• Corpus ID: 239885894

Generalized Multi-Task Learning from Substantially Unlabeled Multi-Source Medical Image Data

  title={Generalized Multi-Task Learning from Substantially Unlabeled Multi-Source Medical Image Data},
  author={Ayaan Haque and Abdullah-Al-Zubaer Imran and Adam Wang and Demetri Terzopoulos},
Deep learning-based models, when trained in a fully-supervised manner, can be effective in performing complex image analysis tasks, although contingent upon the availability of large labeled datasets. Especially in the medical imaging domain, however, expert image annotation is expensive, time-consuming, and prone to variability. Semi-supervised learning from limited quantities of labeled data has shown promise as an alternative. Maximizing knowledge gains from copious unlabeled data benefits… 

Explainable COVID-19 Infections Identification and Delineation Using Calibrated Pseudo Labels

This work proposes a model-agnostic calibrated pseudo-labelling strategy and applies it under a consistency regularization framework to generate explainable identification and delineation results and demonstrates the effectiveness of the model with the combination of limited labelled data and sufficient unlabelled data or weakly-labelled data.

Lightseg: Efficient Yet Effective Medical Image Segmentation

This work proposes a lightweight and faster yet effective medical image segmentation approach namely LightSeg that leverages separable convolutional layers to decrease the model parameters and an attention mechanism to maintain segmentation quality.



Semi-Supervised Multi-Task Learning With Chest X-Ray Images

This work proposes a novel multi-task learning model for jointly learning a classifier and a segmentor, from chest X-ray images, through semi-supervised learning, and hypothesizes that KLTV can be more effective for generalizing multi-tasking models while being competitive in segmentation-only tasks.

Multimix: Sparingly-Supervised, Extreme Multitask Learning from Medical Images

This work proposes MultiMix, a novel multitask learning model that jointly learns disease classification and anatomical segmentation in a sparingly supervised manner, while preserving explainability through bridge saliency between the two tasks.

From Fully-Supervised, Single-Task to Scarcely-Supervised, Multi-Task Deep Learning for Medical Image Analysis

This thesis devises for use in a variety of medical image analysis applications a series of novel deep learning methods, ranging from fully-supervised, single- task learning to scarcely-super supervised, multi-task learning that makes efficient use of annotated training data.

Partly Supervised Multi-Task Learning

This work proposes a novel, general purpose semi-supervised, multiple-task model, S4MTL, for accomplishing two important medical image analysis tasks: segmentation and diagnostic classification and results confirm that the model significantly outperforms semi- supervised single-task, semi/fully- Supervised multi- task, and fully-super supervised single- task models, even with a 50% reduction in class and segmentation labels.

A Feature Transfer Enabled Multi-Task Deep Learning Model on Medical Imaging

Progressive Adversarial Semantic Segmentation

This work proposes a novel end - to-end medical image segmentation model, namely Progressive Adversarial Semantic Segmentation (PASS), which can make improved and consistent pixel-wise segmentation predictions without requiring any domain-specific data during training.

Collaborative Learning of Semi-Supervised Segmentation and Classification for Medical Images

  • Yi ZhouXiaodong He L. Shao
  • Computer Science
    2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2019
This paper proposes a collaborative learning method to jointly improve the performance of disease grading and lesion segmentation by semi-supervised learning with an attention mechanism and achieves consistent improvements over state-of-the-art methods on three public datasets.

An Overview of Deep Semi-Supervised Learning

A comprehensive overview of deep semi-supervised learning is provided, starting with an introduction to the field, followed by a summarization of the dominant semi- supervised approaches in deep learning.

Multi-Adversarial Variational Autoencoder Nets for Simultaneous Image Generation and Classification

MultiAdversarial Variational autoEncoder Networks (MAVENs) is introduced, a novel deep generative model that incorporates an ensemble of discriminators in a VAE-GAN network in order to perform simultaneous adversarial learning and variational inference and is applied to the generation of synthetic images.

Semi-Supervised Multitask Learning

Experimental results on real data sets demonstrate that semi-supervised MTL yields significant improvements in generalization performance over either semi- supervised single-task learning (STL) or supervised MTL.