Local Gamma Augmentation for Ischemic Stroke Lesion Segmentation on MRI

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review


  • Fulltext

    Final published version, 429 KB, PDF document

The identification and localisation of pathological tissues in medical images continues to command much attention among deep learning practitioners. When trained on abundant datasets, deep neural networks can match or exceed human performance. However, the scarcity of annotated data complicates the training of these models. Data augmentation techniques can compensate for a lack of training samples. However, many commonly used augmentation methods can fail to provide meaningful samples during model fitting. We present local gamma augmentation, a technique for introducing new instances of intensities in pathological tissues. We leverage local gamma augmentation to compensate for a bias in intensities corresponding to ischemic stroke lesions in human brain MRIs. On three datasets, we show how local gamma augmentation can improve the image-level sensitivity of a deep neural network tasked with ischemic stroke lesion segmentation on magnetic resonance images.

Original languageEnglish
Title of host publicationProceedings of the 5th Northern Lights Deep Learning Conference ({NLDL})
Publication date2024
Publication statusPublished - 2024
Event5th Northern Lights Deep Learning Conference, NLDL 2024 - Tromso, Norway
Duration: 9 Jan 202411 Jan 2024


Conference5th Northern Lights Deep Learning Conference, NLDL 2024
SeriesProceedings of Machine Learning Research

Bibliographical note

Publisher Copyright:
© NLDL 2024. All rights reserved.


ID: 388690477