Generalizing Deep Learning for Medical Image Segmentation to Unseen Domains via Deep Stacked Transformation

By Ling Zhang, Xiaosong Wang, Dong Yang, Thomas Sanford, S. Harmon, Baris Turkbey, Bradford J. Wood, Holger R. Roth, Andriy Myronenko, Daguang Xu and 1 more. IEEE Transactions on Medical Imaging, 2020

514 citations recorded by the source corpus.

Recent advances in deep learning for medical image segmentation demonstrate expert-level accuracy. However, application of these models in clinically realistic environments can result in poor generalization and decreased accuracy, mainly due to the domain shift across different hospitals, scanner vendors, imaging protocols, and patient populations etc. Common transfer learning and domain adaptation techniques are proposed to address this bottleneck. However, these solutions require data (and annotations) from the target domain to retrain the model, and is therefore restrictive in practice for widespread model deployment. Ideally, we wish to have a trained (locked) model that can work uniformly well across unseen domains without further training. In this paper, we propose a deep stacked transformation approach for domain generalization. Specifically, a series of ${n}$ stacked transformations are applied to each image during network training. The underlying assumption is that the “expected” domain shift for a specific medical imaging modality could be simulated by applying extensive data augmentation on a single source domain, and consequently, a deep model trained on the augmented “big” data (BigAug) could generalize well on unseen domains. We exploit four surprisingly effective, but previously understudied, image-based characteristics for data augmentation to overcome the domain generalization problem. We train and evaluate the BigAug model (with ${n}={9}$ transformations) on three different 3D segmentation tasks (prostate gland, left atrial, left ventricle) covering two medical imaging modalities (MRI and ultrasound) involving eight publicly available challenge datasets. The results show that when training on relatively small dataset (n = 10~32 volumes, depending on the size of the available datasets) from a single source domain: (i) BigAug models degrade an average of 11%(Dice score change) from source to unseen domain, substantially better than conventional augmentation (degrading 39%) and CycleGAN-based domain adaptation method (degrading 25%), (ii) BigAug is better than “shallower” stacked transforms (i.e. those with fewer transforms) on unseen domains and demonstrates modest improvement to conventional augmentation on the source domain, (iii) after training with BigAug on one source domain, performance on an unseen domain is similar to training a model from scratch on that domain when using the same number of training samples. When training on large datasets (n = 465 volumes) with BigAug, (iv) application to unseen domains reaches the performance of state-of-the-art fully supervised models that are trained and tested on their source domains. These findings establish a strong benchmark for the study of domain generalization in medical imaging, and can be generalized to the design of highly robust deep segmentation models for clinical deployment.

Subfields: Artificial Intelligence, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/b37850bfc6e011a4c3d5caaad98787c2ddab193c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Qi-Yan Dou
  2. P. Heng
  3. Jing Qin
  4. Cheng Chen
  5. Quande Liu
  6. Yichi Zhang
  7. Rushi Jiao
  8. Jicong Zhang

In Radiology, Nuclear Medicine and Imaging

  1. P. Heng
  2. Jing Qin
  3. Qi-Yan Dou
  4. Cheng Chen
  5. Quande Liu
  6. Hao Chen
  7. Lequan Yu
  8. Balázs Harangi

Citations in the corpus