3D Context Enhanced Region-based Convolutional Neural Network for End-to-End Lesion Detection

25 Jun 2018  ·  Ke Yan, Mohammadhadi Bagheri, Ronald M. Summers ·

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. We have released the code of 3DCE in https://github.com/rsummers11/CADLab/tree/master/lesion_detector_3DCE.

PDF Abstract

Datasets


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Medical Object Detection DeepLesion 3DCE Sensitivity 75.55 # 8

Methods


No methods listed for this paper. Add relevant methods here