CTformer: convolution-free Token2Token dilated vision transformer for low-dose CT denoising.
Dayang WangFenglei FanZhan WuRui LiuFei WangHengyong YuPublished in: Physics in medicine and biology (2023)
Low-dose computed tomography (LDCT) denoising is an important problem in CT research. Compared to the normal dose CT (NDCT), LDCT images are subjected to severe noise and artifacts. Recently in many studies, vision transformers have shown superior feature representation ability over convolutional neural networks (CNNs). However, unlike CNNs, the potential of vision transformers in LDCT denoising was little explored so far. To fill this gap, we propose a Convolution-free Token2Token Dilated Vision Transformer (CTformer) for low-dose CT denoising. The CTformer uses a more powerful token rearrangement to encompass local contextual information and thus avoids convolution. It also dilates and shifts feature maps to capture longer-range interaction. We interpret the CTformer by statically inspecting patterns of its internal attention maps and dynamically tracing the hierarchical attention flow with an explanatory graph. Furthermore, an overlapped inference mechanism is introduced to effectively eliminate the boundary artifacts that are common for encoder-decoder-based denoising models. Experimental results on Mayo
LDCT dataset suggest that the CTformer
outperforms the state-of-the-art denoising methods with a low computation overhead.
Keyphrases
- convolutional neural network
- image quality
- low dose
- computed tomography
- deep learning
- dual energy
- contrast enhanced
- neural network
- positron emission tomography
- high dose
- working memory
- machine learning
- magnetic resonance imaging
- early onset
- air pollution
- magnetic resonance
- social media
- risk assessment
- case control
- cone beam