DeepAI
Log In Sign Up

AVP: Physics-informed Data Generation for Small-data Learning

02/05/2019
by   Jialei Chen, et al.
14

Deep neural networks have achieved great success in multiple learning problems, and attracted increasing attention from the medicine community. In reality, however, the limited availability and high costs of medical data is a major challenge of applying deep neural networks to computer-aided diagnosis and treatment planning. We address this challenge with adaptive virtual patients (AVPs) and the associated physics-informed learning framework. Specifically, the original training dataset is fused with an additional dataset of AVPs, which are generated by a data-driven model and the associated supervision (e.g., labels) is obtained by a physics-based approach. A key novelty in the proposed framework is the bidirectional and uncoupled generative invertible networks (GIN), which can extract pathophysiological features from the training medical image and generate pathophysiologically meaningful virtual patients. In order to mitigate the possibly high labeling cost of physical experiments, a μ-measure design is conducted: this allows the AVPs to not only further explore the uncertain regions, but also balance the label distribution. We then discuss the pathophysiological interpretability of GIN both theoretically and experimentally, and demonstrate the effectiveness of AVPs using a real medical image dataset, in which the proposed AVPs lower the labeling cost by 90

READ FULL TEXT

page 7

page 9

page 10

page 12

page 16

07/19/2017

Self-paced Convolutional Neural Network for Computer Aided Detection in Medical Imaging Analysis

Tissue characterization has long been an important component of Computer...
05/15/2021

Inferring micro-bubble dynamics with physics-informed deep learning

Micro-bubbles and bubbly flows are widely observed and applied to medici...
06/22/2021

Making Invisible Visible: Data-Driven Seismic Inversion with Physics-Informed Data Augmentation

Deep learning and data-driven approaches have shown great potential in s...
02/28/2021

Improving Medical Image Classification with Label Noise Using Dual-uncertainty Estimation

Deep neural networks are known to be data-driven and label noise can hav...
04/12/2021

Learning from Subjective Ratings Using Auto-Decoded Deep Latent Embeddings

Depending on the application, radiological diagnoses can be associated w...
10/11/2022

3D Matting: A Benchmark Study on Soft Segmentation Method for Pulmonary Nodules Applied in Computed Tomography

Usually, lesions are not isolated but are associated with the surroundin...