Deep Learning vs. Conventional Machine Learning: Pilot Study of WMH Segmentation in Brain MRI with Absence or Mild Vascular Pathology

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

doi:10.3390/jimaging3040066

Cited by 22 publications

(24 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More details about these two methods will be given in the next section. These methods are compared against deep Boltzmann machine (DBM), convolutional encoder network (CEN), patch-wise convolutional neural network (CNN) in [6] for white matter hyperintensities (WMH) segmentation on brain MRI with mild or no vascular pathology. Principal component analysis (PCA) is used along with SVM to reduce the number of features.…”

Section: Segmentation Methodsmentioning

confidence: 99%

“…Dice similarity coefficient (DSC) is another statistic often used for validating medical volume (3D) segmentations [6,16,52]:…”

Section: Metrics Used To Assess the Efficiency Of Disease Diagnosis Mmentioning

confidence: 99%

“…Brain magnetic resonance imaging (MRI) [5][6][7][8][9][10][11] can be used for the diagnosis of glioma, AIDS dementia, Alzheimer's, cancer metastasis, etc. The image processing is applied to T1-weighted (T1-w) and T2-w MRI scans.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Review of Image Processing Techniques Common in Human and Plant Disease Diagnosis

Petrellis

2018

Symmetry

View full text Add to dashboard Cite

Image processing has been extensively used in various (human, animal, plant) disease diagnosis approaches, assisting experts to select the right treatment. It has been applied to both images captured from cameras of visible light and from equipment that captures information in invisible wavelengths (magnetic/ultrasonic sensors, microscopes, etc.). In most of the referenced diagnosis applications, the image is enhanced by various filtering methods and segmentation follows isolating the regions of interest. Classification of the input image is performed at the final stage. The disease diagnosis approaches based on these steps and the common methods are described. The features extracted from a plant/skin disease diagnosis framework developed by the author are used here to demonstrate various techniques adopted in the literature. The various metrics along with the available experimental conditions and results presented in the referenced approaches are also discussed. The accuracy achieved in the diagnosis methods that are based on image processing is often higher than 90%. The motivation for this review is to highlight the most common and efficient methods that have been employed in various disease diagnosis approaches and suggest how they can be used in similar or different applications.

show abstract

Section: Segmentation Methodsmentioning

confidence: 99%

“…Dice similarity coefficient (DSC) is another statistic often used for validating medical volume (3D) segmentations [6,16,52]:…”

Section: Metrics Used To Assess the Efficiency Of Disease Diagnosis Mmentioning

confidence: 99%

See 1 more Smart Citation

A Review of Image Processing Techniques Common in Human and Plant Disease Diagnosis

Petrellis

2018

Symmetry

View full text Add to dashboard Cite

show abstract

“…Correlation between visual ratings and volume of WMH is known to be high . In this study, Fazekas's (Fazekas et al, 1987) and Longstreth's visual rating scales (Longstreth et al, 1996) are used for evaluation of each automatic method, as per (Rachmadi et al, 2017a).…”

Section: Evaluation Metricsmentioning

confidence: 99%

Limited One-time Sampling Irregularity Map (LOTS-IM): Automatic Unsupervised Quantitative Assessment of White Matter Hyperintensities in Structural Brain Magnetic Resonance Images

Rachmadi

Valdés-Hernández

et al. 2018

Preprint

Self Cite

View full text Add to dashboard Cite

We present the application of limited one-time sampling irregularity map (LOTS-IM): a fully automatic unsupervised approach to extract brain tissue irregularities in magnetic resonance images (MRI), for quantitatively assessing white matter hyperintensities (WMH) of presumed vascular origin, and multiple sclerosis (MS) lesions and their progression. LOTS-IM generates an irregularity map (IM) that represents all voxels as irregularity values with respect to the ones considered "normal". Unlike probability values, IM represents both regular and irregular regions in the brain based on the original MRI's texture information. We evaluated and compared the use of IM for WMH and MS lesions segmentation on T2-FLAIR MRI with the stateof-the-art unsupervised lesions' segmentation method, Lesion Growth Algorithm from the public toolbox Lesion Segmentation Toolbox (LST-LGA), with several well established conventional supervised machine learning schemes and with state-of-the-art supervised deep learning methods for WMH segmentation. In our experiments, LOTS-IM outperformed unsupervised method LST-LGA on WMH segmentation, both in performance and processing speed, thanks to the limited one-time sampling scheme and its implementation on GPU. Our method also outperformed supervised conventional machine learning algorithms (i.e., support vector machine (SVM) and random forest (RF)) and deep learning algorithms (i.e., deep Boltzmann machine (DBM) and convolutional encoder network (CEN)), while yielding comparable results to the convolutional neural network schemes that rank top of the algorithms developed up to date for this purpose (i.e., UResNet and UNet). LOTS-IM also performed well on MS lesions segmentation, performing similar to LST-LGA. On the other hand, the high sensitivity of IM on depicting signal change deems suitable for assessing MS progression, although care must be taken with signal changes not reflective of a true pathology.Keywords: white matter hyperintensities (WMH), multiple sclerosis (MS) lesion, unsupervised lesion segmentation, irregularity map, penumbra of brain's lesion, characterisation of WMH and MS lesions.

show abstract

“…The DEP model produces a map named "Disease Evolution Map" (DEM) which characterises each voxel of WMH or brain tissues as progressing, regressing, or stable WMH (discussed in Section 2.1). For this study we have chosen deep neural networks due to their exceptional performance on WMH segmentation (Rachmadi et al, 2017;Li et al, 2018;Kuijf et al, 2019). We use a Generative Adversarial Network (GAN) (Goodfellow et al, 2014) and the U-Residual Network (UResNet) (Guerrero et al, 2018) as base architectures for the DEP model.…”

Section: Introductionmentioning

confidence: 99%

Automatic Spatial Estimation of White Matter Hyperintensities Evolution in Brain MRI using Disease Evolution Predictor Deep Neural Networks

Rachmadi

Valdés-Hernández²,

Makin³

et al. 2019

Preprint

Self Cite

View full text Add to dashboard Cite

AbstractPrevious studies have indicated that white matter hyperintensities (WMH), the main radiological feature of small vessel disease, may evolve (i.e., shrink, grow) or stay stable over a period of time. Predicting these changes are challenging because it involves some unknown clinical risk factors that leads to a non-deterministic prediction task. In this study, we propose a deep learning model to predict the evolution of WMH from baseline to follow-up (i.e., 1-year later), namely “Disease Evolution Predictor” (DEP) model, which can be adjusted to become a non-deterministic model. The DEP model receives a baseline image as input and produces a map called “Disease Evolution Map” (DEM), which represents the evolution of WMH from baseline to follow-up. Two DEP models are proposed, namely DEP-UResNet and DEP-GAN, which are representatives of the supervised (i.e., need expert-generated manual labels to generate the output) and unsupervised (i.e., do not require manual labels produced by experts) deep learning algorithms respectively. To simulate the non-deterministic and unknown parameters involved in WMH evolution, we modulate a Gaussian noise array to the DEP model as auxiliary input. This forces the DEP model to imitate a wider spectrum of alternatives in the prediction results. The alternatives of using other types of auxiliary input instead, such as baseline WMH and stroke lesion loads are also proposed and tested. Based on our experiments, the fully supervised machine learning scheme DEP-UResNet regularly performed better than the DEP-GAN which works in principle without using any expert-generated label (i.e., unsupervised). However, a semi-supervised DEP-GAN model, which uses probability maps produced by a supervised segmentation method in the learning process, yielded similar performances to the DEP-UResNet and performed best in the clinical evaluation. Furthermore, an ablation study showed that an auxiliary input, especially the Gaussian noise, improved the performance of DEP models compared to DEP models that lacked the auxiliary input regardless of the model’s architecture. To the best of our knowledge, this is the first extensive study on modelling WMH evolution using deep learning algorithms, which deals with the non-deterministic nature of WMH evolution.

show abstract

Deep Learning vs. Conventional Machine Learning: Pilot Study of WMH Segmentation in Brain MRI with Absence or Mild Vascular Pathology

Cited by 22 publications

References 33 publications

A Review of Image Processing Techniques Common in Human and Plant Disease Diagnosis

A Review of Image Processing Techniques Common in Human and Plant Disease Diagnosis

Limited One-time Sampling Irregularity Map (LOTS-IM): Automatic Unsupervised Quantitative Assessment of White Matter Hyperintensities in Structural Brain Magnetic Resonance Images

Automatic Spatial Estimation of White Matter Hyperintensities Evolution in Brain MRI using Disease Evolution Predictor Deep Neural Networks

Contact Info

Product

Resources

About