Dataset Information

Catheter segmentation in X-ray fluoroscopy using synthetic data and transfer learning with light U-nets.

ABSTRACT: Background and objectivesAutomated segmentation and tracking of surgical instruments and catheters under X-ray fluoroscopy hold the potential for enhanced image guidance in catheter-based endovascular procedures. This article presents a novel method for real-time segmentation of catheters and guidewires in 2d X-ray images. We employ Convolutional Neural Networks (CNNs) and propose a transfer learning approach, using synthetic fluoroscopic images, to develop a lightweight version of the U-Net architecture. Our strategy, requiring a small amount of manually annotated data, streamlines the training process and results in a U-Net model, which achieves comparable performance to the state-of-the-art segmentation, with a decreased number of trainable parameters. MethodsThe proposed transfer learning approach exploits high-fidelity synthetic images generated from real fluroscopic backgrounds. We implement a two-stage process, initial end-to-end training and fine-tuning, to develop two versions of our model, using synthetic and phantom fluoroscopic images independently. A small number of manually annotated in-vivo images is employed to fine-tune the deepest 7 layers of the U-Net architecture, producing a network specialized for pixel-wise catheter/guidewire segmentation. The network takes as input a single grayscale image and outputs the segmentation result as a binary mask against the background. ResultsEvaluation is carried out with images from in-vivo fluoroscopic video sequences from six endovascular procedures, with different surgical setups. We validate the effectiveness of developing the U-Net models using synthetic data, in tests where fine-tuning and testing in-vivo takes place both by dividing data from all procedures into independent fine-tuning/testing subsets as well as by using different in-vivo sequences. Accurate catheter/guidewire segmentation (average Dice coefficient of ~ 0.55, ~ 0.26 and ~ 0.17) is obtained with both U-Net models. Compared to the state-of-the-art CNN models, the proposed U-Net achieves comparable performance ( ± 5% average Dice coefficients) in terms of segmentation accuracy, while yielding a 84% reduction of the testing time. This adds flexibility for real-time operation and makes our network adaptable to increased input resolution. ConclusionsThis work presents a new approach in the development of CNN models for pixel-wise segmentation of surgical catheters in X-ray fluoroscopy, exploiting synthetic images and transfer learning. Our methodology reduces the need for manually annotating large volumes of data for training. This represents an important advantage, given that manual pixel-wise annotations is a key bottleneck in developing CNN segmentation models. Combined with a simplified U-Net model, our work yields significant advantages compared to current state-of-the-art solutions.

SUBMITTER: Gherardini M

PROVIDER: S-EPMC7903142 | biostudies-literature | 2020 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Catheter segmentation in X-ray fluoroscopy using synthetic data and transfer learning with light U-nets.

Gherardini Marta M Mazomenos Evangelos E Menciassi Arianna A Stoyanov Danail D

Computer methods and programs in biomedicine 20200229

Background and objectivesAutomated segmentation and tracking of surgical instruments and catheters under X-ray fluoroscopy hold the potential for enhanced image guidance in catheter-based endovascular procedures. This article presents a novel method for real-time segmentation of catheters and guidewires in 2d X-ray images. We employ Convolutional Neural Networks (CNNs) and propose a transfer learning approach, using synthetic fluoroscopic images, to develop a lightweight version of the U-Net arc ...[more]

PMID: 32171151

Similar Datasets

Project description:PurposeTo compare in vitro navigation of a magnetically assisted remote-controlled (MARC) catheter under real-time magnetic resonance (MR) imaging with manual navigation under MR imaging and standard x-ray guidance in endovascular catheterization procedures in an abdominal aortic phantom.Materials and methodsThe 2-mm-diameter custom clinical-grade microcatheter prototype with a solenoid coil at the distal tip was deflected with a foot pedal actuator used to deliver 300 mA of positive or negative current. Investigators navigated the catheter into branch vessels in a custom cryogel abdominal aortic phantom. This was repeated under MR imaging guidance without magnetic assistance and under conventional x-ray fluoroscopy. MR experiments were performed at 1.5 T by using a balanced steady-state free precession sequence. The mean procedure times and percentage success data were determined and analyzed with a linear mixed-effects regression analysis.ResultsThe catheter was clearly visible under real-time MR imaging. One hundred ninety-two (80%) of 240 turns were successfully completed with magnetically assisted guidance versus 144 (60%) of 240 turns with nonassisted guidance (P < .001) and 119 (74%) of 160 turns with standard x-ray guidance (P = .028). Overall mean procedure time was shorter with magnetically assisted than with nonassisted guidance under MR imaging (37 seconds ± 6 [standard error of the mean] vs 55 seconds ± 3, P < .001), and time was comparable between magnetically assisted and standard x-ray guidance (37 seconds ± 6 vs 44 seconds ± 3, P = .045). When stratified by angle of branch vessel, magnetic assistance was faster than nonassisted MR guidance at turns of 45°, 60°, and 75°.ConclusionIn this study, a MARC catheter for endovascular navigation under real-time MR imaging guidance was developed and tested. For catheterization of branch vessels arising at large angles, magnetically assisted catheterization was faster than manual catheterization under MR imaging guidance and was comparable to standard x-ray guidance.

Project description:Analyzing medical data to find abnormalities is a time-consuming and costly task, particularly for rare abnormalities, requiring tremendous efforts from medical experts. Therefore, artificial intelligence has become a popular tool for the automatic processing of medical data, acting as a supportive tool for doctors. However, the machine learning models used to build these tools are highly dependent on the data used to train them. Large amounts of data can be difficult to obtain in medicine due to privacy reasons, expensive and time-consuming annotations, and a general lack of data samples for infrequent lesions. In this study, we present a novel synthetic data generation pipeline, called SinGAN-Seg, to produce synthetic medical images with corresponding masks using a single training image. Our method is different from the traditional generative adversarial networks (GANs) because our model needs only a single image and the corresponding ground truth to train. We also show that the synthetic data generation pipeline can be used to produce alternative artificial segmentation datasets with corresponding ground truth masks when real datasets are not allowed to share. The pipeline is evaluated using qualitative and quantitative comparisons between real data and synthetic data to show that the style transfer technique used in our pipeline significantly improves the quality of the generated data and our method is better than other state-of-the-art GANs to prepare synthetic images when the size of training datasets are limited. By training UNet++ using both real data and the synthetic data generated from the SinGAN-Seg pipeline, we show that the models trained on synthetic data have very close performances to those trained on real data when both datasets have a considerable amount of training data. In contrast, we show that synthetic data generated from the SinGAN-Seg pipeline improves the performance of segmentation models when training datasets do not have a considerable amount of data. All experiments were performed using an open dataset and the code is publicly available on GitHub.

Dataset Information

Catheter segmentation in X-ray fluoroscopy using synthetic data and transfer learning with light U-nets.

Publications

Catheter segmentation in X-ray fluoroscopy using synthetic data and transfer learning with light U-nets.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets