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

  title={Multimix: Sparingly-Supervised, Extreme Multitask Learning from Medical Images},
  author={Ayaan Haque and Abdullah-Al-Zubaer Imran and Adam S. Wang and Demetri Terzopoulos},
  journal={2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI)},
Semi-supervised learning from limited quantities of labeled data, an alternative to fully-supervised schemes, benefits by maximizing knowledge gains from copious unlabeled data. Furthermore, learning multiple tasks within the same model improves model generalizability. We propose 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… 

Figures and Tables from this paper

Noise2Quality: non-reference, pixel-wise assessment of low dose CT image quality

Noise2Quality (N2Q)—a novel self-supervised, non-reference, pixel-wise image quality assessment model to predict IQA maps from LDCTs is proposed and demonstrates the effectiveness of the model in accurately predictingIQA maps over various baselines.

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

The proposed MultiMix is a new multi-task learning model that jointly learns disease classification and anatomical segmentation in a semi-supervised manner, while preserving explainability through a novel saliency bridge between the two tasks.

3N-GAN: Semi-Supervised Classification of X-Ray Images with a 3-Player Adversarial Framework

This work proposes 3N-GAN, or 3 Network Generative Adversarial Networks, to perform semi-supervised classification of medical images in fully-super supervised settings, which incorporates a classifier into the adversarial relationship such that the generator trains adversarially against both the classifier and discriminator.

Federated Semi-Supervised Multi-Task Learning to Detect COVID-19 and Lungs Segmentation Marking Using Chest Radiography Images and Raspberry Pi Devices: An Internet of Medical Things Application

This study explores two such medical decision-making tasks, namely COVID-19 detection and lung area segmentation detection, using chest radiography images, and investigates the applicability of computationally less capable edge devices in the IoMT system.

EC-GAN: Low-Sample Classification using Semi-Supervised Algorithms and GANs

This work proposes a novel GAN model namely External Classifier GAN (EC-GAN), that utilizes GANs and semi-supervised algorithms to improve classification in fully-super supervised regimes, and leverages a GAN to generate artificial data used to supplement supervised classification.



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.

Semisupervised Multitask Learning

This paper integrates MTL and semi-supervised learning into a single framework, thereby exploiting two forms of contextual information.

Identifying Medical Diagnoses and Treatable Diseases by Image-Based Deep Learning

FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence

This paper demonstrates the power of a simple combination of two common SSL methods: consistency regularization and pseudo-labeling, and shows that FixMatch achieves state-of-the-art performance across a variety of standard semi-supervised learning benchmarks.

Semi-Supervised Learning (Chapelle, O. et al., Eds.; 2006) [Book reviews]

This book addresses some theoretical aspects of semisupervised learning (SSL) and classify these methods into four classes that correspond to the first four main parts of the book (this would include generative models; low-density separation methods; graph-based methods; and algorithms).

U-Net: Convolutional Networks for Biomedical Image Segmentation

It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.

Y-Net: Joint Segmentation and Classification for Diagnosis of Breast Biopsy Images

Y-Net extends and generalizes U-Net by adding a parallel branch for discriminative map generation and by supporting convolutional block modularity, which allows the user to adjust network efficiency without altering the network topology.

An Overview of Multi-Task Learning in Deep Neural Networks

This article seeks to help ML practitioners apply MTL by shedding light on how MTL works and providing guidelines for choosing appropriate auxiliary tasks, particularly in deep neural networks.

ChestX-Ray8: Hospital-Scale Chest X-Ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases

A new chest X-rays database, namely ChestX-ray8, is presented, which comprises 108,948 frontal-view X-ray images of 32,717 unique patients with the text-mined eight disease image labels from the associated radiological reports using natural language processing, which is validated using the proposed dataset.

Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps

This paper addresses the visualisation of image classification models, learnt using deep Convolutional Networks (ConvNets), and establishes the connection between the gradient-based ConvNet visualisation methods and deconvolutional networks.