Texture-Based Classification of Significant Stenosis in CCTA Multi-view Images of Coronary Arteries

Tejero-de-Pablos, Antonio; Huang, Kaikai; Yamane, Hiroaki; Kurose, Yusuke; Mukuta, Yusuke; Iho, Junichi; Tokunaga, Youji; Horie, Makoto; Nishizawa, Keisuke; Hayashi, Yusaku; Koyama, Yasushi; Harada, Tatsuya

doi:10.1007/978-3-030-32245-8_81

Cited by 17 publications

(17 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We obtained comparable results for each method. Our proposed method -a 2.5D approach -slightly outperforms the other approaches and requires fewer views compared to the method previously described in [6]. Therefore, a faster training procedure and inference is possible.…”

Section: Discussionmentioning

confidence: 85%

“…Texture-based Multi-view 2D-CNN The second baseline approach is described in reference [6]. A VGG-M network backbone pretrained on the ImageNet challenge dataset is used as a texture-based feature extractor.…”

Section: Methodsmentioning

confidence: 99%

“…In this work, we investigate three lumen-extraction independent deep learning algorithms for the task of predicting the revascularisation decision and the arXiv:1912.06417v1 [eess.IV] 13 Dec 2019 significance of a stenosis on a lesion-level. We propose a multi-view 2.5D approach, which we compare with two previously published methods, a 3D-RCNN approach [5] and a multi-view texture-based ensemble approach [6]. Additionally, we introduce adaptions to improve the performance of all approaches on our task.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Deep Learning Algorithms for Coronary Artery Plaque Characterisation from CCTA Scans

et al. 2020

View full text Add to dashboard Cite

Analysing coronary artery plaque segments with respect to their functional significance and therefore their influence to patient management in a non-invasive setup is an important subject of current research. In this work we compare and improve three deep learning algorithms for this task: A 3D recurrent convolutional neural network (RCNN), a 2D multi-view ensemble approach based on texture analysis, and a newly proposed 2.5D approach. Current state of the art methods utilising fluid dynamics based fractional flow reserve (FFR) simulation reach an AUC of up to 0.93 for the task of predicting an abnormal invasive FFR value. For the comparable task of predicting revascularisation decision, we are able to improve the performance in terms of AUC of both existing approaches with the proposed modifications, specifically from 0.80 to 0.90 for the 3D-RCNN, and from 0.85 to 0.90 for the multi-view texture-based ensemble. The newly proposed 2.5D approach achieves comparable results with an AUC of 0.90.

show abstract

Section: Discussionmentioning

confidence: 85%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning Algorithms for Coronary Artery Plaque Characterisation from CCTA Scans

et al. 2020

View full text Add to dashboard Cite

show abstract

“…luminal narrowing > 50%) with the combination of deep learning approach and radiomic features [10]. Also, Tejero-de-Pablos et al extracted features from five views of coronary arteries and employed a Fisher vector to predict the classification probability of significant stenosis according to the features of varied views [11].…”

Section: Introductionmentioning

confidence: 99%

Transformer Network for Significant Stenosis Detection in CCTA of Coronary Arteries

Ma,

Luo,

Wang

et al. 2021

Preprint

View full text Add to dashboard Cite

Coronary artery disease (CAD) has posed a leading threat to the lives of cardiovascular disease patients worldwide for a long time. Therefore, automated diagnosis of CAD has indispensable significance in clinical medicine. However, the complexity of coronary artery plaques that cause CAD makes the automatic detection of coronary artery stenosis in Coronary CT angiography (CCTA) a difficult task. In this paper, we propose a Transformer network (TR-Net) for the automatic detection of significant stenosis (i.e. luminal narrowing > 50%) while practically completing the computer-assisted diagnosis of CAD. The proposed TR-Net introduces a novel Transformer, and tightly combines convolutional layers and Transformer encoders, allowing their advantages to be demonstrated in the task. By analyzing semantic information sequences, TR-Net can fully understand the relationship between image information in each position of a multiplanar reformatted (MPR) image, and accurately detect significant stenosis based on both local and global information. We evaluate our TR-Net on a dataset of 76 patients from different patients annotated by experienced radiologists. Experimental results illustrate that our TR-Net has achieved better results in ACC (0.92), Spec (0.96), PPV (0.84), F1 (0.79) and MCC (0.74) indicators compared with the state-of-the-art methods. The source code is publicly available from the link (https://github.com/XinghuaMa/TR-Net).

show abstract

“…Previous approaches focus on detection and quantification of stenoses and are based on the segmentation of the entire coronary tree [5,10], which is time consuming and often needs manual correction [12]. Recently, deep-learning approaches [6] without the need for a prior segmentation were introduced [1,11,14]. These methods operate on multi-planar reformatted (MPR) image stacks which are extracted by interpolating orthogonal planes for each centerline point of the vessel.…”

Section: Introductionmentioning

confidence: 99%

Automatic CAD-RADS Scoring Using Deep Learning

Denzinger,

Wels,

Breininger

et al. 2020

Preprint

View full text Add to dashboard Cite

Coronary CT angiography (CCTA) has established its role as a non-invasive modality for the diagnosis of coronary artery disease (CAD). 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. The method relies solely on a prior fully-automated centerline extraction and segment labeling and predicts the segment-wise stenosis degree and the overall calcification grade as auxiliary tasks in a multi-task learning setup. We evaluate our approach on a data collection consisting of 2,867 patients. On the task of identifying patients with a CAD-RADS score indicating the need for further invasive investigation our approach reaches an area under curve (AUC) of 0.923 and an AUC of 0.914 for determining whether the patient suffers from CAD. This level of performance enables our approach to be used in a fully-automated screening setup or to assist diagnostic CCTA reading, especially due to its neural architecture design -which allows comprehensive predictions.

show abstract

Texture-Based Classification of Significant Stenosis in CCTA Multi-view Images of Coronary Arteries

Cited by 17 publications

References 11 publications

Deep Learning Algorithms for Coronary Artery Plaque Characterisation from CCTA Scans

Deep Learning Algorithms for Coronary Artery Plaque Characterisation from CCTA Scans

Transformer Network for Significant Stenosis Detection in CCTA of Coronary Arteries

Automatic CAD-RADS Scoring Using Deep Learning

Contact Info

Product

Resources

About