GAN Augmentation: Augmenting Training Data using Generative Adversarial Networks
원문 초록
One of the biggest issues facing the use of machine learning in medical imaging is the lack of availability of large, labelled datasets. The annotation of medical images is not only expensive and time consuming but also highly dependent on the availability of expert observers. The limited amount of training data can inhibit the performance of supervised machine learning algorithms which often need very large quantities of data on which to train to avoid overfitting. So far, much effort has been directed at extracting as much information as possible from what data is available. Generative Adversarial Networks (GANs) offer a novel way to unlock additional information from a dataset by generating synthetic samples with the appearance of real images. This paper demonstrates the feasibility of introducing GAN derived synthetic data to the training datasets in two brain segmentation tasks, leading to improvements in Dice Similarity Coefficient (DSC) of between 1 and 5 percentage points under different conditions, with the strongest effects seen fewer than ten training image stacks are available.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
GOUHFI: a novel contrast- and resolution-agnostic segmentation tool for Ultra-High Field MRI
Full-Head Segmentation of MRI with Abnormal Brain Anatomy: Model and Data Release
Unified 3D MRI Representations via Sequence-Invariant Contrastive Learning
Comparative Study of Probabilistic Atlas and Deep Learning Approaches for Automatic Brain Tissue Segmentation from MRI Using N4 Bias Field Correction and Anisotropic Diffusion Pre-processing Techniques
Bilateral Hippocampi Segmentation in Low Field MRIs Using Mutual Feature Learning via Dual-Views
MedSegMamba: 3D CNN-Mamba Hybrid Architecture for Brain Segmentation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.