Name
Title | ||
|---|---|---|
Diagnostically lossless coding of X-ray angiography images based on background suppression. |
Abstract | ||
|---|---|---|
An automatic segmentation of the diagnostically relevant focal area of X-ray angiography images was developed.A background suppression coding strategy was proposed based on the accurate segmentation results.Our segmentation method identifies the Regions of Interest with an average Dice Similarity Coefficient of 0.98 with respect to manual segmentation.The coding performance improvement reaches 34%, compared to the case of coding with no background suppression. Display Omitted X-ray angiography images are widely used to identify irregularities in the vascular system. Because of their high spatial resolution and the large amount of images generated daily, coding of X-ray angiography images is becoming essential. This paper proposes a diagnostically lossless coding method based on automatic segmentation of the focal area using ray-casting and α-shapes. The diagnostically relevant Region of Interest is first identified by exploiting the inherent symmetrical features of the image. The background is then suppressed and the resulting images are encoded using lossless and progressive lossy-to-lossless methods, including JPEG-LS, JPEG2000, H.264 and HEVC. Experiments on a large set of X-ray angiography images suggest that our method correctly identifies the Region of Interest. When compared to the case of coding with no background suppression, the method achieves average bit-stream reductions of nearly 34% and improvements on the reconstruction quality of up to 20 dB-SNR for progressive decoding. |
Year | DOI | Venue |
|---|---|---|
2016 | 10.1016/j.compeleceng.2016.02.014 | Computers & Electrical Engineering |
Keywords | Field | DocType |
X-ray angiography images,Diagnostically lossless coding,Ray casting segmentation,Alpha-shapes filters,Region of interest compression | Computer vision,Computer science,Segmentation,Coding (social sciences),Artificial intelligence,JPEG 2000,Decoding methods,Region of interest,Image resolution,Angiography,Lossless compression | Journal |
Volume | Issue | ISSN |
53 | C | 0045-7906 |
Citations | PageRank | References |
3 | 0.41 | 13 |
Authors | ||
7 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Zhongwei Xu | 1 | 7 | 1.97 |
| Joan Bartrina-Rapesta | 2 | 60 | 14.31 |
| Ian Blanes | 3 | 73 | 12.99 |
| Victor Sanchez | 4 | 144 | 31.22 |
| Joan Serra-Sagristà | 5 | 103 | 27.96 |
| Marcel García-Bach | 6 | 3 | 0.41 |
| Juan Francisco Muñoz | 7 | 3 | 0.41 |