Multi-site fMRI analysis using privacy-preserving federated learning and domain adaptation: ABIDE results

Adversarial learning-based multi-level dense-transmission knowledge distillation for AP-ROP detection

The Aggressive Posterior Retinopathy of Prematurity (AP-ROP) is the major cause of blindness for premature infants. The automatic diagnosis method has become an important tool for detecting AP-ROP. However, most existing automatic diagnosis methods were with heavy complexity, which hinders the development of the detecting devices. Hence, a small network (student network) with a high imitation ability is exactly needed, which can mimic a large network (teacher network) with promising diagnostic performance. Also, if the student network is too small due to the increasing gap between teacher and student networks, the diagnostic performance will drop. To tackle the above issues, we propose a novel adversarial learning-based multi-level dense knowledge distillation method for detecting AP-ROP. Specifically, the pre-trained teacher network is utilized to train multiple intermediate-size networks (i.e., teacher-assistant networks) and one student network by dense transmission mode, where the knowledge from all upper-level networks is transmitted to the current lower-level network. To ensure that two adjacent networks can distill the abundant knowledge, the adversarial learning module is leveraged to enforce the lower-level network to generate the features that are similar to those of the upper-level network. Extensive experiments demonstrate that our proposed method can realize the effective knowledge distillation from the teacher to student networks. We achieve a promising knowledge distillation performance for our private dataset and a public dataset, which can provide a new insight for devising lightweight detecting systems of fundus diseases for practical use.

AAPM task group report 273: Recommendations on best practices for AI and machine learning for computer-aided diagnosis in medical imaging

Rapid advances in artificial intelligence (AI) and machine learning, and specifically in deep learning (DL) techniques, have enabled broad application of these methods in health care. The promise of the DL approach has spurred further interest in computer-aided diagnosis (CAD) development and applications using both "traditional" machine learning methods and newer DL-based methods. We use the term CAD-AI to refer to this expanded clinical decision support environment that uses traditional and DL-based AI methods. Numerous studies have been published to date on the development of machine learning tools for computer-aided, or AI-assisted, clinical tasks. However, most of these machine learning models are not ready for clinical deployment. It is of paramount importance to ensure that a clinical decision support tool undergoes proper training and rigorous validation of its generalizability and robustness before adoption for patient care in the clinic. To address these important issues, the American Association of Physicists in Medicine (AAPM) Computer-Aided Image Analysis Subcommittee (CADSC) is charged, in part, to develop recommendations on practices and standards for the development and performance assessment of computer-aided decision support systems. The committee has previously published two opinion papers on the evaluation of CAD systems and issues associated with user training and quality assurance of these systems in the clinic. With machine learning techniques continuing to evolve and CAD applications expanding to new stages of the patient care process, the current task group report considers the broader issues common to the development of most, if not all, CAD-AI applications and their translation from the bench to the clinic. The goal is to bring attention to the proper training and validation of machine learning algorithms that may improve their generalizability and reliability and accelerate the adoption of CAD-AI systems for clinical decision support.

A Comprehensive Survey on Federated Learning Techniques for Healthcare Informatics

Healthcare is predominantly regarded as a crucial consideration in promoting the general physical and mental health and well-being of people around the world. The amount of data generated by healthcare systems is enormous, making it challenging to manage. Many machine learning (ML) approaches were implemented to develop dependable and robust solutions to handle the data. ML cannot fully utilize data due to privacy concerns. This primarily happens in the case of medical data. Due to a lack of precise clinical data, the application of ML for the same is challenging and may not yield desired results. Federated learning (FL), which is a recent development in ML where the computation is offloaded to the source of data, appears to be a promising solution to this problem. In this study, we present a detailed survey of applications of FL for healthcare informatics. We initiate a discussion on the need for FL in the healthcare domain, followed by a review of recent review papers. We focus on the fundamentals of FL and the major motivations behind FL for healthcare applications. We then present the applications of FL along with recent state of the art in several verticals of healthcare. Then, lessons learned, open issues, and challenges that are yet to be solved are also highlighted. This is followed by future directions that give directions to the prospective researchers willing to do their research in this domain.

An analysis of the effects of limited training data in distributed learning scenarios for brain age prediction

OBJECTIVE

Distributed learning avoids problems associated with central data collection by training models locally at each site. This can be achieved by federated learning (FL) aggregating multiple models that were trained in parallel or training a single model visiting sites sequentially, the traveling model (TM). While both approaches have been applied to medical imaging tasks, their performance in limited local data scenarios remains unknown. In this study, we specifically analyze FL and TM performances when very small sample sizes are available per site.

MATERIALS AND METHODS

2025 T1-weighted magnetic resonance imaging scans were used to investigate the effect of sample sizes on FL and TM for brain age prediction. We evaluated models across 18 scenarios varying the number of samples per site (1, 2, 5, 10, and 20) and the number of training rounds (20, 40, and 200).

RESULTS

Our results demonstrate that the TM outperforms FL, for every sample size examined. In the extreme case when each site provided only one sample, FL achieved a mean absolute error (MAE) of 18.9 ± 0.13 years, while the TM achieved a MAE of 6.21 ± 0.50 years, comparable to central learning (MAE = 5.99 years).

DISCUSSION

Although FL is more commonly used, our study demonstrates that TM is the best implementation for small sample sizes.

CONCLUSION

The TM offers new opportunities to apply machine learning models in rare diseases and pediatric research but also allows even small hospitals to contribute small datasets.

Blockchain and homomorphic encryption based privacy-preserving model aggregation for medical images

Medical healthcare centers are envisioned as a promising paradigm to handle the massive volume of data for COVID-19 patients using artificial intelligence (AI). Traditionally, AI techniques require centralized data collection and training models within a single organization. This practice can be considered a weakness as it leads to several privacy and security concerns related to raw data communication. To overcome this weakness and secure raw data communication, we propose a blockchain-based federated learning framework that provides a solution for collaborative data training. The proposed framework enables the coordination of multiple hospitals to train and share encrypted federated models while preserving data privacy. Blockchain ledger technology provides decentralization of federated learning models without relying on a central server. Moreover, the proposed homomorphic encryption scheme encrypts and decrypts the gradients of the model to preserve privacy. More precisely, the proposed framework: (i) train the local model by a novel capsule network for segmentation and classification of COVID-19 images, (ii) furthermore, we use the homomorphic encryption scheme to secure the local model that encrypts and decrypts the gradients, (iii) finally, the model is shared over a decentralized platform through the proposed blockchain-based federated learning algorithm. The integration of blockchain and federated learning leads to a new paradigm for medical image data sharing over the decentralized network. To validate our proposed model, we conducted comprehensive experiments and the results demonstrate the superior performance of the proposed scheme.

Shifting machine learning for healthcare from development to deployment and from models to data

In the past decade, the application of machine learning (ML) to healthcare has helped drive the automation of physician tasks as well as enhancements in clinical capabilities and access to care. This progress has emphasized that, from model development to model deployment, data play central roles. In this Review, we provide a data-centric view of the innovations and challenges that are defining ML for healthcare. We discuss deep generative models and federated learning as strategies to augment datasets for improved model performance, as well as the use of the more recent transformer models for handling larger datasets and enhancing the modelling of clinical text. We also discuss data-focused problems in the deployment of ML, emphasizing the need to efficiently deliver data to ML models for timely clinical predictions and to account for natural data shifts that can deteriorate model performance.

Federated Learning in Ocular Imaging: Current Progress and Future Direction

Advances in artificial intelligence deep learning (DL) have made tremendous impacts on the field of ocular imaging over the last few years. Specifically, DL has been utilised to detect and classify various ocular diseases on retinal photographs, optical coherence tomography (OCT) images, and OCT-angiography images. In order to achieve good robustness and generalisability of model performance, DL training strategies traditionally require extensive and diverse training datasets from various sites to be transferred and pooled into a "centralised location". However, such a data transferring process could raise practical concerns related to data security and patient privacy. Federated learning (FL) is a distributed collaborative learning paradigm which enables the coordination of multiple collaborators without the need for sharing confidential data. This distributed training approach has great potential to ensure data privacy among different institutions and reduce the potential risk of data leakage from data pooling or centralisation. This review article aims to introduce the concept of FL, provide current evidence of FL in ocular imaging, and discuss potential challenges as well as future applications.

Reducing variations in multi-center Alzheimer's disease classification with convolutional adversarial autoencoder

Based on brain magnetic resonance imaging (MRI), multiple variations ranging from MRI scanners to center-specific parameter settings, imaging protocols, and brain region-of-interest (ROI) definitions pose a big challenge for multi-center Alzheimer's disease characterization and classification. Existing approaches to reduce such variations require intricate multi-step, often manual preprocessing pipelines, including skull stripping, segmentation, registration, cortical reconstruction, and ROI outlining. Such procedures are time-consuming, and more importantly, tend to be user biased. Contrasting costly and biased preprocessing pipelines, the question arises whether we can design a deep learning model to automatically reduce these variations from multiple centers for Alzheimer's disease classification? In this study, we used T1 and T2-weighted structural MRI from Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset based on three groups with 375 subjects, respectively: patients with Alzheimer's disease (AD) dementia, with mild cognitive impairment (MCI), and healthy controls (HC); to test our approach, we defined AD classification as classifying an individual's structural image to one of the three group labels. We first introduced a convolutional adversarial autoencoder (CAAE) to reduce the variations existing in multi-center raw MRI scans by automatically registering them into a common aligned space. Afterward, a convolutional residual soft attention network (CRAT) was further proposed for AD classification. Canonical classification procedures demonstrated that our model achieved classification accuracies of 91.8%, 90.05%, and 88.10% for the 2-way classification tasks using the RAW aligned MRI scans, including AD vs. HC, AD vs. MCI, and MCI vs. HC, respectively. Thus, our automated approach achieves comparable or even better classification performance by comparing it with many baselines with dedicated conventional preprocessing pipelines. Furthermore, the uncovered brain hotpots, i.e., hippocampus, amygdala, and temporal pole, are consistent with previous studies.

A comparison of distributed machine learning methods for the support of “many labs” collaborations in computational modeling of decision making

Deep learning models are powerful tools for representing the complex learning processes and decision-making strategies used by humans. Such neural network models make fewer assumptions about the underlying mechanisms thus providing experimental flexibility in terms of applicability. However, this comes at the cost of involving a larger number of parameters requiring significantly more data for effective learning. This presents practical challenges given that most cognitive experiments involve relatively small numbers of subjects. Laboratory collaborations are a natural way to increase overall dataset size. However, data sharing barriers between laboratories as necessitated by data protection regulations encourage the search for alternative methods to enable collaborative data science. Distributed learning, especially federated learning (FL), which supports the preservation of data privacy, is a promising method for addressing this issue. To verify the reliability and feasibility of applying FL to train neural networks models used in the characterization of decision making, we conducted experiments on a real-world, many-labs data pool including experiment data-sets from ten independent studies. The performance of single models trained on single laboratory data-sets was poor. This unsurprising finding supports the need for laboratory collaboration to train more reliable models. To that end we evaluated four collaborative approaches. The first approach represents conventional centralized learning (CL-based) and is the optimal approach but requires complete sharing of data which we wish to avoid. The results however establish a benchmark for the other three approaches, federated learning (FL-based), incremental learning (IL-based), and cyclic incremental learning (CIL-based). We evaluate these approaches in terms of prediction accuracy and capacity to characterize human decision-making strategies. The FL-based model achieves performance most comparable to that of the CL-based model. This indicates that FL has value in scaling data science methods to data collected in computational modeling contexts when data sharing is not convenient, practical or permissible.

Defending against Reconstruction Attacks through Differentially Private Federated Learning for Classification of Heterogeneous Chest X-ray Data

Privacy regulations and the physical distribution of heterogeneous data are often primary concerns for the development of deep learning models in a medical context. This paper evaluates the feasibility of differentially private federated learning for chest X-ray classification as a defense against data privacy attacks. To the best of our knowledge, we are the first to directly compare the impact of differentially private training on two different neural network architectures, DenseNet121 and ResNet50. Extending the federated learning environments previously analyzed in terms of privacy, we simulated a heterogeneous and imbalanced federated setting by distributing images from the public CheXpert and Mendeley chest X-ray datasets unevenly among 36 clients. Both non-private baseline models achieved an area under the receiver operating characteristic curve (AUC) of 0.94 on the binary classification task of detecting the presence of a medical finding. We demonstrate that both model architectures are vulnerable to privacy violation by applying image reconstruction attacks to local model updates from individual clients. The attack was particularly successful during later training stages. To mitigate the risk of a privacy breach, we integrated Rényi differential privacy with a Gaussian noise mechanism into local model training. We evaluate model performance and attack vulnerability for privacy budgets ε∈{1,3,6,10}. The DenseNet121 achieved the best utility-privacy trade-off with an AUC of 0.94 for ε=6. Model performance deteriorated slightly for individual clients compared to the non-private baseline. The ResNet50 only reached an AUC of 0.76 in the same privacy setting. Its performance was inferior to that of the DenseNet121 for all considered privacy constraints, suggesting that the DenseNet121 architecture is more robust to differentially private training.

CNNG: A Convolutional Neural Networks With Gated Recurrent Units for Autism Spectrum Disorder Classification

As a neurodevelopmental disorder, autism spectrum disorder (ASD) severely affects the living conditions of patients and their families. Early diagnosis of ASD can enable the disease to be effectively intervened in the early stage of development. In this paper, we present an ASD classification network defined as CNNG by combining of convolutional neural network (CNN) and gate recurrent unit (GRU). First, CNNG extracts the 3D spatial features of functional magnetic resonance imaging (fMRI) data by using the convolutional layer of the 3D CNN. Second, CNNG extracts the temporal features by using the GRU and finally classifies them by using the Sigmoid function. The performance of CNNG was validated on the international public data—autism brain imaging data exchange (ABIDE) dataset. According to the experiments, CNNG can be highly effective in extracting the spatio-temporal features of fMRI and achieving a classification accuracy of 72.46%.

SSPNet: An interpretable 3D-CNN for classification of schizophrenia using phase maps of resting-state complex-valued fMRI data

Convolutional neural networks (CNNs) have shown promising results in classifying individuals with mental disorders such as schizophrenia using resting-state fMRI data. However, complex-valued fMRI data is rarely used since additional phase data introduces high-level noise though it is potentially useful information for the context of classification. As such, we propose to use spatial source phase (SSP) maps derived from complex-valued fMRI data as the CNN input. The SSP maps are not only less noisy, but also more sensitive to spatial activation changes caused by mental disorders than magnitude maps. We build a 3D-CNN framework with two convolutional layers (named SSPNet) to fully explore the 3D structure and voxel-level relationships from the SSP maps. Two interpretability modules, consisting of saliency map generation and gradient-weighted class activation mapping (Grad-CAM), are incorporated into the well-trained SSPNet to provide additional information helpful for understanding the output. Experimental results from classifying schizophrenia patients (SZs) and healthy controls (HCs) show that the proposed SSPNet significantly improved accuracy and AUC compared to CNN using magnitude maps extracted from either magnitude-only (by 23.4 and 23.6% for DMN) or complex-valued fMRI data (by 10.6 and 5.8% for DMN). SSPNet captured more prominent HC-SZ differences in saliency maps, and Grad-CAM localized all contributing brain regions with opposite strengths for HCs and SZs within SSP maps. These results indicate the potential of SSPNet as a sensitive tool that may be useful for the development of brain-based biomarkers of mental disorders.

Position paper on management of personal data in environment and health research in Europe

Management of datasets that include health information and other sensitive personal information of European study participants has to be compliant with the General Data Protection Regulation (GDPR, Regulation (EU) 2016/679). Within scientific research, the widely subscribed'FAIR' data principles should apply, meaning that research data should be findable, accessible, interoperable and re-usable. Balancing the aim of open science driven FAIR data management with GDPR compliant personal data protection safeguards is now a common challenge for many research projects dealing with (sensitive) personal data. In December 2020 a workshop was held with representatives of several large EU research consortia and of the European Commission to reflect on how to apply the FAIR data principles for environment and health research (E&H). Several recent data intensive EU funded E&H research projects face this challenge and work intensively towards developing solutions to access, exchange, store, handle, share, process and use such sensitive personal data, with the aim to support European and transnational collaborations. As a result, several recommendations, opportunities and current limitations were formulated. New technical developments such as federated data management and analysis systems, machine learning together with advanced search software, harmonized ontologies and data quality standards should in principle facilitate the FAIRification of data. To address ethical, legal, political and financial obstacles to the wider re-use of data for research purposes, both specific expertise and underpinning infrastructure are needed. There is a need for the E&H research data to find their place in the European Open Science Cloud. Communities using health and population data, environmental data and other publicly available data have to interconnect and synergize. To maximize the use and re-use of environment and health data, a dedicated supporting European infrastructure effort, such as the EIRENE research infrastructure within the ESFRI roadmap 2021, is needed that would interact with existing infrastructures.

Deep learning-based medical diagnostic services: A secure, lightweight, and accurate realization1

In this paper, we propose CryptMed, a system framework that enables medical service providers to offer secure, lightweight, and accurate medical diagnostic service to their customers via an execution of neural network inference in the ciphertext domain. CryptMed ensures the privacy of both parties with cryptographic guarantees. Our technical contributions include: 1) presenting a secret sharing based inference protocol that can well cope with the commonly-used linear and non-linear NN layers; 2) devising optimized secure comparison function that can efficiently support comparison-based activation functions in NN architectures; 3) constructing a suite of secure smooth functions built on precise approximation approaches for accurate medical diagnoses. We evaluate CryptMed on 6 neural network architectures across a wide range of non-linear activation functions over two benchmark and four real-world medical datasets. We comprehensively compare our system with prior art in terms of end-to-end service workload and prediction accuracy. Our empirical results demonstrate that CryptMed achieves up to respectively 413 ×, 19 ×, and 43 × bandwidth savings for MNIST, CIFAR-10, and medical applications compared with prior art. For the smooth activation based inference, the best choice of our proposed approximations preserve the precision of original functions, with less than 1.2% accuracy loss and could enhance the precision due to the newly introduced activation function family.

Identification of Pathogenetic Brain Regions via Neuroimaging Data for Diagnosis of Autism Spectrum Disorders

Autism spectrum disorder (ASD) is a kind of neurodevelopmental disorder that often occurs in children and has a hidden onset. Patients usually have lagged development of communication ability and social behavior and thus suffer an unhealthy physical and mental state. Evidence has indicated that diseases related to ASD have commonalities in brain imaging characteristics. This study aims to study the pathogenesis of ASD based on brain imaging data to locate the ASD-related brain regions. Specifically, we collected the functional magnetic resonance image data of 479 patients with ASD and 478 normal subjects matched in age and gender and used a machine-learning framework named random support vector machine cluster to extract distinctive brain regions from the preprocessed data. According to the experimental results, compared with other existing approaches, the method used in this study can more accurately distinguish patients from normal individuals based on brain imaging data. At the same time, this study found that the development of ASD was highly correlated with certain brain regions, e.g., lingual gyrus, superior frontal gyrus, medial gyrus, insular lobe, and olfactory cortex. This study explores the effectiveness of a novel machine-learning approach in the study of ASD brain imaging and provides a reference brain area for the medical research and clinical treatment of ASD.

A systematic review of federated learning applications for biomedical data

OBJECTIVES

Federated learning (FL) allows multiple institutions to collaboratively develop a machine learning algorithm without sharing their data. Organizations instead share model parameters only, allowing them to benefit from a model built with a larger dataset while maintaining the privacy of their own data. We conducted a systematic review to evaluate the current state of FL in healthcare and discuss the limitations and promise of this technology.

METHODS

We conducted a literature search using PRISMA guidelines. At least two reviewers assessed each study for eligibility and extracted a predetermined set of data. The quality of each study was determined using the TRIPOD guideline and PROBAST tool.

RESULTS

13 studies were included in the full systematic review. Most were in the field of oncology (6 of 13; 46.1%), followed by radiology (5 of 13; 38.5%). The majority evaluated imaging results, performed a binary classification prediction task via offline learning (n = 12; 92.3%), and used a centralized topology, aggregation server workflow (n = 10; 76.9%). Most studies were compliant with the major reporting requirements of the TRIPOD guidelines. In all, 6 of 13 (46.2%) of studies were judged at high risk of bias using the PROBAST tool and only 5 studies used publicly available data.

CONCLUSION

Federated learning is a growing field in machine learning with many promising uses in healthcare. Few studies have been published to date. Our evaluation found that investigators can do more to address the risk of bias and increase transparency by adding steps for data homogeneity or sharing required metadata and code.

Federated Learning in Medical Imaging: Part II: Methods, Challenges, and Considerations

Federated learning is a machine learning method that allows decentralized training of deep neural networks among multiple clients while preserving the privacy of each client's data. Federated learning is instrumental in medical imaging due to the privacy considerations of medical data. Setting up federated networks in hospitals comes with unique challenges, primarily because medical imaging data and federated learning algorithms each have their own set of distinct characteristics. This article introduces federated learning algorithms in medical imaging and discusses technical challenges and considerations of real-world implementation of them.

Semi-Synchronous Federated Learning for Energy-Efficient Training and Accelerated Convergence in Cross-Silo Settings

There are situations where data relevant to machine learning problems are distributed across multiple locations that cannot share the data due to regulatory, competitiveness, or privacy reasons. Machine learning approaches that require data to be copied to a single location are hampered by the challenges of data sharing. Federated Learning (FL) is a promising approach to learn a joint model over all the available data across silos. In many cases, the sites participating in a federation have different data distributions and computational capabilities. In these heterogeneous environments existing approaches exhibit poor performance: synchronous FL protocols are communication efficient, but have slow learning convergence and high energy cost; conversely, asynchronous FL protocols have faster convergence with lower energy cost, but higher communication. In this work, we introduce a novel energy-efficient Semi-Synchronous Federated Learning protocol that mixes local models periodically with minimal idle time and fast convergence. We show through extensive experiments over established benchmark datasets in the computer-vision domain as well as in real-world biomedical settings that our approach significantly outperforms previous work in data and computationally heterogeneous environments .

Multi-Source Domain Adaptation Techniques for Mitigating Batch Effects: A Comparative Study

The past decade has seen an increasing number of applications of deep learning (DL) techniques to biomedical fields, especially in neuroimaging-based analysis. Such DL-based methods are generally data-intensive and require a large number of training instances, which might be infeasible to acquire from a single acquisition site, especially for data, such as fMRI scans, due to the time and costs that they demand. We can attempt to address this issue by combining fMRI data from various sites, thereby creating a bigger heterogeneous dataset. Unfortunately, the inherent differences in the combined data, known as batch effects, often hamper learning a model. To mitigate this issue, techniques such as multi-source domain adaptation [Multi-source Domain Adversarial Networks (MSDA)] aim at learning an effective classification function that uses (learned) domain-invariant latent features. This article analyzes and compares the performance of various popular MSDA methods [MDAN, Domain AggRegation Networks (DARN), Multi-Domain Matching Networks (MDMN), and Moment Matching for MSDA (M3SDA)] at predicting different labels (illness, age, and sex) of images from two public rs-fMRI datasets: ABIDE 1and ADHD-200. It also evaluates the impact of various conditions such as class imbalance, the number of sites along with a comparison of the degree of adaptation of each of the methods, thereby presenting the effectiveness of MSDA models in neuroimaging-based applications.

Decentralized Distributed Multi-institutional PET Image Segmentation Using a Federated Deep Learning Framework

PURPOSE

The generalizability and trustworthiness of deep learning (DL)-based algorithms depend on the size and heterogeneity of training datasets. However, because of patient privacy concerns and ethical and legal issues, sharing medical images between different centers is restricted. Our objective is to build a federated DL-based framework for PET image segmentation utilizing a multicentric dataset and to compare its performance with the centralized DL approach.

METHODS

PET images from 405 head and neck cancer patients from 9 different centers formed the basis of this study. All tumors were segmented manually. PET images converted to SUV maps were resampled to isotropic voxels (3 × 3 × 3 mm3) and then normalized. PET image subvolumes (12 × 12 × 12 cm3) consisting of whole tumors and background were analyzed. Data from each center were divided into train/validation (80% of patients) and test sets (20% of patients). The modified R2U-Net was used as core DL model. A parallel federated DL model was developed and compared with the centralized approach where the data sets are pooled to one server. Segmentation metrics, including Dice similarity and Jaccard coefficients, percent relative errors (RE%) of SUVpeak, SUVmean, SUVmedian, SUVmax, metabolic tumor volume, and total lesion glycolysis were computed and compared with manual delineations.

RESULTS

The performance of the centralized versus federated DL methods was nearly identical for segmentation metrics: Dice (0.84 ± 0.06 vs 0.84 ± 0.05) and Jaccard (0.73 ± 0.08 vs 0.73 ± 0.07). For quantitative PET parameters, we obtained comparable RE% for SUVmean (6.43% ± 4.72% vs 6.61% ± 5.42%), metabolic tumor volume (12.2% ± 16.2% vs 12.1% ± 15.89%), and total lesion glycolysis (6.93% ± 9.6% vs 7.07% ± 9.85%) and negligible RE% for SUVmax and SUVpeak. No significant differences in performance (P > 0.05) between the 2 frameworks (centralized vs federated) were observed.

CONCLUSION

The developed federated DL model achieved comparable quantitative performance with respect to the centralized DL model. Federated DL models could provide robust and generalizable segmentation, while addressing patient privacy and legal and ethical issues in clinical data sharing.

Classifying Autism From Crowdsourced Semistructured Speech Recordings: Machine Learning Model Comparison Study

BACKGROUND

Autism spectrum disorder (ASD) is a neurodevelopmental disorder that results in altered behavior, social development, and communication patterns. In recent years, autism prevalence has tripled, with 1 in 44 children now affected. Given that traditional diagnosis is a lengthy, labor-intensive process that requires the work of trained physicians, significant attention has been given to developing systems that automatically detect autism. We work toward this goal by analyzing audio data, as prosody abnormalities are a signal of autism, with affected children displaying speech idiosyncrasies such as echolalia, monotonous intonation, atypical pitch, and irregular linguistic stress patterns.

OBJECTIVE

We aimed to test the ability for machine learning approaches to aid in detection of autism in self-recorded speech audio captured from children with ASD and neurotypical (NT) children in their home environments.

METHODS

We considered three methods to detect autism in child speech: (1) random forests trained on extracted audio features (including Mel-frequency cepstral coefficients); (2) convolutional neural networks trained on spectrograms; and (3) fine-tuned wav2vec 2.0-a state-of-the-art transformer-based speech recognition model. We trained our classifiers on our novel data set of cellphone-recorded child speech audio curated from the Guess What? mobile game, an app designed to crowdsource videos of children with ASD and NT children in a natural home environment.

RESULTS

The random forest classifier achieved 70% accuracy, the fine-tuned wav2vec 2.0 model achieved 77% accuracy, and the convolutional neural network achieved 79% accuracy when classifying children's audio as either ASD or NT. We used 5-fold cross-validation to evaluate model performance.

CONCLUSIONS

Our models were able to predict autism status when trained on a varied selection of home audio clips with inconsistent recording qualities, which may be more representative of real-world conditions. The results demonstrate that machine learning methods offer promise in detecting autism automatically from speech without specialized equipment.

Federated learning for multi-center imaging diagnostics: a simulation study in cardiovascular disease

Deep learning models can enable accurate and efficient disease diagnosis, but have thus far been hampered by the data scarcity present in the medical world. Automated diagnosis studies have been constrained by underpowered single-center datasets, and although some results have shown promise, their generalizability to other institutions remains questionable as the data heterogeneity between institutions is not taken into account. By allowing models to be trained in a distributed manner that preserves patients’ privacy, federated learning promises to alleviate these issues, by enabling diligent multi-center studies. We present the first simulated federated learning study on the modality of cardiovascular magnetic resonance and use four centers derived from subsets of the M&M and ACDC datasets, focusing on the diagnosis of hypertrophic cardiomyopathy. We adapt a 3D-CNN network pretrained on action recognition and explore two different ways of incorporating shape prior information to the model, and four different data augmentation set-ups, systematically analyzing their impact on the different collaborative learning choices. We show that despite the small size of data (180 subjects derived from four centers), the privacy preserving federated learning achieves promising results that are competitive with traditional centralized learning. We further find that federatively trained models exhibit increased robustness and are more sensitive to domain shift effects.

Domain adaptation based on rough adjoint inconsistency and optimal transport for identifying autistic patients

BACKGROUND AND OBJECTIVE

Computer aided diagnosis technology has been widely used to diagnose autism spectrum disorder (ASD) from neural images. The performance of the model usually depends largely on a sufficient number of training samples that reflect the real sample distribution. Due to the lack of labelled neural images data, multisite data are often pooled together to expand the sample size. However, the heterogeneity among sites will inevitably lead to a decline in the generalization of models. To solve this problem, we propose a multisource unsupervised domain adaptation method using rough adjoint inconsistency and optimal transport.

METHODS

First, we define the concept of rough adjoint inconsistency and propose a double quantization method based on rough adjoint inconsistency and Dempster-Shafer (D-S) evidence theory to estimate the weight coefficient of each source domain to accurately describe the importance of each source domain to the target domain. Second, using optimal transport theory, we weaken the data distribution differences between domains and solve the problem of class imbalance by adjusting the sampling weights among classes.

RESULTS

The ASD recognition accuracy of the proposed method is improved on all eight tasks, which are 70.67%, 64.86%, 62.50%, 70.80%, 73.08%, 71.19%, 75.41% and 75.76%, respectively. Our proposed model achieves superior performance compared to traditional machine learning methods and other recently proposed deep learning model.

CONCLUSIONS

Our method demonstrates that the fusion of rough adjoint inconsistency and optimal transport can be a powerful tool for identifying ASD and quantifying the correlations between domains.

A Federated Mining Approach on Predicting Diabetes-Related Complications: Demonstration Using Real-World Clinical Data

Chronic diabetes can lead to microvascular complications, including diabetic eye disease, diabetic kidney disease, and diabetic neuropathy. However, the long-term complications often remain undetected at the early stages of diagnosis. Developing a machine learning model to identify the patients at high risk of developing diabetes-related complications can help design better treatment interventions. Building robust machine learning models require large datasets which further requires sharing data among different healthcare systems, hence, involving privacy and confidentiality concerns. The main objective of this study is to design a decentralized privacy-protected federated learning architecture that can deliver comparable performance to centralized learning. We demonstrate the potential of adopting federated learning to address the challenges such as class-imbalance in using real-world clinical data. In all our experiments, federated learning showed comparable performance to the gold-standard of centralized learning, and applying class balancing techniques improved performance across all cohorts.

Applications of Federated Learning; Taxonomy, Challenges, and Research Trends

The federated learning technique (FL) supports the collaborative training of machine learning and deep learning models for edge network optimization. Although a complex edge network with heterogeneous devices having different constraints can affect its performance, this leads to a problem in this area. Therefore, some research can be seen to design new frameworks and approaches to improve federated learning processes. The purpose of this study is to provide an overview of the FL technique and its applicability in different domains. The key focus of the paper is to produce a systematic literature review of recent research studies that clearly describes the adoption of FL in edge networks. The search procedure was performed from April 2020 to May 2021 with a total initial number of papers being 7546 published in the duration of 2016 to 2020. The systematic literature synthesizes and compares the algorithms, models, and frameworks of federated learning. Additionally, we have presented the scope of FL applications in different industries and domains. It has been revealed after careful investigation of studies that 25% of the studies used FL in IoT and edge-based applications and 30% of studies implement the FL concept in the health industry, 10% for NLP, 10% for autonomous vehicles, 10% for mobile services, 10% for recommender systems, and 5% for FinTech. A taxonomy is also proposed on implementing FL for edge networks in different domains. Moreover, another novelty of this paper is that datasets used for the implementation of FL are discussed in detail to provide the researchers an overview of the distributed datasets, which can be used for employing FL techniques. Lastly, this study discusses the current challenges of implementing the FL technique. We have found that the areas of medical AI, IoT, edge systems, and the autonomous industry can adapt the FL in many of its sub-domains; however, the challenges these domains can encounter are statistical heterogeneity, system heterogeneity, data imbalance, resource allocation, and privacy.

Federated Learning for Healthcare: Systematic Review and Architecture Proposal

The use of machine learning (ML) with electronic health records (EHR) is growing in popularity as a means to extract knowledge that can improve the decision-making process in healthcare. Such methods require training of high-quality learning models based on diverse and comprehensive datasets, which are hard to obtain due to the sensitive nature of medical data from patients. In this context, federated learning (FL) is a methodology that enables the distributed training of machine learning models with remotely hosted datasets without the need to accumulate data and, therefore, compromise it. FL is a promising solution to improve ML-based systems, better aligning them to regulatory requirements, improving trustworthiness and data sovereignty. However, many open questions must be addressed before the use of FL becomes widespread. This article aims at presenting a systematic literature review on current research about FL in the context of EHR data for healthcare applications. Our analysis highlights the main research topics, proposed solutions, case studies, and respective ML methods. Furthermore, the article discusses a general architecture for FL applied to healthcare data based on the main insights obtained from the literature review. The collected literature corpus indicates that there is extensive research on the privacy and confidentiality aspects of training data and model sharing, which is expected given the sensitive nature of medical data. Studies also explore improvements to the aggregation mechanisms required to generate the learning model from distributed contributions and case studies with different types of medical data.

Federated learning and differential privacy for medical image analysis

The artificial intelligence revolution has been spurred forward by the availability of large-scale datasets. In contrast, the paucity of large-scale medical datasets hinders the application of machine learning in healthcare. The lack of publicly available multi-centric and diverse datasets mainly stems from confidentiality and privacy concerns around sharing medical data. To demonstrate a feasible path forward in medical image imaging, we conduct a case study of applying a differentially private federated learning framework for analysis of histopathology images, the largest and perhaps most complex medical images. We study the effects of IID and non-IID distributions along with the number of healthcare providers, i.e., hospitals and clinics, and the individual dataset sizes, using The Cancer Genome Atlas (TCGA) dataset, a public repository, to simulate a distributed environment. We empirically compare the performance of private, distributed training to conventional training and demonstrate that distributed training can achieve similar performance with strong privacy guarantees. We also study the effect of different source domains for histopathology images by evaluating the performance using external validation. Our work indicates that differentially private federated learning is a viable and reliable framework for the collaborative development of machine learning models in medical image analysis.

Federated learning for computational pathology on gigapixel whole slide images

Deep Learning-based computational pathology algorithms have demonstrated profound ability to excel in a wide array of tasks that range from characterization of well known morphological phenotypes to predicting non human-identifiable features from histology such as molecular alterations. However, the development of robust, adaptable and accurate deep learning-based models often rely on the collection and time-costly curation large high-quality annotated training data that should ideally come from diverse sources and patient populations to cater for the heterogeneity that exists in such datasets. Multi-centric and collaborative integration of medical data across multiple institutions can naturally help overcome this challenge and boost the model performance but is limited by privacy concerns among other difficulties that may arise in the complex data sharing process as models scale towards using hundreds of thousands of gigapixel whole slide images. In this paper, we introduce privacy-preserving federated learning for gigapixel whole slide images in computational pathology using weakly-supervised attention multiple instance learning and differential privacy. We evaluated our approach on two different diagnostic problems using thousands of histology whole slide images with only slide-level labels. Additionally, we present a weakly-supervised learning framework for survival prediction and patient stratification from whole slide images and demonstrate its effectiveness in a federated setting. Our results show that using federated learning, we can effectively develop accurate weakly-supervised deep learning models from distributed data silos without direct data sharing and its associated complexities, while also preserving differential privacy using randomized noise generation. We also make available an easy-to-use federated learning for computational pathology software package: http://github.com/mahmoodlab/HistoFL.

A Privacy-Preserved Transfer Learning Concept to Predict Diabetic Kidney Disease at Out-of-Network Siloed Sites Using an In-Network Federated Model on Real-World Data

Successful implementation of data-driven artificial intelligence (AI) applications requires access to large datasets. Healthcare institutions can establish coordinated data-sharing networks to address the complexity of large clinical data accessibility for scientific advancements. However, persisting challenges from controlled access, safe data transferring, license restrictions from regulatory and legal concerns discourage data sharing among the in-network hospitals. In contrast, out-of-network healthcare institutions are deprived of access to any big EHR database; hence, limiting their research scope. The main objective of this study is to design a privacy-preserved transfer learning architecture that can utilize the knowledge from a federated model developed from in-network hospital-site EHR data for predicting diabetic kidney cases at out-of-network siloed hospital sites. In all our experiments, transfer learning showed improved performance compared to models trained with out-of-network site datasets. Thus, we demonstrate the proof-of-concept of transferring knowledge from established networks to aid data-driven AI discoveries at siloed sites.

A review of methods for classification and recognition of ASD using fMRI data

Autism spectrum disorder (ASD) is a severe neuropsychiatric brain disorder that affects people's social communication and daily routine. Considering the phenomenon of abnormal brain function in the early stage of ASD, functional magnetic resonance imaging (fMRI), an excellent technique that measures brain activity, provides effective data to study ASD. Therefore, based on fMRI data of ASD cases, this paper reviews the progress of machine learning methods and deep learning methods in ASD classification and recognition in the last three years and summarizes the different research results of fMRI data extracted from the Autism Brain Imaging Data Exchange (ABIDE). From the classification performance of classification and recognition of ASD by the two methods, comparing the important classification indicators such as accuracy, sensitivity and specificity, the current challenges and future development trends are reported, which can provide an essential reference for the early diagnosis of ASD cases.

A comprehensive review of federated learning for COVID‐19 detection

The coronavirus of 2019 (COVID‐19) was declared a global pandemic by World Health Organization in March 2020. Effective testing is crucial to slow the spread of the pandemic. Artificial intelligence and machine learning techniques can help COVID‐19 detection using various clinical symptom data. While deep learning (DL) approach requiring centralized data is susceptible to a high risk of data privacy breaches, federated learning (FL) approach resting on decentralized data can preserve data privacy, a critical factor in the health domain. This paper reviews recent advances in applying DL and FL techniques for COVID‐19 detection with a focus on the latter. A model FL implementation use case in health systems with a COVID‐19 detection using chest X‐ray image data sets is studied. We have also reviewed applications of previously published FL experiments for COVID‐19 research to demonstrate the applicability of FL in tackling health research issues. Last, several challenges in FL implementation in the healthcare domain are discussed in terms of potential future work.

Federated Learning for Microvasculature Segmentation and Diabetic Retinopathy Classification of OCT Data

Purpose

To evaluate the performance of a federated learning framework for deep neural network-based retinal microvasculature segmentation and referable diabetic retinopathy (RDR) classification using OCT and OCT angiography (OCTA).

Design

Retrospective analysis of clinical OCT and OCTA scans of control participants and patients with diabetes.

Participants

The 153 OCTA en face images used for microvasculature segmentation were acquired from 4 OCT instruments with fields of view ranging from 2 × 2-mm to 6 × 6-mm. The 700 eyes used for RDR classification consisted of OCTA en face images and structural OCT projections acquired from 2 commercial OCT systems.

Methods

OCT angiography images used for microvasculature segmentation were delineated manually and verified by retina experts. Diabetic retinopathy (DR) severity was evaluated by retinal specialists and was condensed into 2 classes: non-RDR and RDR. The federated learning configuration was demonstrated via simulation using 4 clients for microvasculature segmentation and was compared with other collaborative training methods. Subsequently, federated learning was applied over multiple institutions for RDR classification and was compared with models trained and tested on data from the same institution (internal models) and different institutions (external models).

Main Outcome Measures

For microvasculature segmentation, we measured the accuracy and Dice similarity coefficient (DSC). For severity classification, we measured accuracy, area under the receiver operating characteristic curve (AUROC), area under the precision-recall curve, balanced accuracy, F1 score, sensitivity, and specificity.

Results

For both applications, federated learning achieved similar performance as internal models. Specifically, for microvasculature segmentation, the federated learning model achieved similar performance (mean DSC across all test sets, 0.793) as models trained on a fully centralized dataset (mean DSC, 0.807). For RDR classification, federated learning achieved a mean AUROC of 0.954 and 0.960; the internal models attained a mean AUROC of 0.956 and 0.973. Similar results are reflected in the other calculated evaluation metrics.

Conclusions

Federated learning showed similar results to traditional deep learning in both applications of segmentation and classification, while maintaining data privacy. Evaluation metrics highlight the potential of collaborative learning for increasing domain diversity and the generalizability of models used for the classification of OCT data.

A Systematic Review of Federated Learning in the Healthcare Area: From the Perspective of Data Properties and Applications

Recent advances in deep learning have shown many successful stories in smart healthcare applications with data-driven insight into improving clinical institutions’ quality of care. Excellent deep learning models are heavily data-driven. The more data trained, the more robust and more generalizable the performance of the deep learning model. However, pooling the medical data into centralized storage to train a robust deep learning model faces privacy, ownership, and strict regulation challenges. Federated learning resolves the previous challenges with a shared global deep learning model using a central aggregator server. At the same time, patient data remain with the local party, maintaining data anonymity and security. In this study, first, we provide a comprehensive, up-to-date review of research employing federated learning in healthcare applications. Second, we evaluate a set of recent challenges from a data-centric perspective in federated learning, such as data partitioning characteristics, data distributions, data protection mechanisms, and benchmark datasets. Finally, we point out several potential challenges and future research directions in healthcare applications.

Federated Learning via Conditional Mutual Learning for Alzheimer's Disease Classification on T1w MRI

Data-driven deep learning has been considered a promising method for building powerful models for medical data, which often requires a large amount of diverse data to be sufficiently effective. However, the expensive cost of collecting and the privacy constraints lead to the fact that existing medical datasets are small-scale and distributed. Federated learning via model distillation is a data-private collaborative learning where the model can leverage all available data without direct sharing. The data knowledge is shared by distillation through the multi-site average prediction scores on the public dataset. However, the average consensus is suboptimal to individual client due to data domain shift in MRI data caused by acquisition protocols, recruitment criteria, etc. In this work, we propose a federated conditional mutual learning (FedCM) to improve the performance by considering the clients' local performance and the similarity between clients. This work is the first federated learning on multi-dataset Alzheimer's disease classification by 3DCNN using T1w MRI. Our method achieves the best recognition rates comparing with FedMD and other frameworks. Further visualization and relevance ranking on the region of interests (ROI) in human brains implies that the left hemisphere may have greater relevance than the right hemisphere does. Several potential regions are listed for future investigation.

Recent Developments in Privacy-Preserving Mining of Clinical Data

With the dramatic increases in both the capability to collect personal data and the capability to analyze large amounts of data, increasingly sophisticated and personal insights are being drawn. These insights are valuable for clinical applications but also open up possibilities for identification and abuse of personal information. In this paper, we survey recent research on classical methods of privacy-preserving data mining. Looking at dominant techniques and recent innovations to them, we examine the applicability of these methods to the privacy-preserving analysis of clinical data. We also discuss promising directions for future research in this area.

Autism spectrum disorder diagnosis using graph attention network based on spatial-constrained sparse functional brain networks

The accurate diagnosis of autism spectrum disorder (ASD), a common mental disease in children, has always been an important task in clinical practice. In recent years, the use of graph neural network (GNN) based on functional brain network (FBN) has shown powerful performance for disease diagnosis. The challenge to construct "ideal" FBN from resting-state fMRI data remained. Moreover, it remains unclear whether and to what extent the non-Euclidean structure of different FBNs affect the performance of GNN-based disease classification. In this paper, we proposed a new method named Pearson's correlation-based Spatial Constraints Representation (PSCR) to estimate the FBN structures that were transformed to brain graphs and then fed into a graph attention network (GAT) to diagnose ASD. Extensive experiments on comparing different FBN construction methods and classification frameworks were conducted on the ABIDE I dataset (n = 871). The results demonstrated the superiority of our PSCR method and the influence of different FBNs on the GNN-based classification results. The proposed PSCR and GAT framework achieved promising classification results for ASD (accuracy: 72.40%), which significantly outperformed competing methods. This will help facilitate patient-control separation, and provide a promising solution for future disease diagnosis based on the FBN and GNN framework.

Federated learning for predicting clinical outcomes in patients with COVID-19

Federated learning (FL) is a method used for training artificial intelligence models with data from multiple sources while maintaining data anonymity, thus removing many barriers to data sharing. Here we used data from 20 institutes across the globe to train a FL model, called EXAM (electronic medical record (EMR) chest X-ray AI model), that predicts the future oxygen requirements of symptomatic patients with COVID-19 using inputs of vital signs, laboratory data and chest X-rays. EXAM achieved an average area under the curve (AUC) >0.92 for predicting outcomes at 24 and 72 h from the time of initial presentation to the emergency room, and it provided 16% improvement in average AUC measured across all participating sites and an average increase in generalizability of 38% when compared with models trained at a single site using that site's data. For prediction of mechanical ventilation treatment or death at 24 h at the largest independent test site, EXAM achieved a sensitivity of 0.950 and specificity of 0.882. In this study, FL facilitated rapid data science collaboration without data exchange and generated a model that generalized across heterogeneous, unharmonized datasets for prediction of clinical outcomes in patients with COVID-19, setting the stage for the broader use of FL in healthcare.

Differential privacy in health research: A scoping review

OBJECTIVE

Differential privacy is a relatively new method for data privacy that has seen growing use due its strong protections that rely on added noise. This study assesses the extent of its awareness, development, and usage in health research.

MATERIALS AND METHODS

A scoping review was conducted by searching for ["differential privacy" AND "health"] in major health science databases, with additional articles obtained via expert consultation. Relevant articles were classified according to subject area and focus.

RESULTS

A total of 54 articles met the inclusion criteria. Nine articles provided descriptive overviews, 31 focused on algorithm development, 9 presented novel data sharing systems, and 8 discussed appraisals of the privacy-utility tradeoff. The most common areas of health research where differential privacy has been discussed are genomics, neuroimaging studies, and health surveillance with personal devices. Algorithms were most commonly developed for the purposes of data release and predictive modeling. Studies on privacy-utility appraisals have considered economic cost-benefit analysis, low-utility situations, personal attitudes toward sharing health data, and mathematical interpretations of privacy risk.

DISCUSSION

Differential privacy remains at an early stage of development for applications in health research, and accounts of real-world implementations are scant. There are few algorithms for explanatory modeling and statistical inference, particularly with correlated data. Furthermore, diminished accuracy in small datasets is problematic. Some encouraging work has been done on decision making with regard to epsilon. The dissemination of future case studies can inform successful appraisals of privacy and utility.

CONCLUSIONS

More development, case studies, and evaluations are needed before differential privacy can see widespread use in health research.

Privacy considerations for sharing genomics data

An increasing amount of attention has been geared towards understanding the privacy risks that arise from sharing genomic data of human origin. Most of these efforts have focused on issues in the context of genomic sequence data, but the popularity of techniques for collecting other types of genome-related data has prompted researchers to investigate privacy concerns in a broader genomic context. In this review, we give an overview of different types of genome-associated data, their individual ways of revealing sensitive information, the motivation to share them as well as established and upcoming methods to minimize information leakage. We further discuss the concise threats that are being posed, who is at risk, and how the risk level compares to potential benefits, all while addressing the topic in the context of modern technology, methodology, and information sharing culture. Additionally, we will discuss the current legal situation regarding the sharing of genomic data in a selection of countries, evaluating the scope of their applicability as well as their limitations. We will finalize this review by evaluating the development that is required in the scientific field in the near future in order to improve and develop privacy-preserving data sharing techniques for the genomic context.

Multi-institutional Collaborations for Improving Deep Learning-based Magnetic Resonance Image Reconstruction Using Federated Learning

Fast and accurate reconstruction of magnetic resonance (MR) images from under-sampled data is important in many clinical applications. In recent years, deep learning-based methods have been shown to produce superior performance on MR image reconstruction. However, these methods require large amounts of data which is difficult to collect and share due to the high cost of acquisition and medical data privacy regulations. In order to overcome this challenge, we propose a federated learning (FL) based solution in which we take advantage of the MR data available at different institutions while preserving patients' privacy. However, the generalizability of models trained with the FL setting can still be suboptimal due to domain shift, which results from the data collected at multiple institutions with different sensors, disease types, and acquisition protocols, etc. With the motivation of circumventing this challenge, we propose a cross-site modeling for MR image reconstruction in which the learned intermediate latent features among different source sites are aligned with the distribution of the latent features at the target site. Extensive experiments are conducted to provide various insights about FL for MR image reconstruction. Experimental results demonstrate that the proposed framework is a promising direction to utilize multi-institutional data without compromising patients' privacy for achieving improved MR image reconstruction. Our code is available at https://github.com/guopengf/FL-MRCM.

A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promises

Since its renaissance, deep learning has been widely used in various medical imaging tasks and has achieved remarkable success in many medical imaging applications, thereby propelling us into the so-called artificial intelligence (AI) era. It is known that the success of AI is mostly attributed to the availability of big data with annotations for a single task and the advances in high performance computing. However, medical imaging presents unique challenges that confront deep learning approaches. In this survey paper, we first present traits of medical imaging, highlight both clinical needs and technical challenges in medical imaging, and describe how emerging trends in deep learning are addressing these issues. We cover the topics of network architecture, sparse and noisy labels, federating learning, interpretability, uncertainty quantification, etc. Then, we present several case studies that are commonly found in clinical practice, including digital pathology and chest, brain, cardiovascular, and abdominal imaging. Rather than presenting an exhaustive literature survey, we instead describe some prominent research highlights related to these case study applications. We conclude with a discussion and presentation of promising future directions.

A marathon, not a sprint - neuroimaging, Open Science and ethics

Open Science is calling for a radical re-thinking of existing scientific practices. Within the neuroimaging community, Open Science practices are taking the form of open data repositories and open lab notebooks. The broad sharing of data that accompanies Open Science, however, raises some difficult ethical and legal issues. With neuroethics as a focusing lens, we explore eight central concerns posed by open data with regard to human brain imaging studies: respect for individuals and communities, concern for marginalized communities, consent, privacy protections, participatory research designs, contextual integrity, fusions of clinical and research goals, and incidental findings. Each consideration assists in bringing nuance to the potential benefits for open data sharing against associated challenges. We combine current understandings with forward-looking solutions to key issues. We conclude by underscoring the need for new policy tools to enhance the potential for responsible open data.

A Deep Learning Approach to Predict Autism Spectrum Disorder Using Multisite Resting-State fMRI

Autism spectrum disorder (ASD) is a complex and degenerative neuro-developmental disorder. Most of the existing methods utilize functional magnetic resonance imaging (fMRI) to detect ASD with a very limited dataset which provides high accuracy but results in poor generalization. To overcome this limitation and to enhance the performance of the automated autism diagnosis model, in this paper, we propose an ASD detection model using functional connectivity features of resting-state fMRI data. Our proposed model utilizes two commonly used brain atlases, Craddock 200 (CC200) and Automated Anatomical Labelling (AAL), and two rarely used atlases Bootstrap Analysis of Stable Clusters (BASC) and Power. A deep neural network (DNN) classifier is used to perform the classification task. Simulation results indicate that the proposed model outperforms state-of-the-art methods in terms of accuracy. The mean accuracy of the proposed model was 88%, whereas the mean accuracy of the state-of-the-art methods ranged from 67% to 85%. The sensitivity, F1-score, and area under receiver operating characteristic curve (AUC) score of the proposed model were 90%, 87%, and 96%, respectively. Comparative analysis on various scoring strategies show the superiority of BASC atlas over other aforementioned atlases in classifying ASD and control.

Distributed learning: a reliable privacy-preserving strategy to change multicenter collaborations using AI

Purpose

The present scoping review aims to assess the non-inferiority of distributed learning over centrally and locally trained machine learning (ML) models in medical applications.

Methods

We performed a literature search using the term “distributed learning” OR “federated learning” in the PubMed/MEDLINE and EMBASE databases. No start date limit was used, and the search was extended until July 21, 2020. We excluded articles outside the field of interest; guidelines or expert opinion, review articles and meta-analyses, editorials, letters or commentaries, and conference abstracts; articles not in the English language; and studies not using medical data. Selected studies were classified and analysed according to their aim(s).

Results

We included 26 papers aimed at predicting one or more outcomes: namely risk, diagnosis, prognosis, and treatment side effect/adverse drug reaction. Distributed learning was compared to centralized or localized training in 21/26 and 14/26 selected papers, respectively. Regardless of the aim, the type of input, the method, and the classifier, distributed learning performed close to centralized training, but two experiments focused on diagnosis. In all but 2 cases, distributed learning outperformed locally trained models.

Conclusion

Distributed learning resulted in a reliable strategy for model development; indeed, it performed equally to models trained on centralized datasets. Sensitive data can get preserved since they are not shared for model development. Distributed learning constitutes a promising solution for ML-based research and practice since large, diverse datasets are crucial for success.

Transfer Learning in Magnetic Resonance Brain Imaging: A Systematic Review

(1) Background: Transfer learning refers to machine learning techniques that focus on acquiring knowledge from related tasks to improve generalization in the tasks of interest. In magnetic resonance imaging (MRI), transfer learning is important for developing strategies that address the variation in MR images from different imaging protocols or scanners. Additionally, transfer learning is beneficial for reutilizing machine learning models that were trained to solve different (but related) tasks to the task of interest. The aim of this review is to identify research directions, gaps in knowledge, applications, and widely used strategies among the transfer learning approaches applied in MR brain imaging; (2) Methods: We performed a systematic literature search for articles that applied transfer learning to MR brain imaging tasks. We screened 433 studies for their relevance, and we categorized and extracted relevant information, including task type, application, availability of labels, and machine learning methods. Furthermore, we closely examined brain MRI-specific transfer learning approaches and other methods that tackled issues relevant to medical imaging, including privacy, unseen target domains, and unlabeled data; (3) Results: We found 129 articles that applied transfer learning to MR brain imaging tasks. The most frequent applications were dementia-related classification tasks and brain tumor segmentation. The majority of articles utilized transfer learning techniques based on convolutional neural networks (CNNs). Only a few approaches utilized clearly brain MRI-specific methodology, and considered privacy issues, unseen target domains, or unlabeled data. We proposed a new categorization to group specific, widely-used approaches such as pretraining and fine-tuning CNNs; (4) Discussion: There is increasing interest in transfer learning for brain MRI. Well-known public datasets have clearly contributed to the popularity of Alzheimer's diagnostics/prognostics and tumor segmentation as applications. Likewise, the availability of pretrained CNNs has promoted their utilization. Finally, the majority of the surveyed studies did not examine in detail the interpretation of their strategies after applying transfer learning, and did not compare their approach with other transfer learning approaches.

Toward a global and reproducible science for brain imaging in neurotrauma: the ENIGMA adult moderate/severe traumatic brain injury working group

The global burden of mortality and morbidity caused by traumatic brain injury (TBI) is significant, and the heterogeneity of TBI patients and the relatively small sample sizes of most current neuroimaging studies is a major challenge for scientific advances and clinical translation. The ENIGMA (Enhancing NeuroImaging Genetics through Meta-Analysis) Adult moderate/severe TBI (AMS-TBI) working group aims to be a driving force for new discoveries in AMS-TBI by providing researchers world-wide with an effective framework and platform for large-scale cross-border collaboration and data sharing. Based on the principles of transparency, rigor, reproducibility and collaboration, we will facilitate the development and dissemination of multiscale and big data analysis pipelines for harmonized analyses in AMS-TBI using structural and functional neuroimaging in combination with non-imaging biomarkers, genetics, as well as clinical and behavioral measures. Ultimately, we will offer investigators an unprecedented opportunity to test important hypotheses about recovery and morbidity in AMS-TBI by taking advantage of our robust methods for large-scale neuroimaging data analysis. In this consensus statement we outline the working group's short-term, intermediate, and long-term goals.

Impact of Machine Learning Pipeline Choices in Autism Prediction From Functional Connectivity Data

Autism Spectrum Disorder (ASD) is a largely prevalent neurodevelopmental condition with a big social and economical impact affecting the entire life of families. There is an intense search for biomarkers that can be assessed as early as possible in order to initiate treatment and preparation of the family to deal with the challenges imposed by the condition. Brain imaging biomarkers have special interest. Specifically, functional connectivity data extracted from resting state functional magnetic resonance imaging (rs-fMRI) should allow to detect brain connectivity alterations. Machine learning pipelines encompass the estimation of the functional connectivity matrix from brain parcellations, feature extraction, and building classification models for ASD prediction. The works reported in the literature are very heterogeneous from the computational and methodological point of view. In this paper, we carry out a comprehensive computational exploration of the impact of the choices involved while building these machine learning pipelines. Specifically, we consider six brain parcellation definitions, five methods for functional connectivity matrix construction, six feature extraction/selection approaches, and nine classifier building algorithms. We report the prediction performance sensitivity to each of these choices, as well as the best results that are comparable with the state of the art.