Muhammad Febrian Rachmadi

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

In the wake of the use of deep learning algorithms in medical image analysis, we compared performance of deep learning algorithms, namely the deep Boltzmann machine (DBM), convolutional encoder network (CEN) and patch-wise convolutional neural network (patch-CNN), with two conventional machine learning schemes: Support vector machine (SVM) and random forest (RF), for white matter hyperintensities (WMH) segmentation on brain MRI with mild or no vascular pathology. We also compared all these approaches with a method in the Lesion Segmentation Tool public toolbox named lesion growth algorithm (LGA). We used a dataset comprised of 60 MRI data from 20 subjects in the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database, each scanned once every year during three consecutive years. Spatial agreement score, receiver operating characteristic and precision-recall performance curves, volume disagreement score, agreement with intra-/inter-observer reliability measurements and visual evaluation were used to find the best configuration of each learning algorithm for WMH segmentation. By using optimum threshold values for the probabilistic output from each algorithm to produce binary masks of WMH, we found that SVM and RF produced good results for medium to very large WMH burden but deep learning algorithms performed generally better than conventional ones in most evaluations.

Segmentation of White Matter Hyperintensities using Convolutional Neural Networks with Global Spatial Information in Routine Clinical Brain MRI with None or Mild Vascular Pathology

We propose an adaptation of a convolutional neural network (CNN) scheme proposed for segmenting brain lesions with considerable mass-effect, to segment white matter hyperintensities (WMH) characteristic of brains with none or mild vascular pathology in routine clinical brain magnetic resonance images (MRI). This is a rather difficult segmentation problem because of the small area (i.e., volume) of the WMH and their similarity to non-pathological brain tissue. We investigate the effectiveness of the 2D CNN scheme by comparing its performance against those obtained from another deep learning approach: Deep Boltzmann Machine (DBM), two conventional machine learning approaches: Support Vector Machine (SVM) and Random Forest (RF), and a public toolbox: Lesion Segmentation Tool (LST), all reported to be useful for segmenting WMH in MRI. We also introduce a way to incorporate spatial information in convolution level of CNN for WMH segmentation named global spatial information (GSI). Analysis of covariance corroborated known associations between WMH progression, as assessed by all methods evaluated, and demographic and clinical data. Deep learning algorithms outperform conventional machine learning algorithms by excluding MRI artefacts and pathologies that appear similar to WMH. Our proposed approach of incorporating GSI also successfully helped CNN to achieve better automatic WMH segmentation regardless of networks settings tested. The mean Dice Similarity Coefficient (DSC) values for LST-LGA, SVM, RF, DBM, CNN and CNN-GSI were 0.2963, 0.1194, 0.1633, 0.3264, 0.5359 and 5389 respectively.

Evaluation of Four Supervised Learning Schemes in White Matter Hyperintensities Segmentation in Absence or Mild Presence of Vascular Pathology

We investigated the performance of four popular supervised learning algorithms in medical image analysis for white matter hyperintensities segmentation in brain MRI with mild or no vascular pathology. The algorithms evaluated in this study are support vector machine (SVM), random forest (RF), deep Boltzmann machine (DBM) and convolution encoder network (CEN). We compared these algorithms with two methods in the Lesion Segmentation Tool (LST) public toolbox which are lesion growth algorithm (LGA) and lesion prediction algorithm (LPA). We used a dataset comprised of 60 MRI data from 20 subjects from the ADNI database, each scanned once in three consecutive years. In this study, CEN produced the best Dice similarity coefficient (DSC): mean value 0.44. All algorithms struggled to produce good DSC due to the very small WMH burden (i.e., smaller than 1,500 \(\text {mm}^3\)). LST-LGA, LST-LPA, SVM, RF and DBM produced mean DSC scores ranging from 0.17 to 0.34.

Automatic Irregular Texture Detection in Brain MRI Without Human Supervision.

We propose a novel approach named one-time sampling irregularity age map (OTS-IAM) to detect any irregular texture in FLAIR brain MRI without any human supervision or interaction. In this study, we show that OTS-IAM is able to detect FLAIR’s brain tissue irregularities (i.e. hyperintensities) without any manual labelling. One-time sampling (OTS) scheme is proposed in this study to speed up the computation. The proposed OTS-IAM implementation on GPU successfully speeds up IAM’s computation by more than 17 times. We compared the performance of OTS-IAM with two unsupervised methods for hyperintensities’ detection; the original IAM and the Lesion Growth Algorithm from public toolbox Lesion Segmentation Toolbox (LST-LGA), and two conventional supervised machine learning algorithms; support vector machine (SVM) and random forest (RF). Furthermore, we also compared OTS-IAM’s performance with three supervised deep neural networks algorithms; Deep Boltzmann machine (DBM), convolutional encoder network (CEN) and 2D convolutional neural network (2D Patch-CNN). Based on our experiments, OTS-IAM outperformed LST-LGA, SVM, RF and DBM while it was on par with CEN.

Limited One-time Sampling Irregularity Age Map (LOTS-IAM): Automatic Unsupervised Detection of Brain White Matter Abnormalities in Structural Magnetic Resonance Images

We propose a novel unsupervised approach of detecting and segmenting white matter abnormalities, using limited one-time sampling irregularity age map (LOTS-IAM). LOTS-IAM is a fully automatic unsupervised approach to extract brain tissue irregularities in magnetic resonance images (MRI) (e.g. T2-FLAIR white matter hyperintensities (WMH)). In this study, the limited one-time sampling scheme is proposed and implemented on GPU. We compared the performance of LOTS-IAM in detecting and segmenting WMH, with three unsupervised methods; the original IAM, one-time sampling IAM (OTS-IAM) and Lesion Growth Algorithm from public toolbox Lesion Segmentation Toolbox (LST-LGA), and two conventional supervised machine learning algorithms; support vector machine (SVM) and random forest (RF). Furthermore, we also compared LOTS-IAM’s performance with five supervised deep neural networks algorithms; deep Boltzmann machine (DBM), convolutional encoder network (CEN), and three convolutional neural network (CNN) schemes: the 2D implementation of DeepMedic with the addition of global spatial information (2D-CNNGSI), patch-uResNet and patch-uNet. Based on our experiments, LOTS-IAM outperformed LST-LGA, the state-of-the-art of unsupervised WMH segmentation method, both in performance and processing speed. Our method also outperformed supervised conventional machine learning algorithms SVM and RF, and supervised deep neural networks algorithms DBM and CEN.Abstract 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 state-of-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.

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

The Irregularity Age Map (IAM) for the unsupervised assessment of brain white matter hyperintensities (WMH) opens several opportunities in machine learning-based MRI analysis, including transfer task adaptation learning in the segmentation and prediction of brain lesion progression and regression. The lack of need for manual labels is useful for transfer learning. Whereas the nature of IAM itself can be exploited for predicting lesion progression/regression. In this study, we propose the use of task adaptation transfer learning for WMH segmentation using CNN through weakly-training UNet and UResNet using the output from IAM and the use of IAM for predicting patterns of WMH progression and regression.