Local Gamma Augmentation for Ischemic Stroke Lesion Segmentation on MRI
This work addresses data scarcity in medical imaging for deep learning practitioners, though it appears incremental as it builds on existing augmentation methods.
The paper tackled the problem of ischemic stroke lesion segmentation on MRI by introducing local gamma augmentation to compensate for intensity bias in pathological tissues, resulting in improved image-level sensitivity on three datasets.
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 lesion segmentation on magnetic resonance images.