Local Gamma Augmentation for Ischemic Stroke Lesion Segmentation on MRI
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Standard
Local Gamma Augmentation for Ischemic Stroke Lesion Segmentation on MRI. / Middleton, Jon; Bauer, Marko; Johansen, Jacob; Perslev, Mathias; Sheng, Kaining; Ingala, Silvia; Nielsen, Mads; Pai, Akshay.
Proceedings of the 5th Northern Lights Deep Learning Conference ({NLDL}). PMLR, 2024. p. 158-164 (Proceedings of Machine Learning Research, Vol. 233).Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Local Gamma Augmentation for Ischemic Stroke Lesion Segmentation on MRI
AU - Middleton, Jon
AU - Bauer, Marko
AU - Johansen, Jacob
AU - Perslev, Mathias
AU - Sheng, Kaining
AU - Ingala, Silvia
AU - Nielsen, Mads
AU - Pai, Akshay
N1 - Publisher Copyright: © NLDL 2024. All rights reserved.
PY - 2024
Y1 - 2024
N2 - 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.
AB - 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.
M3 - Article in proceedings
AN - SCOPUS:85189352715
T3 - Proceedings of Machine Learning Research
SP - 158
EP - 164
BT - Proceedings of the 5th Northern Lights Deep Learning Conference ({NLDL})
PB - PMLR
T2 - 5th Northern Lights Deep Learning Conference, NLDL 2024
Y2 - 9 January 2024 through 11 January 2024
ER -
ID: 388690477