Challenge 1 – Artery Detection


Due to the increasing number of medical images being used in medical praxis, the manual processing of the data becomes impossible especially with the vast number of data available, which makes the automatic processing necessary. One of the cases, where the full automation of measuring process is needed is the measurement of static and dynamic parameters of arteries, such as lumen diameter (LD), artery stiffness (AS), or intima media thickness (IMT). The results of such measurements can be used for the prediction of patient’s risk of cardio-vascular events. The measurement process typically consists of two subsequent steps – the detection of the artery (localization in an  ultrasound image) and later segmentation of artery wall. Recently, the issue of segmentation (the second step) is quite well explored and this step is fully automated. But still many measurement systems are not fully automated; often the localization step requires the interaction with operator. To achieve the fully automatic system it is required to automate the localization of the artery in order to make it ready for next processing.

Challenge Definition

This challenge deals with automatic localisation of the transverse section of the carotis communis artery in ultrasound images taken from imaging devices with different settings from different volunteers, which can help with the full automation of medical systems. The objective of this challenge is to propose an automatic algorithm, which will be able to find the position and size of the artery accurately in the source image. The results can be compared to data labelled by human expert.

Training and Testing Data

Training and Testing data are frames extracted from videos that we aquired from a Sonographic device, each frame is of size 800×600 pixels. The training set consists of 1450 frames, and the Testing set consists of 1380 frames.

Experement  Accuracy                        Description
Human     operator    100% A human operator will locate the aretry manualy and we take this as “ground truth” information.
Viola- Jones 89% Using the Viola-Jones detector that is implemented in OpenCV to detect the artery with combination of Circular Hough Transform for estimating the center and radius of the artey.
Optical               Flow    85% Using optical flow to detect the artery in n-number of frames with Hough Transform (see: ŘÍHA, K.; BENEŠ, R. Circle Detection in Pulsative Medical Video Sequence. In Proceedings of International Conference on Signal Processing, vol. I. Beijing, IEEE Press. 2010. p. 674 – 677. ISBN 978-1-4244-5898-1.)

Why to participate

  • You will participate in still up-to-date research problem,
  • You will be invited* to present your work on recognized TSP conference, which is indexed by most indexes, such as:IEEE Xplore®CPCI (ISI web of Knowledge), SCOPUSDBLP, and Google Scholar. More information about deadlines and information for authors can be found on page website:
  • Selected results will be sent to selected journal with Impact Factor.


Primary references:

ŘÍHA, K.; BENEŠ, R. Circle Detection in Pulsative Medical Video Sequence. In Proceedings of International Conference on Signal Processing, vol. I. Beijing, IEEE Press. 2010. p. 674 – 677. ISBN 978-1-4244-5898-1. (download pdf)

ŘÍHA, K.; CHEN, P.; FU, D. Detection of Artery Section Area Using Artificial Immune System Algorithm Using Artificial Immune System Algorithm. In Proceedings of The 7th WSEAS International Conference on CIRCUITS, SYSTEMS, ELECTRONICS, CONTROL & SIGNAL PROCESSING. Puerto De La Cruz, Spain. 2008. p. 46 – 52. ISBN 978-960-474-035-2. (download pdf)


* It is possible that some invited papers may be rejected. However, this is expected to be a rare case since the Organizer should recruit only the high-quality participants to the Special Session.


Ing. Kamil Riha, Ph.D.,