Learning Inductive Attention Guidance for Partially Supervised Pancreatic Ductal Adenocarcinoma Prediction
arXiv:2105.14773 · doi:10.1109/TMI.2021.3060066
Abstract
Pancreatic ductal adenocarcinoma (PDAC) is the third most common cause of cancer death in the United States. Predicting tumors like PDACs (including both classification and segmentation) from medical images by deep learning is becoming a growing trend, but usually a large number of annotated data are required for training, which is very labor-intensive and time-consuming. In this paper, we consider a partially supervised setting, where cheap image-level annotations are provided for all the training data, and the costly per-voxel annotations are only available for a subset of them. We propose an Inductive Attention Guidance Network (IAG-Net) to jointly learn a global image-level classifier for normal/PDAC classification and a local voxel-level classifier for semi-supervised PDAC segmentation. We instantiate both the global and the local classifiers by multiple instance learning (MIL), where the attention guidance, indicating roughly where the PDAC regions are, is the key to bridging them: For global MIL based normal/PDAC classification, attention serves as a weight for each instance (voxel) during MIL pooling, which eliminates the distraction from the background; For local MIL based semi-supervised PDAC segmentation, the attention guidance is inductive, which not only provides bag-level pseudo-labels to training data without per-voxel annotations for MIL training, but also acts as a proxy of an instance-level classifier. Experimental results show that our IAG-Net boosts PDAC segmentation accuracy by more than 5% compared with the state-of-the-arts.
References in corpus (20)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Fully Convolutional Networks for Semantic Segmentation
- A large annotated medical image dataset for the development and evaluation of segmentation algorithms
- Attention-based Deep Multiple Instance Learning
- 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation
- Weakly Supervised Object Localization with Multi-fold Multiple Instance Learning
- An application of cascaded 3D fully convolutional networks for medical image segmentation
- Semi-supervised Medical Image Classification with Relation-driven Self-ensembling Model
- Abdominal multi-organ segmentation with organ-attention networks and statistical fusion
- Semi-Supervised Medical Image Segmentation via Learning Consistency under Transformations
- Joint Weakly and Semi-Supervised Deep Learning for Localization and Classification of Masses in Breast Ultrasound Images
- DeepOrgan: Multi-level Deep Convolutional Networks for Automated Pancreas Segmentation
- 3D Deeply Supervised Network for Automatic Liver Segmentation from CT Volumes
- H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation from CT Volumes
- Weakly Supervised Medical Diagnosis and Localization from Multiple Resolutions
- Prior-aware Neural Network for Partially-Supervised Multi-Organ Segmentation
- DeepLesion: Automated Deep Mining, Categorization and Detection of Significant Radiology Image Findings using Large-Scale Clinical Lesion Annotations
- Spatial Aggregation of Holistically-Nested Networks for Automated Pancreas Segmentation
- Deep Nets: What have they ever done for Vision?
- Extreme Consistency: Overcoming Annotation Scarcity and Domain Shifts