-
Semi-Supervised Multi-Task Learning With Chest X-Ray Images
Especially in the medical imaging domain when large labeled datasets are...
read it
-
MultiMix: Sparingly Supervised, Extreme Multitask Learning From Medical Images
Semi-supervised learning via learning from limited quantities of labeled...
read it
-
Integrating Reinforcement Learning to Self Training for Pulmonary Nodule Segmentation in Chest X-rays
Machine learning applications in medical imaging are frequently limited ...
read it
-
Multitask Hopfield Networks
Multitask algorithms typically use task similarity information as a bias...
read it
-
Semi-supervised Pathology Segmentation with Disentangled Representations
Automated pathology segmentation remains a valuable diagnostic tool in c...
read it
-
False Positive Reduction by Actively Mining Negative Samples for Pulmonary Nodule Detection in Chest Radiographs
Generating large quantities of quality labeled data in medical imaging i...
read it
-
Semi-Supervised Learning for Bone Mineral Density Estimation in Hip X-ray Images
Bone mineral density (BMD) is a clinically critical indicator of osteopo...
read it
Partly Supervised Multitask Learning
Semi-supervised learning has recently been attracting attention as an alternative to fully supervised models that require large pools of labeled data. Moreover, optimizing a model for multiple tasks can provide better generalizability than single-task learning. Leveraging self-supervision and adversarial training, we propose a novel general purpose semi-supervised, multiple-task model—namely, self-supervised, semi-supervised, multitask learning (S^4MTL)—for accomplishing two important tasks in medical imaging, segmentation and diagnostic classification. Experimental results on chest and spine X-ray datasets suggest that our S^4MTL model significantly outperforms semi-supervised single task, semi/fully-supervised multitask, and fully-supervised single task models, even with a 50% reduction of class and segmentation labels. We hypothesize that our proposed model can be effective in tackling limited annotation problems for joint training, not only in medical imaging domains, but also for general-purpose vision tasks.
READ FULL TEXT
Comments
There are no comments yet.