Combined morphologic and metabolic pipeline for Positron emission tomography/computed tomography based radiotherapy response evaluation in locally advanced pancreatic adenocarcinoma

Abstract

Background and purpose: Adaptive radiation planning for pancreatic adenocarcinoma (PA) relies on accurate treatment response assessment, while traditional response evaluation criteria inefficiently characterize tumors with complex morphological features or intrinsically low metabolism. To better assess treatment response of PA, we quantify and compare regional morphological and metabolic features of the 3D pre-and post-radiation therapy (RT) tumor models. Materials and methods: Thirty-one PA patients with pre and post-RT Positron emission tomography/computed tomography (PET/CT) scans were evaluated. 3D meshes of pre-and post-RT tumors were generated and registered to establish vertex-wise correspondence. To assess tumor response, Mahalanobis distances (M dist | Fusion) between pre-and post-RT tumor surfaces with anatomic and metabolic fused vectors were calculated for each patient. M dist | Fusion was evaluated by overall survival (OS) prediction and survival risk classification. As a comparison, the same analyses were conducted on traditional imaging/physiological predictors, and distances measurements based on metabolic and morphological features only. Results: Among all the imaging/physiological parameters, M dist | Fusion was shown to be the best predictor of OS (HR = 0.52, p = 0.008), while other parameters failed to reach significance. Moreover, M dist | Fusion outperformed traditional morphologic and metabolic measurements in patient risk stratification, either alone (HR = 11.51, p < 0.001) or combined with age (HR = 9.04, p < 0.001). Conclusions: We introduced a PET/CT-based novel morphologic and metabolic pipeline for response evaluation in locally advanced PA. The fused M dist | Fusion outperformed traditional morphologic, metabolic, and physiological measurements in OS prediction and risk stratification. The novel fusion model may serve as a new imagingmarker to more accurately characterize the heterogeneous tumor RT response.

Imaging science and development in modern high-precision radiotherapy

“…Recent studies have investigated the potential of radiomics for precision RT [19] , [83] , [84] , [85] . Of note, for high quality usage of functional and anatomic imaging data, dedicated robust strategies for image registration [86] , [87] , [88] , [89] and data analysis [90] are needed. Only then, reliable new segmentation algorithms [91] , [92] and prediction models can be trained [16] , [93] .…”