딥러닝 성능 향상을 위한 3D 의료 영상 증강법

다국어 초록 (Multilingual Abstract)

This paper proposes a 3D image augmentation method for improving the generalization performance of deep neural networks. It allows us to enrich the diversity of training data samples that is essential in medical image segmentation tasks, thus reducing the data overfitting problem caused by the fact the scale of medical image dataset is typically smaller. It also enables us to predict medical segmentation surfaces in Euclidean space without additional labeled datasets. This method includes image transformation functions, which are comprised of a spatial deformation and image intensity change, enabling the synthesis of complex effects such as variations in anatomy and image acquisition procedures. Our numerical experiments demonstrate that the proposed approach provides significant improvements over state-of-the-art methods for 3D medical image segmentation.

목차 (Table of Contents)

• ABSTRACT
• 1. 서론
• 2. 데이터 증강법
• 3. 수치 실험 및 고찰
• 4. 결론
• References

참고문헌 (Reference)

1 "https://pytorch.org/"

2 "https://nipy.org/nibabel/coordinate_systems.html"

3 "https://brain-development.org/ixi-dataset/"

4 Xie, Q., "Unsupervised Data Augmentation"

5 Pérez-García, F., "TorchIO: a Python Library for Efficient Loading, Preprocessing, Augmentation and Patch-based Sampling of Medical Images in Deep Learning"

6 Cubuk, E. D., "Randaugment: Practical Automated Data Augmentation with a Reduced Search Space"

7 Nyul, L. G., "New Variants of a Method of MRI Scale Standardization" 19 (19): 2000

8 Yi, X., "Generative Adversarial Network in Medical Imaging: A Review" 58 : 2018

9 Lim, S., "Fast Autoaugment"

10 Loshchilov, I., "Decoupled Weight Decay Regularization"

11 Cubuk, E. D., "Autoaugment: Learning Augmentation Strategies from Data" 2019

12 Çiçek, Ö., "3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation"