Medical image segmentation has significantly benefitted thanks to deep learning architectures. Furthermore, semi-supervised learning (SSL) has recently been a growing trend for improving a model's overall performance by leveraging abundant unlabeled data. Moreover, learning multiple tasks within the same model further improves model generalizability. To generate smoother and accurate segmentation masks from 3D cardiac MR images, we present a Multi-task Cross-task learning consistency approach to enforce the correlation between the pixel-level (segmentation) and the geometric-level (distance map) tasks. Our extensive experimentation with varied quantities of labeled data in the training sets justifies the effectiveness of our model for the segmentation of the left atrial cavity from Gadolinium-enhanced magnetic resonance (GE-MR) images. With the incorporation of uncertainty estimates to detect failures in the segmentation masks generated by CNNs, our study further showcases the potential of our model to flag low-quality segmentation from a given model.
翻译:此外,半监督学习(SSL)最近成为通过利用大量未贴标签的数据改进模型总体性能的日益增长的趋势。此外,在同一模型中学习多重任务,进一步提高了模型的通用性。为了从3D心脏MR图像中产生更顺畅和准确的分解面罩,我们提出了一个多任务跨任务学习一致性方法,以强制执行像素级(分解)和几何级(远距图)任务之间的相互关系。我们广泛试验了各组培训中各种有标签的数据,这证明我们从加多林恩强化磁共振图像中分离左侧腔的模型的有效性。我们的研究纳入了不确定性估计数,以检测CNN生成的分解面面罩的故障,从而进一步展示了我们模型在标出某一模型的低质量分解方面的潜力。