Detection of Peri-Pancreatic Edema using Deep Learning and Radiomics Techniques

Identifying peri-pancreatic edema is a pivotal indicator for identifying disease progression and prognosis, emphasizing the critical need for accurate detection and assessment in pancreatitis diagnosis and management. This study $\mathit{\text{introduces}}\mathit{\text{a}}\mathit{\text{novel}}\mathit{\text{CT}}\mathit{\text{dataset}}\mathit{\text{sourced}}\mathit{\text{from}}\mathit{\text{255}}\mathit{\text{patients}}\mathit{\text{with}}\mathit{\text{pancreatic}}\mathit{\text{diseases,}}\mathit{\text{featuring}}\mathit{\text{annotated}}\mathit{\text{pancreas}}\mathit{\text{segmentation}}\mathit{\text{masks}}\mathit{\text{and}}\mathit{\text{corresponding}}\mathit{\text{diagnostic}}\mathit{\text{labels}}\mathit{\text{for}}\mathit{\text{peri-pancreatic}}\mathit{\text{edema}}\mathit{\text{condition}}$. With the novel dataset, we first evaluate the efficacy of the $\mathit{\text{LinTransUNet}}$ model, a linear Transformer based segmentation algorithm, to segment the pancreas accurately from CT imaging data. Then, we use segmented pancreas regions with two distinctive machine learning classifiers to identify existence of peri-pancreatic edema: deep learning-based models and a radiomics-based eXtreme Gradient Boosting (XGBoost). The LinTransUNet achieved promising results, with a dice coefficient of 80.85%, and mIoU of 68.73%. Among the nine benchmarked classification models for peri-pancreatic edema detection, $\mathit{\text{Swin-Tiny}}$ transformer model demonstrated the highest recall of $98.85\pm 0.42$ and precision of $98.38\pm 0.17$. Comparatively, the radiomics-based XGBoost model achieved an accuracy of $79.61\pm 4.04$ and recall of $91.05\pm 3.28$, showcasing its potential as a supplementary diagnostic tool given its rapid processing speed and reduced training time. Our code is available \url{https://github.com/NUBagciLab/Peri-Pancreatic-Edema-Detection}.