Efficient Active Learning for Image Classification and Segmentation Using a Sample Selection and Conditional Generative Adversarial Network

Mahapatra, Dwarikanath; Bozorgtabar, Behzad; Thiran, Jean-Philippe; Reyes, Mauricio (2018). Efficient Active Learning for Image Classification and Segmentation Using a Sample Selection and Conditional Generative Adversarial Network. In: Frangi, Alejandro F.; Schnabel, Julia A.; Davatzikos, Christos; Alberola-López, Carlos; Fichtinger, Gabor (eds.) Medical Image Computing and Computer Assisted Interventions. Lecture Notes in Computer Science: Vol. 11071 (pp. 580-588). Cham: Springer International Publishing 10.1007/978-3-030-00934-2_65

[img] Text
MahapatraMiccai2018.pdf - Accepted Version
Restricted to registered users only
Available under License Publisher holds Copyright.

Download (1MB)

Training robust deep learning (DL) systems for medical image classification or segmentation is challenging due to limited images covering different disease types and severity. We propose an active learning (AL) framework to select most informative samples and add to the training data. We use conditional generative adversarial networks (cGANs) to generate realistic chest xray images with different disease characteristics by conditioning its generation on a real image sample. Informative samples to add to the training set are identified using a Bayesian neural network. Experiments show our proposed AL framework is able to achieve state of the art performance by using about $$35\backslash%$$of the full dataset, thus saving significant time and effort over conventional methods.

Item Type:

Conference or Workshop Item (Paper)

Division/Institute:

04 Faculty of Medicine > Pre-clinic Human Medicine > Institute for Surgical Technology & Biomechanics ISTB [discontinued]

UniBE Contributor:

Reyes, Mauricio

Subjects:

500 Science > 570 Life sciences; biology
600 Technology > 610 Medicine & health

ISBN:

978-3-030-00934-2

Series:

Lecture Notes in Computer Science

Publisher:

Springer International Publishing

Language:

English

Submitter:

Mauricio Antonio Reyes Aguirre

Date Deposited:

02 Oct 2019 17:23

Last Modified:

02 Mar 2023 23:32

Publisher DOI:

10.1007/978-3-030-00934-2_65

BORIS DOI:

10.7892/boris.132344

URI:

https://boris.unibe.ch/id/eprint/132344

Actions (login required)

Edit item Edit item
Provide Feedback