Deep learning for Alzheimer's disease: Mapping large-scale histological tau protein for neuroimaging biomarker validation

Ushizima, Daniela; Chen, Yuheng; Alegro, Maryana; Dulce, Ovando,; Eser, Rana; Lee, WingHung; Poon, Kinson; Shankar, Anubhav; Kantamneni, Namrata; Satrawada, Shruti; Júnior, Edson Amaro; Heinsen, Helmut; Tosun, Duygu; Grinberg, Lea T.

doi:10.1016/j.neuroimage.2021.118790

Cited by 22 publications

(17 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Greve et al [ 80 ] developed a tool using CNN for segmentation of sub-cortical limbic structures for early detection of AD. Ushizima et al [ 81 ] designed a pipeline in order to extract tau associated features for AD classification using CNN.…”

Section: DL For Ad Diagnosismentioning

confidence: 99%

Deep Learning-Based Diagnosis of Alzheimer’s Disease

Saleem

Zahra

et al. 2022

JPM

View full text Add to dashboard Cite

Alzheimer’s disease (AD), the most familiar type of dementia, is a severe concern in modern healthcare. Around 5.5 million people aged 65 and above have AD, and it is the sixth leading cause of mortality in the US. AD is an irreversible, degenerative brain disorder characterized by a loss of cognitive function and has no proven cure. Deep learning techniques have gained popularity in recent years, particularly in the domains of natural language processing and computer vision. Since 2014, these techniques have begun to achieve substantial consideration in AD diagnosis research, and the number of papers published in this arena is rising drastically. Deep learning techniques have been reported to be more accurate for AD diagnosis in comparison to conventional machine learning models. Motivated to explore the potential of deep learning in AD diagnosis, this study reviews the current state-of-the-art in AD diagnosis using deep learning. We summarize the most recent trends and findings using a thorough literature review. The study also explores the different biomarkers and datasets for AD diagnosis. Even though deep learning has shown promise in AD diagnosis, there are still several challenges that need to be addressed.

show abstract

Section: DL For Ad Diagnosismentioning

confidence: 99%

Deep Learning-Based Diagnosis of Alzheimer’s Disease

Saleem

Zahra

et al. 2022

JPM

View full text Add to dashboard Cite

show abstract

“…We can see a tremendous expansion of studies in the field of neuroimaging, where DL has numerous applications and farreaching implications. Recently researchers have utilized DL for tasks such as segmentation (e.g., Zhao, 2019;Billot et al, 2020;Brown et al, 2020;Li et al, 2021;Henschel et al, 2022;Mojiri Forooshani et al, 2022;Ushizima et al, 2022) prediction of neurologic disease (e.g., Payan and Montana, 2015;Liu et al, 2017;Lu et al, 2018;Shi et al, 2018;Wang et al, 2018;Qureshi et al, 2019;Zhou et al, 2021) and psychiatric disorder (e.g., Kuang and He, 2014;Hao et al, 2015;Kim et al, 2016;Yan et al, 2017;Heinsfeld et al, 2018;Ulloa et al, 2018;Yang et al, 2021b;Loh et al, 2022;Zhao et al, 2022), trajectory of a disorder (e.g., Spasov et al, 2019;Bae et al, 2021;Dong et al, 2021;Jung et al, 2021), different tasks (e.g., Jang et al, 2017;Vu et al, 2020;Ngo et al, 2022), brain age (e.g., Levakov et al, 2020;Ren et al, 2022), personality (e.g., Bhardwaj et al, 2021), search for biomarkers (e.g., Yang et al, 2021b), motor imagery decoding (e.g., Xu et al, 2020;Dehghani et al, 2021;Fan et al, 2021), modeling different functions of the neural system (e.g., Hebling…”

Section: Deep Learningmentioning

confidence: 99%

“…For example, GBP was used by Wang et al (2020b) to study the features learned from 3DCNN, whose task was to classify task states based on fMRI data. Grad-CAM was used in studies where CNNs were used to examine features learned for AD prediction based on PET data (Ushizima et al, 2022), brain age prediction based on sMRI and blood parameters (Ren et al, 2022), emotion recognition based on electrode frequency distribution maps (Wang et al, 2020a), and comatose patient outcome based on EEG (Jonas et al, 2019). LRP was used in a study in which the authors trained a DNN to predict SCZ based on resting-state functional connectivity MRI data (Yan et al, 2017).…”

Section: Interpretationmentioning

confidence: 99%

“…While few studies have used perturbation methods (e.g., Ushizima et al, 2022), there are numerous studies that use other forms of quantitative techniques. Many studies used perturbation methods, in which the input (e.g., a brain area or functional network) is modified and the changes in the output (e.g., prediction accuracy) are examined (Vieira et al, 2017).…”

Section: Interpretationmentioning

confidence: 99%

“…In the following paragraphs we review studies that used DL for segmentation in neuroimaging. Ushizima et al (2022) applied Deep Learning to the segmentation of tau proteins in PET images, which is important for understanding the neurobiological basis of AD. Their endto-end solution was able to achieve high performance, with ROC curves ranging from 0.85 to 0.91 for different tracers.…”

Section: Segmentationmentioning

confidence: 99%

See 2 more Smart Citations

Deep learning in neuroimaging data analysis: Applications, challenges, and solutions

Avberšek

Repovš

2022

Front. Neuroimaging

View full text Add to dashboard Cite

Methods for the analysis of neuroimaging data have advanced significantly since the beginning of neuroscience as a scientific discipline. Today, sophisticated statistical procedures allow us to examine complex multivariate patterns, however most of them are still constrained by assuming inherent linearity of neural processes. Here, we discuss a group of machine learning methods, called deep learning, which have drawn much attention in and outside the field of neuroscience in recent years and hold the potential to surpass the mentioned limitations. Firstly, we describe and explain the essential concepts in deep learning: the structure and the computational operations that allow deep models to learn. After that, we move to the most common applications of deep learning in neuroimaging data analysis: prediction of outcome, interpretation of internal representations, generation of synthetic data and segmentation. In the next section we present issues that deep learning poses, which concerns multidimensionality and multimodality of data, overfitting and computational cost, and propose possible solutions. Lastly, we discuss the current reach of DL usage in all the common applications in neuroimaging data analysis, where we consider the promise of multimodality, capability of processing raw data, and advanced visualization strategies. We identify research gaps, such as focusing on a limited number of criterion variables and the lack of a well-defined strategy for choosing architecture and hyperparameters. Furthermore, we talk about the possibility of conducting research with constructs that have been ignored so far or/and moving toward frameworks, such as RDoC, the potential of transfer learning and generation of synthetic data.

show abstract

Three‐dimensional histology reveals dissociable human hippocampal long‐axis gradients of Alzheimer's pathology

Ortega‐Cruz,

Bress,

Gazula

et al. 2024

Alzheimer's & Dementia

View full text Add to dashboard Cite

INTRODUCTIONThree‐dimensional (3D) histology analyses are essential to overcome sampling variability and understand pathological differences beyond the dissection axis. We present Path2MR, the first pipeline allowing 3D reconstruction of sparse human histology without a magnetic resonance imaging (MRI) reference. We implemented Path2MR with post‐mortem hippocampal sections to explore pathology gradients in Alzheimer's disease.METHODSBlockface photographs of brain hemisphere slices are used for 3D reconstruction, from which an MRI‐like image is generated using machine learning. Histology sections are aligned to the reconstructed hemisphere and subsequently to an atlas in standard space.RESULTSPath2MR successfully registered histological sections to their anatomic position along the hippocampal longitudinal axis. Combined with histopathology quantification, we found an expected peak of tau pathology at the anterior end of the hippocampus, whereas amyloid‐beta (Aβ) displayed a quadratic anterior‐posterior distribution.CONCLUSIONPath2MR, which enables 3D histology using any brain bank data set, revealed significant differences along the hippocampus between tau and Aβ.Highlights Path2MR enables three‐dimensional (3D) brain reconstruction from blockface dissection photographs. This pipeline does not require dense specimen sampling or a subject‐specific magnetic resonance (MR) image. Anatomically consistent mapping of hippocampal sections was obtained with Path2MR. Our analyses revealed an anterior‐posterior gradient of hippocampal tau pathology. In contrast, the peak of amyloid‐beta (Aβ) deposition was closer to the hippocampal body.

show abstract

Deep learning for Alzheimer's disease: Mapping large-scale histological tau protein for neuroimaging biomarker validation

Cited by 22 publications

References 50 publications

Deep Learning-Based Diagnosis of Alzheimer’s Disease

Deep Learning-Based Diagnosis of Alzheimer’s Disease

Deep learning in neuroimaging data analysis: Applications, challenges, and solutions

Three‐dimensional histology reveals dissociable human hippocampal long‐axis gradients of Alzheimer's pathology

Contact Info

Product

Resources

About