ElixirNet: Relation-aware Network Architecture Adaptation for Medical Lesion Detection
arXiv:2003.08770
Abstract
Most advances in medical lesion detection network are limited to subtle modification on the conventional detection network designed for natural images. However, there exists a vast domain gap between medical images and natural images where the medical image detection often suffers from several domain-specific challenges, such as high lesion/background similarity, dominant tiny lesions, and severe class imbalance. Is a hand-crafted detection network tailored for natural image undoubtedly good enough over a discrepant medical lesion domain? Is there more powerful operations, filters, and sub-networks that better fit the medical lesion detection problem to be discovered? In this paper, we introduce a novel ElixirNet that includes three components: 1) TruncatedRPN balances positive and negative data for false positive reduction; 2) Auto-lesion Block is automatically customized for medical images to incorporate relation-aware operations among region proposals, and leads to more suitable and efficient classification and localization. 3) Relation transfer module incorporates the semantic relationship and transfers the relevant contextual information with an interpretable the graph thus alleviates the problem of lack of annotations for all types of lesions. Experiments on DeepLesion and Kits19 prove the effectiveness of ElixirNet, achieving improvement of both sensitivity and precision over FPN with fewer parameters.
7 pages, 5 figure, AAAI2020
References in corpus (12)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Neural Architecture Search with Reinforcement Learning
- R-FCN: Object Detection via Region-based Fully Convolutional Networks
- DARTS: Differentiable Architecture Search
- Focal Loss for Dense Object Detection
- Improving Computer-aided Detection using Convolutional Neural Networks and Random View Aggregation
- SMASH: One-Shot Model Architecture Search through HyperNetworks
- The KiTS19 Challenge Data: 300 Kidney Tumor Cases with Clinical Context, CT Semantic Segmentations, and Surgical Outcomes
- Random Search and Reproducibility for Neural Architecture Search
- Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation
- FRAGE: Frequency-Agnostic Word Representation
- Automated soft tissue lesion detection and segmentation in digital mammography using a u-net deep learning network