Abstract
We consider a model-agnostic solution to the problem of Multi-Domain Learning (MDL) for multi-modal applications. Many existing MDL techniques are model-dependent solutions which explicitly require nontrivial architectural changes to construct domain-specific modules. Thus, properly applying these MDL techniques for new problems with well-established models, e.g. U-Net for semantic segmentation, may demand various low-level implementation efforts. In this paper, given emerging multi-modal data (e.g., various structural neuroimaging modalities), we aim to enable MDL purely algorithmically so that widely used neural networks can trivially achieve MDL in a model-independent manner. To this end, we consider a weighted loss function and extend it to an effective procedure by employing techniques from the recently active area of learning-to-learn (meta-learning). Specifically, we take inner-loop gradient steps to dynamically estimate posterior distributions over the hyperparameters of our loss function. Thus, our method is model-agnostic, requiring no additional model parameters and no network architecture changes; instead, only a few efficient algorithmic modifications are needed to improve performance in MDL. We demonstrate our solution to a fitting problem in medical imaging, specifically, in the automatic segmentation of white matter hyperintensity (WMH). We look at two neuroimaging modalities (T1-MR and FLAIR) with complementary information fitting for our problem.
Original language | English |
---|---|
Title of host publication | 2021 IEEE 18th International Symposium on Biomedical Imaging, ISBI 2021 |
Publisher | IEEE Computer Society |
Pages | 650-654 |
Number of pages | 5 |
ISBN (Electronic) | 9781665412469 |
DOIs | |
Publication status | Published - 2021 Apr 13 |
Event | 18th IEEE International Symposium on Biomedical Imaging, ISBI 2021 - Nice, France Duration: 2021 Apr 13 → 2021 Apr 16 |
Publication series
Name | Proceedings - International Symposium on Biomedical Imaging |
---|---|
Volume | 2021-April |
ISSN (Print) | 1945-7928 |
ISSN (Electronic) | 1945-8452 |
Conference
Conference | 18th IEEE International Symposium on Biomedical Imaging, ISBI 2021 |
---|---|
Country/Territory | France |
City | Nice |
Period | 21/4/13 → 21/4/16 |
Bibliographical note
Funding Information:This work was supported by the NIH/NIA (R01 AG063752, RF1 AG025516, P01 AG025204, K23 MH118070), and SCI Undergraduate Research Scholars Award. We report no conflicts of interests.
Publisher Copyright:
© 2021 IEEE.
All Science Journal Classification (ASJC) codes
- Biomedical Engineering
- Radiology Nuclear Medicine and imaging