1
|
Kaplan E, Chan WY, Altinsoy HB, Baygin M, Barua PD, Chakraborty S, Dogan S, Tuncer T, Acharya UR. PFP-HOG: Pyramid and Fixed-Size Patch-Based HOG Technique for Automated Brain Abnormality Classification with MRI. J Digit Imaging 2023; 36:2441-2460. [PMID: 37537514 PMCID: PMC10584767 DOI: 10.1007/s10278-023-00889-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/02/2023] [Revised: 07/18/2023] [Accepted: 07/24/2023] [Indexed: 08/05/2023] Open
Abstract
Detecting neurological abnormalities such as brain tumors and Alzheimer's disease (AD) using magnetic resonance imaging (MRI) images is an important research topic in the literature. Numerous machine learning models have been used to detect brain abnormalities accurately. This study addresses the problem of detecting neurological abnormalities in MRI. The motivation behind this problem lies in the need for accurate and efficient methods to assist neurologists in the diagnosis of these disorders. In addition, many deep learning techniques have been applied to MRI to develop accurate brain abnormality detection models, but these networks have high time complexity. Hence, a novel hand-modeled feature-based learning network is presented to reduce the time complexity and obtain high classification performance. The model proposed in this work uses a new feature generation architecture named pyramid and fixed-size patch (PFP). The main aim of the proposed PFP structure is to attain high classification performance using essential feature extractors with both multilevel and local features. Furthermore, the PFP feature extractor generates low- and high-level features using a handcrafted extractor. To obtain the high discriminative feature extraction ability of the PFP, we have used histogram-oriented gradients (HOG); hence, it is named PFP-HOG. Furthermore, the iterative Chi2 (IChi2) is utilized to choose the clinically significant features. Finally, the k-nearest neighbors (kNN) with tenfold cross-validation is used for automated classification. Four MRI neurological databases (AD dataset, brain tumor dataset 1, brain tumor dataset 2, and merged dataset) have been utilized to develop our model. PFP-HOG and IChi2-based models attained 100%, 94.98%, 98.19%, and 97.80% using the AD dataset, brain tumor dataset1, brain tumor dataset 2, and merged brain MRI dataset, respectively. These findings not only provide an accurate and robust classification of various neurological disorders using MRI but also hold the potential to assist neurologists in validating manual MRI brain abnormality screening.
Collapse
Affiliation(s)
- Ela Kaplan
- Department of Radiology, Elazig Fethi Sekin City Hospital, Elazig, Turkey
| | - Wai Yee Chan
- Imaging Department, Gleneagles Hospital Kuala Lumpur, Jalan Ampang, Kampung Berembang, 50450, Kuala Lumpur, Wilayah Persekutuan Kuala Lumpur, Malaysia
| | - Hasan Baki Altinsoy
- Department of Radiology, Faculty of Medicine, Duzce University, Duzce, Turkey
| | - Mehmet Baygin
- Department of Computer Engineering, College of Engineering, Erzurum Technical University, Erzurum, Turkey
| | - Prabal Datta Barua
- School of Business (Information System), University of Southern Queensland, Springfield, Australia
| | - Subrata Chakraborty
- Faculty of Science, Agriculture, Business and Law, School of Science and Technology, University of New England, Armidale, NSW, 2351, Australia
- Center for Advanced Modelling and Geospatial Information Systems, Faculty of Engineering and IT, University of Technology Sydney, Sydney, NSW, 2007, Australia
| | - Sengul Dogan
- Department of Digital Forensics Engineering, Technology Faculty, Firat University, Elazig, Turkey.
| | - Turker Tuncer
- Department of Digital Forensics Engineering, Technology Faculty, Firat University, Elazig, Turkey
| | - U Rajendra Acharya
- School of Mathematics, Physics and Computing, University of Southern Queensland, Springfield, Australia
| |
Collapse
|
2
|
Multi-Class Classifier in Parkinson’s Disease Using an Evolutionary Multi-Objective Optimization Algorithm. APPLIED SCIENCES-BASEL 2022. [DOI: 10.3390/app12063048] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Abstract
In this contribution, a novel methodology for multi-class classification in the field of Parkinson’s disease is proposed. The methodology is structured in two phases. In a first phase, the most relevant volumes of interest (VOI) of the brain are selected by means of an evolutionary multi-objective optimization (MOE) algorithm. Each of these VOIs are subjected to volumetric feature extraction using the Three-Dimensional Discrete Wavelet Transform (3D-DWT). When applying 3D-DWT, a high number of coefficients is obtained, requiring the use of feature selection/reduction algorithms to find the most relevant features. The method used in this contribution is based on Mutual Redundancy (MI) and Minimum Maximum Relevance (mRMR) and PCA. To optimize the VOI selection, a first group of 550 MRI was used for the 5 classes: PD, SWEDD, Prodromal, GeneCohort and Normal. Once the Pareto Front of the solutions is obtained (with varying degrees of complexity, reflected in the number of selected VOIs), these solutions are tested in a second phase. In order to analyze the SVM classifier accuracy, a test set of 367 MRI was used. The methodology obtains relevant results in multi-class classification, presenting several solutions with different levels of complexity and precision (Pareto Front solutions), reaching a result of 97% as the highest precision in the test data.
Collapse
|
3
|
Sundarasekar R, Appathurai A. Efficient brain tumor detection and classification using magnetic resonance imaging. Biomed Phys Eng Express 2021; 7. [PMID: 34260415 DOI: 10.1088/2057-1976/ac0ccc] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/25/2021] [Accepted: 06/18/2021] [Indexed: 01/19/2023]
Abstract
Magnetic Resonance Imaging (MRI) inputs are most noticeable in diagnosing brain tumors via computer and manual clinical understanding. Multi-level detection and classification of the images utilizing computer-aided processing depend on labels and annotations. Though the two processes are dynamic and time-consuming, without which the precise accuracy is less assured. For augmenting the accuracy in processing un-labeled or annotation-less images, this article introduces Absolute Classification-Detection Model (AC-DM). This model uses a conventional neural network for training the morphological variations proficient of achieving label-less classification and tumor detection. The traditional neural network trains the images based on differential lattice morphology for classification and detection. In this process, training for the lattices and their corresponding gradients is validated to improve the precision of the regional analysis. This helps to retain the precision of identifying tumors. The variations are recognized for their lattice mapping in the detected boundaries of the input image. The detected boundaries help to map accurate lattices for adapting morphological transforms. Thus, the partial and complex processing in detecting tumors is restrained in the suggested model, adapting to the classification. The efficiency of the suggested model is verified utilizing accuracy, precision, sensitivity, and classification time.
Collapse
Affiliation(s)
| | - Ahilan Appathurai
- Department of ECE, Infant Jesus College of Engineering, ANNA University, Chennai, India
| |
Collapse
|
4
|
Alongi P, Chiaravalloti A, Berti V, Vellani C, Trifirò G, Puccini G, Carli G, Chincarini A, Morbelli S, Perani D, Sestini S. Amyloid PET in the diagnostic workup of neurodegenerative disease. Clin Transl Imaging 2021. [DOI: 10.1007/s40336-021-00428-x] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/20/2022]
|
5
|
Almubark I, Chang LC, Shattuck KF, Nguyen T, Turner RS, Jiang X. A 5-min Cognitive Task With Deep Learning Accurately Detects Early Alzheimer's Disease. Front Aging Neurosci 2020; 12:603179. [PMID: 33343337 PMCID: PMC7744695 DOI: 10.3389/fnagi.2020.603179] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/05/2020] [Accepted: 11/13/2020] [Indexed: 12/15/2022] Open
Abstract
Introduction: The goal of this study was to investigate and compare the classification performance of machine learning with behavioral data from standard neuropsychological tests, a cognitive task, or both. Methods: A neuropsychological battery and a simple 5-min cognitive task were administered to eight individuals with mild cognitive impairment (MCI), eight individuals with mild Alzheimer's disease (AD), and 41 demographically match controls (CN). A fully connected multilayer perceptron (MLP) network and four supervised traditional machine learning algorithms were used. Results: Traditional machine learning algorithms achieved similar classification performances with neuropsychological or cognitive data. MLP outperformed traditional algorithms with the cognitive data (either alone or together with neuropsychological data), but not neuropsychological data. In particularly, MLP with a combination of summarized scores from neuropsychological tests and the cognitive task achieved ~90% sensitivity and ~90% specificity. Applying the models to an independent dataset, in which the participants were demographically different from the ones in the main dataset, a high specificity was maintained (100%), but the sensitivity was dropped to 66.67%. Discussion: Deep learning with data from specific cognitive task(s) holds promise for assisting in the early diagnosis of Alzheimer's disease, but future work with a large and diverse sample is necessary to validate and to improve this approach.
Collapse
Affiliation(s)
- Ibrahim Almubark
- Department of Electrical Engineering and Computer Science, Catholic University of America, Washington, DC, United States
| | - Lin-Ching Chang
- Department of Electrical Engineering and Computer Science, Catholic University of America, Washington, DC, United States
| | - Kyle F Shattuck
- Department of Neuroscience, Georgetown University Medical Center, Washington, DC, United States
| | - Thanh Nguyen
- Department of Electrical Engineering and Computer Science, Catholic University of America, Washington, DC, United States
| | - Raymond Scott Turner
- Department of Neurology, Georgetown University Medical Center, Washington, DC, United States
| | - Xiong Jiang
- Department of Neuroscience, Georgetown University Medical Center, Washington, DC, United States
| |
Collapse
|