=Paper=
{{Paper
|id=Vol-2272/short4
|storemode=property
|title=Segmentation of vessel tree from cine-angiography images for intraoperative clinical evaluation
|pdfUrl=https://ceur-ws.org/Vol-2272/short4.pdf
|volume=Vol-2272
|authors=Pierangela Bruno,Paolo Zaffino,Salvatore Scaramuzzino,Salvatore De Rosa,Ciro Indolfi,Francesco Calimeri,Maria Francesca Spadea
|dblpUrl=https://dblp.org/rec/conf/aiia/BrunoZSRICS18a
}}
==Segmentation of vessel tree from cine-angiography images for intraoperative clinical evaluation==
https://ceur-ws.org/Vol-2272/short4.pdf
Segmentation of vessel tree from
cine-angiography images for intraoperative
clinical evaluation.
Pierangela Bruno1[0000−0002−0832−0151] , Paolo Zaffino2[0000−0002−0219−0157] ,
Salvatore Scaramuzzino2* , Salvatore De Rosa3 , Ciro Indolfi3 , Francesco
Calimeri1[0000−0002−0866−0834] , and Maria Francesca
Spadea2[0000−0002−5339−9583]
1
Department of Mathematics and Computer Science, University of Calabria, Italy
{bruno, calimeri}@mat.unical.it
2
Department of Experimental and Clinical Medicine, University of Catanzaro, Italy
(∗ at the time of the study)
{p.zaffino, s.scaramuzzino, mfspadea}@unicz.it
3
Division of Cardiology, Department of Medical and Surgical Sciences, University of
Catanzaro, Italy
{saderosa, indolfi}@unicz.it
Abstract. The assessment of vascular complexity in the lower limbs
provides relevant information about peripheral artery diseases, with a
relevant impact on both therapeutic decisions and on prognostic esti-
mation. Such evaluation is currently carried out by human operators
via visual inspection of cine-angiograms, resulting in conflicting results
and scorings that are largely operator-dependent, mostly because of the
technical difficulties in the quantification of vascular network and its flow
capability.
We propose a new method to automatically segment the vessel tree from
cine-angiography video for intraoperative clinical evaluation, in order to
improve the clinical interpretation of the complexity of vascular collat-
erals in Peripheral Arterial Occlusive Disease (PAOD) patients.
1 Introduction
The assessment of vascular complexity in the lower limbs provides relevant in-
formation about peripheral artery diseases; in fact, vascular collaterals act as a
sort of natural bypass system, sustaining tissue perfusion downward of vascular
occlusion [1]. Intuitively, they can exert a protective impact on limb ischemia,
thus reducing symptoms and improving the outcome in patients with Peripheral
Arterial Occlusive Disease (PAOD) [2].
In current clinical practice, cine-angiography is widely used to assess the
vascular complexity in the lower limbs, in order to obtain relevant information
about PAOD. Therapeutic decisions and prognostic forecasts, in fact, are based
on visual inspection of such images. Despite its wide use, this technique re-
mains a largely operator-dependent process, also prone to errors mostly due to
2 P. Bruno et al.
misinterpretations. Indeed, besides the hard task of identifying the vessel tree,
video images feature the presence of surgical instruments, tools, electrode ca-
bles, catheters, etc., that makes the correct automatic evaluation even more
challenging. In this work we define a new methodology for automatic vessel tree
identification from a set of images obtained subdividing cine-angiography videos
in different frames, with the goal of fostering more reliable clinical assessments
in the described scenario. In particular, we aim at making use of Convolutional
Neural Networks (CNNs) for the segmentation of the vascular tree over a set of
images extracted during the cine-angiography process.
Interestingly, to the best of our knowledge, this is one of the first attempts
to segment vessels in the ilio-femoral district on a set of 2-D frames. In fact, the
method presents several challenges: (i) non-trivial image pre-processing opera-
tions are needed in order to elaborate and extract a set of static image from the
cine-angiography video; (ii) fine-tuning of CNN parameters in each layers, in
order to reach a high segmentation accuracy as described in [3]; (iii) assemble
the segmented images to create the original cine-angiography video for intraop-
erative application.
2 Proposed Approach
The main goal of this work is to provide a new approach for automatic vessel
segmentation from cine-angiography videos. The workflow of the proposed frame-
work, illustrated in Figure 1, can be divided into three steps: (i) pre-processing
operations build a set of images from cine-angiography videos and increase vessel
enhancement, (ii) a fully convolutional deep neural network architecture called
“U-net” [4] used in [3] is used to segment the vascular tree from the video frames,
and (iii) sequences of segmented static images are combined to reconstruct the
cine-angiography videos for the intraoperative application. It is worth noting
that we start from the approach of [3] in order to provide clinicians with a dif-
ferent tool for segmenting ilio-femoral district; indeed, differently from the cited
work, the cine-angiography video is subdivided into different frames instead of a
static reconstructed image. Then, U-net perform segmentation on different kind
of dataset.
3 Pre-processing of ilio-femoral images
Ilio-femoral images show some lighting variations, poor contrast and noise. To
reduce these imperfections and generate images more suitable for extracting
blood vessels, we applied following preprocessing steps:
– Contrast Limited Adaptive Histogram Equalization [5]
– Gamma correction [6]
– Background homogenization
Segmentation of vessel tree from cine-angiography images 3
Fig. 1. Workflow of the proposed framework.
As shown in Fig. 2, the resulting image shows an improvement of the lighting
variations and the contrast between background and vessels. These preprocessing
steps are necessary to remove noise and artifacts from the image in order to
improve segmentation accuracy and detection of blood vessels.
Fig. 2. Example of ilio-femoral image before (left) and after pre-processing operations
(right)
4 P. Bruno et al.
4 Network Description
The U-net model is a fully convolutional network with symmetrical structure,
composed of a contracting and an up-sampling part. The contracting path con-
sists of the repeated application of two 3×3 convolutions and a 2×2 maxpooling
operation with stride 2 for downsampling. The expansive path consists of an up-
sampling of the feature map followed by a two 3 × 3 convolutions. In the final
layer, a 1 × 1 convolution is used to map all 64 component feature vectors to the
desired number of classes [4]. All layers use Rectified Linear Unit (ReLU) [7],
except for the last layer, where Softmax [8] is used in order to select the best
scoring category; hence, for each pixel it returns the probability to be part of a
vessel or not. The U-net architecture adapted by [3] is showed in Figure 3.
Fig. 3. U-net architecture adapted by [3]
5 Experimental Setting and Results
The U-net [4] was trained on 30, 600 tiles extracted from cine-angiographies. The
ground truth used to accomplish the supervised learning was represented by a
manual segmentation executed by an expert clinician. Data acquisition, as well
as, data annotation, was executed the Interventional Cardiology Units of Magna
Graecia University Hospital (Catanzaro, Italy) and at Federico II University
Hospital (Naples, Italy).
For the real daily usage, once a DICOM file has been read, automatic segmen-
tation of a 60 seconds cine-angiography (357 frames) takes, on the average, 90
seconds with an AUC mean value of 0.988 ± 0.006. As a result, original images
with the highlited vessel tree is shown to the clinicians.
Segmentation of vessel tree from cine-angiography images 5
6 Conclusion
Considering that the cineangiography is an invasive procedure, the time avail-
able for collecting all data and defining a correct prognosis is usually quite
short. Hence, a shorter timescale is needed for improving the clinical interpreta-
tion of the complexity of vascular collaterals in PAOD patients. Our proposed
method features an intraoperative application to identify vascular abnormalities,
thanks to a robust segmentation process of the cine-angiography video during
the surgery.
By looking to this enhanced cine-angiography, operators can better visualize
the vessels and evaluate condition of patients more easily. Structures that are
not of interest (such as catheters and cables) are correctly recognized as “non
vessel” and excluded from the final segmentation. Finally, given that the process
result to be efficient enough to grant the generation of such enriched images
also on ordinary hardware, the proposed workflow is already applicable into any
typical intraoperative scenario.
Further efforts will be spent to both improve the segmentation accuracy and
speed-up the process in order to obtain a more accurate and fast, up to real-time,
segmentation workflow.
References
1. Prior B.M., Lloyd P.G., Ren J., Li H., Yang H.T., Laughlin M.H., Terjung R.L.,
“Time course of changes in collateral blood flow and isolated vessel size and gene
expression after femoral artery occlusion in rats,” American Journal of Physiology-
Heart and Circulatory Physiology, vol. 287(6), pp. H2434–H2447, 2004.
2. McDermott M.M., Liu K., Carroll T.J., Tian L., Ferrucci L., Li D., Carr J., Gu-
ralnik J.M., Kibbe M., Pearce W.H., Yuan C., “Superficial femoral artery plaque
and functional performance in peripheral arterial disease: walking and leg circulation
study (WALCS III),” JACC: Cardiovascular Imaging, vol. 4(7), pp. 730–739, 2011.
3. Bruno P., Zaffino P., Scaramuzzino S., De Rosa S., Indolfi C., Calimeri F., Spadea
M. F., “Using CNNs for Designing and Implementing an Automatic Vascular Seg-
mentation Method of Biomedical Images,” 2018.
4. Ronneberger, Olaf, Fischer P., Brox T., “U-net: Convolutional networks for biomed-
ical image segmentation,” International Conference on Medical image computing and
computer-assisted intervention, Springer, Cham, pp. 234–241 2015.
5. Reza A. M., “Realization of the contrast limited adaptive histogram equalization
(CLAHE) for real-time image enhancement,” Journal of VLSI signal processing sys-
tems for signal, image and video technology, vol. 38(1), pp. 35–44, 2004
6. Farid H., “Blind inverse gamma correction. IEEE Transactions on Image Process-
ing,” vol. 10(10), pp. 1428–1433, 2001.
7. Dahl G. E., Sainath T. N., Hinton G. E., “Improving deep neural networks for
LVCSR using rectified linear units and dropout,” IEEE International Conference,
pp. 8609–8613, 2013.
8. Gold S., Rangarajan A., “Softmax to softassign: Neural network algorithms for
combinatorial optimization,” Journal of Artificial Neural Networks, vol. 2(4), pp. 381–
399, 1996.