.3) and non-diagnostic 42.1 (35.2–47.7; p < 0.001). Corresponding values for SNR were 16.1 (14.0–18.0); 14.0 (12.4–16.2) and 11.1 (9.6–14.0; p < 0.001). ROC analysis for prediction of a non-diagnostic study showed an AUC for noise of 0.73 (CI 0.64–0.83) and for SNR of 0.80 (CI 0.71–0.89). In conclusion, NoiseNet can perform noise and SNR measurements with high accuracy. Noise and SNR impact image quality and automatic measurements may be used to identify CCTA studies with low image quality.

Accurate object localization facilitates automatic esophagus segmentation in deep learning

BackgroundCurrently, automatic esophagus segmentation remains a challenging task due to its small size, low contrast, and large shape variation. We aimed to improve the performance of esophagus segmentation in deep learning by applying a strategy that involves locating the object first and then performing the segmentation task.MethodsA total of 100 cases with thoracic computed tomography scans from two publicly available datasets were used in this study. A modified CenterNet, an object location network, was employed to locate the center of the esophagus for each slice. Subsequently, the 3D U-net and 2D U-net_coarse models were trained to segment the esophagus based on the predicted object center. A 2D U-net_fine model was trained based on the updated object center according to the 3D U-net model. The dice similarity coefficient and the 95% Hausdorff distance were used as quantitative evaluation indexes for the delineation performance. The characteristics of the automatically delineated esophageal contours by the 2D U-net and 3D U-net models were summarized. Additionally, the impact of the accuracy of object localization on the delineation performance was analyzed. Finally, the delineation performance in different segments of the esophagus was also summarized.ResultsThe mean dice coefficient of the 3D U-net, 2D U-net_coarse, and 2D U-net_fine models were 0.77, 0.81, and 0.82, respectively. The 95% Hausdorff distance for the above models was 6.55, 3.57, and 3.76, respectively. Compared with the 2D U-net, the 3D U-net has a lower incidence of delineating wrong objects and a higher incidence of missing objects. After using the fine object center, the average dice coefficient was improved by 5.5% in the cases with a dice coefficient less than 0.75, while that value was only 0.3% in the cases with a dice coefficient greater than 0.75. The dice coefficients were lower for the esophagus between the orifice of the inferior and the pulmonary bifurcation compared with the other regions.ConclusionThe 3D U-net model tended to delineate fewer incorrect objects but also miss more objects. Two-stage strategy with accurate object location could enhance the robustness of the segmentation model and significantly improve the esophageal delineation performance, especially for cases with poor delineation results.

Automatic segmentation of dura for quantitative analysis of lumbar stenosis: A deep learning study with 518 CT myelograms.

The diagnosis of lumbar spinal stenosis (LSS) can be challenging because radicular pain is not often present in the culprit-level localization. Accurate segmentation and quantitative analysis of the lumbar dura on radiographic images are key to the accurate differential diagnosis of LSS. The aim of this study is to develop an automatic dura-contouring tool for radiographic quantification on computed tomography myelogram (CTM) for patients with LSS. A total of 518 CTM cases with or without lumbar stenosis were included in this study. A deep learning (DL) segmentation algorithm 3-dimensional (3D) U-Net was deployed. A total of 210 labeled cases were used to develop the dura-contouring tool, with the ratio of the training, independent testing, and external validation datasets being 150:30:30. The Dice score (DCS) was the primary measure to evaluate the segmentation performance of the 3D U-Net, which was subsequently developed as the dura-contouring tool to segment another unlabeled 308 CTM cases with LSS. Automatic masks of 446 slices on the stenotic levels were then meticulously reviewed and revised by human experts, and the cross-sectional area (CSA) of the dura was compared. The mean DCS of the 3D U-Net were 0.905±0.080, 0.933±0.018, and 0.928±0.034 in the five-fold cross-validation, the independent testing, and the external validation datasets, respectively. The segmentation performance of the dura-contouring tool was also comparable to that of the second observer (the human expert). With the dura-contouring tool, only 59.0% (263/446) of the automatic masks of the stenotic slices needed to be revised. In the revised cases, there were no significant differences in the dura CSA between automatic masks and corresponding revised masks (p=0.652). Additionally, a strong correlation of dura CSA was found between the automatic masks and corresponding revised masks (r=0.805). A dura-contouring tool was developed that could automatically segment the dural sac on CTM, and it demonstrated high accuracy and generalization ability. Additionally, the dura-contouring tool has the potential to be applied in patients with LSS because it facilitates the quantification of the dural CSA on stenotic slices.

Rapid multi-catheter segmentation for magnetic resonance image-guided catheter-based interventions.

Magnetic resonance imaging (MRI) is the gold standard for delineating cancerous lesions in soft tissue. Catheter-based interventions require the accurate placement of multiple long, flexible catheters at the target site. The manual segmentation of catheters in MR images is a challenging and time-consuming task. There is a need for automated catheter segmentation to improve the efficiency of MR-guided procedures. To develop and assess a machine learning algorithm for the detection of multiple catheters in magnetic resonance images used during catheter-based interventions. In this work, a 3D U-Net was trained to retrospectively segment catheters in scans acquired during clinical MR-guided high dose rate (HDR) prostate brachytherapy cases. To assess confidence in segmentation, multiple AI models were trained. On clinical test cases, average segmentation results were used to plan the brachytherapy delivery. Dosimetric parameters were compared to the original clinical plan. Data was obtained from 35 patients who underwent HDR prostate brachytherapy for focal disease with a total of 214 image volumes. 185 image volumes from 30 patients were used for training using a five-fold cross validation split to divide the data for training and validation. To generate confidence measures of segmentation accuracy, five trained models were generated. The remaining five patients (29 volumes) were used to test the performance of the trained model by comparison to manual segmentations of three independent observers and assessment of dosimetric impact on the final clinical brachytherapy plans. The network successfully identified 95% of catheters in the test set at a rate of 0.89s per volume. The multi-model method identified the small number of cases where AI segmentation of individual catheters was poor, flagging the need for user input. AI-based segmentation performed as well as segmentations by independent observers. Plan dosimetry using AI-segmented catheters was comparable to the original plan. The vast majority of catheters were accurately identified by AI segmentation, with minimal impact on plan outcomes. The use of multiple AI models provided confidence in the segmentation accuracy and identified catheter segmentations that required further manual assessment. Real-time AI catheter segmentation can be used during MR-guided insertions to assess deflections and for rapid planning of prostate brachytherapy.

1783: Dwell locations and dwell time prediction of cervical cancer brachytherapy using 3D U-net

1783: Dwell locations and dwell time prediction of cervical cancer brachytherapy using 3D U-net

Repairing the in situ hybridization missing data in the hippocampus region by using a 3D residual U-Net model.

The hippocampus is a critical brain region. Transcriptome data provides valuable insights into the structure and function of the hippocampus at the gene level. However, transcriptome data is often incomplete. To address this issue, we use the convolutional neural network model to repair the missing voxels in the hippocampus region, based on Allen institute coronal slices in situ hybridization (ISH) dataset. Moreover, we analyze the gene expression correlation between coronal and sagittal dataset in the hippocampus region. The results demonstrated that the trend of gene expression correlation between the coronal and sagittal datasets remained consistent following the repair of missing data in the coronal ISH dataset. In the last, we use repaired ISH dataset to identify novel genes specific to hippocampal subregions. Our findings demonstrate the accuracy and effectiveness of using deep learning method to repair ISH missing data. After being repaired, ISH has the potential to improve our comprehension of the hippocampus's structure and function.

WITHDRAWN: Coronary artery segmentation based on ACMA-Net and unscented Kalman filter algorithm

Accurate segmentation of coronary arteries is a prerequisite for high-precision reconstruction of three-dimensional (3D) models of coronary arteries. With personalized 3D coronary anatomy, clinicians can more readily visually determine the location, type, and severity of a stenotic lesion. However, due to the complex structure and small size of coronary arteries, and the interference of image acquisition conditions, 3D models of segmented and reconstructed coronary arteries are noisy and prone to disconnection; accurate segmentation of coronary arteries is still a challenge.To overcome the above challenges, this study proposes a two-stage coronary segmentation algorithm. In the first stage, we added an atrous convolution feature fusion module (ACFFM) and a multi-axis attention module (MAM) to 3D U-Net, referred to as ACMA-Net, to enhance the feature expression ability of the network and effect the preliminary segmentation of coronary arteries. In the second stage, the preliminary segmentation results were skeletonized and endpoint detection was performed. The regions of coronary artery disconnection were determined by finding the minimum distance between the main trunk branch and the endpoint of each disconnected branch. The disconnected skeleton was repaired by reconnection using an unscented Kalman filter (UKF) algorithm.On the private CORO dataset and the public ASOCA dataset, our method obtains an average Dice coefficient of 0.818 and 0.731, respectively, so it outperforms most of the state-of-the-art algorithms compared, proving its excellent effectiveness and robustness.

Automatic segmentation of tumour and organs at risk in 3D MRI for cervical cancer radiation therapy with anatomical variations.

Cervical cancer is a common cancer in women globally, with treatment usually involving radiation therapy (RT). Accurate segmentation for the tumour site and organ-at-risks (OARs) could assist in the reduction of treatment side effects and improve treatment planning efficiency. Cervical cancer Magnetic Resonance Imaging (MRI) segmentation is challenging due to a limited amount of training data available and large inter- and intra- patient shape variation for OARs. The proposed Masked-Net consists of a masked encoder within the 3D U-Net to account for the large shape variation within the dataset, with additional dilated layers added to improve segmentation performance. A new loss function was introduced to consider the bounding box loss during training with the proposed Masked-Net. Transfer learning from a male pelvis MRI data with a similar field of view was included. The approaches were compared to the 3D U-Net which was widely used in MRI image segmentation. The data used consisted of 52 volumes obtained from 23 patients with stage IB to IVB cervical cancer across a maximum of 7 weeks of RT with manually contoured labels including the bladder, cervix, gross tumour volume, uterus and rectum. The model was trained and tested with a 5-fold cross validation. Outcomes were evaluated based on the Dice Similarity Coefficients (DSC), the Hausdorff Distance (HD) and the Mean Surface Distance (MSD). The proposed method accounted for the small dataset, large variations in OAR shape and tumour sizes with an average DSC, HD and MSD for all anatomical structures of 0.790, 30.19mm and 3.15mm respectively.

A novel method for glioma segmentation and classification on pre-operative MRI scans using 3D U-Nets and transfer learning

A novel method for glioma segmentation and classification on pre-operative MRI scans using 3D U-Nets and transfer learning