论文标题
学习通过在双参数MRI中的涂鸦侵略性来分割前列腺癌
Learning to segment prostate cancer by aggressiveness from scribbles in bi-parametric MRI
论文作者
论文摘要
在这项工作中，我们提出了一个基于U-NET的深层模型，以根据较弱的涂鸦注释在MRI中的侵略性来应对前列腺癌分割的具有挑战性的任务。该模型扩展了Kervadec等人提出的大小约束损失。 1在多类检测和分割任务的背景下。该模型具有很高的临床兴趣，因为它允许对前列腺活检样品进行培训，并避免耗时的完整注释过程。在一个私人数据集（219名患者）上评估了性能，在该数据集（219名患者）中以及Prostatex-2挑战数据库中都有可用的地面真相，在不同的地方，只有活检作为参考。我们表明，只有6.35％的体素进行训练，我们可以在对病变进行分级时接近完全监督的基线。我们报告了病变的Cohen的Kappa评分为0.29 $ \ pm $ 0.07 $ 0.07，而基线为0.32 $ \ pm $ 0.05。我们还报告了Prostatex-2挑战数据集上的Kappa分数（0.276 $ \ pm $ 0.037），我们的弱U-NET培训了Prostatex-2和我们的数据集的组合，这是该挑战数据集的最高报告价值，对于我们所知，该挑战数据集的价值最高。
In this work, we propose a deep U-Net based model to tackle the challenging task of prostate cancer segmentation by aggressiveness in MRI based on weak scribble annotations. This model extends the size constraint loss proposed by Kervadec et al. 1 in the context of multiclass detection and segmentation task. This model is of high clinical interest as it allows training on prostate biopsy samples and avoids time-consuming full annotation process. Performance is assessed on a private dataset (219 patients) where the full ground truth is available as well as on the ProstateX-2 challenge database, where only biopsy results at different localisations serve as reference. We show that we can approach the fully-supervised baseline in grading the lesions by using only 6.35% of voxels for training. We report a lesion-wise Cohen's kappa score of 0.29 $\pm$ 0.07 for the weak model versus 0.32 $\pm$ 0.05 for the baseline. We also report a kappa score (0.276 $\pm$ 0.037) on the ProstateX-2 challenge dataset with our weak U-Net trained on a combination of ProstateX-2 and our dataset, which is the highest reported value on this challenge dataset for a segmentation task to our knowledge.
