ChapterPDF Available

Neurodegenerative Alzheimer’s Disease Disorders and Deep Learning Approaches

June 2023

DOI:10.1007/978-981-99-2154-6_3

In book: Data Analysis for Neurodegenerative Disorders (pp.49-66)

Authors:

Bhuvanesh Baniya

Jai Narain Vyas University

Nema Ram

Bhupal Nobel's Institute of Pharmaceutical Sciences

Convolutional neural networks (CNN) can no longer make a significant contribution to Alzheimer’s disease diagnosis because there is insufficient data to work with. We have built a cutting-edge deep learning system and are currently putting it to use to increase the effectiveness of the work we are doing to achieve this goal. To achieve the highest level of performance, we combine the advantages of fully stacked bidirectional long short-term memory (FSBi-LSTM) with those of three-dimensional convolutional neural networks. These two methods of data storage are stacked one on top of the other. Before interpreting the MRI and PET images, it is critical to train a three-dimensional convolutional neural network. This must be completed to proceed to the next stage. The essential qualities of the deep features can be agreed upon. Before any further inquiry into the matter can proceed, this must be done. Here is only one example of how this method may be applied. Even if only one individual is made aware of this, the ramifications might be terrible. Lastly, we compared our findings to those of an Alzheimer’s disease neuroimaging research study to show definitively that our technique is beneficial in Alzheimer’s disease management. According to our observations, our approach surpasses other theoretically comparable algorithms published in academic literature. These algorithms were evaluated based on their ability to tackle the same issue. This is true regardless of whether our technique is technically equivalent to other published methods: cases of pMCI can be distinguished from NC with a success rate of 94.82%; cases of sMCI can be distinguished from NC with an 86.30% success rate; and cases of Alzheimer’s Disease (AD) can be distinguished from NC with an 86.30% success rate. This result was obtained despite the fact that there was inadequate imaging evidence to back it up.KeywordsConvolution neural networkFully stacked bidirectionalLong short-term memoryDeep learningRecurrent neural networks

Content uploaded by Bhuvanesh Baniya

Content may be subject to copyright.

6/2/23, 11:04 AM

Neurodegenerative Alzheimer’s Disease Disorders and Deep Learning Approaches | SpringerLink

https://link.springer.com/chapter/10.1007/978-981-99-2154-6_3#citeas

1/13

Neurodegenerative Alzheimer’s Disease

Disorders and Deep Learning

Approaches

Bhuvanesh Baniya , Shashikant V. Athawale, Mangi Lal

Choudhary & Nema Ram

Chapter First Online: 01 June 2023

Part of the Cognitive Technologies book series (COGTECH)

Abstract

Convolutional neural networks (CNN) can no longer

make a significant contribution to Alzheimer’s disease

diagnosis because there is insufficient data to work

with. We have built a cutting-edge deep learning

system and are currently putting it to use to increase

the effectiveness of the work we are doing to achieve

this goal. To achieve the highest level of performance,

we combine the advantages of fully stacked

bidirectional long short-term memory (FSBi-LSTM)

with those of three-dimensional convolutional neural

Home

Data Analysis for Neurodegenerative Disor…

Chapter

Search Log in

Data Analysis for Neurodegenerative Disorders pp 49–66

6/2/23, 11:04 AM

Neurodegenerative Alzheimer’s Disease Disorders and Deep Learning Approaches | SpringerLink

https://link.springer.com/chapter/10.1007/978-981-99-2154-6_3#citeas

2/13

networks. These two methods of data storage are

stacked one on top of the other. Before interpreting

the MRI and PET images, it is critical to train a three-

dimensional convolutional neural network. This must

be completed to proceed to the next stage. The

essential qualities of the deep features can be agreed

upon. Before any further inquiry into the matter can

proceed, this must be done. Here is only one example

of how this method may be applied. Even if only one

individual is made aware of this, the ramifications

might be terrible. Lastly, we compared our findings to

those of an Alzheimer’s disease neuroimaging

research study to show definitively that our technique

is beneficial in Alzheimer’s disease management.

According to our observations, our approach

surpasses other theoretically comparable algorithms

published in academic literature. These algorithms

were evaluated based on their ability to tackle the

same issue. This is true regardless of whether our

technique is technically equivalent to other published

methods: cases of pMCI can be distinguished from

NC with a success rate of 94.82%; cases of sMCI can

be distinguished from NC with an 86.30% success

rate; and cases of Alzheimer’s Disease (AD) can be

distinguished from NC with an 86.30% success rate.

This result was obtained despite the fact that there

was inadequate imaging evidence to back it up.

Keywords

Convolution neural network

6/2/23, 11:04 AM

Neurodegenerative Alzheimer’s Disease Disorders and Deep Learning Approaches | SpringerLink

https://link.springer.com/chapter/10.1007/978-981-99-2154-6_3#citeas

3/13

Fully stacked bidirectional

Long short-term memory Deep learning

Recurrent neural networks

This is a preview of subscription content, access via

your institution.

Chapter EUR  29.95

Price includes VAT (India)

Buy Chapter

eBook EUR  149.79

Price includes VAT (India)

Buy eBook

Hardcover Book EUR  179.99

Price excludes VAT (India)

DOI: 10.1007/978-981-99-2154-6_3

Chapter length: 18 pages

Instant PDF download

Readable on all devices

Own it forever

Exclusive offer for individuals only

Tax calculation will be finalised during checkout

ISBN: 978-981-99-2154-6

Instant EPUB and PDF download

Readable on all devices

Own it forever

Exclusive offer for individuals only

Tax calculation will be finalised during checkout

6/2/23, 11:04 AM

Neurodegenerative Alzheimer’s Disease Disorders and Deep Learning Approaches | SpringerLink

https://link.springer.com/chapter/10.1007/978-981-99-2154-6_3#citeas

4/13

Buy Hardcover Book

Learn about institutional subscriptions

References

1. Minati, L., Edginton, T., Grazia Bruzzone, M.,

Giaccone, G.: Reviews: Current concepts in

alzheimer’s disease: a multidisciplinary review. Am.

J. Alzheimer’s Dis. Other Dem. 24, 95–121 (2009)

2. Trépel, D.: The economics of preventing dementia.

In: New Developments in Dementia Prevention

Research, pp. 156–169 (2018)

3. Feng, C., Elazab, A., Yang, P., Wang, T., Zhou, F., Hu,

H., Xiao, X., Lei, B.: Deep learning framework for

Alzheimer’s disease diagnosis via 3D-CNN and

FSBI-LSTM. IEEE Access 7, 63605–63618 (2019)

4. Zhang, D., Shen, D.: Multi-modal multi-task

learning for joint prediction of multiple regression

and classification variables in Alzheimer’s disease.

Neuroimage 59, 895–907 (2012)

ISBN: 978-981-99-2153-9

Dispatched in 3 to 5 business days

Exclusive offer for individuals only

Free shipping worldwide

See shipping information.

Tax calculation will be finalised during checkout

6/2/23, 11:04 AM

Neurodegenerative Alzheimer’s Disease Disorders and Deep Learning Approaches | SpringerLink

https://link.springer.com/chapter/10.1007/978-981-99-2154-6_3#citeas

5/13

5. Zhu, X., Suk, H.-I., Wang, L., Lee, S.-W., Shen, D.: A

novel relational regularization feature selection

method for joint regression and classification in

AD diagnosis. Med. Image Anal. 38, 205–214

(2017)

6. Suk, H.-I., Lee, S.-W., Shen, D.: Hierarchical feature

representation and multimodal fusion with deep

learning for AD/MCI diagnosis. Neuroimage 101,

569–582 (2014)

7. Wang, S., Wu, X., Wei, K., Kong, W.: An improved

fusion paired group lasso structured sparse

canonical correlation analysis based on brain

imaging genetics to identify biomarkers of

Alzheimer’s disease. Front. Aging Neurosci. 13

(2022)

8. Hussain, M., Koundal, D., Manhas, J.: Deep

learning-based diagnosis of disc degenerative

diseases using MRI: a comprehensive review.

Comput. Electr. Eng. 105, 108524 (2023)

9. Malhotra, P., Gupta, S., Koundal, D., Zaguia, A.,

Enbeyle, W.: Deep neural networks for medical

image segmentation. J. Healthcare Eng. 2022

(2022)

6/2/23, 11:04 AM

Neurodegenerative Alzheimer’s Disease Disorders and Deep Learning Approaches | SpringerLink

https://link.springer.com/chapter/10.1007/978-981-99-2154-6_3#citeas

6/13

10. Tuan, P.M., Phan, T.-L., Adel, M., Bourennane, S.,

Trung, N.L., Guedj, E.: C-atlas: a brain mapping

based on FDG-pet images for Alzheimer’s

disease diagnosis. In: 2022 RIVF International

Conference on Computing and Communication

Technologies (RIVF) (2022)

11. Chen, Z., Liu, Y., Zhang, Y., Li, Q.: Orthogonal

latent space learning with feature weighting and

Graph Learning for multimodal Alzheimer’s

disease diagnosis. Med. Image Anal. 84, 102698

(2023)

12. Pan, Q., Ding, K., Chen, D.: Multi-classification

prediction of Alzheimer’s disease based on

fusing multi-modal features. In: 2021 IEEE

International Conference on Data Mining (ICDM)

(2021)

13. Nair, R., Bhagat, A.: Healthcare information

exchange through blockchain-based

approaches. In: Transforming Businesses with

Bitcoin Mining and Blockchain Applications, pp.

234–246 (2020)

14. Nair, R., Vishwakarma, S., Soni, M., Patel, T., Joshi,

S.: Detection of covid-19 cases through X-ray

6/2/23, 11:04 AM

Neurodegenerative Alzheimer’s Disease Disorders and Deep Learning Approaches | SpringerLink

https://link.springer.com/chapter/10.1007/978-981-99-2154-6_3#citeas

7/13

images using hybrid deep neural network. World

J. Eng. 19, 33–39 (2021)

15. Wu, X., Chen, C., Zhong, M., Wang, J., Shi, J.:

Covid-al: the diagnosis of COVID-19 with deep

active learning. Med. Image Anal. 68, 101913

(2021)

16. Garali, I., Adel, M., Bourennane, S., Guedj, E.:

Histogram-based features selection and volume

of interest ranking for brain pet image

classification. IEEE J. Transl. Eng. Health Med. 6,

1–12 (2018)

17. Dimitriadis, S.I., Liparas, D., Tsolaki, M.N.:

Random Forest feature selection, fusion and

ensemble strategy: Combining multiple

morphological MRI measures to discriminate

among healhy elderly, MCI, CMCI and

Alzheimer’s disease patients: from the

Alzheimer’s disease neuroimaging initiative

(ADNI) database. J. Neurosci. Methods 302, 14–

23 (2018)

18. Reza, G., Davar, K.: Amyloid-beta clearance in

alzheimer’s disease: Does exercise play a role?

Ann Alzheimer’s and Demen Care, 018–020

(2020)

6/2/23, 11:04 AM

Neurodegenerative Alzheimer’s Disease Disorders and Deep Learning Approaches | SpringerLink

https://link.springer.com/chapter/10.1007/978-981-99-2154-6_3#citeas

8/13

19. Pan, Y., Liu, M., Xia, Y., Shen, D.: Disease-image-

specific learning for diagnosis-oriented

neuroimage synthesis with incomplete multi-

modality data. IEEE Trans. Pattern Anal. Mach.

Intell. 44, 6839–6853 (2022)

20. Ramirez-Asis, E., Bolivar, R.P., Gonzales, L.A.,

Chaudhury, S., Kashyap, R., Alsanie, W.F., Viju,

G.K.: A lightweight hybrid dilated ghost model-

based approach for the prognosis of breast

cancer. Comput. Intell. Neurosci. 2022, 1–10

(2022)

21. Mohanakurup, V., Parambil Gangadharan, S.M.,

Goel, P., Verma, D., Alshehri, S., Kashyap, R.,

Malakhil, B.: Breast cancer detection on

histopathological images using a composite

dilated backbone network. Comput. Intell.

Neurosci. 2022, 1–10 (2022)

22. Parashar, V., Kashyap, R., Rizwan, A., Karras, D.A.,

Altamirano, G.C., Dixit, E., Ahmadi, F.:

Aggregation-based dynamic channel bonding to

maximise the performance of wireless local area

networks (WLAN). Wirel. Commun. Mob.

Comput. 2022, 1–11 (2022)

6/2/23, 11:04 AM

Neurodegenerative Alzheimer’s Disease Disorders and Deep Learning Approaches | SpringerLink

https://link.springer.com/chapter/10.1007/978-981-99-2154-6_3#citeas

9/13

23. Kashyap, R.: Evolution of histopathological

breast cancer images classification using

stochastic dilated residual ghost model. Turk. J.

Electr. Eng. Comput. Sci. 29, 2758–2779 (2021)

24. Zhou, T., Thung, K.H., Zhu, X., Shen, D.: Effective

feature learning and fusion of multimodality

data using stage-wise deep neural network for

dementia diagnosis. Hum. Brain Mapp. 40,

1001–1016 (2018)

25. Nair, R., Alhudhaif, A., Koundal, D., Doewes, R.I.,

Sharma, P.: Deep learning-based COVID-19

detection system using pulmonary CT scans.

Turk. J. Electr. Eng. Comput. Sci. 29(8), 2716–

2727 (2021)

26. Chen, H.: Alzheimer’s disease classification using

brain MRI based on combination of

convolutional neural network and Random

Forest Model. Highlights Sci. Eng. Technol. 14,

203–212 (2022)

27. Liu, M., Cheng, D., Wang, K., Wang, Y.: Multi-

modality cascaded convolutional neural

networks for Alzheimer’s disease diagnosis.

Neuroinformatics 16, 295–308 (2018)

6/2/23, 11:04 AM

Neurodegenerative Alzheimer’s Disease Disorders and Deep Learning Approaches | SpringerLink

https://link.springer.com/chapter/10.1007/978-981-99-2154-6_3#citeas

10/13

28. Liu, M., Cheng, D., Yan, W.: Classification of

Alzheimer’s disease by combination of

convolutional and recurrent neural networks

using FDG-pet images. Front. Neuroinf. 12

(2018)

29. Feichtenhofer, C., Pinz, A., Wildes, R.P., Zisserman,

A.: Deep insights into convolutional networks for

video recognition. Int. J. Comput. Vision 128,

420–437 (2019)

30. Bengio, Y., Lecun, Y., Hinton, G.: Deep learning

for AI. Commun. ACM 64, 58–65 (2021)

31. Kashyap, R.: Artificial intelligence systems in

aviation. Adv. Comput. Electr. Eng., 1–26 (2019)

32. Koundal, D.: Texture-based image segmentation

using neutrosophic clustering. IET Image Proc.

11(8), 640–645 (2017)

33. Sethi, M., Ahuja, S., Rani, S., Koundal, D., Zaguia,

A., Enbeyle, W.: An exploration: Alzheimer’s

disease classification based on convolutional

neural network. BioMed Res. Int. 2022 (2022)

6/2/23, 11:04 AM

Neurodegenerative Alzheimer’s Disease Disorders and Deep Learning Approaches | SpringerLink

https://link.springer.com/chapter/10.1007/978-981-99-2154-6_3#citeas

11/13

34. Koundal, D., Gupta, S., Singh, S.: Nakagami-

based total variation method for speckle

reduction in thyroid ultrasound images. Proc.

Inst. Mech. Eng. [H] 230(2), 97–110 (2016)

Author information

Authors and Affiliations

Department of Pharmaceutical Sciences,

University College of Science, Mohanlal Sukhadiya

University, Udaipur, Rajasthan, India

Bhuvanesh Baniya

Department of Computer Engineering, AISSMS

COE, Pune, India

Shashikant V. Athawale

Savitribai Phule Pune University, Pune, India

Shashikant V. Athawale

B.N. College of Pharmacy, Udaipur, India

Mangi Lal Choudhary

B.N. University, Udaipur, Rajasthan, India

Nema Ram

Corresponding author

Correspondence to Bhuvanesh Baniya .

Editor information

Editors and Affiliations

6/2/23, 11:04 AM

Neurodegenerative Alzheimer’s Disease Disorders and Deep Learning Approaches | SpringerLink

https://link.springer.com/chapter/10.1007/978-981-99-2154-6_3#citeas

12/13

School of Computer Science, University of

Petroleum and Energy Studies, Dehradun,

Uttarakhand, India

Deepika Koundal

Chongqing University of Posts and

Telecommunications, Chongqing, China

Deepak Kumar Jain

Department of Computer Science, University of

Illinois at Springfield, Springfield, IL, USA

Yanhui Guo

Faculty of Engineering, Tanta University, Tanta, Al-

Garbia, Egypt

Amira S. Ashour

Department of Computer Science, Taif University,

Taif, Saudi Arabia

Atef Zaguia

Rights and permissions

Reprints and Permissions

Springer Nature Singapore Pte Ltd.

About this chapter

Cite this chapter

6/2/23, 11:04 AM

Neurodegenerative Alzheimer’s Disease Disorders and Deep Learning Approaches | SpringerLink

https://link.springer.com/chapter/10.1007/978-981-99-2154-6_3#citeas

13/13

Baniya, B., Athawale, S.V., Choudhary, M.L., Ram, N. (2023).

Neurodegenerative Alzheimer’s Disease Disorders and Deep

Learning Approaches. In: Koundal, D., Jain, D.K., Guo, Y.,

Ashour, A.S., Zaguia, A. (eds) Data Analysis for

Neurodegenerative Disorders. Cognitive Technologies.

Springer, Singapore. https://doi.org/10.1007/978-981-99-

2154-6_3

.RIS .ENW .BIB

DOI

https://doi.org/10.1007/978-981-99-2154-6_3

Published

01 June 2023

Publisher Name

Springer,

Singapore

Print ISBN

978-981-99-2153-

Online ISBN

978-981-99-2154-

eBook Packages

Computer Science

(R0)

Not logged in - 152.58.71.51

Not affiliated

ResearchGate has not been able to resolve any citations for this publication.

Alzheimer’s Disease Classification Using Brain MRI Based on Combination of Convolutional Neural Network and Random Forest Model

Article

Full-text available

Sep 2022

Haoyu Chen

Worldwide, someone develops dementia every 3 seconds. Dementia is mostly brought on by Alzheimer's disease (AD). Research has concentrated on diagnosing AD and dementia over the past centuries, and brain Magnetic Resonance Imaging (MRI) has been proved an effective biomarker of AD and other dementias. Throughout the years, many methods, including various forms of Neural Networks, Support Vector Machines, and other machine learning algorithms, have been innovated and applied to the classification of brain MRI scans. This paper aims to propose a model framework that has been rarely used in this field. This novel architecture utilizes a Convolutional Neural Network (CNN) for the feature extracting task and a Random Forest (RF) model for classifying different stages of dementias. The model was evaluated on each label's performance and overall performance. The performance metrics include accuracy, f-1 score, precision, and recall. The comparisons between the proposed model and the other two sodels, a CNN and a combination of Principal Component Analysis (PCA) and RF, were also provided. The implementation of the proposed model resulted in the highest overall accuracy, weighted precision, weighted recall, and weighted f-1 score. It also guaranteed stable and excellent performance across every label.

A Lightweight Hybrid Dilated Ghost Model-Based Approach for the Prognosis of Breast Cancer

Article

Full-text available

Aug 2022
Comput Intell Neurosci

Most approaches use interactive priors to find tumours and then segment them based on tumour-centric candidates. A fully convolutional network is demonstrated for end-to-end breast tumour segmentation. When confronted with such a variety of options, to enhance tumour detection in digital mammograms, one uses multiscale picture information. Enhanced segmentation precision. The sampling of convolution layers are carefully chosen without adding parameters to prevent overfitting. The loss function is tuned to the tumor pixel fraction during training. Several studies have shown that the recommended method is effective. Tumour segmentation is automated for a variety of tumour sizes and forms postprocessing. Due to an increase in malignant cases, fundamental IoT malignant detection and family categorisation methodologies have been put to the test. In this paper, a novel malignant detection and family categorisation model based on the improved stochastic channel attention of convolutional neural networks (CNNs) is presented. The lightweight deep learning model complies with tougher execution, training, and energy limits in practice. The improved stochastic channel attention and DenseNet models are employed to identify malignant cells, followed by family classification. On our datasets, the proposed model detects malignant cells with 99.3 percent accuracy and family categorisation with 98.5 percent accuracy. The model can detect and classify malignancy.

Breast Cancer Detection on Histopathological Images Using a Composite Dilated Backbone Network

Article

Full-text available

Jul 2022
Comput Intell Neurosci

Breast cancer is a lethal illness that has a high mortality rate. In treatment, the accuracy of diagnosis is crucial. Machine learning and deep learning may be beneficial to doctors. The proposed backbone network is critical for the present performance of CNN-based detectors. Integrating dilated convolution, ResNet, and Alexnet increases detection performance. The composite dilated backbone network (CDBN) is an innovative method for integrating many identical backbones into a single robust backbone. Hence, CDBN uses the lead backbone feature maps to identify objects. It feeds high-level output features from previous backbones into the next backbone in a stepwise way. We show that most contemporary detectors can easily include CDBN to improve performance achieved mAP improvements ranging from 1.5 to 3.0 percent on the breast cancer histopathological image classification (BreakHis) dataset. Experiments have also shown that instance segmentation may be improved. In the BreakHis dataset, CDBN enhances the baseline detector cascade mask R-CNN (mAP = 53.3). The proposed CDBN detector does not need pretraining. It creates high-level traits by combining low-level elements. This network is made up of several identical backbones that are linked together. The composite dilated backbone considers the linked backbones CDBN.

Aggregation-Based Dynamic Channel Bonding to Maximise the Performance of Wireless Local Area Networks (WLAN)

Article

Full-text available

Jun 2022
WIREL COMMUN MOB COM

Channel bonding is considered by the IEEE 802.11ac amendment to improve wireless local area network (WLAN) performance. In this article, the channel bonding and aggregation method were proposed to increase wireless local area network performance (WLANs). It combines many channels (or lanes) to boost the capacity of modem traffic. Channel bonding is the combination of two neighbouring channels within a certain frequency band to increase wireless device throughput. Wi-Fi employs channel bonding, also known as Ethernet bonding. Channel bandwidth is equal to the uplink/downlink ratio multiplied by the operational capacity. A single 20 MHz channel is divided into two, four, or eight power channels. At 80 MHz, there are more main and smaller channels. Performance of short-range WLANs is determined through graph-based approach. The two-channel access techniques including channel bonding proposed for the IEEE 802.11ac amendment are analysed and contrasted. The novel channel sizing algorithm based on starvation threshold is proposed to expand the channel size to improve WLAN performance. Second-cycle throughput is estimated at 20 Mbps, much beyond the starvation threshold. Our test reveals access points (AP) 1, 2, and 4 have enough throughput. A four-AP WLAN with a 5-Mbps starvation threshold is presented. C160 = 1 since there is only one 160 MHz channel. MIR (3, 160 (a, a, a)) =0, indicating that AP 3's predicted throughput is 0. The algorithm rejects the 160 MHz channel width since ST is larger than 0. The channel width in MHz is given by B =0,1 MIR. The MIR was intended to maximise simultaneous broadcasts in WLANs. The authors claim that aggregation with channel bonding outperforms so all WLAN APs should have a single-channel width. It usually outperforms fairness-based measures by 15% to 20%. Wi-Fi standards advise "channel bonding," or using higher frequency channels. Later standards allow channel bonding by increasing bands and channel lengths. Wider channels enhance average WLAN AP throughput, but narrower channels reduce appetite. Finally, it is concluded that APs are more useful than STAs.

Deep Neural Networks for Medical Image Segmentation

Article

Full-text available

Mar 2022

Image segmentation is a branch of digital image processing which has numerous applications in the field of analysis of images, augmented reality, machine vision, and many more. The field of medical image analysis is growing and the segmentation of the organs, diseases, or abnormalities in medical images has become demanding. The segmentation of medical images helps in checking the growth of disease like tumour, controlling the dosage of medicine, and dosage of exposure to radiations. Medical image segmentation is really a challenging task due to the various artefacts present in the images. Recently, deep neural models have shown application in various image segmentation tasks. This significant growth is due to the achievements and high performance of the deep learning strategies. This work presents a review of the literature in the field of medical image segmentation employing deep convolutional neural networks. The paper examines the various widely used medical image datasets, the different metrics used for evaluating the segmentation tasks, and performances of different CNN based networks. In comparison to the existing review and survey papers, the present work also discusses the various challenges in the field of segmentation of medical images and different state-of-the-art solutions available in the literature.

An Exploration: Alzheimer’s Disease Classification Based on Convolutional Neural Network

Article

Full-text available

Jan 2022
BMRI

Alzheimer’s disease (AD) is the most generally known neurodegenerative disorder, leading to a steady deterioration in cognitive ability. Deep learning models have shown outstanding performance in the diagnosis of AD, and these models do not need any handcrafted feature extraction over conventional machine learning algorithms. Since the 2012 AlexNet accomplishment, the convolutional neural network (CNN) has been progressively utilized by the medical community to assist practitioners to early diagnose AD. This paper explores the current cutting edge applications of CNN on single and multimodality (combination of two or more modalities) neuroimaging data for the classification of AD. An exhaustive systematic search is conducted on four notable databases: Google Scholar, IEEE Xplore, ACM Digital Library, and PubMed in June 2021. The objective of this study is to examine the effectiveness of classification approaches on AD to analyze different kinds of datasets, neuroimaging modalities, preprocessing techniques, and data handling methods. However, CNN has achieved great success in the classification of AD; still, there are a lot of challenges particularly due to scarcity of medical imaging data and its possible scope in this field.

C-Atlas: A Brain Mapping based on FDG-PET Images for Alzheimer's Disease Diagnosis

Conference Paper

Dec 2022

Deep learning-based diagnosis of disc degenerative diseases using MRI: A comprehensive review

Article

Jan 2023
COMPUT ELECTR ENG

Deep learning (DL) models in general and convolutional neural networks (CNN) in particular, have rapidly turned out to be methodologies of interest for applications concerned with analysing medical images for classification of different types of disc abnormalities to avoid false outcomes in diagnosis and to automate the domain to a greater extent. In this paper, a detailed review has been conducted on how different state-of-the-art DL methodologies have been applied on disc disease diagnosis by using various medical imaging modalities. It focuses on how to maximize the decision analysis in disease diagnosis in terms of five different aspects, such as types of medical imaging modalities used, datasets and their available categories, pre-processing techniques, various DL models, and performance metrics used for disc degenerative disease (DDD) classification. Further, this study outlines quantitative, qualitative, and critical analysis of the five objectives. amongst the selected studies most of them used a pre-trained model or constructed a new DL model to classify DDD. Finally, this review outlines eight open challenges for researchers who are interested in DDD classification models. This review study will enhance the knowledge domain of researchers and will also provide a comprehensive insight of the effectiveness of the DL techniques being employed in medical diagnosis of DDD.

Orthogonal latent space learning with feature weighting and graph learning for multimodal Alzheimer’s disease diagnosis

Article

Nov 2022
MED IMAGE ANAL

Recent studies have shown that multimodal neuroimaging data provide complementary information of the brain and latent space-based methods have achieved promising results in fusing multimodal data for Alzheimer’s disease (AD) diagnosis. However, most existing methods treat all features equally and adopt nonorthogonal projections to learn the latent space, which can not retain enough discriminative information in the latent space. Besides, they usually preserve the relationships among subjects in the latent space based on the similarity graph constructed on original features for performance boosting. However, the noises and redundant features significantly corrupt the graph. To address these limitations, we propose an Orthogonal Latent space learning with Feature weighting and Graph learning (OLFG) model for multimodal AD diagnosis. Specifically, we map multiple modalities into a common latent space by orthogonal constrained projection to capture the discriminative information for AD diagnosis. Then, a feature weighting matrix is utilized to sort the importance of features in AD diagnosis adaptively. Besides, we devise a regularization term with learned graph to preserve the local structure of the data in the latent space and integrate the graph construction into the learning processing for accurately encoding the relationships among samples. Instead of constructing a similarity graph for each modality, we learn a joint graph for multiple modalities to capture the correlations among modalities. Finally, the representations in the latent space are projected into the target space to perform AD diagnosis. An alternating optimization algorithm with proved convergence is developed to solve the optimization objective. Extensive experimental results show the effectiveness of the proposed method.

Multi-Classification Prediction of Alzheimer’s Disease based on Fusing Multi-modal Features

Conference Paper