Classification and localization of early-stage Alzheimer's disease in magnetic resonance images using a patch-based classifier ensemble

A review on Alzheimer's disease classification from normal controls and mild cognitive impairment using structural MR images

Alzheimer's disease (AD) is an irreversible neurodegenerative brain disorder that degrades the memory and cognitive ability in elderly people. The main reason for memory loss and reduction in cognitive ability is the structural changes in the brain that occur due to neuronal loss. These structural changes are most conspicuous in the hippocampus, cortex, and grey matter and can be assessed by using neuroimaging techniques viz. Positron Emission Tomography (PET), structural Magnetic Resonance Imaging (MRI) and functional MRI (fMRI), etc. Out of these neuroimaging techniques, structural MRI has evolved as the best technique as it indicates the best soft tissue contrast and high spatial resolution which is important for AD detection. Currently, the focus of researchers is on predicting the conversion of Mild Cognitive Impairment (MCI) into AD. MCI represents the transition state between expected cognitive changes with normal aging and Alzheimer's disease. Not every MCI patient progresses into Alzheimer's disease. MCI can develop into stable MCI (sMCI, patients are called non-converters) or into progressive MCI (pMCI, patients are diagnosed as MCI converters). This paper discusses the prognosis of MCI to AD conversion and presents a review of structural MRI-based studies for AD detection. AD detection framework includes feature extraction, feature selection, and classification process. This paper reviews the studies for AD detection based on different feature extraction methods and machine learning algorithms for classification. The performance of various feature extraction methods has been compared and it has been observed that the wavelet transform-based feature extraction method would give promising results for AD classification. The present study indicates that researchers are successful in classifying AD from Normal Controls (N_rmC) but, it still requires a lot of work to be done for MCI/ N_rmC and MCI/AD, which would help in detecting AD at its early stage.

Probabilistic principal component analysis and long short-term memory classifier for automatic detection of Alzheimer’s disease using MRI brain images

The automatic recognition and classification of Alzheimer disease utilizing magnetic resonance imaging is a hard task, due to the complexity and variability of the size, location, texture and shape of the lesions. The objective of this study is to propose a proper feature dimensional reduction and classification approach to improve the performance of Alzheimer disease recognition and classification. At first, the input brain images were acquired from Open Access Series of Imaging Studies (OASIS) and National Institute of Mental Health and Neuro Sciences (NIMHANS) databases. Then, the image pre-processing and feature extraction were attained by applying Contrast Limited Adaptive Histogram Equalization (CLAHE) and Discrete Wavelet Transform (DWT) approach to denoise and extract the feature vectors from the images. In addition, Probabilistic Principal Component Analysis (PPCA) was used to diminish the extracted features dimension that effectively lessen the “curse of dimensionality” concern. At last, Long Short-Term Memory (LSTM) classifier was employed to classify the brain images as Alzheimer disease, normal, and Mild Cognitive Impairment (MCI). From the simulation outcome, the proposed system attained better performance compared to the existing systems and showed 3–11% improvement in recognition accuracy.

An optimized automatic prediction of stage and grade in bladder cancer based on U-ResNet

The grade and stage of bladder tumors is an essential key for diagnosing and treating bladder cancer. This study proposed an automated bladder tumor prediction system to automatically assess the bladder tumor grade and stage automatically on Magnetic Resonance Imaging (MRI) images. The system included three modules: tumor segmentation, feature extraction and prediction. We proposed a U-ResNet network that automatically extracts morphological and texture features for detecting tumor regions. These features were used in support vector machine (SVM) classifiers to predict the grade and stage. Our proposed method segmented the tumor area and predicted the grade and stage more accurately compared to different methods in our experiments on MRI images. The accuracy of bladder tumor grade prediction was about 70%, and the accuracy of the data set was about 77.5%. The extensive experiments demonstrated the usefulness and effectiveness of our method.

The invasion depth measurement of bladder cancer using T2-weighted magnetic resonance imaging

BACKGROUND

Invasion depth is an important index for staging and clinical treatment strategy of bladder cancer (BCa). The aim of this study was to investigate the feasibility of segmenting the BCa region from bladder wall region on MRI, and quantitatively measuring the invasion depth of the tumor mass in bladder lumen for further clinical decision-making. This retrospective study involved 20 eligible patients with postoperatively pathologically confirmed BCa. It was conducted in the following steps: (1) a total of 1159 features were extracted from each voxel of both the certain cancerous and wall tissues with the T2-weighted (T2W) MRI data; (2) the support vector machine (SVM)-based recursive feature elimination (RFE) method was implemented to first select an optimal feature subset, and then develop the classification model for the precise separation of the cancerous regions; (3) after excluding the cancerous region from the bladder wall, the three-dimensional bladder wall thickness (BWT) was calculated using Laplacian method, and the invasion depth of BCa was eventually defined by the subtraction of the mean BWT excluding the cancerous region and the minimum BWT of the cancerous region.

RESULTS

The segmented results showed a promising accuracy, with the mean Dice similarity coefficient of 0.921. The "soft boundary" defined by the voxels with the probabilities between 0.1 and 0.9 could demonstrate the overlapped region of cancerous and wall tissues. The invasion depth calculated from proposed segmentation method was compared with that from manual segmentation, with a mean difference of 0.277 mm.

CONCLUSION

The proposed strategy could accurately segment the BCa region, and, as the first attempt, realize the quantitative measurement of BCa invasion depth.

Magnetic Resonance Texture Analysis in Alzheimer's disease

Texture analysis is an emerging field that allows mathematical detection of changes in MRI signals that are not visible among image pixels. Alzheimer's disease, a progressive neurodegenerative disease, is the most common cause of dementia. Recently, multiple texture analysis studies in patients with Alzheimer's disease have been performed. This review summarizes the main contributors to Alzheimer's disease-associated cognitive decline, presents a brief overview of texture analysis, followed by review of various MR imaging texture analysis applications in Alzheimer's disease. We also discuss the current challenges for widespread clinical utilization. MR texture analysis could potentially be applied to develop neuroimaging biomarkers for use in Alzheimer's disease clinical trials and diagnosis.

An empirical assessment of appearance descriptors applied to MRI for automated diagnosis of TLE and MCI

OBJECTIVE

Differential diagnosis of mild cognitive impairment MCI and temporal lobe epilepsy TLE is a debated issue, specifically because these conditions may coincide in the elderly population. We evaluate automated differential diagnosis based on characteristics derived from structural brain MRI of different brain regions.

METHODS

In 22 healthy controls, 19 patients with MCI, and 17 patients with TLE we used scale invariant feature transform (SIFT), local binary patterns (LBP), and wavelet-based features and investigate their predictive performance for MCI and TLE.

RESULTS

The classification based on SIFT features resulted in an accuracy of 81% of MCI vs. TLE and reasonable generalizability. Local binary patterns yielded satisfactory diagnostic performance with up to 94.74% sensitivity and 88.24% specificity in the right Thalamus for the distinction of MCI vs. TLE, but with limited generalizable. Wavelet features yielded similar results as LPB with 94.74% sensitivity and 82.35% specificity but generalize better.

SIGNIFICANCE

Features beyond volume analysis are a valid approach when applied to specific regions of the brain. Most significant information could be extracted from the thalamus, frontal gyri, and temporal regions, among others. These results suggest that analysis of changes of the central nervous system should not be limited to the most typical regions of interest such as the hippocampus and parahippocampal areas. Region-independent approaches can add considerable information for diagnosis. We emphasize the need to characterize generalizability in future studies, as our results demonstrate that not doing so can lead to overestimation of classification results.

LIMITATIONS

The data used within this study allows for separation of MCI and TLE subjects using a simple age threshold. While we present a strong indication that the presented method is age-invariant and therefore agnostic to this situation, new data would be needed for a rigorous empirical assessment of this findings.

Single-slice Alzheimer's disease classification and disease regional analysis with Supervised Switching Autoencoders

BACKGROUND

Alzheimer's disease (AD) is a difficult to diagnose pathology of the brain that progressively impairs cognitive functions. Computer-assisted diagnosis of AD based on image analysis is an emerging tool to support AD diagnosis. In this article, we explore the application of Supervised Switching Autoencoders (SSAs) to perform AD classification using only one structural Magnetic Resonance Imaging (sMRI) slice. SSAs are revised supervised autoencoder architectures, combining unsupervised representation and supervised classification as one unified model. In this work, we study the capabilities of SSAs to capture complex visual neurodegeneration patterns, and fuse disease semantics simultaneously. We also examine how regions associated to disease state can be discovered by SSAs following a local patch-based approach.

METHODS

Patch-based SSAs models are trained on individual patches extracted from a single 2D slice, independently for Axial, Coronal, and Sagittal anatomical planes of the brain at selected informative locations, exploring different patch sizes and network parameterizations. Then, models perform binary class prediction - healthy (CDR = 0) or AD-demented (CDR > 0) - on test data at patch level. The final subject classification is performed employing a majority rule from the ensemble of patch predictions. In addition, relevant regions are identified, by computing accuracy densities from patch-level predictions, and analyzed, supported by Atlas-based regional definitions.

RESULTS

Our experiments employing a single 2D T1-w sMRI slice per subject show that SSAs perform similarly to previous proposals that rely on full volumetric information and feature-engineered representations. SSAs classification accuracy on slices extracted along the Axial, Coronal, and Sagittal anatomical planes from a balanced cohort of 40 independent test subjects was 87.5%, 90.0%, and 90.0%, respectively. A top sensitivity of 95.0% on both Coronal and Sagittal planes was also obtained.

CONCLUSIONS

SSAs provided well-ranked accuracy performance among previous classification proposals, including feature-engineered and feature learning based methods, using only one scan slice per subject, instead of the whole 3D volume, as it is conventionally done. In addition, regions identified as relevant by SSAs' were, in most part, coherent or partially coherent in regard to relevant regions reported on previous works. These regions were also associated with findings from medical knowledge, which gives value to our methodology as a potential analytical aid for disease understanding.

ALTEA: A Software Tool for the Evaluation of New Biomarkers for Alzheimer's Disease by Means of Textures Analysis on Magnetic Resonance Images

The current criteria for diagnosing Alzheimer’s disease (AD) require the presence of relevant cognitive deficits, so the underlying neuropathological damage is important by the time the diagnosis is made. Therefore, the evaluation of new biomarkers to detect AD in its early stages has become one of the main research focuses. The purpose of the present study was to evaluate a set of texture parameters as potential biomarkers of the disease. To this end, the ALTEA (ALzheimer TExture Analyzer) software tool was created to perform 2D and 3D texture analysis on magnetic resonance images. This intuitive tool was used to analyze textures of circular and spherical regions situated in the right and left hippocampi of a cohort of 105 patients: 35 AD patients, 35 patients with early mild cognitive impairment (EMCI) and 35 cognitively normal (CN) subjects. A total of 25 statistical texture parameters derived from the histogram, the Gray-Level Co-occurrence Matrix and the Gray-Level Run-Length Matrix, were extracted from each region and analyzed statistically to study their predictive capacity. Several textural parameters were statistically significant (p < 0.05) when differentiating AD subjects from CN and EMCI patients, which indicates that texture analysis could help to identify the presence of AD.

Relationship between Glioblastoma Heterogeneity and Survival Time: An MR Imaging Texture Analysis

BACKGROUND AND PURPOSE

The heterogeneity of glioblastoma contributes to the poor and variant prognosis. The aim of this retrospective study was to assess the glioblastoma heterogeneity with MR imaging textures and to evaluate its impact on survival time.

MATERIALS AND METHODS

A total of 133 patients with primary glioblastoma who underwent postcontrast T1-weighted imaging (acquired before treatment) and whose data were filed with the survival times were selected from the Cancer Genome Atlas. On the basis of overall survival, the patients were divided into 2 groups: long-term (≥12 months, n = 67) and short-term (<12 months, n = 66) survival. To measure heterogeneity, we extracted 3 types of textures, co-occurrence matrix, run-length matrix, and histogram, reflecting local, regional, and global spatial variations, respectively. Then the support vector machine classification was used to determine how different texture types perform in differentiating the 2 groups, both alone and in combination. Finally, a recursive feature-elimination method was used to find an optimal feature subset with the best differentiation performance.

RESULTS

When used alone, the co-occurrence matrix performed best, while all the features combined obtained the best survival stratification. According to feature selection and ranking, 43 top-ranked features were selected as the optimal subset. Among them, the top 10 features included 7 run-length matrix and 3 co-occurrence matrix features, in which all 6 regional run-length matrix features emphasizing high gray-levels ranked in the top 7.

CONCLUSIONS

The results suggest that local and regional heterogeneity may play an important role in the survival stratification of patients with glioblastoma.

Preoperative prediction of muscular invasiveness of bladder cancer with radiomic features on conventional MRI and its high-order derivative maps

PURPOSE

To determine radiomic features which are capable of reflecting muscular invasiveness of bladder cancer (BC) and propose a non-invasive strategy for the differentiation of muscular invasiveness preoperatively.

METHODS

Sixty-eight patients with clinicopathologically confirmed BC were included in this retrospective study. A total of 118 cancerous volumes of interest (VOI) were segmented from patients' T2 weighted MR images (T2WI), including 34 non-muscle invasive bladder carcinomas (NMIBCs, stage <T2) and 84 muscle invasive ones (MIBCs, stage ≥T2). The radiomic features quantifying tumor signal intensity and textures were extracted from each VOI and its high-order derivative maps to characterize heterogeneity of tumor tissues. Statistical analysis was used to build radiomic signatures with significant inter-group differences of NMIBCs and MIBCs. The synthetic minority oversampling technique (SMOTE) and a support vector machine (SVM)-based feature selection and classification strategy were proposed to first rebalance the imbalanced sample size and then further select the most predictive and compact signature subset to verify its differentiation capability.

RESULTS

From each tumor VOI, a total of 63 radiomic features were derived and 30 of them showed significant inter-group differences (P ≤ 0.01). By using the SVM-based feature selection algorithm with rebalanced samples, an optimal subset including 13 radiomic signatures was determined. The area under receiver operating characteristic curve and Youden index were improved to 0.8610 and 0.7192, respectively.

CONCLUSION

3D radiomic signatures derived from T2WI and its high-order derivative maps could reflect muscular invasiveness of bladder cancer, and the proposed strategy can be used to facilitate the preoperative prediction of muscular invasiveness in patients with bladder cancer.

Classification of brain disease in magnetic resonance images using two-stage local feature fusion

BACKGROUND

Many classification methods have been proposed based on magnetic resonance images. Most methods rely on measures such as volume, the cerebral cortical thickness and grey matter density. These measures are susceptible to the performance of registration and limited in representation of anatomical structure. This paper proposes a two-stage local feature fusion method, in which deformable registration is not desired and anatomical information is represented from moderate scale.

METHODS

Keypoints are firstly extracted from scale-space to represent anatomical structure. Then, two kinds of local features are calculated around the keypoints, one for correspondence and the other for representation. Scores are assigned for keypoints to quantify their effect in classification. The sum of scores for all effective keypoints is used to determine which group the test subject belongs to.

RESULTS

We apply this method to magnetic resonance images of Alzheimer's disease and Parkinson's disease. The advantage of local feature in correspondence and representation contributes to the final classification. With the help of local feature (Scale Invariant Feature Transform, SIFT) in correspondence, the performance becomes better. Local feature (Histogram of Oriented Gradient, HOG) extracted from 16×16 cell block obtains better results compared with 4×4 and 8×8 cell block.

DISCUSSION

This paper presents a method which combines the effect of SIFT descriptor in correspondence and the representation ability of HOG descriptor in anatomical structure. This method has the potential in distinguishing patients with brain disease from controls.

Three-dimensional texture features from intensity and high-order derivative maps for the discrimination between bladder tumors and wall tissues via MRI

PURPOSE

This study aims to determine the three-dimensional (3D) texture features extracted from intensity and high-order derivative maps that could reflect textural differences between bladder tumors and wall tissues, and propose a noninvasive, image-based strategy for bladder tumor differentiation preoperatively.

METHODS

A total of 62 cancerous and 62 wall volumes of interest (VOI) were extracted from T2-weighted MRI datasets of 62 patients with pathologically confirmed bladder cancer. To better reflect heterogeneous distribution of tumor tissues, 3D high-order derivative maps (the gradient and curvature maps) were calculated from each VOI. Then 3D Haralick features based on intensity and high-order derivative maps and Tamura features based on intensity maps were extracted from each VOI. Statistical analysis and recursive feature elimination-based support vector machine classifier (RFE-SVM) was proposed to first select the features with significant differences and then obtain a more predictive and compact feature subset to verify its differentiation performance.

RESULTS

From each VOI, a total of 58 texture features were derived. Among them, 37 features showed significant inter-class differences ([Formula: see text]). With 29 optimal features selected by RFE-SVM, the classification results namely the sensitivity, specificity, accuracy and area under the curve (AUC) of the receiver operating characteristics were 0.9032, 0.8548, 0.8790 and 0.9045, respectively. By using synthetic minority oversampling technique to augment the sample number of each group to 200, the sensitivity, specificity, accuracy an AUC value of the feature selection-based classification were improved to 0.8967, 0.8780, 0.8874 and 0.9416, respectively.

CONCLUSIONS

Our results suggest that 3D texture features derived from intensity and high-order derivative maps can better reflect heterogeneous distribution of cancerous tissues. Texture features optimally selected together with sample augmentation could improve the performance on differentiating bladder carcinomas from wall tissues, suggesting a potential way for tumor noninvasive staging of bladder cancer preoperatively.

Classification of brain disease from magnetic resonance images based on multi-level brain partitions

In this paper, we present a classification method based on the multi-level brain partitions. Bag-of-visual-words model is used. Firstly, the representative SIFT features are extracted from brain template as the basic visual words. Secondly, individual MR images are described using the basic visual words and support vector machine classifiers are trained for different brain partitions respectively. Thirdly, the final classification is derived from the combination of multiple classifiers. We apply this method to MR images of Alzheimer's disease and Parkinson's disease. The results demonstrate that the multi-level partitions favors the classification accuracy of brain disease from MR images.