Catheter Segmentation in X-ray Fluoroscopy using Synthetic Data and Transfer Learning with Light U-Nets

There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

Abstract

Highlights • Fully-automated, real-time catheter and guidewire segmentation in fluoroscopy using CNNs. • Two-stage training strategy based on transfer learning technique, using synthetic images with predefined labelled segmentation. • Methods to reduce the need of manual pixel-level labelling to facilitate the development of CNN models for semantic segmentation, especially in the medical field. • Lightweight CNN model with a decreased number of network parameters which results in more efficient training and faster run times (84% reduction in testing time compared to the state-of-the-art).

Related collections

Most cited references 37

Record: found
Abstract: not found
Book Chapter: not found

U-Net: Convolutional Networks for Biomedical Image Segmentation

Olaf Ronneberger, Philipp Fischer, Thomas Brox (2015)

0 comments Cited 3167 times – based on 0 reviews

Bookmark

Record: found
Abstract: not found
Conference Proceedings: not found

Fully convolutional networks for semantic segmentation

Jonathan Long, Evan Shelhamer, Trevor Darrell (2015)

0 comments Cited 1646 times – based on 0 reviews

Bookmark

Record: found
Abstract: found
Article: found

Is Open Access

Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning

Hoo-Chang Shin, Holger R. Roth, Mingchen Gao … (2016)

Remarkable progress has been made in image recognition, primarily due to the availability of large-scale annotated datasets and deep convolutional neural networks (CNNs). CNNs enable learning data-driven, highly representative, hierarchical image features from sufficient training data. However, obtaining datasets as comprehensively annotated as ImageNet in the medical imaging domain remains a challenge. There are currently three major techniques that successfully employ CNNs to medical image classification: training the CNN from scratch, using off-the-shelf pre-trained CNN features, and conducting unsupervised CNN pre-training with supervised fine-tuning. Another effective method is transfer learning, i.e., fine-tuning CNN models pre-trained from natural image dataset to medical image tasks. In this paper, we exploit three important, but previously understudied factors of employing deep convolutional neural networks to computer-aided detection problems. We first explore and evaluate different CNN architectures. The studied models contain 5 thousand to 160 million parameters, and vary in numbers of layers. We then evaluate the influence of dataset scale and spatial image context on performance. Finally, we examine when and why transfer learning from pre-trained ImageNet (via fine-tuning) can be useful. We study two specific computer-aided detection (CADe) problems, namely thoraco-abdominal lymph node (LN) detection and interstitial lung disease (ILD) classification. We achieve the state-of-the-art performance on the mediastinal LN detection, and report the first five-fold cross-validation classification results on predicting axial CT slices with ILD categories. Our extensive empirical evaluation, CNN model analysis and valuable insights can be extended to the design of high performance CAD systems for other medical imaging tasks.