Transfer Learning for Task Adaptation of Brain Lesion Assessment and Prediction of Brain Abnormalities Progression/Regression Using Irregularity Age Map in Brain MRI

Rachmadi, Muhammad Febrian; Valdés-Hernández, Maria del C.; Komura, Taku

doi:10.1007/978-3-030-00320-3_11

Cited by 5 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…the task domain changes), 3) when performing tasks that are related to but not the same as that on which they were trained (e.g. lesion segmentation vs. lesion assessment) ( Rachmadi et al, 2018 ). To overcome these limitations, there are several ways to enhance the performance of CNN architectures without modifying the architecture itself.…”

Section: Introductionmentioning

confidence: 99%

Identification of the presence of ischaemic stroke lesions by means of texture analysis on brain magnetic resonance images

Ortiz-Ramón

Valdés-Hernández

González-Castro

et al. 2019

Computerized Medical Imaging and Graphics

Self Cite

View full text Add to dashboard Cite

Highlights Radiomics in conventionally segmented tissues can identify MRI scans that had a stroke. Patient’s advanced age can negatively influence classification results. Feature selection and stroke subtype influence but do not determine accuracy. Stroke subtype cannot be ascertained from texture analysis in brain tissues.

show abstract

Section: Introductionmentioning

confidence: 99%

Identification of the presence of ischaemic stroke lesions by means of texture analysis on brain magnetic resonance images

Ortiz-Ramón

Valdés-Hernández

González-Castro

et al. 2019

Computerized Medical Imaging and Graphics

Self Cite

View full text Add to dashboard Cite

show abstract

“…Another study pre-trained CNN using natural images for segmentation of neonatal to adult brain images (Xu et al, 2017), and other study pre-trained a CNN for brain lesion segmentation using MRI data acquired with other protocols (Ghafoorian et al, 2017). Task adaptation transfer learning has been applied to WMH segmentation, by teaching a CNN to “learn" to detect texture irregularities instead of binary expert-delineated WMH segmentations (Rachmadi et al, 2018a).…”

Section: Introductionmentioning

confidence: 99%

Evaluation of Enhanced Learning Techniques for Segmenting Ischaemic Stroke Lesions in Brain Magnetic Resonance Perfusion Images Using a Convolutional Neural Network Scheme

Malla

Hernández

Rachmadi

et al. 2019

Front. Neuroinform.

Self Cite

View full text Add to dashboard Cite

Magnetic resonance (MR) perfusion imaging non-invasively measures cerebral perfusion, which describes the blood's passage through the brain's vascular network. Therefore, it is widely used to assess cerebral ischaemia. Convolutional Neural Networks (CNN) constitute the state-of-the-art method in automatic pattern recognition and hence, in segmentation tasks. But none of the CNN architectures developed to date have achieved high accuracy when segmenting ischaemic stroke lesions, being the main reasons their heterogeneity in location, shape, size, image intensity and texture, especially in this imaging modality. We use a freely available CNN framework, developed for MR imaging lesion segmentation, as core algorithm to evaluate the impact of enhanced machine learning techniques, namely data augmentation, transfer learning and post-processing, in the segmentation of stroke lesions using the ISLES 2017 dataset, which contains expert annotated diffusion-weighted perfusion and diffusion brain MRI of 43 stroke patients. Of all the techniques evaluated, data augmentation with binary closing achieved the best results, improving the mean Dice score in 17% over the baseline model. Consistent with previous works, better performance was obtained in the presence of large lesions.

show abstract

“…In this paper, we propose to use IAM as an additional input data to train a U-Net neural network architecture for WMH segmentation, owed to the fact that LOTS-IM can easily produce IAM without the need for training using manually marked WMH ground-truth data. U-Net architecture is selected as a base model for our experiments as it has shown the best learning performance using IAM (Rachmadi et al, 2018a). To address the incorporation of IAM to U-Net for WMH segmentation, we propose feed-forwarding IAM as regional map to a Saliency U-Net architecture.…”

Section: Introductionmentioning

confidence: 99%

Dilated Saliency U-Net for White Matter Hyperintensities Segmentation Using Irregularity Age Map

Jeong

Rachmadi

Valdés-Hernández

et al. 2019

Front. Aging Neurosci.

Self Cite

View full text Add to dashboard Cite

White matter hyperintensities (WMH) appear as regions of abnormally high signal intensity on T2-weighted magnetic resonance image (MRI) sequences. In particular, WMH have been noteworthy in age-related neuroscience for being a crucial biomarker for all types of dementia and brain aging processes. The automatic WMH segmentation is challenging because of their variable intensity range, size and shape. U-Net tackles this problem through the dense prediction and has shown competitive performances not only on WMH segmentation/detection but also on varied image segmentation tasks. However, its network architecture is high complex. In this study, we propose the use of Saliency U-Net and Irregularity map (IAM) to decrease the U-Net architectural complexity without performance loss. We trained Saliency U-Net using both: a T2-FLAIR MRI sequence and its correspondent IAM. Since IAM guides locating image intensity irregularities, in which WMH are possibly included, in the MRI slice, Saliency U-Net performs better than the original U-Net trained only using T2-FLAIR. The best performance was achieved with fewer parameters and shorter training time. Moreover, the application of dilated convolution enhanced Saliency U-Net by recognizing the shape of large WMH more accurately through multi-context learning. This network named Dilated Saliency U-Net improved Dice coefficient score to 0.5588 which was the best score among our experimental models, and recorded a relatively good sensitivity of 0.4747 with the shortest training time and the least number of parameters. In conclusion, based on our experimental results, incorporating IAM through Dilated Saliency U-Net resulted an appropriate approach for WMH segmentation.

show abstract

Transfer Learning for Task Adaptation of Brain Lesion Assessment and Prediction of Brain Abnormalities Progression/Regression Using Irregularity Age Map in Brain MRI

Cited by 5 publications

References 10 publications

Identification of the presence of ischaemic stroke lesions by means of texture analysis on brain magnetic resonance images

Identification of the presence of ischaemic stroke lesions by means of texture analysis on brain magnetic resonance images

Evaluation of Enhanced Learning Techniques for Segmenting Ischaemic Stroke Lesions in Brain Magnetic Resonance Perfusion Images Using a Convolutional Neural Network Scheme

Dilated Saliency U-Net for White Matter Hyperintensities Segmentation Using Irregularity Age Map

Contact Info

Product

Resources

About