3D Context Enhanced Region-based Convolutional Neural Network for End-to-End Lesion Detection
Published in
International Conference on Medical Image Compu...(2018)External Links:
TL
TL;DR
3D context enhanced region-based CNN (3DCE) is proposed to incorporate 3D context information efficiently by aggregating feature maps of 2D images to detect lesions from computed tomography scans.
Abstract
Detecting lesions from computed tomography (CT) scans is an important but difficult problem because non-lesions and true lesions can appear similar. 3D context is known to be helpful in this differentiation task. However, existing end-to-end detection frameworks of convolutional neural networks (CNNs) are mostly designed for 2D images. In this paper, we propose 3D context enhanced region-based CNN (3DCE) to incorporate 3D context information efficiently by aggregating feature maps of 2D images. 3DCE is easy to train and end-to-end in training and inference. A universal lesion detector is developed to detect all kinds of lesions in one algorithm using the DeepLesion dataset. Experimental results on this challenging task prove the effectiveness of 3DCE.
References12 items
1
Deep Lesion Graphs in the Wild: Relationship Learning and Organization of Significant Radiology Image Findings in a Diverse Large-Scale Lesion Database
2
Evaluate the Malignancy of Pulmonary Nodules Using the 3-D Deep Leaky Noisy-OR Network
3
Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks
4
Multilevel Contextual 3-D CNNs for False Positive Reduction in Pulmonary Nodule Detection
5