An Automatic 3D PET Tumor Segmentation Framework Assisted by Geodesic Sequences

Positron Emission Tomography (PET) images reflect the metabolic rate of tracers in different tissues of the human body, crucial for early cancer diagnosis and treatment. Accurate tumor segmentation is essential to aid clinicians in determining drug dosages. Due to the low resolution of PET images, prior information (such as CT, MRI or distance information) are often incorporated to assist PET segmentation. In this paper, we propose an automatic 3D PET tumor segmentation framework assisted by geodesic sequences. Specifically, considering the intrinsic characteristics of PET images, we first construct geodesic prior, which effectively enhances the contrast between the tumor and background while suppressing noise and the influence of other tissues. To address the need for seed points in the geodesic prior, an automatic marking strategy is designed that identifies all suspected lesion regions and uses their central points as a series of seeds to generate the corresponding geodesic sequences. Subsequently, we develop a three-branch network architecture to simultaneously process PET images, geodesic sequences, and background geodesic information. To enhance image features, a distance attention mechanism is introduced at the end of the network encoder to effectively measure the similarity between different geodesic features, refining the image features. Finally, the network incorporates spatial regularization and local PET intensity information into the activation function via the Soft Threshold Dynamics with Local Intensity Fitting (STDLIF) module, further improving segmentation accuracy. Experimental results demonstrate that, compared to existing state-of-the-art algorithms, the proposed method shows better segmentation performance on both clinical and public datasets.

Authors

• Lin Yang
• Dan Shao
• Chuanli Cheng
• Chao Zou
• Zhenxing Huang
• Hairong Zheng
• Dong Liang
• Zhi-Feng Pang
• Xue-Cheng Tai
• Zhanli Hu Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Chinese Academy of Sciences

Keywords

• Image segmentation
• Tumors
• Computed tomography
• Positron emission tomography
• Lesions
• Biomedical imaging
• Attention mechanisms
• Accuracy
• Training
• Deep learning
• Tumor Segmentation
• 3D Positron Emission Tomography
• Activation Function
• Low Resolution
• Image Features
• Spatial Information
• Attention Mechanism
• Positron Emission Tomography Imaging
• Segmentation Accuracy
• Local Intensity
• Intensity Information
• Segmentation Performance
• Spatial Intensity
• Local Fitting
• Dynamic Threshold
• Spatial Regularization
• Local Spatial Information
• Improve Segmentation Accuracy
• Target Region
• Computed Tomography Images
• 3D U-Net
• Lung Cancer Datasets
• Geodesic Distance
• Breast Cancer Dataset
• Tumor Regions
• Cancer Datasets
• Positron Emission Tomography Data
• Standardized Uptake Value
• Segmentation Results
• Tumor Area
• Positron emission tomograph
• 3D tumor segmentation
• geodesic prior
• Humans
• Positron-Emission Tomography
• Imaging, Three-Dimensional
• Algorithms
• Neoplasms
• Image Interpretation, Computer-Assisted