Enhancing Lesion Segmentation in PET/CT Imaging with Deep Learning and Advanced Data Preprocessing Techniques
This work addresses the need for precise diagnostic tools in oncology by enhancing lesion segmentation, though it appears incremental as it focuses on standardizing preprocessing and augmentation strategies.
This research tackled lesion segmentation in PET/CT imaging for cancer diagnosis by applying deep learning with advanced preprocessing and data augmentation, achieving improved model robustness and generalizability on a dataset of 1500 PET/CT studies.
The escalating global cancer burden underscores the critical need for precise diagnostic tools in oncology. This research employs deep learning to enhance lesion segmentation in PET/CT imaging, utilizing a dataset of 900 whole-body FDG-PET/CT and 600 PSMA-PET/CT studies from the AutoPET challenge III. Our methodical approach includes robust preprocessing and data augmentation techniques to ensure model robustness and generalizability. We investigate the influence of non-zero normalization and modifications to the data augmentation pipeline, such as the introduction of RandGaussianSharpen and adjustments to the Gamma transform parameter. This study aims to contribute to the standardization of preprocessing and augmentation strategies in PET/CT imaging, potentially improving the diagnostic accuracy and the personalized management of cancer patients. Our code will be open-sourced and available at https://github.com/jiayiliu-pku/DC2024.