A New 2.5D Representation for Lymph Node Detection using Random Sets of Deep Convolutional Neural Network Observations
arXiv:1406.2639 · doi:10.1007/978-3-319-10404-1_65
Abstract
Automated Lymph Node (LN) detection is an important clinical diagnostic task but very challenging due to the low contrast of surrounding structures in Computed Tomography (CT) and to their varying sizes, poses, shapes and sparsely distributed locations. State-of-the-art studies show the performance range of 52.9% sensitivity at 3.1 false-positives per volume (FP/vol.), or 60.9% at 6.1 FP/vol. for mediastinal LN, by one-shot boosting on 3D HAAR features. In this paper, we first operate a preliminary candidate generation stage, towards 100% sensitivity at the cost of high FP levels (40 per patient), to harvest volumes of interest (VOI). Our 2.5D approach consequently decomposes any 3D VOI by resampling 2D reformatted orthogonal views N times, via scale, random translations, and rotations with respect to the VOI centroid coordinates. These random views are then used to train a deep Convolutional Neural Network (CNN) classifier. In testing, the CNN is employed to assign LN probabilities for all N random views that can be simply averaged (as a set) to compute the final classification probability per VOI. We validate the approach on two datasets: 90 CT volumes with 388 mediastinal LNs and 86 patients with 595 abdominal LNs. We achieve sensitivities of 70%/83% at 3 FP/vol. and 84%/90% at 6 FP/vol. in mediastinum and abdomen respectively, which drastically improves over the previous state-of-the-art work.
arXiv commentThis article will be presented at MICCAI (Medical Image Computing and Computer-Assisted Interventions) 2014
Cited by in corpus (19)
- ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases
- Improving Computer-aided Detection using Convolutional Neural Networks and Random View Aggregation
- NiftyNet: a deep-learning platform for medical imaging
- DeepNAT: Deep Convolutional Neural Network for Segmenting Neuroanatomy
- Models Genesis
- Machine Learning Techniques for Biomedical Image Segmentation: An Overview of Technical Aspects and Introduction to State-of-Art Applications
- Comparison of machine learning methods for classifying mediastinal lymph node metastasis of non-small cell lung cancer from 18F-FDG PET/CT images
- nnDetection: A Self-configuring Method for Medical Object Detection
- Melanoma Detection using Adversarial Training and Deep Transfer Learning
- 3D RoI-aware U-Net for Accurate and Efficient Colorectal Tumor Segmentation
- Deep learning trends for focal brain pathology segmentation in MRI
- Evaluation of Multi-Slice Inputs to Convolutional Neural Networks for Medical Image Segmentation
- Lesion Harvester: Iteratively Mining Unlabeled Lesions and Hard-Negative Examples at Scale
- Mediastinal Lymph Node Detection and Segmentation Using Deep Learning
- Automated Thalamic Nuclei Segmentation Using Multi-Planar Cascaded Convolutional Neural Networks
- CT Reconstruction using Diffusion Posterior Sampling conditioned on a Nonlinear Measurement Model
- A Gradient Mapping Guided Explainable Deep Neural Network for Extracapsular Extension Identification in 3D Head and Neck Cancer Computed Tomography Images
- Scatter Correction in X-ray CT by Physics-Inspired Deep Learning
- The Application of Deep Learning for Lymph Node Segmentation: A Systematic Review