Automatic coronary artery segmentation of CCTA images using UNet with a local contextual transformer

Few-shot small vessel segmentation using a detail-preserving network enhanced by discriminator

Accurate segmentation of small vessels, such as coronary and pulmonary arteries, is crucial for early detection and treatment of vascular diseases. However, challenges persist due to the vessel's small size, complex structures, morphological variations, and limited annotated data. To address these challenges, we propose a detail-preserving network enhanced by a discriminator to improve the few-shot small vessel segmentation performance. The detail-preserving network constructs a complex module with multi-residual hybrid dilated convolution, which can enhance the network's receptive field while preserving the image's full detail features, enabling it to better capture the small vessel's structural features. Simultaneously, discriminator enhancement is incorporated into the training process through adversarial learning, effectively utilizing large amounts of unlabeled data to boost the generalization and robustness of the segmentation model. We validate the proposed method on in-house and public coronary artery datasets and public pulmonary artery datasets. Experimental results demonstrate that the proposed method significantly improves segmentation accuracy, particularly for small vessels. Compared with other state-of-the-art methods, the proposed method achieves higher accuracy, a lower false positive rate, and superior generalization capability, effectively assisting the clinical diagnosis of vessel diseases.

Transformer and Attention-Based Architectures for Segmentation of Coronary Arterial Walls in Intravascular Ultrasound: A Narrative Review

Background: The leading global cause of death is coronary artery disease (CAD), necessitating early and precise diagnosis. Intravascular ultrasound (IVUS) is a sophisticated imaging technique that provides detailed visualization of coronary arteries. However, the methods for segmenting walls in the IVUS scan into internal wall structures and quantifying plaque are still evolving. This study explores the use of transformers and attention-based models to improve diagnostic accuracy for wall segmentation in IVUS scans. Thus, the objective is to explore the application of transformer models for wall segmentation in IVUS scans to assess their inherent biases in artificial intelligence systems for improving diagnostic accuracy. Methods: By employing the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) framework, we pinpointed and examined the top strategies for coronary wall segmentation using transformer-based techniques, assessing their traits, scientific soundness, and clinical relevancy. Coronary artery wall thickness is determined by using the boundaries (inner: lumen-intima and outer: media-adventitia) through cross-sectional IVUS scans. Additionally, it is the first to investigate biases in deep learning (DL) systems that are associated with IVUS scan wall segmentation. Finally, the study incorporates explainable AI (XAI) concepts into the DL structure for IVUS scan wall segmentation. Findings: Because of its capacity to automatically extract features at numerous scales in encoders, rebuild segmented pictures via decoders, and fuse variations through skip connections, the UNet and transformer-based model stands out as an efficient technique for segmenting coronary walls in IVUS scans. Conclusions: The investigation underscores a deficiency in incentives for embracing XAI and pruned AI (PAI) models, with no UNet systems attaining a bias-free configuration. Shifting from theoretical study to practical usage is crucial to bolstering clinical evaluation and deployment.

HWA-ResMamba: automatic segmentation of coronary arteries based on residual Mamba with high-order wavelet-enhanced convolution and attention feature aggregation

Objective.Automatic segmentation of coronary arteries is a crucial prerequisite in assisting in the diagnosis of coronary artery disease. However, due to the fuzzy boundaries, small-slender branches, and significant individual variations, automatic segmentation of coronary arteries is extremely challenging.Approach.This study proposes a residual Mamba with high-order wavelet-enhanced convolution and attention feature aggregation (HWA-ResMamba) for coronary arteries segmentation. The network consists of three core modules: high-order wavelet-enhanced convolution block (HWCB), residual Mamba (ResMamba), and attention feature aggregation (AFA) module. Firstly, the HWCB captures low-frequency information of the image in the shallow layers of the network, allowing for detailed exploration of subtle changes in the boundaries of coronary arteries. Secondly, the ResMamba module establishes long-range dependencies between features in the deep layers of the encoder and at the beginning of the decoder, improving the continuity of the segmentation process. Finally, the AFA module in the decoder reduces semantic differences between the encoder and decoder, which can capture small-slender coronary artery branches and further improve segmentation accuracy.Main results.Experiments on three coronary artery segmentation datasets have shown that the HWA-ResMamba outperforms other state-of-the-art methods in performance and generalization. Specifically, in the self-built dataset, HWA-ResMamba obtained Dice of 0.8857 and Hausdorff Distance (HD) of 1.9028, outperforming nnUnet by 0.0521, and 0.5489, respectively. HWA-ResMamba obtained Dice of 0.8371, and 0.7861 in the two public datasets, outperforming nnUnet by 0.0255, and 0.0107, respectively.Significance.Our method can accurately segment coronary arteries and can contribute to improved diagnosis and assessment of CAD.

A Robust Blood Vessel Segmentation Technique for Angiographic Images Employing Multi-Scale Filtering Approach

Background: This study focuses on the critical task of blood vessel segmentation in medical image analysis, essential for diagnosing cardiovascular diseases and enabling effective treatment planning. Although deep learning architectures often produce very high segmentation results in medical images, coronary computed tomography angiography (CTA) images are more challenging than invasive coronary angiography (ICA) images due to noise and the complexity of vessel structures. Methods: Classical architectures for medical images, such as U-Net, achieve only moderate accuracy, with an average Dice score of 0.722. Results: This study introduces Morpho-U-Net, an enhanced U-Net architecture that integrates advanced morphological operations, including Gaussian blurring, thresholding, and morphological opening/closing, to improve vascular integrity, reduce noise, and achieve a higher Dice score of 0.9108, a precision of 0.9341, and a recall of 0.8872. These enhancements demonstrate superior robustness to noise and intricate vessel geometries. Conclusions: This pre-processing filter effectively reduces noise by grouping neighboring pixels with similar intensity values, allowing the model to focus on relevant anatomical structures, thus outperforming traditional methods in handling the challenges posed by CTA images.

Improving coronary artery segmentation with self-supervised learning and automated pericoronary adipose tissue segmentation: a multi-institutional study on coronary computed tomography angiography images

Purpose

Coronary artery disease (CAD) is a leading cause of morbidity and mortality worldwide, with coronary computed tomography angiography (CCTA) playing a crucial role in its diagnosis. The mean Hounsfield unit (HU) of pericoronary adipose tissue (PCAT) is linked to cardiovascular risk. We utilized a self-supervised learning framework (SSL) to improve the accuracy and generalizability of coronary artery segmentation on CCTA volumes while addressing the limitations of small-annotated datasets.

Approach

We utilized self-supervised pretraining followed by supervised fine-tuning to segment coronary arteries. To evaluate the data efficiency of SSL, we varied the number of CCTA volumes used during pretraining. In addition, we developed an automated PCAT segmentation algorithm utilizing centerline extraction, spatial-geometric coronary identification, and landmark detection. We evaluated our method on a multi-institutional dataset by assessing coronary artery and PCAT segmentation accuracy via Dice scores and comparing mean PCAT HU values with the ground truth.

Results

Our approach significantly improved coronary artery segmentation, achieving Dice scores up to 0.787 after self-supervised pretraining. The automated PCAT segmentation achieved near-perfect performance, with R -squared values of 0.9998 for both the left anterior descending artery and the right coronary artery indicating excellent agreement between predicted and actual mean PCAT HU values. Self-supervised pretraining notably enhanced model generalizability on external datasets, improving overall segmentation accuracy.

Conclusions

We demonstrate the potential of SSL to advance CCTA image analysis, enabling more accurate CAD diagnostics. Our findings highlight the robustness of SSL for automated coronary artery and PCAT segmentation, offering promising advancements in cardiovascular care.

Application of the U-Net Deep Learning Model for Segmenting Single-Photon Emission Computed Tomography Myocardial Perfusion Images

BACKGROUND

Myocardial perfusion imaging (MPI) is a type of single-photon emission computed tomography (SPECT) used to evaluate patients with suspected or confirmed coronary artery disease (CAD). Detection and diagnosis of CAD are complex processes requiring precise and accurate image processing. Proper segmentation is critical for accurate diagnosis, but segmentation issues can pose significant challenges, leading to diagnostic difficulties. Machine learning (ML) algorithms have demonstrated superior performance in addressing segmentation problems.

METHODS

In this study, a deep learning (DL) algorithm, U-Net, was employed to enhance segmentation accuracy for image segmentation in MPI. Data were collected from 1100 patients who underwent MPI studies at Al-Jahra Hospital between 2015 and 2024. To train the U-Net model, 100 studies were segmented by nuclear medicine (NM) experts to create a ground truth (gold-standard coordinates). The dataset was divided into a training set (n = 100 images) and a validation set (n = 900 images). The performance of the U-Net model was evaluated using multiple cross-validation metrics, including accuracy, precision, intersection over union (IOU), recall, and F1 score.

RESULT

A dataset of 4560 images and corresponding masks was generated. Both holdout and k-fold (k = 5) validation strategies were applied, utilizing cross-entropy and Dice score as evaluation metrics. The best results were achieved with the holdout split and cross-entropy loss function, yielding a test accuracy of 98.9%, a test IOU of 89.6%, and a test Dice coefficient of 94%. The k-fold validation scenario provided a more balanced true positive and false positive rate. The U-Net segmentation results were comparable to those produced by expert nuclear medicine technologists, with no significant difference (p = 0.1).

CONCLUSIONS

The findings demonstrate that the U-Net model effectively addresses some segmentation challenges in MPI, facilitating improved diagnosis and analysis of mega data.

Automatic vessel segmentation and reformation of non-contrast coronary magnetic resonance angiography using transfer learning-based three-dimensional U-net with attention mechanism

BACKGROUND

Coronary magnetic resonance angiography (CMRA) presents distinct advantages, but its reliance on manual image post-processing is labor-intensive and requires specialized knowledge. This study aims to design and test an efficient artificial intelligence (AI) model capable of automating coronary artery segmentation and reformation from CMRA images for coronary artery disease (CAD) diagnosis.

METHODS

By leveraging transfer learning from a pre-existing coronary computed tomography angiography model, a three-dimensional attention-aware U-Net was established, trained, and validated on a dataset of 104 subjects' CMRA. Furthermore, an independent clinical evaluation was conducted on an additional cohort of 70 patients. The AI model's performance in segmenting coronary arteries was assessed using the Dice similarity coefficient (DSC) and recall. The comparison between the AI model and manual processing by experienced radiologists on vessel reformation was based on reformatted image quality (rIQ) scoring, post-processing time, and the number of necessary user interactions. The diagnostic performance of AI-segmented CMRA for significant stenosis (≥50% diameter reduction) was evaluated using conventional coronary angiography (CAG) as a reference in sub-set data.

RESULTS

The DSC of the AI model achieved on the training and validation sets were 0.952 and 0.944, with recalls of 0.936 and 0.923, respectively. In the clinical evaluation, the model outperformed manual processes by reducing vessel post-processing time, from 632.6±17.0 s to 77.4±8.9 s, and the number of user interactions from 221±59 to 8±2. The AI post-processed images maintained high rIQ scores comparable to those processed manually (2.7±0.8 vs 2.7±0.6; P = 0.4806). In subjects with CAG, the prevalence of CAD was 71%. The sensitivity, specificity, and accuracy at patient-based analysis were 94%, 71%, and 88%, respectively, by AI post-processed whole-heart CMRA.

CONCLUSION

The AI auto-segmentation system can effectively facilitate CMRA vessel reformation and reduce the time consumption for radiologists. It has the potential to become a standard component of daily workflows, optimizing the clinical application of CMRA in the future.

Efficient Extraction of Coronary Artery Vessels from Computed Tomography Angiography Images Using ResUnet and Vesselness

Accurate and efficient segmentation of coronary arteries from CTA images is crucial for diagnosing and treating cardiovascular diseases. This study proposes a structured approach that combines vesselness enhancement, heart region of interest (ROI) extraction, and the ResUNet deep learning method to accurately and efficiently extract coronary artery vessels. Vesselness enhancement and heart ROI extraction significantly improve the accuracy and efficiency of the segmentation process, while ResUNet enables the model to capture both local and global features. The proposed method outperformed other state-of-the-art methods, achieving a Dice similarity coefficient (DSC) of 0.867, a Recall of 0.881, and a Precision of 0.892. The exceptional results for segmenting coronary arteries from CTA images demonstrate the potential of this method to significantly contribute to accurate diagnosis and effective treatment of cardiovascular diseases.

A comparative analysis of deep learning-based location-adaptive threshold method software against other commercially available software

Automatic segmentation of the coronary artery using coronary computed tomography angiography (CCTA) images can facilitate several analyses related to coronary artery disease (CAD). Accurate segmentation of the lumen or plaque region is one of the most important factors. This study aimed to analyze the performance of the coronary artery segmentation of a software platform with a deep learning-based location-adaptive threshold method (DL-LATM) against commercially available software platforms using CCTA. The dataset from intravascular ultrasound (IVUS) of 26 vessel segments from 19 patients was used as the gold standard to evaluate the performance of each software platform. Statistical analyses (Pearson correlation coefficient [PCC], intraclass correlation coefficient [ICC], and Bland-Altman plot) were conducted for the lumen or plaque parameters by comparing the dataset of each software platform with IVUS. The software platform with DL-LATM showed the bias closest to zero for detecting lumen volume (mean difference = -9.1 mm3, 95% confidence interval [CI] = -18.6 to 0.4 mm3) or area (mean difference = -0.72 mm2, 95% CI = -0.80 to -0.64 mm2) with the highest PCC and ICC. Moreover, lumen or plaque area in the stenotic region was analyzed. The software platform with DL-LATM showed the bias closest to zero for detecting lumen (mean difference = -0.07 mm2, 95% CI = -0.16 to 0.02 mm2) or plaque area (mean difference = 1.70 mm2, 95% CI = 1.37 to 2.03 mm2) in the stenotic region with significantly higher correlation coefficient than other commercially available software platforms (p < 0.001). The result shows that the software platform with DL-LATM has the potential to serve as an aiding system for CAD evaluation.