Image processing for semantic analysis of the coronary interventions in cardiology

Abstract : Percutaneous coronary intervention (PCI) is performed using real-time radiographic imaging in an interventional suite. Modeling these ICP procedures to help the practitioner involves understanding the different phases of the ICP procedure, by the interventional machine, which can be used to optimize the X-ray dose and the contrast agent. One of the important tasks in achieving this goal is to segment different interventional tools into the flow of fluoroscopic images and to derive semantic information from them. The component tree, a powerful mathematical morphological tool, forms the basis of the proposed segmentation methods. We present this work in two parts: 1) the segmentation of the low-contrast empty catheter, and 2) the segmentation of the tip of the guide and the monitoring of the detection of the intervention vessel. We present a new multi-scale space-based segmentation method for detecting low-contrast objects such as an empty catheter. For the last part, we present the segmentation of the tip of the guide with filtering based on the component tree and propose an algorithm to semantically follow the segmented tip to determine the intervention vessel
Document type :
Theses
Complete list of metadatas

Cited literature [197 references]  Display  Hide  Download

https://pastel.archives-ouvertes.fr/tel-01981918
Contributor : Abes Star <>
Submitted on : Tuesday, January 15, 2019 - 12:24:14 PM
Last modification on : Tuesday, March 19, 2019 - 11:43:24 PM
Long-term archiving on : Tuesday, April 16, 2019 - 1:54:59 PM

File

TH2018PESC1074.pdf
Version validated by the jury (STAR)

Identifiers

  • HAL Id : tel-01981918, version 1

Collections

Citation

Ketan Bacchuwar. Image processing for semantic analysis of the coronary interventions in cardiology. Document and Text Processing. Université Paris-Est, 2018. English. ⟨NNT : 2018PESC1074⟩. ⟨tel-01981918⟩

Share

Metrics

Record views

104

Files downloads

45