CAD-RADS scoring of coronary CT angiography with Multi-Axis Vision Transformer: a clinically-inspired deep learning pipeline

• URL: http://arxiv.org/abs/2304.07277v1
• Date: Fri, 14 Apr 2023 17:41:07 GMT
• Title: CAD-RADS scoring of coronary CT angiography with Multi-Axis Vision Transformer: a clinically-inspired deep learning pipeline
• Authors: Alessia Gerbasi, Arianna Dagliati, Giuseppe Albi, Mattia Chiesa, Daniele Andreini, Andrea Baggiano, Saima Mushtaq, Gianluca Pontone, Riccardo Bellazzi, Gualtiero Colombo
• Abstract summary: This work proposes a fully automated, and visually explainable, deep learning pipeline to be used as a decision support system for the Coronary Artery Disease screening procedure. The pipeline pre-processes multiplanar projections of the coronary arteries, extracted from the original Coronary Computed Tomography Angiography (CCTA) It is trained to assign a per-patient score by stacking the bi-dimensional longitudinal cross-sections of the three main coronary arteries along channel dimension.
• Score: 0.5366236361669898
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: The standard non-invasive imaging technique used to assess the severity and extent of Coronary Artery Disease (CAD) is Coronary Computed Tomography Angiography (CCTA). However, manual grading of each patient's CCTA according to the CAD-Reporting and Data System (CAD-RADS) scoring is time-consuming and operator-dependent, especially in borderline cases. This work proposes a fully automated, and visually explainable, deep learning pipeline to be used as a decision support system for the CAD screening procedure. The pipeline performs two classification tasks: firstly, identifying patients who require further clinical investigations and secondly, classifying patients into subgroups based on the degree of stenosis, according to commonly used CAD-RADS thresholds. The pipeline pre-processes multiplanar projections of the coronary arteries, extracted from the original CCTAs, and classifies them using a fine-tuned Multi-Axis Vision Transformer architecture. With the aim of emulating the current clinical practice, the model is trained to assign a per-patient score by stacking the bi-dimensional longitudinal cross-sections of the three main coronary arteries along channel dimension. Furthermore, it generates visually interpretable maps to assess the reliability of the predictions. When run on a database of 1873 three-channel images of 253 patients collected at the Monzino Cardiology Center in Milan, the pipeline obtained an AUC of 0.87 and 0.93 for the two classification tasks, respectively. According to our knowledge, this is the first model trained to assign CAD-RADS scores learning solely from patient scores and not requiring finer imaging annotation steps that are not part of the clinical routine.

Related papers

• CADICA: a new dataset for coronary artery disease detection by using invasive coronary angiography [1.5404452377809545]
  Coronary artery disease (CAD) remains the leading cause of death globally. Deep learning classification methods are well-developed in other areas of medical imaging. One of the most important reasons is the lack of available and high-quality open-access datasets.
  arXiv  Detail & Related papers  (2024-02-01T13:03:13Z)
• Multivessel Coronary Artery Segmentation and Stenosis Localisation using Ensemble Learning [3.656984996633334]
  This study introduces an end-to-end machine learning solution developed as part of our solution for the MICCAI 2023 Automatic Region-based Coronary Artery Disease diagnostics. It aims to benchmark solutions for multivessel coronary artery segmentation and potential stenotic lesion localisation from X-ray coronary angiograms. Our solution achieved a mean F1 score of $37.69%$ for coronary artery segmentation, and $39.41%$ for stenosis localisation, positioning our team in the 5th position on both leaderboards.
  arXiv  Detail & Related papers  (2023-10-27T08:03:12Z)
• Accurate Fine-Grained Segmentation of Human Anatomy in Radiographs via Volumetric Pseudo-Labeling [66.75096111651062]
  We created a large-scale dataset of 10,021 thoracic CTs with 157 labels. We applied an ensemble of 3D anatomy segmentation models to extract anatomical pseudo-labels. Our resulting segmentation models demonstrated remarkable performance on CXR.
  arXiv  Detail & Related papers  (2023-06-06T18:01:08Z)
• Longitudinal Multimodal Transformer Integrating Imaging and Latent Clinical Signatures From Routine EHRs for Pulmonary Nodule Classification [4.002181247287472]
  We propose a transformer-based multimodal strategy to integrate repeat imaging with longitudinal clinical signatures from EHRs for solitary pulmonary nodule (SPN) classification. We perform unsupervised disentanglement of latent clinical signatures and leverage time-distance scaled self-attention to jointly learn from clinical signatures expressions and chest computed tomography (CT) scans.
  arXiv  Detail & Related papers  (2023-04-06T03:03:07Z)
• Cross-modal Clinical Graph Transformer for Ophthalmic Report Generation [116.87918100031153]
  We propose a Cross-modal clinical Graph Transformer (CGT) for ophthalmic report generation (ORG) CGT injects clinical relation triples into the visual features as prior knowledge to drive the decoding procedure. Experiments on the large-scale FFA-IR benchmark demonstrate that the proposed CGT is able to outperform previous benchmark methods.
  arXiv  Detail & Related papers  (2022-06-04T13:16:30Z)
• An Algorithm for the Labeling and Interactive Visualization of the Cerebrovascular System of Ischemic Strokes [59.116811751334225]
  VirtualDSA++ is an algorithm designed to segment and label the cerebrovascular tree on CTA scans. We extend the labeling mechanism for the cerebral arteries to identify occluded vessels. We present the generic concept of iterative systematic search for pathways on all nodes of said model, which enables new interactive features.
  arXiv  Detail & Related papers  (2022-04-26T14:20:26Z)
• CAD-RADS Scoring using Deep Learning and Task-Specific Centerline Labeling [5.854918673468336]
  In clinical practice, the severeness of coronary artery disease (CAD) is often assessed with a coronary CT angiography (CCTA) scan. We propose using severity-based label encoding, test time augmentation (TTA) and model ensembling for a task-specific deep learning architecture. We were able to raise the previously reported area under the receiver operating characteristic curve (AUC) from 0.914 to 0.942 in the rule-out and from 0.921 to 0.950 in the hold-out task respectively.
  arXiv  Detail & Related papers  (2022-02-08T06:22:03Z)
• A Deep Learning Approach to Predicting Collateral Flow in Stroke Patients Using Radiomic Features from Perfusion Images [58.17507437526425]
  Collateral circulation results from specialized anastomotic channels which provide oxygenated blood to regions with compromised blood flow. The actual grading is mostly done through manual inspection of the acquired images. We present a deep learning approach to predicting collateral flow grading in stroke patients based on radiomic features extracted from MR perfusion data.
  arXiv  Detail & Related papers  (2021-10-24T18:58:40Z)
• AI-based Aortic Vessel Tree Segmentation for Cardiovascular Diseases Treatment: Status Quo [55.04215695343928]
  The aortic vessel tree is composed of the aorta and its branching arteries. We systematically review computing techniques for the automatic and semi-automatic segmentation of the aortic vessel tree.
  arXiv  Detail & Related papers  (2021-08-06T08:18:28Z)
• Automatic CAD-RADS Scoring Using Deep Learning [5.789689435835229]
  The CAD-Reporting and Data System (CAD-RADS) has been developed to standardize communication and aid in decision making based on CCTA findings. The CAD-RADS score is determined by manual assessment of all coronary vessels and the grading of lesions within the coronary artery tree. We propose a bottom-up approach for fully-automated prediction of this score using deep-learning operating on a segment-wise representation of the coronary arteries.
  arXiv  Detail & Related papers  (2020-10-05T12:48:15Z)
• Deep Q-Network-Driven Catheter Segmentation in 3D US by Hybrid Constrained Semi-Supervised Learning and Dual-UNet [74.22397862400177]
  We propose a novel catheter segmentation approach, which requests fewer annotations than the supervised learning method. Our scheme considers a deep Q learning as the pre-localization step, which avoids voxel-level annotation. With the detected catheter, patch-based Dual-UNet is applied to segment the catheter in 3D volumetric data.
  arXiv  Detail & Related papers  (2020-06-25T21:10:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.