Multi-site MRI harmonization via attention-guided deep domain adaptation for brain disorder identification

Deep learning for the harmonization of structural MRI scans: a survey

Medical imaging datasets for research are frequently collected from multiple imaging centers using different scanners, protocols, and settings. These variations affect data consistency and compatibility across different sources. Image harmonization is a critical step to mitigate the effects of factors like inherent differences between various vendors, hardware upgrades, protocol changes, and scanner calibration drift, as well as to ensure consistent data for medical image processing techniques. Given the critical importance and widespread relevance of this issue, a vast array of image harmonization methodologies have emerged, with deep learning-based approaches driving substantial advancements in recent times. The goal of this review paper is to examine the latest deep learning techniques employed for image harmonization by analyzing cutting-edge architectural approaches in the field of medical image harmonization, evaluating both their strengths and limitations. This paper begins by providing a comprehensive fundamental overview of image harmonization strategies, covering three critical aspects: established imaging datasets, commonly used evaluation metrics, and characteristics of different scanners. Subsequently, this paper analyzes recent structural MRI (Magnetic Resonance Imaging) harmonization techniques based on network architecture, network learning algorithm, network supervision strategy, and network output. The underlying architectures include U-Net, Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), flow-based generative models, transformer-based approaches, as well as custom-designed network architectures. This paper investigates the effectiveness of Disentangled Representation Learning (DRL) as a pivotal learning algorithm in harmonization. Lastly, the review highlights the primary limitations in harmonization techniques, specifically the lack of comprehensive quantitative comparisons across different methods. The overall aim of this review is to serve as a guide for researchers and practitioners to select appropriate architectures based on their specific conditions and requirements. It also aims to foster discussions around ongoing challenges in the field and shed light on promising future research directions with the potential for significant advancements.

Performance changes due to differences among annotating radiologists for training data in computerized lesion detection

PURPOSE

The quality and bias of annotations by annotators (e.g., radiologists) affect the performance changes in computer-aided detection (CAD) software using machine learning. We hypothesized that the difference in the years of experience in image interpretation among radiologists contributes to annotation variability. In this study, we focused on how the performance of CAD software changes with retraining by incorporating cases annotated by radiologists with varying experience.

METHODS

We used two types of CAD software for lung nodule detection in chest computed tomography images and cerebral aneurysm detection in magnetic resonance angiography images. Twelve radiologists with different years of experience independently annotated the lesions, and the performance changes were investigated by repeating the retraining of the CAD software twice, with the addition of cases annotated by each radiologist. Additionally, we investigated the effects of retraining using integrated annotations from multiple radiologists.

RESULTS

The performance of the CAD software after retraining differed among annotating radiologists. In some cases, the performance was degraded compared to that of the initial software. Retraining using integrated annotations showed different performance trends depending on the target CAD software, notably in cerebral aneurysm detection, where the performance decreased compared to using annotations from a single radiologist.

CONCLUSIONS

Although the performance of the CAD software after retraining varied among the annotating radiologists, no direct correlation with their experience was found. The performance trends differed according to the type of CAD software used when integrated annotations from multiple radiologists were used.

Connectional-style-guided contextual representation learning for brain disease diagnosis

Structural magnetic resonance imaging (sMRI) has shown great clinical value and has been widely used in deep learning (DL) based computer-aided brain disease diagnosis. Previous DL-based approaches focused on local shapes and textures in brain sMRI that may be significant only within a particular domain. The learned representations are likely to contain spurious information and have poor generalization ability in other diseases and datasets. To facilitate capturing meaningful and robust features, it is necessary to first comprehensively understand the intrinsic pattern of the brain that is not restricted within a single data/task domain. Considering that the brain is a complex connectome of interlinked neurons, the connectional properties in the brain have strong biological significance, which is shared across multiple domains and covers most pathological information. In this work, we propose a connectional style contextual representation learning model (CS-CRL) to capture the intrinsic pattern of the brain, used for multiple brain disease diagnosis. Specifically, it has a vision transformer (ViT) encoder and leverages mask reconstruction as the proxy task and Gram matrices to guide the representation of connectional information. It facilitates the capture of global context and the aggregation of features with biological plausibility. The results indicate that CS-CRL achieves superior accuracy in multiple brain disease diagnosis tasks across six datasets and three diseases and outperforms state-of-the-art models. Furthermore, we demonstrate that CS-CRL captures more brain-network-like properties, and better aggregates features, is easier to optimize, and is more robust to noise, which explains its superiority in theory.

Multi-Template Meta-Information Regularized Network for Alzheimer's Disease Diagnosis Using Structural MRI

Structural magnetic resonance imaging (sMRI) has been widely applied in computer-aided Alzheimer's disease (AD) diagnosis, owing to its capabilities in providing detailed brain morphometric patterns and anatomical features in vivo. Although previous works have validated the effectiveness of incorporating metadata (e.g., age, gender, and educational years) for sMRI-based AD diagnosis, existing methods solely paid attention to metadata-associated correlation to AD (e.g., gender bias in AD prevalence) or confounding effects (e.g., the issue of normal aging and metadata-related heterogeneity). Hence, it is difficult to fully excavate the influence of metadata on AD diagnosis. To address these issues, we constructed a novel Multi-template Meta-information Regularized Network (MMRN) for AD diagnosis. Specifically, considering diagnostic variation resulting from different spatial transformations onto different brain templates, we first regarded different transformations as data augmentation for self-supervised learning after template selection. Since the confounding effects may arise from excessive attention to meta-information owing to its correlation with AD, we then designed the modules of weakly supervised meta-information learning and mutual information minimization to learn and disentangle meta-information from learned class-related representations, which accounts for meta-information regularization for disease diagnosis. We have evaluated our proposed MMRN on two public multi-center cohorts, including the Alzheimer's Disease Neuroimaging Initiative (ADNI) with 1,950 subjects and the National Alzheimer's Coordinating Center (NACC) with 1,163 subjects. The experimental results have shown that our proposed method outperformed the state-of-the-art approaches in both tasks of AD diagnosis, mild cognitive impairment (MCI) conversion prediction, and normal control (NC) vs. MCI vs. AD classification.

Maximum Classifier Discrepancy Generative Adversarial Network for Jointly Harmonizing Scanner Effects and Improving Reproducibility of Downstream Tasks

OBJECTIVE

Multi-site collaboration is essential for overcoming small-sample problems when exploring reproducible biomarkers in MRI studies. However, various scanner-specific factors dramatically reduce the cross-scanner replicability. Moreover, existing harmony methods mostly could not guarantee the improved performance of downstream tasks.

METHODS

we proposed a new multi-scanner harmony framework, called 'maximum classifier discrepancy generative adversarial network', or MCD-GAN, for removing scanner effects in the original feature space while preserving substantial biological information for downstream tasks. Specifically, the adversarial generative network was utilized for persisting the structural layout of each sample, and the maximum classifier discrepancy module was introduced for regulating GAN generators by incorporating the downstream tasks.

RESULTS

We compared the MCD-GAN with other state-of-the-art data harmony approaches (e.g., ComBat, CycleGAN) on simulated data and the Adolescent Brain Cognitive Development (ABCD) dataset. Results demonstrate that MCD-GAN outperformed other approaches in improving cross-scanner classification performance while preserving the anatomical layout of the original images.

SIGNIFICANCE

To the best of our knowledge, the proposed MCD-GAN is the first generative model which incorporates downstream tasks while harmonizing, and is a promising solution for facilitating cross-site reproducibility in various tasks such as classification and regression.

Deep learning for unsupervised domain adaptation in medical imaging: Recent advancements and future perspectives

Deep learning has demonstrated remarkable performance across various tasks in medical imaging. However, these approaches primarily focus on supervised learning, assuming that the training and testing data are drawn from the same distribution. Unfortunately, this assumption may not always hold true in practice. To address these issues, unsupervised domain adaptation (UDA) techniques have been developed to transfer knowledge from a labeled domain to a related but unlabeled domain. In recent years, significant advancements have been made in UDA, resulting in a wide range of methodologies, including feature alignment, image translation, self-supervision, and disentangled representation methods, among others. In this paper, we provide a comprehensive literature review of recent deep UDA approaches in medical imaging from a technical perspective. Specifically, we categorize current UDA research in medical imaging into six groups and further divide them into finer subcategories based on the different tasks they perform. We also discuss the respective datasets used in the studies to assess the divergence between the different domains. Finally, we discuss emerging areas and provide insights and discussions on future research directions to conclude this survey.

Image harmonization improves consistency of intra-rater delineations of MS lesions in heterogeneous MRI

Clinical magnetic resonance images (MRIs) lack a standard intensity scale due to differences in scanner hardware and the pulse sequences used to acquire the images. When MRIs are used for quantification, as in the evaluation of white matter lesions (WMLs) in multiple sclerosis, this lack of intensity standardization becomes a critical problem affecting both the staging and tracking of the disease and its treatment. This paper presents a study of harmonization on WML segmentation consistency, which is evaluated using an object detection classification scheme that incorporates manual delineations from both the original and harmonized MRIs. A cohort of ten people scanned on two different imaging platforms was studied. An expert rater, blinded to the image source, manually delineated WMLs on images from both scanners before and after harmonization. It was found that there is closer agreement in both global and per-lesion WML volume and spatial distribution after harmonization, demonstrating the importance of image harmonization prior to the creation of manual delineations. These results could lead to better truth models in both the development and evaluation of automated lesion segmentation algorithms.

Strategies for Implementing Machine Learning Algorithms in the Clinical Practice of Radiology

Despite recent advancements in machine learning (ML) applications in health care, there have been few benefits and improvements to clinical medicine in the hospital setting. To facilitate clinical adaptation of methods in ML, this review proposes a standardized framework for the step-by-step implementation of artificial intelligence into the clinical practice of radiology that focuses on three key components: problem identification, stakeholder alignment, and pipeline integration. A review of the recent literature and empirical evidence in radiologic imaging applications justifies this approach and offers a discussion on structuring implementation efforts to help other hospital practices leverage ML to improve patient care. Clinical trial registration no. 04242667 © RSNA, 2024 Supplemental material is available for this article.

Toward hippocampal volume measures on ultra-high field magnetic resonance imaging: a comprehensive comparison study between deep learning and conventional approaches

The hippocampus is a complex brain structure that plays an important role in various cognitive aspects such as memory, intelligence, executive function, and path integration. The volume of this highly plastic structure is identified as one of the most important biomarkers of specific neuropsychiatric and neurodegenerative diseases. It has also been extensively investigated in numerous aging studies. However, recent studies on aging show that the performance of conventional approaches in measuring the hippocampal volume is still far from satisfactory, especially in terms of delivering longitudinal measures from ultra-high field magnetic resonance images (MRIs), which can visualize more boundary details. The advancement of deep learning provides an alternative solution to measuring the hippocampal volume. In this work, we comprehensively compared a deep learning pipeline based on nnU-Net with several conventional approaches including Freesurfer, FSL and DARTEL, for automatically delivering hippocampal volumes: (1) Firstly, we evaluated the segmentation accuracy and precision on a public dataset through cross-validation. Results showed that the deep learning pipeline had the lowest mean (L = 1.5%, R = 1.7%) and the lowest standard deviation (L = 5.2%, R = 6.2%) in terms of volume percentage error. (2) Secondly, sub-millimeter MRIs of a group of healthy adults with test-retest 3T and 7T sessions were used to extensively assess the test-retest reliability. Results showed that the deep learning pipeline achieved very high intraclass correlation coefficients (L = 0.990, R = 0.986 for 7T; L = 0.985, R = 0.983 for 3T) and very small volume percentage differences (L = 1.2%, R = 0.9% for 7T; L = 1.3%, R = 1.3% for 3T). (3) Thirdly, a Bayesian linear mixed effect model was constructed with respect to the hippocampal volumes of two healthy adult datasets with longitudinal 7T scans and one disease-related longitudinal dataset. It was found that the deep learning pipeline detected both the subtle and disease-related changes over time with high sensitivity as well as the mild differences across subjects. Comparison results from the aforementioned three aspects showed that the deep learning pipeline significantly outperformed the conventional approaches by large margins. Results also showed that the deep learning pipeline can better accommodate longitudinal analysis purposes.

Federated Domain Adaptation via Transformer for Multi-Site Alzheimer's Disease Diagnosis

In multi-site studies of Alzheimer's disease (AD), the difference of data in multi-site datasets leads to the degraded performance of models in the target sites. The traditional domain adaptation method requires sharing data from both source and target domains, which will lead to data privacy issue. To solve it, federated learning is adopted as it can allow models to be trained with multi-site data in a privacy-protected manner. In this paper, we propose a multi-site federated domain adaptation framework via Transformer (FedDAvT), which not only protects data privacy, but also eliminates data heterogeneity. The Transformer network is used as the backbone network to extract the correlation between the multi-template region of interest features, which can capture the brain abundant information. The self-attention maps in the source and target domains are aligned by applying mean squared error for subdomain adaptation. Finally, we evaluate our method on the multi-site databases based on three AD datasets. The experimental results show that the proposed FedDAvT is quite effective, achieving accuracy rates of 88.75%, 69.51%, and 69.88% on the AD vs. NC, MCI vs. NC, and AD vs. MCI two-way classification tasks, respectively.

A three-dimensional deep learning model for inter-site harmonization of structural MR images of the brain: Extensive validation with a multicenter dataset

In multicenter MRI studies, pooling the imaging data can introduce site-related variabilities and can therefore bias the subsequent analyses. To harmonize the intensity distributions of brain MR images in a multicenter dataset, unsupervised deep learning methods can be employed. Here, we developed a model based on cycle-consistent adversarial networks for the harmonization of T1-weighted brain MR images. In contrast to previous works, it was designed to process three-dimensional whole-brain images in a stable manner while optimizing computation resources. Using six different MRI datasets for healthy adults (n=1525 in total) with different acquisition parameters, we tested the model in (i) three pairwise harmonizations with site effects of various sizes, (ii) an overall harmonization of the six datasets with different age distributions, and (iii) a traveling-subject dataset. Our results for intensity distributions, brain volumes, image quality metrics and radiomic features indicated that the MRI characteristics at the various sites had been effectively homogenized. Next, brain age prediction experiments and the observed correlation between the gray-matter volume and age showed that thanks to an appropriate training strategy and despite biological differences between the dataset populations, the model reinforced biological patterns. Furthermore, radiologic analyses of the harmonized images attested to the conservation of the radiologic information in the original images. The robustness of the harmonization model (as judged with various datasets and metrics) demonstrates its potential for application in retrospective multicenter studies.

Style transfer generative adversarial networks to harmonize multisite MRI to a single reference image to avoid overcorrection

Recent work within neuroimaging consortia have aimed to identify reproducible, and often subtle, brain signatures of psychiatric or neurological conditions. To allow for high-powered brain imaging analyses, it is often necessary to pool MR images that were acquired with different protocols across multiple scanners. Current retrospective harmonization techniques have shown promise in removing site-related image variation. However, most statistical approaches may over-correct for technical, scanning-related, variation as they cannot distinguish between confounded image-acquisition based variability and site-related population variability. Such statistical methods often require that datasets contain subjects or patient groups with similar clinical or demographic information to isolate the acquisition-based variability. To overcome this limitation, we consider site-related magnetic resonance (MR) imaging harmonization as a style transfer problem rather than a domain transfer problem. Using a fully unsupervised deep-learning framework based on a generative adversarial network (GAN), we show that MR images can be harmonized by inserting the style information encoded from a single reference image, without knowing their site/scanner labels a priori. We trained our model using data from five large-scale multisite datasets with varied demographics. Results demonstrated that our style-encoding model can harmonize MR images, and match intensity profiles, without relying on traveling subjects. This model also avoids the need to control for clinical, diagnostic, or demographic information. We highlight the effectiveness of our method for clinical research by comparing extracted cortical and subcortical features, brain-age estimates, and case-control effect sizes before and after the harmonization. We showed that our harmonization removed the site-related variances, while preserving the anatomical information and clinical meaningful patterns. We further demonstrated that with a diverse training set, our method successfully harmonized MR images collected from unseen scanners and protocols, suggesting a promising tool for ongoing collaborative studies. Source code is released in USC-IGC/style_transfer_harmonization (github.com).

Structural MRI Harmonization via Disentangled Latent Energy-Based Style Translation

Multi-site brain magnetic resonance imaging (MRI) has been widely used in clinical and research domains, but usually is sensitive to non-biological variations caused by site effects (e.g., field strengths and scanning protocols). Several retrospective data harmonization methods have shown promising results in removing these non-biological variations at feature or whole-image level. Most existing image-level harmonization methods are implemented through generative adversarial networks, which are generally computationally expensive and generalize poorly on independent data. To this end, this paper proposes a disentangled latent energy-based style translation (DLEST) framework for image-level structural MRI harmonization. Specifically, DLEST disentangles site-invariant image generation and site-specific style translation via a latent autoencoder and an energy-based model. The autoencoder learns to encode images into low-dimensional latent space, and generates faithful images from latent codes. The energy-based model is placed in between the encoding and generation steps, facilitating style translation from a source domain to a target domain implicitly. This allows highly generalizable image generation and efficient style translation through the latent space. We train our model on 4,092 T1-weighted MRIs in 3 tasks: histogram comparison, acquisition site classification, and brain tissue segmentation. Qualitative and quantitative results demonstrate the superiority of our approach, which generally outperforms several state-of-the-art methods.

Subtype classification of attention deficit hyperactivity disorder with hierarchical binary hypothesis testing framework

Objective. The diagnosis of attention deficit hyperactivity disorder (ADHD) subtypes is important for the refined treatment of ADHD children. Although automated diagnosis methods based on machine learning are performed with structural and functional magnetic resonance imaging (sMRI and fMRI) data which have full observation of brains, they are not satisfactory with the accuracy of less than80%for the ADHD subtype diagnosis.Approach. To improve the accuracy and obtain the biomarker of ADHD subtypes, we proposed a hierarchical binary hypothesis testing (H-BHT) framework by using brain functional connectivity (FC) as input bio-signals. The framework includes a two-stage procedure with a decision tree strategy and thus becomes suitable for the subtype classification. Also, typical FC is extracted in both two stages of identifying ADHD subtypes. That means the important FC is found out for the subtype recognition.Main results. We apply the proposed H-BHT framework to resting state fMRI datasets from ADHD-200 consortium. The results are achieved with the average accuracy97.1%and an average kappa score 0.947. Discriminative FC between ADHD subtypes is found by comparing the P-values of typical FC.Significance. The proposed framework not only is an effective structure for ADHD subtype classification, but also provides useful reference for multiclass classification of mental disease subtypes.

Improving Alzheimer's Disease Diagnosis With Multi-Modal PET Embedding Features by a 3D Multi-Task MLP-Mixer Neural Network

Positron emission tomography (PET) with fluorodeoxyglucose (FDG) or florbetapir (AV45) has been proved effective in the diagnosis of Alzheimer's disease. However, the expensive and radioactive nature of PET has limited its application. Here, employing multi-layer perceptron mixer architecture, we present a deep learning model, namely 3-dimensional multi-task multi-layer perceptron mixer, for simultaneously predicting the standardized uptake value ratios (SUVRs) for FDG-PET and AV45-PET from the cheap and widely used structural magnetic resonance imaging data, and the model can be further used for Alzheimer's disease diagnosis based on embedding features derived from SUVR prediction. Experiment results demonstrate the high prediction accuracy of the proposed method for FDG/AV45-PET SUVRs, where we achieved Pearson's correlation coefficients of 0.66 and 0.61 respectively between the estimated and actual SUVR and the estimated SUVRs also show high sensitivity and distinct longitudinal patterns for different disease status. By taking into account PET embedding features, the proposed method outperforms other competing methods on five independent datasets in the diagnosis of Alzheimer's disease and discriminating between stable and progressive mild cognitive impairments, achieving the area under receiver operating characteristic curves of 0.968 and 0.776 respectively on ADNI dataset, and generalizes better to other external datasets. Moreover, the top-weighted patches extracted from the trained model involve important brain regions related to Alzheimer's disease, suggesting good biological interpretability of our proposed method."

ImUnity: A generalizable VAE-GAN solution for multicenter MR image harmonization

ImUnity is an original 2.5D deep-learning model designed for efficient and flexible MR image harmonization. A VAE-GAN network, coupled with a confusion module and an optional biological preservation module, uses multiple 2D slices taken from different anatomical locations in each subject of the training database, as well as image contrast transformations for its training. It eventually generates 'corrected' MR images that can be used for various multi-center population studies. Using 3 open source databases (ABIDE, OASIS and SRPBS), which contain MR images from multiple acquisition scanner types or vendors and a large range of subjects ages, we show that ImUnity: (1) outperforms state-of-the-art methods in terms of quality of images generated using traveling subjects; (2) removes sites or scanner biases while improving patients classification; (3) harmonizes data coming from new sites or scanners without the need for an additional fine-tuning and (4) allows the selection of multiple MR reconstructed images according to the desired applications. Tested here on T1-weighted images, ImUnity could be used to harmonize other types of medical images.

Challenges of implementing computer-aided diagnostic models for neuroimages in a clinical setting

Advances in artificial intelligence have cultivated a strong interest in developing and validating the clinical utilities of computer-aided diagnostic models. Machine learning for diagnostic neuroimaging has often been applied to detect psychological and neurological disorders, typically on small-scale datasets or data collected in a research setting. With the collection and collation of an ever-growing number of public datasets that researchers can freely access, much work has been done in adapting machine learning models to classify these neuroimages by diseases such as Alzheimer's, ADHD, autism, bipolar disorder, and so on. These studies often come with the promise of being implemented clinically, but despite intense interest in this topic in the laboratory, limited progress has been made in clinical implementation. In this review, we analyze challenges specific to the clinical implementation of diagnostic AI models for neuroimaging data, looking at the differences between laboratory and clinical settings, the inherent limitations of diagnostic AI, and the different incentives and skill sets between research institutions, technology companies, and hospitals. These complexities need to be recognized in the translation of diagnostic AI for neuroimaging from the laboratory to the clinic.

Image harmonization: A review of statistical and deep learning methods for removing batch effects and evaluation metrics for effective harmonization

Magnetic resonance imaging and computed tomography from multiple batches (e.g. sites, scanners, datasets, etc.) are increasingly used alongside complex downstream analyses to obtain new insights into the human brain. However, significant confounding due to batch-related technical variation, called batch effects, is present in this data; direct application of downstream analyses to the data may lead to biased results. Image harmonization methods seek to remove these batch effects and enable increased generalizability and reproducibility of downstream results. In this review, we describe and categorize current approaches in statistical and deep learning harmonization methods. We also describe current evaluation metrics used to assess harmonization methods and provide a standardized framework to evaluate newly-proposed methods for effective harmonization and preservation of biological information. Finally, we provide recommendations to end-users to advocate for more effective use of current methods and to methodologists to direct future efforts and accelerate development of the field.

Fused Brain Functional Connectivity Network and Edge-attention Graph Convolution Network for Fibromyalgia Syndrome Diagnosis

Fibromyalgia syndrome (FMS) is a type of rheumatology that seriously affects the normal life of patients. Due to the complex clinical manifestations of FMS, it is challenging to detect FMS. Therefore, an automatic FMS diagnosis model is urgently needed to assist physicians. Brain functional connectivity networks (BFCNs) constructed by resting-state functional magnetic resonance imaging (rs-fMRI) to describe brain functions have been widely used to identify individuals with relevant diseases from normal control (NC). Therefore, we propose a novel model based on BFCN and graph convolutional network (GCN) for automatic FMS diagnosis. Firstly, a novel fused BFCN method is proposed by fusing Pearson's correlation (PC) and low-rank (LR) BFCN, which retains information and reduces data redundancy to construct BFCN. Then we combine the feature of BFCN with non-image information of subjects to obtain nodes and adjacency matrices, which builds a graph with edge attention. Finally, the graph is sent to the GCN layer for FMS diagnosis. Our model is evaluated on the in-house FMS dataset to achieve 82.48% accuracy. The experimental results show that our method outperforms the state-of-the-art competing methods.

Unpaired, unsupervised domain adaptation assumes your domains are already similar

Unsupervised domain adaptation is a popular method in medical image analysis, but it can be tricky to make it work: without labels to link the domains, domains must be matched using feature distributions. If there is no additional information, this often leaves a choice between multiple possibilities to map the data that may be equally likely but not equally correct. In this paper we explore the fundamental problems that may arise in unsupervised domain adaptation, and discuss conditions that might still make it work. Focusing on medical image analysis, we argue that images from different domains may have similar class balance, similar intensities, similar spatial structure, or similar textures. We demonstrate how these implicit conditions can affect domain adaptation performance in experiments with synthetic data, MNIST digits, and medical images. We observe that practical success of unsupervised domain adaptation relies on existing similarities in the data, and is anything but guaranteed in the general case. Understanding these implicit assumptions is a key step in identifying potential problems in domain adaptation and improving the reliability of the results.

Comprehensive evaluation of harmonization on functional brain imaging for multisite data-fusion

To embrace big-data neuroimaging, harmonizing the site effect in resting-state functional magnetic resonance imaging (R-fMRI) data fusion is a fundamental challenge. A comprehensive evaluation of potentially effective harmonization strategies, particularly with specifically collected data, has been scarce, especially for R-fMRI metrics. Here, we comprehensively assess harmonization strategies from multiple perspectives, including tests on residual site effect, individual identification, test-retest reliability, and replicability of group-level statistical results, on widely used R-fMRI metrics across various datasets, including data obtained from participants with repetitive measures at different scanners. For individual identifiability (i.e., whether the same subject could be identified across R-fMRI data scanned across different sites), we found that, while most methods decreased site effects, the Subsampling Maximum-mean-distance based distribution shift correction Algorithm (SMA) and parametric unadjusted CovBat outperformed linear regression models, linear mixed models, ComBat series and invariant conditional variational auto-encoder in clustering accuracy. Test-retest reliability was better for SMA and parametric adjusted CovBat than unadjusted ComBat series and parametric unadjusted CovBat in the number of overlapped voxels. At the same time, SMA was superior to the latter in replicability in terms of the Dice coefficient and the scale of brain areas showing sex differences reproducibly observed across datasets. Furthermore, SMA better detected reproducible sex differences of ALFF under the site-sex confounded situation. Moreover, we designed experiments to identify the best target site features to optimize SMA identifiability, test-retest reliability, and stability. We noted both sample size and distribution of the target site matter and introduced a heuristic formula for selecting the target site. In addition to providing practical guidelines, this work can inform continuing improvements and innovations in harmonizing methodologies for big R-fMRI data.

SAN-Net: Learning generalization to unseen sites for stroke lesion segmentation with self-adaptive normalization

There are considerable interests in automatic stroke lesion segmentation on magnetic resonance (MR) images in the medical imaging field, as stroke is an important cerebrovascular disease. Although deep learning-based models have been proposed for this task, generalizing these models to unseen sites is difficult due to not only the large inter-site discrepancy among different scanners, imaging protocols, and populations, but also the variations in stroke lesion shape, size, and location. To tackle this issue, we introduce a self-adaptive normalization network, termed SAN-Net, to achieve adaptive generalization on unseen sites for stroke lesion segmentation. Motivated by traditional z-score normalization and dynamic network, we devise a masked adaptive instance normalization (MAIN) to minimize inter-site discrepancies, which standardizes input MR images from different sites into a site-unrelated style by dynamically learning affine parameters from the input; i.e., MAIN can affinely transform the intensity values. Then, we leverage a gradient reversal layer to force the U-net encoder to learn site-invariant representation with a site classifier, which further improves the model generalization in conjunction with MAIN. Finally, inspired by the "pseudosymmetry" of the human brain, we introduce a simple yet effective data augmentation technique, termed symmetry-inspired data augmentation (SIDA), that can be embedded within SAN-Net to double the sample size while halving memory consumption. Experimental results on the benchmark Anatomical Tracings of Lesions After Stroke (ATLAS) v1.2 dataset, which includes MR images from 9 different sites, demonstrate that under the "leave-one-site-out" setting, the proposed SAN-Net outperforms recently published methods in terms of quantitative metrics and qualitative comparisons.

Machine Learning for Brain MRI Data Harmonisation: A Systematic Review

BACKGROUND

Magnetic Resonance Imaging (MRI) data collected from multiple centres can be heterogeneous due to factors such as the scanner used and the site location. To reduce this heterogeneity, the data needs to be harmonised. In recent years, machine learning (ML) has been used to solve different types of problems related to MRI data, showing great promise.

OBJECTIVE

This study explores how well various ML algorithms perform in harmonising MRI data, both implicitly and explicitly, by summarising the findings in relevant peer-reviewed articles. Furthermore, it provides guidelines for the use of current methods and identifies potential future research directions.

METHOD

This review covers articles published through PubMed, Web of Science, and IEEE databases through June 2022. Data from studies were analysed based on the criteria of Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA). Quality assessment questions were derived to assess the quality of the included publications.

RESULTS

a total of 41 articles published between 2015 and 2022 were identified and analysed. In the review, MRI data has been found to be harmonised either in an implicit (n = 21) or an explicit (n = 20) way. Three MRI modalities were identified: structural MRI (n = 28), diffusion MRI (n = 7) and functional MRI (n = 6).

CONCLUSION

Various ML techniques have been employed to harmonise different types of MRI data. There is currently a lack of consistent evaluation methods and metrics used across studies, and it is recommended that the issue be addressed in future studies. Harmonisation of MRI data using ML shows promises in improving performance for ML downstream tasks, while caution should be exercised when using ML-harmonised data for direct interpretation.

Multimodal cross enhanced fusion network for diagnosis of Alzheimer's disease and subjective memory complaints

Deep learning methods using multimodal imagings have been proposed for the diagnosis of Alzheimer's disease (AD) and its early stages (SMC, subjective memory complaints), which may help to slow the progression of the disease through early intervention. However, current fusion methods for multimodal imagings are generally coarse and may lead to suboptimal results through the use of shared extractors or simple downscaling stitching. Another issue with diagnosing brain diseases is that they often affect multiple areas of the brain, making it important to consider potential connections throughout the brain. However, traditional convolutional neural networks (CNNs) may struggle with this issue due to their limited local receptive fields. To address this, many researchers have turned to transformer networks, which can provide global information about the brain but can be computationally intensive and perform poorly on small datasets. In this work, we propose a novel lightweight network called MENet that adaptively recalibrates the multiscale long-range receptive field to localize discriminative brain regions in a computationally efficient manner. Based on this, the network extracts the intensity and location responses between structural magnetic resonance imagings (sMRI) and 18-Fluoro-Deoxy-Glucose Positron Emission computed Tomography (FDG-PET) as an enhancement fusion for AD and SMC diagnosis. Our method is evaluated on the publicly available ADNI datasets and achieves 97.67% accuracy in AD diagnosis tasks and 81.63% accuracy in SMC diagnosis tasks using sMRI and FDG-PET. These results achieve state-of-the-art (SOTA) performance in both tasks. To the best of our knowledge, this is one of the first deep learning research methods for SMC diagnosis with FDG-PET.

MPS-FFA: A multiplane and multiscale feature fusion attention network for Alzheimer's disease prediction with structural MRI

Structural magnetic resonance imaging (sMRI) is a popular technique that is widely applied in Alzheimer's disease (AD) diagnosis. However, only a few structural atrophy areas in sMRI scans are highly associated with AD. The degree of atrophy in patients' brain tissues and the distribution of lesion areas differ among patients. Therefore, a key challenge in sMRI-based AD diagnosis is identifying discriminating atrophy features. Hence, we propose a multiplane and multiscale feature-level fusion attention (MPS-FFA) model. The model has three components, (1) A feature encoder uses a multiscale feature extractor with hybrid attention layers to simultaneously capture and fuse multiple pathological features in the sagittal, coronal, and axial planes. (2) A global attention classifier combines clinical scores and two global attention layers to evaluate the feature impact scores and balance the relative contributions of different feature blocks. (3) A feature similarity discriminator minimizes the feature similarities among heterogeneous labels to enhance the ability of the network to discriminate atrophy features. The MPS-FFA model provides improved interpretability for identifying discriminating features using feature visualization. The experimental results on the baseline sMRI scans from two databases confirm the effectiveness (e.g., accuracy and generalizability) of our method in locating pathological locations. The source code is available at https://github.com/LiuFei-AHU/MPSFFA.

B-mode ultrasound based CAD for liver cancers via multi-view privileged information learning

B-mode ultrasound-based computer-aided diagnosis model can help sonologists improve the diagnostic performance for liver cancers, but it generally suffers from the bottleneck due to the limited structure and internal echogenicity information in B-mode ultrasound images. Contrast-enhanced ultrasound images provide additional diagnostic information on dynamic blood perfusion of liver lesions for B-mode ultrasound images with improved diagnostic accuracy. Since transfer learning has indicated its effectiveness in promoting the performance of target computer-aided diagnosis model by transferring knowledge from related imaging modalities, a multi-view privileged information learning framework is proposed to improve the diagnostic accuracy of the single-modal B-mode ultrasound-based diagnosis for liver cancers. This framework can make full use of the shared label information between the paired B-mode ultrasound images and contrast-enhanced ultrasound images to guide knowledge transfer It consists of a novel supervised dual-view deep Boltzmann machine and a new deep multi-view SVM algorithm. The former is developed to implement knowledge transfer from the multi-phase contrast-enhanced ultrasound images to the B-mode ultrasound-based diagnosis model via a feature-level learning using privileged information paradigm, which is totally different from the existing learning using privileged information paradigm that performs knowledge transfer in the classifier. The latter further fuses and enhances feature representation learned from three pre-trained supervised dual-view deep Boltzmann machine networks for the classification task. An experiment is conducted on a bimodal ultrasound liver cancer dataset. The experimental results show that the proposed framework outperforms all the compared algorithms with the best classification accuracy of 88.91 ± 1.52%, sensitivity of 88.31 ± 2.02%, and specificity of 89.50 ± 3.12%. It suggests the effectiveness of our proposed MPIL framework for the BUS-based CAD of liver cancers.

Prototype-guided multi-scale domain adaptation for Alzheimer's disease detection

Alzheimer's disease (AD) is the most common form of dementia and there is no effective treatment currently. Using artificial intelligence technology to assist the diagnosis and intervention as early as possible is of great significance to delay the development of AD. Structural Magnetic Resonance Imaging (sMRI) has shown great practical values on computer-aided AD diagnosis. Affected by data from different sources or acquisition domains in realistic scenarios, MRI data often suffer from domain shift problem. In this paper, we propose a deep Prototype-Guided Multi-Scale Domain Adaptation (PMDA) framework to handle MRI data with domain shift problem, and realize automatic auxiliary diagnosis of AD, Mild Cognitive Impairment (MCI) and Cognitively Normal (CN). PMDA is composed of three modules: (1) MRI multi-scale feature extraction module combines the advantages of 3D convolution and self-attention to effectively extract multi-scale features in high-dimensional space, (2) Prototype Maximum Density Divergence (Pro-MDD) module adopts prototype learning to constrain the feature outlier samples in a mini-batch when MDD is used to align source domain and target domain, and (3) Adversarial Domain Adaptation module is applied to achieve global feature alignment of the source domain and target domain and co-training two distinctive discriminators to mitigate the over-fitting issue. Experiments have been performed on 3T and 1.5T sMRI with domain shift in ADNI dataset. The experimental results demonstrated that the proposed framework PMDA outperforms supervised learning methods and several state-of-the-art domain adaptation methods and achieves a superior accuracy of 92.11%, 76.01% and 82.37% on AD vs. CN, AD vs. MCI, and MCI vs. CN tasks, respectively.

DomainATM: Domain adaptation toolbox for medical data analysis

Domain adaptation (DA) is an important technique for modern machine learning-based medical data analysis, which aims at reducing distribution differences between different medical datasets. A proper domain adaptation method can significantly enhance the statistical power by pooling data acquired from multiple sites/centers. To this end, we have developed the Domain Adaptation Toolbox for Medical data analysis (DomainATM) - an open-source software package designed for fast facilitation and easy customization of domain adaptation methods for medical data analysis. The DomainATM is implemented in MATLAB with a user-friendly graphical interface, and it consists of a collection of popular data adaptation algorithms that have been extensively applied to medical image analysis and computer vision. With DomainATM, researchers are able to facilitate fast feature-level and image-level adaptation, visualization and performance evaluation of different adaptation methods for medical data analysis. More importantly, the DomainATM enables the users to develop and test their own adaptation methods through scripting, greatly enhancing its utility and extensibility. An overview characteristic and usage of DomainATM is presented and illustrated with three example experiments, demonstrating its effectiveness, simplicity, and flexibility. The software, source code, and manual are available online.

Generative adversarial network constrained multiple loss autoencoder: A deep learning-based individual atrophy detection for Alzheimer's disease and mild cognitive impairment

Exploring individual brain atrophy patterns is of great value in precision medicine for Alzheimer's disease (AD) and mild cognitive impairment (MCI). However, the current individual brain atrophy detection models are deficient. Here, we proposed a framework called generative adversarial network constrained multiple loss autoencoder (GANCMLAE) for precisely depicting individual atrophy patterns. The GANCMLAE model was trained using normal controls (NCs) from the Alzheimer's Disease Neuroimaging Initiative cohort, and the Xuanwu cohort was employed to validate the robustness of the model. The potential of the model for identifying different atrophy patterns of MCI subtypes was also assessed. Furthermore, the clinical application potential of the GANCMLAE model was investigated. The results showed that the model can achieve good image reconstruction performance on the structural similarity index measure (0.929 ± 0.003), peak signal-to-noise ratio (31.04 ± 0.09), and mean squared error (0.0014 ± 0.0001) with less latent loss in the Xuanwu cohort. The individual atrophy patterns extracted from this model are more precise in reflecting the clinical symptoms of MCI subtypes. The individual atrophy patterns exhibit a better discriminative power in identifying patients with AD and MCI from NCs than those of the t-test model, with areas under the receiver operating characteristic curve of 0.867 (95%: 0.837-0.897) and 0.752 (95%: 0.71-0.790), respectively. Similar findings are also reported in the AD and MCI subgroups. In conclusion, the GANCMLAE model can serve as an effective tool for individualised atrophy detection.

Multicenter and Multichannel Pooling GCN for Early AD Diagnosis Based on Dual-Modality Fused Brain Network

For significant memory concern (SMC) and mild cognitive impairment (MCI), their classification performance is limited by confounding features, diverse imaging protocols, and limited sample size. To address the above limitations, we introduce a dual-modality fused brain connectivity network combining resting-state functional magnetic resonance imaging (fMRI) and diffusion tensor imaging (DTI), and propose three mechanisms in the current graph convolutional network (GCN) to improve classifier performance. First, we introduce a DTI-strength penalty term for constructing functional connectivity networks. Stronger structural connectivity and bigger structural strength diversity between groups provide a higher opportunity for retaining connectivity information. Second, a multi-center attention graph with each node representing a subject is proposed to consider the influence of data source, gender, acquisition equipment, and disease status of those training samples in GCN. The attention mechanism captures their different impacts on edge weights. Third, we propose a multi-channel mechanism to improve filter performance, assigning different filters to features based on feature statistics. Applying those nodes with low-quality features to perform convolution would also deteriorate filter performance. Therefore, we further propose a pooling mechanism, which introduces the disease status information of those training samples to evaluate the quality of nodes. Finally, we obtain the final classification results by inputting the multi-center attention graph into the multi-channel pooling GCN. The proposed method is tested on three datasets (i.e., an ADNI 2 dataset, an ADNI 3 dataset, and an in-house dataset). Experimental results indicate that the proposed method is effective and superior to other related algorithms, with a mean classification accuracy of 93.05% in our binary classification tasks. Our code is available at: https://github.com/Xuegang-S.

Deep Learning for Image Enhancement and Correction in Magnetic Resonance Imaging-State-of-the-Art and Challenges

Magnetic resonance imaging (MRI) provides excellent soft-tissue contrast for clinical diagnoses and research which underpin many recent breakthroughs in medicine and biology. The post-processing of reconstructed MR images is often automated for incorporation into MRI scanners by the manufacturers and increasingly plays a critical role in the final image quality for clinical reporting and interpretation. For image enhancement and correction, the post-processing steps include noise reduction, image artefact correction, and image resolution improvements. With the recent success of deep learning in many research fields, there is great potential to apply deep learning for MR image enhancement, and recent publications have demonstrated promising results. Motivated by the rapidly growing literature in this area, in this review paper, we provide a comprehensive overview of deep learning-based methods for post-processing MR images to enhance image quality and correct image artefacts. We aim to provide researchers in MRI or other research fields, including computer vision and image processing, a literature survey of deep learning approaches for MR image enhancement. We discuss the current limitations of the application of artificial intelligence in MRI and highlight possible directions for future developments. In the era of deep learning, we highlight the importance of a critical appraisal of the explanatory information provided and the generalizability of deep learning algorithms in medical imaging.

General psychopathology factor (p-factor) prediction using resting-state functional connectivity and a scanner-generalization neural network

The general psychopathology factor (p-factor) represents shared variance across mental disorders based on psychopathologic symptoms. The Adolescent Brain Cognitive Development (ABCD) Study offers an unprecedented opportunity to investigate functional networks (FNs) from functional magnetic resonance imaging (fMRI) associated with the psychopathology of an adolescent cohort (n > 10,000). However, the heterogeneities associated with the use of multiple sites and multiple scanners in the ABCD Study need to be overcome to improve the prediction of the p-factor using fMRI. We proposed a scanner-generalization neural network (SGNN) to predict the individual p-factor by systematically reducing the scanner effect for resting-state functional connectivity (RSFC). We included 6905 adolescents from 18 sites whose fMRI data were collected using either Siemens or GE scanners. The p-factor was estimated based on the Child Behavior Checklist (CBCL) scores available in the ABCD study using exploratory factor analysis. We evaluated the Pearson's correlation coefficients (CCs) for p-factor prediction via leave-one/two-site-out cross-validation (LOSOCV/LTSOCV) and identified important FNs from the weight features (WFs) of the SGNN. The CCs were higher for the SGNN than for alternative models when using both LOSOCV (0.1631 ± 0.0673 for the SGNN vs. 0.1497 ± 0.0710 for kernel ridge regression [KRR]; p < 0.05 from a two-tailed paired t-test) and LTSOCV (0.1469 ± 0.0381 for the SGNN vs. 0.1394 ± 0.0359 for KRR; p = 0.01). It was found that (a) the default-mode and dorsal attention FNs were important for p-factor prediction, and (b) the intra-visual FN was important for scanner generalization. We demonstrated the efficacy of our novel SGNN model for p-factor prediction while simultaneously eliminating scanner-related confounding effects for RSFC.

[Applications of Artificial Intelligence in MR Image Acquisition and Reconstruction]

Recently, artificial intelligence (AI) technology has shown potential clinical utility in a wide range of MRI fields. In particular, AI models for improving the efficiency of the image acquisition process and the quality of reconstructed images are being actively developed by the MR research community. AI is expected to further reduce acquisition times in various MRI protocols used in clinical practice when compared to current parallel imaging techniques. Additionally, AI can help with tasks such as planning, parameter optimization, artifact reduction, and quality assessment. Furthermore, AI is being actively applied to automate MR image analysis such as image registration, segmentation, and object detection. For this reason, it is important to consider the effects of protocols or devices in MR image analysis. In this review article, we briefly introduced issues related to AI application of MR image acquisition and reconstruction.

Resting-State Functional MRI Adaptation with Attention Graph Convolution Network for Brain Disorder Identification

Multi-site resting-state functional magnetic resonance imaging (rs-fMRI) data can facilitate learning-based approaches to train reliable models on more data. However, significant data heterogeneity between imaging sites, caused by different scanners or protocols, can negatively impact the generalization ability of learned models. In addition, previous studies have shown that graph convolution neural networks (GCNs) are effective in mining fMRI biomarkers. However, they generally ignore the potentially different contributions of brain regions- of-interest (ROIs) to automated disease diagnosis/prognosis. In this work, we propose a multi-site rs-fMRI adaptation framework with attention GCN (A2GCN) for brain disorder identification. Specifically, the proposed A2GCN consists of three major components: (1) a node representation learning module based on GCN to extract rs-fMRI features from functional connectivity networks, (2) a node attention mechanism module to capture the contributions of ROIs, and (3) a domain adaptation module to alleviate the differences in data distribution between sites through the constraint of mean absolute error and covariance. The A2GCN not only reduces data heterogeneity across sites, but also improves the interpretability of the learning algorithm by exploring important ROIs. Experimental results on the public ABIDE database demonstrate that our method achieves remarkable performance in fMRI-based recognition of autism spectrum disorders.

Fast Image-Level MRI Harmonization via Spectrum Analysis

Pooling structural magnetic resonance imaging (MRI) data from different imaging sites helps increase sample size to facilitate machine learning based neuroimage analysis, but usually suffers from significant cross-site and/or cross-scanner data heterogeneity. Existing studies often focus on reducing cross-site and/or cross-scanner heterogeneity at handcrafted feature level targeting specific tasks (e.g., classification or segmentation), limiting their adaptability in clinical practice. Research on image-level MRI harmonization targeting a broad range of applications is very limited. In this paper, we develop a spectrum swapping based image-level MRI harmonization (SSIMH) framework. Different from previous work, our method focuses on alleviating cross-scanner heterogeneity at raw image level. We first construct spectrum analysis to explore the influences of different frequency components on MRI harmonization. We then utilize a spectrum swapping method for the harmonization of raw MRIs acquired by different scanners. Our method does not rely on complex model training, and can be directly applied to fast real-time MRI harmonization. Experimental results on T1- and T2-weighted MRIs of phantom subjects acquired by using different scanners from the public ABCD dataset suggest the effectiveness of our method in structural MRI harmonization at the image level.

'Harmless' adversarial network harmonization approach for removing site effects and improving reproducibility in neuroimaging studies

Multi-site collaboration, which gathers together samples from multiple sites, is a powerful way to overcome the small-sample problem in the neuroimaging field and has the potential to discover more robust and reproducible biomarkers. However, confounds among the datasets caused by various site-specific factors may dramatically reduce the cross-site reproducibility performance. To properly remove confounds while improving cross-site task performances, we propose a maximum classifier discrepancy generative adversarial network (MCD-GAN) that combines the advantages of generative models and maximum discrepancy theory. The mechanisms of MCD-GAN and how it harmonizes the dataset are visualized using simulated data. The performance of MCD-GAN was also compared with state-of-the-art methods (e.g., ComBat, cycle-GAN) within Adolescent Brain Cognitive Development (ABCD) dataset. Result demonstrates that the proposed MCD-GAN can effectively improve the cross-site gender classification performance by harmonizing site effects. Our proposed framework is also suitable for various classification/prediction tasks and is promising to facilitate the cross-site reproducibility of neuroimaging studies. Clinical Relevance- This work provides an efficient method for removing sites effects and improving reproducibility in large-cohort neuroimaging studies.

Multi-site harmonization of MRI data uncovers machine-learning discrimination capability in barely separable populations: An example from the ABIDE dataset

Machine Learning (ML) techniques have been widely used in Neuroimaging studies of Autism Spectrum Disorders (ASD) both to identify possible brain alterations related to this condition and to evaluate the predictive power of brain imaging modalities. The collection and public sharing of large imaging samples has favored an even greater diffusion of the use of ML-based analyses. However, multi-center data collections may suffer the batch effect, which, especially in case of Magnetic Resonance Imaging (MRI) studies, should be curated to avoid confounding effects for ML classifiers and masking biases. This is particularly important in the study of barely separable populations according to MRI data, such as subjects with ASD compared to controls with typical development (TD). Here, we show how the implementation of a harmo- nization protocol on brain structural features unlocks the case-control ML separation capability in the analysis of a multi-center MRI dataset. This effect is demonstrated on the ABIDE data collection, involving subjects encompassing a wide age range. After data harmonization, the overall ASD vs. TD discrimination capability by a Random Forest (RF) classifier improves from a very low performance (AUC = 0.58 ± 0.04) to a still low, but reasonably significant AUC = 0.67 ± 0.03. The performances of the RF classifier have been evaluated also in the age-specific subgroups of children, adolescents and adults, obtaining AUC = 0.62 ± 0.02, AUC = 0.65 ± 0.03 and AUC = 0.69 ± 0.06, respectively. Specific and consistent patterns of anatomical differences related to the ASD condition have been identified for the three different age subgroups.

Data harmonisation for information fusion in digital healthcare: A state-of-the-art systematic review, meta-analysis and future research directions

Removing the bias and variance of multicentre data has always been a challenge in large scale digital healthcare studies, which requires the ability to integrate clinical features extracted from data acquired by different scanners and protocols to improve stability and robustness. Previous studies have described various computational approaches to fuse single modality multicentre datasets. However, these surveys rarely focused on evaluation metrics and lacked a checklist for computational data harmonisation studies. In this systematic review, we summarise the computational data harmonisation approaches for multi-modality data in the digital healthcare field, including harmonisation strategies and evaluation metrics based on different theories. In addition, a comprehensive checklist that summarises common practices for data harmonisation studies is proposed to guide researchers to report their research findings more effectively. Last but not least, flowcharts presenting possible ways for methodology and metric selection are proposed and the limitations of different methods have been surveyed for future research.

ID-Seg: an infant deep learning-based segmentation framework to improve limbic structure estimates

Infant brain magnetic resonance imaging (MRI) is a promising approach for studying early neurodevelopment. However, segmenting small regions such as limbic structures is challenging due to their low inter-regional contrast and high curvature. MRI studies of the adult brain have successfully applied deep learning techniques to segment limbic structures, and similar deep learning models are being leveraged for infant studies. However, these deep learning-based infant MRI segmentation models have generally been derived from small datasets, and may suffer from generalization problems. Moreover, the accuracy of segmentations derived from these deep learning models relative to more standard Expectation-Maximization approaches has not been characterized. To address these challenges, we leveraged a large, public infant MRI dataset (n = 473) and the transfer-learning technique to first pre-train a deep convolutional neural network model on two limbic structures: amygdala and hippocampus. Then we used a leave-one-out cross-validation strategy to fine-tune the pre-trained model and evaluated it separately on two independent datasets with manual labels. We term this new approach the Infant Deep learning SEGmentation Framework (ID-Seg). ID-Seg performed well on both datasets with a mean dice similarity score (DSC) of 0.87, a mean intra-class correlation (ICC) of 0.93, and a mean average surface distance (ASD) of 0.31 mm. Compared to the Developmental Human Connectome pipeline (dHCP) pipeline, ID-Seg significantly improved segmentation accuracy. In a third infant MRI dataset (n = 50), we used ID-Seg and dHCP separately to estimate amygdala and hippocampus volumes and shapes. The estimates derived from ID-seg, relative to those from the dHCP, showed stronger associations with behavioral problems assessed in these infants at age 2. In sum, ID-Seg consistently performed well on two different datasets with an 0.87 DSC, however, multi-site testing and extension for brain regions beyond the amygdala and hippocampus are still needed.

Multi-task multi-level feature adversarial network for joint Alzheimer’s disease diagnosis and atrophy localization using sMRI

Capitalizing on structural magnetic resonance imaging (sMRI), existing deep learning methods (especially convolutional neural networks, CNNs) have been widely and successfully applied to computer-aided diagnosis of Alzheimer’s disease (AD) and its prodromal stage (i.e. mild cognitive impairment, MCI). But considering the generalization capability of the obtained model trained on limited number of samples, we construct a multi-task multi-level feature adversarial network (M2FAN) for joint diagnosis and atrophy localization using baseline sMRI. Specifically, the linear-aligned T1 MR images were first processed by a lightweight CNN backbone to capture the shared intermediate feature representations, which were then branched into a global subnet for preliminary dementia diagnosis and a multi instance learning network for brain atrophy localization in multi-task learning manner. As the global discriminative information captured by the global subnet might be unstable for disease diagnosis, we further designed a module of multi-level feature adversarial learning that accounts for regularization to make global features robust against the adversarial perturbation synthesized by the local/instance features to improve the diagnostic performance. Our proposed method was evaluated on three public datasets (i.e. ADNI-1, ADNI-2, and AIBL), demonstrating competitive performance compared with several state-of-the-art methods in both tasks of AD diagnosis and MCI conversion prediction.

Neuroproteomics Chip-Based Mass Spectrometry and Other Techniques for Alzheimer´S Disease Biomarkers – Update

Background:

Alzheimer's disease (AD) is a progressive neurodegenerative disease of growing interest given that there is cognitive damage and symptom onset acceleration. Therefore, it is important to find AD biomarkers for early diagnosis, disease progression, and discrimination of AD and other diseases.

Objective:

To update the relevance of mass spectrometry for the identification of peptides and proteins involved in AD useful as discriminating biomarkers.

Methods:

Proteomics and peptidomics technologies that show the highest possible specificity and selectivity for AD biomarkers are analyzed, together with the biological fluids used. In addition to positron emission tomography and magnetic resonance imaging, MALDI-TOF mass spectrometry is widely used to identify proteins and peptides involved in AD. The use of protein chips in SELDI technology and electroblotting chips for peptides makes feasible small amounts (L) of samples for analysis.

Results:

Suitable biomarkers are related to AD pathology, such as intracellular neurofibrillary tangles; extraneuronal senile plaques; neuronal and axonal degeneration; inflammation and oxidative stress. Recently, peptides were added to the candidate list, which are not amyloid-b or tau fragments, but are related to coagulation, brain plasticity, and complement/neuroinflammation systems involving the neurovascular unit.

Conclusion:

The progress made in the application of mass spectrometry and recent chip techniques is promising for discriminating between AD, mild cognitive impairment, and matched healthy controls. The application of this technique to blood samples from patients with AD has shown to be less invasive and fast enough to determine the diagnosis, stage of the disease, prognosis, and follow-up of the therapeutic response.