Archana Venkataraman

Sarthak Pati, Ujjwal Baid, Brandon Edwards et al.

Although machine learning (ML) has shown promise in numerous domains, there are concerns about generalizability to out-of-sample data. This is currently addressed by centrally sharing ample, and importantly diverse, data from multiple sites. However, such centralization is challenging to scale (or even not feasible) due to various limitations. Federated ML (FL) provides an alternative to train accurate and generalizable ML models, by only sharing numerical model updates. Here we present findings from the largest FL study to-date, involving data from 71 healthcare institutions across 6 continents, to generate an automatic tumor boundary detector for the rare disease of glioblastoma, utilizing the largest dataset of such patients ever used in the literature (25,256 MRI scans from 6,314 patients). We demonstrate a 33% improvement over a publicly trained model to delineate the surgically targetable tumor, and 23% improvement over the tumor's entire extent. We anticipate our study to: 1) enable more studies in healthcare informed by large and diverse data, ensuring meaningful results for rare diseases and underrepresented populations, 2) facilitate further quantitative analyses for glioblastoma via performance optimization of our consensus model for eventual public release, and 3) demonstrate the effectiveness of FL at such scale and task complexity as a paradigm shift for multi-site collaborations, alleviating the need for data sharing.

Zijian Chen, Maria Varkanitsa, Prakash Ishwar et al.

We propose a lesion-aware graph neural network (LEGNet) to predict language ability from resting-state fMRI (rs-fMRI) connectivity in patients with post-stroke aphasia. Our model integrates three components: an edge-based learning module that encodes functional connectivity between brain regions, a lesion encoding module, and a subgraph learning module that leverages functional similarities for prediction. We use synthetic data derived from the Human Connectome Project (HCP) for hyperparameter tuning and model pretraining. We then evaluate the performance using repeated 10-fold cross-validation on an in-house neuroimaging dataset of post-stroke aphasia. Our results demonstrate that LEGNet outperforms baseline deep learning methods in predicting language ability. LEGNet also exhibits superior generalization ability when tested on a second in-house dataset that was acquired under a slightly different neuroimaging protocol. Taken together, the results of this study highlight the potential of LEGNet in effectively learning the relationships between rs-fMRI connectivity and language ability in a patient cohort with brain lesions for improved post-stroke aphasia evaluation.

Ravi Shankar, Abdouh Harouna Kenfack, Arjun Somayazulu et al.

Automated emotion recognition in speech is a long-standing problem. While early work on emotion recognition relied on hand-crafted features and simple classifiers, the field has now embraced end-to-end feature learning and classification using deep neural networks. In parallel to these models, researchers have proposed several data augmentation techniques to increase the size and variability of existing labeled datasets. Despite many seminal contributions in the field, we still have a poor understanding of the interplay between the network architecture and the choice of data augmentation. Moreover, only a handful of studies demonstrate the generalizability of a particular model across multiple datasets, which is a prerequisite for robust real-world performance. In this paper, we conduct a comprehensive evaluation of popular deep learning approaches for emotion recognition. To eliminate bias, we fix the model architectures and optimization hyperparameters using the VESUS dataset and then use repeated 5-fold cross validation to evaluate the performance on the IEMOCAP and CREMA-D datasets. Our results demonstrate that long-range dependencies in the speech signal are critical for emotion recognition and that speed/rate augmentation offers the most robust performance gain across models.

Niharika S. D'Souza, Archana Venkataraman

Connectomics has emerged as a powerful tool in neuroimaging and has spurred recent advancements in statistical and machine learning methods for connectivity data. Despite connectomes inhabiting a matrix manifold, most analytical frameworks ignore the underlying data geometry. This is largely because simple operations, such as mean estimation, do not have easily computable closed-form solutions. We propose a geometrically aware neural framework for connectomes, i.e., the mSPD-NN, designed to estimate the geodesic mean of a collections of symmetric positive definite (SPD) matrices. The mSPD-NN is comprised of bilinear fully connected layers with tied weights and utilizes a novel loss function to optimize the matrix-normal equation arising from Fréchet mean estimation. Via experiments on synthetic data, we demonstrate the efficacy of our mSPD-NN against common alternatives for SPD mean estimation, providing competitive performance in terms of scalability and robustness to noise. We illustrate the real-world flexibility of the mSPD-NN in multiple experiments on rs-fMRI data and demonstrate that it uncovers stable biomarkers associated with subtle network differences among patients with ADHD-ASD comorbidities and healthy controls.

Ravi Shankar, Archana Venkataraman

In this paper, we propose the first method to modify the prosodic features of a given speech signal using actor-critic reinforcement learning strategy. Our approach uses a Bayesian framework to identify contiguous segments of importance that links segments of the given utterances to perception of emotions in humans. We train a neural network to produce the variational posterior of a collection of Bernoulli random variables; our model applies a Markov prior on it to ensure continuity. A sample from this distribution is used for downstream emotion prediction. Further, we train the neural network to predict a soft assignment over emotion categories as the target variable. In the next step, we modify the prosodic features (pitch, intensity, and rhythm) of the masked segment to increase the score of target emotion. We employ an actor-critic reinforcement learning to train the prosody modifier by discretizing the space of modifications. Further, it provides a simple solution to the problem of gradient computation through WSOLA operation for rhythm manipulation. Our experiments demonstrate that this framework changes the perceived emotion of a given speech utterance to the target. Further, we show that our unified technique is on par with state-of-the-art emotion conversion models from supervised and unsupervised domains that require pairwise training.

Jueqi Wang, Zachary Jacokes, John Darrell Van Horn et al.

While imaging-genetics holds great promise for unraveling the complex interplay between brain structure and genetic variation in neurological disorders, traditional methods are limited to simplistic linear models or to black-box techniques that lack interpretability. In this paper, we present NeuroPathX, an explainable deep learning framework that uses an early fusion strategy powered by cross-attention mechanisms to capture meaningful interactions between structural variations in the brain derived from MRI and established biological pathways derived from genetics data. To enhance interpretability and robustness, we introduce two loss functions over the attention matrix - a sparsity loss that focuses on the most salient interactions and a pathway similarity loss that enforces consistent representations across the cohort. We validate NeuroPathX on both autism spectrum disorder and Alzheimer's disease. Our results demonstrate that NeuroPathX outperforms competing baseline approaches and reveals biologically plausible associations linked to the disorder. These findings underscore the potential of NeuroPathX to advance our understanding of complex brain disorders. Code is available at https://github.com/jueqiw/NeuroPathX .

Markus D. Schirmer, Archana Venkataraman, Islem Rekik et al.

Large, open-source consortium datasets have spurred the development of new and increasingly powerful machine learning approaches in brain connectomics. However, one key question remains: are we capturing biologically relevant and generalizable information about the brain, or are we simply overfitting to the data? To answer this, we organized a scientific challenge, the Connectomics in NeuroImaging Transfer Learning Challenge (CNI-TLC), held in conjunction with MICCAI 2019. CNI-TLC included two classification tasks: (1) diagnosis of Attention-Deficit/Hyperactivity Disorder (ADHD) within a pre-adolescent cohort; and (2) transference of the ADHD model to a related cohort of Autism Spectrum Disorder (ASD) patients with an ADHD comorbidity. In total, 240 resting-state fMRI time series averaged according to three standard parcellation atlases, along with clinical diagnosis, were released for training and validation (120 neurotypical controls and 120 ADHD). We also provided demographic information of age, sex, IQ, and handedness. A second set of 100 subjects (50 neurotypical controls, 25 ADHD, and 25 ASD with ADHD comorbidity) was used for testing. Models were submitted in a standardized format as Docker images through ChRIS, an open-source image analysis platform. Utilizing an inclusive approach, we ranked the methods based on 16 different metrics. The final rank was calculated using the rank product for each participant across all measures. Furthermore, we assessed the calibration curves of each method. Five participants submitted their model for evaluation, with one outperforming all other methods in both ADHD and ASD classification. However, further improvements are needed to reach the clinical translation of functional connectomics. We are keeping the CNI-TLC open as a publicly available resource for developing and validating new classification methodologies in the field of connectomics.

Zijian Chen, Jueqi Wang, Archana Venkataraman

We propose an image-conditioned diffusion model to estimate high angular resolution diffusion weighted imaging (DWI) from a low angular resolution acquisition. Our model, which we call QID$^2$, takes as input a set of low angular resolution DWI data and uses this information to estimate the DWI data associated with a target gradient direction. We leverage a U-Net architecture with cross-attention to preserve the positional information of the reference images, further guiding the target image generation. We train and evaluate QID$^2$ on single-shell DWI samples curated from the Human Connectome Project (HCP) dataset. Specifically, we sub-sample the HCP gradient directions to produce low angular resolution DWI data and train QID$^2$ to reconstruct the missing high angular resolution samples. We compare QID$^2$ with two state-of-the-art GAN models. Our results demonstrate that QID$^2$ not only achieves higher-quality generated images, but it consistently outperforms the GAN models in downstream tensor estimation across multiple metrics. Taken together, this study highlights the potential of diffusion models, and QID$^2$ in particular, for q-space up-sampling, thus offering a promising toolkit for clinical and research applications.

Deeksha M Shama, Archana Venkataraman

Deep learning methods are at the forefront of automated epileptic seizure detection and onset zone localization using scalp-EEG. However, the performance of deep learning methods rely heavily on the quality of annotated training datasets. Scalp EEG is susceptible to high noise levels, which in turn leads to imprecise annotations of the seizure timing and characteristics. This label noise presents a significant challenge in model training and generalization. In this paper, we introduce a novel statistical framework that informs a deep learning model of label ambiguity, thereby enhancing the overall seizure detection performance. Our Bayesian UncertaiNty-aware Deep Learning, BUNDL, strategy offers a straightforward and model-agnostic method for training deep neural networks with noisy training labels that does not add any parameters to existing architectures. By integrating domain knowledge into the statistical framework, we derive a novel KL-divergence-based loss function that capitalizes on uncertainty to better learn seizure characteristics from scalp EEG. Additionally, we explore the impact of improved seizure detection on the task of automated onset zone localization. We validate BUNDL using a comprehensive simulated EEG dataset and two publicly available datasets, TUH and CHB-MIT. BUNDL consistently improves the performance of three base models on simulated data under seven types of label noise and three EEG signal-to-noise ratios. Similar improvements were observed in the real-world TUH and CHB-MIT datasets. Finally, we demonstrate that BUNDL improves the accuracy of seizure onset zone localization. BUNDL is specifically designed to address label ambiguities, enabling the training of reliable and trustworthy models for epilepsy evaluation.

Ashwin De Silva, Rahul Ramesh, Lyle Ungar et al.

Learning is a process which can update decision rules, based on past experience, such that future performance improves. Traditionally, machine learning is often evaluated under the assumption that the future will be identical to the past in distribution or change adversarially. But these assumptions can be either too optimistic or pessimistic for many problems in the real world. Real world scenarios evolve over multiple spatiotemporal scales with partially predictable dynamics. Here we reformulate the learning problem to one that centers around this idea of dynamic futures that are partially learnable. We conjecture that certain sequences of tasks are not retrospectively learnable (in which the data distribution is fixed), but are prospectively learnable (in which distributions may be dynamic), suggesting that prospective learning is more difficult in kind than retrospective learning. We argue that prospective learning more accurately characterizes many real world problems that (1) currently stymie existing artificial intelligence solutions and/or (2) lack adequate explanations for how natural intelligences solve them. Thus, studying prospective learning will lead to deeper insights and solutions to currently vexing challenges in both natural and artificial intelligences.

Ravi Shankar, Archana Venkataraman

We propose the first method to adaptively modify the duration of a given speech signal. Our approach uses a Bayesian framework to define a latent attention map that links frames of the input and target utterances. We train a masked convolutional encoder-decoder network to produce this attention map via a stochastic version of the mean absolute error loss function; our model also predicts the length of the target speech signal using the encoder embeddings. The predicted length determines the number of steps for the decoder operation. During inference, we generate the attention map as a proxy for the similarity matrix between the given input speech and an unknown target speech signal. Using this similarity matrix, we compute a warping path of alignment between the two signals. Our experiments demonstrate that this adaptive framework produces similar results to dynamic time warping, which relies on a known target signal, on both voice conversion and emotion conversion tasks. We also show that our technique results in a high quality of generated speech that is on par with state-of-the-art vocoders.

Niharika Shimona D'Souza, Mary Beth Nebel, Deana Crocetti et al.

We propose a novel matrix autoencoder to map functional connectomes from resting state fMRI (rs-fMRI) to structural connectomes from Diffusion Tensor Imaging (DTI), as guided by subject-level phenotypic measures. Our specialized autoencoder infers a low dimensional manifold embedding for the rs-fMRI correlation matrices that mimics a canonical outer-product decomposition. The embedding is simultaneously used to reconstruct DTI tractography matrices via a second manifold alignment decoder and to predict inter-subject phenotypic variability via an artificial neural network. We validate our framework on a dataset of 275 healthy individuals from the Human Connectome Project database and on a second clinical dataset consisting of 57 subjects with Autism Spectrum Disorder. We demonstrate that the model reliably recovers structural connectivity patterns across individuals, while robustly extracting predictive and interpretable brain biomarkers in a cross-validated setting. Finally, our framework outperforms several baselines at predicting behavioral phenotypes in both real-world datasets.

Sayan Ghosal, Qiang Chen, Giulio Pergola et al.

We propose a novel deep neural network architecture to integrate imaging and genetics data, as guided by diagnosis, that provides interpretable biomarkers. Our model consists of an encoder, a decoder and a classifier. The encoder learns a non-linear subspace shared between the input data modalities. The classifier and the decoder act as regularizers to ensure that the low-dimensional encoding captures predictive differences between patients and controls. We use a learnable dropout layer to extract interpretable biomarkers from the data, and our unique training strategy can easily accommodate missing data modalities across subjects. We have evaluated our model on a population study of schizophrenia that includes two functional MRI (fMRI) paradigms and Single Nucleotide Polymorphism (SNP) data. Using 10-fold cross validation, we demonstrate that our model achieves better classification accuracy than baseline methods, and that this performance generalizes to a second dataset collected at a different site. In an exploratory analysis we further show that the biomarkers identified by our model are closely associated with the well-documented deficits in schizophrenia.

Naresh Nandakumar, Niharika Shimona D'souza, Komal Manzoor et al.

We present a novel deep learning framework that uses dynamic functional connectivity to simultaneously localize the language and motor areas of the eloquent cortex in brain tumor patients. Our method leverages convolutional layers to extract graph-based features from the dynamic connectivity matrices and a long-short term memory (LSTM) attention network to weight the relevant time points during classification. The final stage of our model employs multi-task learning to identify different eloquent subsystems. Our unique training strategy finds a shared representation between the cognitive networks of interest, which enables us to handle missing patient data. We evaluate our method on resting-state fMRI data from 56 brain tumor patients while using task fMRI activations as surrogate ground-truth labels for training and testing. Our model achieves higher localization accuracies than conventional deep learning approaches and can identify bilateral language areas even when trained on left-hemisphere lateralized cases. Hence, our method may ultimately be useful for preoperative mapping in tumor patients.

Niharika Shimona D'Souza, Mary Beth Nebel, Deana Crocetti et al.

We propose a novel integrated framework that jointly models complementary information from resting-state functional MRI (rs-fMRI) connectivity and diffusion tensor imaging (DTI) tractography to extract biomarkers of brain connectivity predictive of behavior. Our framework couples a generative model of the connectomics data with a deep network that predicts behavioral scores. The generative component is a structurally-regularized Dynamic Dictionary Learning (sr-DDL) model that decomposes the dynamic rs-fMRI correlation matrices into a collection of shared basis networks and time varying subject-specific loadings. We use the DTI tractography to regularize this matrix factorization and learn anatomically informed functional connectivity profiles. The deep component of our framework is an LSTM-ANN block, which uses the temporal evolution of the subject-specific sr-DDL loadings to predict multidimensional clinical characterizations. Our joint optimization strategy collectively estimates the basis networks, the subject-specific time-varying loadings, and the neural network weights. We validate our framework on a dataset of neurotypical individuals from the Human Connectome Project (HCP) database to map to cognition and on a separate multi-score prediction task on individuals diagnosed with Autism Spectrum Disorder (ASD) in a five-fold cross validation setting. Our hybrid model outperforms several state-of-the-art approaches at clinical outcome prediction and learns interpretable multimodal neural signatures of brain organization.

Niharika Shimona D'Souza, Mary Beth Nebel, Nicholas Wymbs et al.

We propose a novel optimization framework to predict clinical severity from resting state fMRI (rs-fMRI) data. Our model consists of two coupled terms. The first term decomposes the correlation matrices into a sparse set of representative subnetworks that define a network manifold. These subnetworks are modeled as rank-one outer-products which correspond to the elemental patterns of co-activation across the brain; the subnetworks are combined via patient-specific non-negative coefficients. The second term is a linear regression model that uses the patient-specific coefficients to predict a measure of clinical severity. We validate our framework on two separate datasets in a ten fold cross validation setting. The first is a cohort of fifty-eight patients diagnosed with Autism Spectrum Disorder (ASD). The second dataset consists of sixty three patients from a publicly available ASD database. Our method outperforms standard semi-supervised frameworks, which employ conventional graph theoretic and statistical representation learning techniques to relate the rs-fMRI correlations to behavior. In contrast, our joint network optimization framework exploits the structure of the rs-fMRI correlation matrices to simultaneously capture group level effects and patient heterogeneity. Finally, we demonstrate that our proposed framework robustly identifies clinically relevant networks characteristic of ASD.

Ravi Shankar, Hsi-Wei Hsieh, Nicolas Charon et al.

We propose a novel method for emotion conversion in speech based on a chained encoder-decoder-predictor neural network architecture. The encoder constructs a latent embedding of the fundamental frequency (F0) contour and the spectrum, which we regularize using the Large Diffeomorphic Metric Mapping (LDDMM) registration framework. The decoder uses this embedding to predict the modified F0 contour in a target emotional class. Finally, the predictor uses the original spectrum and the modified F0 contour to generate a corresponding target spectrum. Our joint objective function simultaneously optimizes the parameters of three model blocks. We show that our method outperforms the existing state-of-the-art approaches on both, the saliency of emotion conversion and the quality of resynthesized speech. In addition, the LDDMM regularization allows our model to convert phrases that were not present in training, thus providing evidence for out-of-sample generalization.

Ravi Shankar, Jacob Sager, Archana Venkataraman

We introduce a novel method for emotion conversion in speech that does not require parallel training data. Our approach loosely relies on a cycle-GAN schema to minimize the reconstruction error from converting back and forth between emotion pairs. However, unlike the conventional cycle-GAN, our discriminator classifies whether a pair of input real and generated samples corresponds to the desired emotion conversion (e.g., A to B) or to its inverse (B to A). We will show that this setup, which we refer to as a variational cycle-GAN (VC-GAN), is equivalent to minimizing the empirical KL divergence between the source features and their cyclic counterpart. In addition, our generator combines a trainable deep network with a fixed generative block to implement a smooth and invertible transformation on the input features, in our case, the fundamental frequency (F0) contour. This hybrid architecture regularizes our adversarial training procedure. We use crowd sourcing to evaluate both the emotional saliency and the quality of synthesized speech. Finally, we show that our model generalizes to new speakers by modifying speech produced by Wavenet.

Niharika Shimona D'Souza, Mary Beth Nebel, Deana Crocetti et al.

We propose an integrated deep-generative framework, that jointly models complementary information from resting-state functional MRI (rs-fMRI) connectivity and diffusion tensor imaging (DTI) tractography to extract predictive biomarkers of a disease. The generative part of our framework is a structurally-regularized Dynamic Dictionary Learning (sr-DDL) model that decomposes the dynamic rs-fMRI correlation matrices into a collection of shared basis networks and time varying patient-specific loadings. This matrix factorization is guided by the DTI tractography matrices to learn anatomically informed connectivity profiles. The deep part of our framework is an LSTM-ANN block, which models the temporal evolution of the patient sr-DDL loadings to predict multidimensional clinical severity. Our coupled optimization procedure collectively estimates the basis networks, the patient-specific dynamic loadings, and the neural network weights. We validate our framework on a multi-score prediction task in 57 patients diagnosed with Autism Spectrum Disorder (ASD). Our hybrid model outperforms state-of-the-art baselines in a five-fold cross validated setting and extracts interpretable multimodal neural signatures of brain dysfunction in ASD.

Niharika Shimona D'Souza, Mary Beth Nebel, Nicholas Wymbs et al.

We propose a unified optimization framework that combines neural networks with dictionary learning to model complex interactions between resting state functional MRI and behavioral data. The dictionary learning objective decomposes patient correlation matrices into a collection of shared basis networks and subject-specific loadings. These subject-specific features are simultaneously input into a neural network that predicts multidimensional clinical information. Our novel optimization framework combines the gradient information from the neural network with that of a conventional matrix factorization objective. This procedure collectively estimates the basis networks, subject loadings, and neural network weights most informative of clinical severity. We evaluate our combined model on a multi-score prediction task using 52 patients diagnosed with Autism Spectrum Disorder (ASD). Our integrated framework outperforms state-of-the-art methods in a ten-fold cross validated setting to predict three different measures of clinical severity.

Niharika Shimona D'Souza, Mary Beth Nebel, Nicholas Wymbs et al.

The problem of linking functional connectomics to behavior is extremely challenging due to the complex interactions between the two distinct, but related, data domains. We propose a coupled manifold optimization framework which projects fMRI data onto a low dimensional matrix manifold common to the cohort. The patient specific loadings simultaneously map onto a behavioral measure of interest via a second, non-linear, manifold. By leveraging the kernel trick, we can optimize over a potentially infinite dimensional space without explicitly computing the embeddings. As opposed to conventional manifold learning, which assumes a fixed input representation, our framework directly optimizes for embedding directions that predict behavior. Our optimization algorithm combines proximal gradient descent with the trust region method, which has good convergence guarantees. We validate our framework on resting state fMRI from fifty-eight patients with Autism Spectrum Disorder using three distinct measures of clinical severity. Our method outperforms traditional representation learning techniques in a cross validated setting, thus demonstrating the predictive power of our coupled objective.

Nicha C. Dvornek, Daniel Yang, Archana Venkataraman et al.

Treating children with autism spectrum disorders (ASD) with behavioral interventions, such as Pivotal Response Treatment (PRT), has shown promise in recent studies. However, deciding which therapy is best for a given patient is largely by trial and error, and choosing an ineffective intervention results in loss of valuable treatment time. We propose predicting patient response to PRT from baseline task-based fMRI by the novel application of a random forest and tree bagging strategy. Our proposed learning pipeline uses random forest regression to determine candidate brain voxels that may be informative in predicting treatment response. The candidate voxels are then tested stepwise for inclusion in a bagged tree ensemble. After the predictive model is constructed, bias correction is performed to further increase prediction accuracy. Using data from 19 ASD children who underwent a 16 week trial of PRT and a leave-one-out cross-validation framework, the presented learning pipeline was tested against several standard methods and variations of the pipeline and resulted in the highest prediction accuracy.