Anatomical Landmark Detection in Medical Applications Driven by Synthetic Data
Authors:
- Gernot RieglerGRGernot Riegler
- Martin UrschlerMUMartin Urschler
- Matthias RutherMRMatthias Ruther
- Horst BischofHBHorst Bischof
- Darko SternDSDarko Stern
- 1 December 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 85-89
Abstract
An important initial step in many medical image analysis applications is the accurate detection of anatomical landmarks. Most successful methods for this task rely on data-driven machine learning algorithms. However, modern machine learning techniques, e.g. convolutional neural networks, need a large corpus of training data, which is often an unrealistic setting for medical datasets. In this work, we investigate how to adapt synthetic image datasets from other computer vision tasks to overcome the under-representation of the anatomical pose and shape variations in medical image datasets. We transform both data domains to a common one in such a way that a convolutional neural network can be trained on the larger synthetic image dataset and fine-tuned on the smaller medical image dataset. Our evaluations on data of MR hand and whole body CT images demonstrate that this approach improves the detection results compared to training a convolutional neural network only on the medical data. The proposed approach may also be usable in other medical applications, where training data is scarce.Keywords
This publication has 15 references indexed in Scilit:
- A Framework for Articulated Hand Pose Estimation and Evaluation2015
- Real-Time Continuous Pose Recovery of Human Hands Using Convolutional NetworksACM Transactions on Graphics, 2014
- Latent Regression Forest: Structured Estimation of 3D Articulated Hand Posture2014
- DeepPose: Human Pose Estimation via Deep Neural Networks2014
- Virtual and Real World Adaptation for Pedestrian DetectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- Incremental Domain Adaptation of Deformable Part-based Models2014
- Global localization of 3D anatomical structures by pre-filtered Hough Forests and discrete optimizationMedical Image Analysis, 2013
- Brain templates and atlasesNeuroImage, 2012
- Real-time human pose recognition in parts from single depth images2011
- Regression Forests for Efficient Anatomy Detection and Localization in CT Studies2011