Département de physique, de génie physique et d'optique, et Centre de recherche sur le cancer, Université Laval, Québec, QC, Canada.
CHU de Québec - Université Laval et CRCHU de Québec, Québec, QC, Canada.
Sci Rep. 2024 Nov 6;14(1):26928. doi: 10.1038/s41598-024-77498-0.
We propose a fully automatic multi-task Bayesian model, named Bayesian Sequential Network (BSN), for predicting high-grade (Gleason 8) prostate cancer (PCa) prognosis using pre-prostatectomy FDG-PET/CT images and clinical data. BSN performs one classification task and five survival tasks: predicting lymph node invasion (LNI), biochemical recurrence-free survival (BCR-FS), metastasis-free survival, definitive androgen deprivation therapy-free survival, castration-resistant PCa-free survival, and PCa-specific survival (PCSS). Experiments are conducted using a dataset of 295 patients. BSN outperforms widely used nomograms on all tasks except PCSS, leveraging multi-task learning and imaging data. BSN also provides automated prostate segmentation, uncertainty quantification, personalized feature-based explanations, and introduces dynamic predictions, a novel approach that relies on short-term outcomes to refine long-term prognosis. Overall, BSN shows great promise in its ability to exploit imaging and clinicopathological data to predict poor outcome patients that need treatment intensification with loco-regional or systemic adjuvant therapy for high-risk PCa.
我们提出了一种全自动多任务贝叶斯模型，命名为贝叶斯序列网络（BSN），用于使用前列腺切除术前行 FDG-PET/CT 图像和临床数据预测高级别（Gleason 8）前列腺癌（PCa）预后。BSN 执行一个分类任务和五个生存任务：预测淋巴结侵犯（LNI）、生化无复发生存（BCR-FS）、无转移生存、确定性雄激素剥夺治疗无复发生存、去势抵抗性 PCa 无复发生存和 PCa 特异性生存（PCSS）。实验使用 295 名患者的数据集进行。BSN 在所有任务上的表现都优于广泛使用的列线图，除了 PCSS，它利用多任务学习和成像数据。BSN 还提供了自动前列腺分割、不确定性量化、基于个性化特征的解释，并引入了动态预测，这是一种依赖短期结果来改进长期预后的新方法。总的来说，BSN 具有利用成像和临床病理数据预测需要局部或全身辅助治疗强化治疗的高危 PCa 预后不良患者的巨大潜力。
