Aortic Dissection Diagnosis Based on Sequence Information and燚eep燣earning
Source abstract
Abstract
Aortic dissection (AD) is one of the most serious diseases with high mortality, and its diagnosis mainly depends on computed tomography (CT) results. Most existing automatic diagnosis methods of AD are only suitable for AD recognition, which usually require preselection of CT images and cannot be further classified to different types. In this work, we constructed a dataset of 105 cases with a total of 49021 slices, including 31043 slices expert-level annotation and proposed a two-stage AD diagnosis structure based on sequence information and deep learning. The proposed region of interest (RoI) extraction algorithm based on sequence information (RESI) can realize high-precision for RoI identification in the first stage. Then DenseNet-121 is applied for further diagnosis. Specially, the proposed method can judge the type of AD without preselection of CT images. The experimental results show that the accuracy of Stanford typing classification of AD is 89.19%, and the accuracy at the slice-level reaches 97.41%, which outperform the state-of-art methods. It can provide important decision-making information for the determination of further surgical treatment plan for patients.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Aortic Disease and Treatment Approaches · Aortic aneurysm repair treatments · Cardiac Valve Diseases and Treatments
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (40)
Show source-provided references
1. Acute aortic dissection and intramural hematoma: A systematic review10.1001/jama.2016.10026 ↗
2. Recent progress of medical CT image processing based on deep learning
3. Misdiagnosis of aortic dissection: A systematic review of the literature10.1016/j.ajem.2021.11.047 ↗
4. WBCs-Net: Type identification of white blood cells using convolutional neural network
5. Algorithm of helmet wearing detection based on at-YOLO deep mode10.32604/cmc.2021.017480 ↗
6. Af-net: A medical image segmentation network based on attention mechanism and feature fusion10.32604/cmc.2021.017481 ↗
7. Deep residual learning for image recognition
8. Densely connected convolutional networks
9. Efficientnetv2: Smaller models and faster training
10. Hybrid model of faster R-CNN and SVM for tumor detection and classification of MRI brain images10.24247/ijmperdjun2020651 ↗
11. Intelligent solutions in chest abnormality detection based on YOLOv5 and ResNet5010.1155/2021/2267635 ↗
12. Multi- class classification of breast cancer abnormalities using deep convolutional neural network (CNN)
13. ROI detection of hand bone based on YOLO V3
14. Real-time detection of aortic valve in echocardiography using convolutional neural networks10.2174/1573405615666190114151255 ↗
15. Enhanced region of interest extraction method for finger vein images10.52098/airdj.20218 ↗
16. YOLO as a region proposal network for diagnosing breast cancer
17. An automatic detection scheme of acute Stanford type A aortic dissection based on DCNNs in CTA images
18. Mask R-CNN
19. Automatic detection of aortic dissection based on morphology and deep learning10.32604/cmc.2020.07127 ↗
20. Classification of aortic dissection and rupture on post-contrast CT images using a convolutional neural network10.1007/s10278-019-00281-5 ↗
21. Deep learning algorithm for detection of aortic dissection on non-contrast-enhanced CT10.1007/s00330-020-07213-w ↗
22. A three-dimensional deep convolutional neural network for automatic segmentation and diameter measurement of type B aortic dissection10.3348/kjr.2020.0313 ↗
23. MOLS-Net: Multi-organ and lesion segmentation network based on sequence feature pyramid and attention mechanism for aortic dissection diagnosis10.1016/j.knosys.2021.107853 ↗
24. Siam R-CNN: Visual tracking by re-detection
25. MPM: Joint representation of motion and position map for cell tracking
26. Review of imaging with focus on new techniques in aortic dissection10.1016/j.tvir.2021.100748 ↗
27. Endovascular repair of aortic dissection involving the left subclavian artery by castor stent graft: A multicentre respective trial10.1016/j.ejvs.2020.08.022 ↗
28. Prediction of distal aortic enlargement after proximal repair of aortic dissection using machine learning10.1016/j.avsg.2021.02.039 ↗
29. Novel morphological features for prediction of distal thoracic aortic enlargement after thoracic endovascular aortic repair of DeBakey IIIb aortic dissection10.1016/j.avsg.2017.07.039 ↗
30. Detection, segmentation, simulation and visualization of aortic dissections: A review10.1016/j.media.2020.101773 ↗
31. Deep learning based detection of acute aortic syndrome in contrast CT images
32. Epidemiology of thoracic aortic dissection10.1038/nrcardio.2010.187 ↗
33. Surgical treatment of aneurysm and/or dissection of the ascending aorta, transverse aortic arch, and ascending aorta and transverse aortic arch: Factors influencing survival in 717 patients10.1016/S0022-5223(19)34288-6 ↗
34. Type A aortic dissection—Experience over 5 decades: JACC historical breakthroughs in perspective10.1016/j.jacc.2020.07.061 ↗
35. Systematic review and meta-analysis of acute type B thoracic aortic dissection, open, or endovascular repair10.1016/j.jvs.2018.08.187 ↗
36. G. Jocher, K. Nishimura, T. Mineeva and R. Vilariño, “YOLOv5,” 2020. [Online]. Available: https://github.com/ultralytics/yolov5.
37. A. Bochkovskiy, C. Y. Wang and H. Y. M. Liao, “YOLOv4: Optimal speed and accuracy of object detection,” arXiv preprint, 2020. [Online]. Available: https://arxiv.org/abs/2004.10934.
38. CSPNet: A new backbone that can enhance learning capability of CNN
39. Feature pyramid networks for object detection
40. Path aggregation network for instance segmentation