Rajat M. Thomas

Ahmed El Gazzar, Rajat Mani Thomas, Guido Van Wingen

Single subject prediction of brain disorders from neuroimaging data has gained increasing attention in recent years. Yet, for some heterogeneous disorders such as major depression disorder (MDD) and autism spectrum disorder (ASD), the performance of prediction models on large-scale multi-site datasets remains poor. We present a two-stage framework to improve the diagnosis of heterogeneous psychiatric disorders from resting-state functional magnetic resonance imaging (rs-fMRI). First, we propose a self-supervised mask prediction task on data from healthy individuals that can exploit differences between healthy controls and patients in clinical datasets. Next, we train a supervised classifier on the learned discriminative representations. To model rs-fMRI data, we develop Graph-S4; an extension to the recently proposed state-space model S4 to graph settings where the underlying graph structure is not known in advance. We show that combining the framework and Graph-S4 can significantly improve the diagnostic performance of neuroimaging-based single subject prediction models of MDD and ASD on three open-source multi-center rs-fMRI clinical datasets.

Ahmed ElGazzar, Rajat Thomas, Guido van Wingen

Graph Neural Networks (GNNs) have emerged as a powerful tool to learn from graph-structured data. A paramount example of such data is the brain, which operates as a network, from the micro-scale of neurons, to the macro-scale of regions. This organization deemed GNNs a natural tool of choice to model brain activity, and have consequently attracted a lot of attention in the neuroimaging community. Yet, the advantage of adopting these models over conventional methods has not yet been assessed in a systematic way to gauge if GNNs are capable of leveraging the underlying structure of the data to improve learning. In this work, we study and evaluate the performance of five popular GNN architectures in diagnosing major depression disorder and autism spectrum disorder in two multi-site clinical datasets, and sex classification on the UKBioBank, from functional brain scans under a general uniform framework. Our results show that GNNs fail to outperform kernel-based and structure-agnostic deep learning models, in which 1D CNNs outperform the other methods in all scenarios. We highlight that creating optimal graph structures for functional brain data is a major bottleneck hindering the performance of GNNs, where existing works use arbitrary measures to define the edges resulting in noisy graphs. We therefore propose to integrate graph diffusion into existing architectures and show that it can alleviate this problem and improve their performance. Our results call for increased moderation and rigorous validation when evaluating graph methods and advocate for more data-centeric approaches in developing GNNs for functional neuroimaging applications.

Ahmed El-Gazzar, Rajat Mani Thomas, Guido Van Wingen

Single-subject mapping of resting-state brain functional activity to non-imaging phenotypes is a major goal of neuroimaging. The large majority of learning approaches applied today rely either on static representations or on short-term temporal correlations. This is at odds with the nature of brain activity which is dynamic and exhibit both short- and long-range dependencies. Further, new sophisticated deep learning approaches have been developed and validated on single tasks/datasets. The application of these models for the study of a different targets typically require exhaustive hyperparameter search, model engineering and trial and error to obtain competitive results with simpler linear models. This in turn limit their adoption and hinder fair benchmarking in a rapidly developing area of research. To this end, we propose fMRI-S4; a versatile deep learning model for the classification of phenotypes and psychiatric disorders from the timecourses of resting-state functional magnetic resonance imaging scans. fMRI-S4 capture short- and long- range temporal dependencies in the signal using 1D convolutions and the recently introduced state-space models S4. The proposed architecture is lightweight, sample-efficient and robust across tasks/datasets. We validate fMRI-S4 on the tasks of diagnosing major depressive disorder (MDD), autism spectrum disorder (ASD) and sex classifcation on three multi-site rs-fMRI datasets. We show that fMRI-S4 can outperform existing methods on all three tasks and can be trained as a plug&play model without special hyperpararameter tuning for each setting

Bhavesh Tangirala, Ishan Bhandari, Daniel Laszlo et al.

Tracking the behaviour of livestock enables early detection and thus prevention of contagious diseases in modern animal farms. Apart from economic gains, this would reduce the amount of antibiotics used in livestock farming which otherwise enters the human diet exasperating the epidemic of antibiotic resistance - a leading cause of death. We could use standard video cameras, available in most modern farms, to monitor livestock. However, most computer vision algorithms perform poorly on this task, primarily because, (i) animals bred in farms look identical, lacking any obvious spatial signature, (ii) none of the existing trackers are robust for long duration, and (iii) real-world conditions such as changing illumination, frequent occlusion, varying camera angles, and sizes of the animals make it hard for models to generalize. Given these challenges, we develop an end-to-end behaviour monitoring system for group-housed pigs to perform simultaneous instance level segmentation, tracking, action recognition and re-identification (STAR) tasks. We present starformer, the first end-to-end multiple-object livestock monitoring framework that learns instance-level embeddings for grouped pigs through the use of transformer architecture. For benchmarking, we present Pigtrace, a carefully curated dataset comprising video sequences with instance level bounding box, segmentation, tracking and activity classification of pigs in real indoor farming environment. Using simultaneous optimization on STAR tasks we show that starformer outperforms popular baseline models trained for individual tasks.

Sumit Bhattacharya, Devanshu Arya, Debjani Bhowmick et al.

Optimizing the design of solar cell metallizations is one of the ways to improve the performance of solar cells. Recently, it has been shown that Topology Optimization (TO) can be used to design complex metallization patterns for solar cells that lead to improved performance. TO generates unconventional design patterns that cannot be obtained with the traditional shape optimization methods. In this paper, we show that this design process can be improved further using a deep learning inspired strategy. We present SolarNet, a CNN-based reparameterization scheme that can be used to obtain improved metallization designs. SolarNet modifies the optimization domain such that rather than optimizing the electrode material distribution directly, the weights of a CNN model are optimized. The design generated by CNN is then evaluated using the physics equations, which in turn generates gradients for backpropagation. SolarNet is trained end-to-end involving backpropagation through the solar cell model as well as the CNN pipeline. Through application on solar cells of different shapes as well as different busbar geometries, we demonstrate that SolarNet improves the performance of solar cells compared to the traditional TO approach.

Ahmed El-Gazzar, Mirjam Quaak, Leonardo Cerliani et al.

Functional Magnetic Resonance Imaging (fMRI) captures the temporal dynamics of neural activity as a function of spatial location in the brain. Thus, fMRI scans are represented as 4-Dimensional (3-space + 1-time) tensors. And it is widely believed that the spatio-temporal patterns in fMRI manifests as behaviour and clinical symptoms. Because of the high dimensionality ($\sim$ 1 Million) of fMRI, and the added constraints of limited cardinality of data sets, extracting such patterns are challenging. A standard approach to overcome these hurdles is to reduce the dimensionality of the data by either summarizing activation over time or space at the expense of possible loss of useful information. Here, we introduce an end-to-end algorithm capable of extracting spatiotemporal features from the full 4-D data using 3-D CNNs and 3-D Convolutional LSTMs. We evaluate our proposed model on the publicly available ABIDE dataset to demonstrate the capability of our model to classify Autism Spectrum Disorder (ASD) from resting-state fMRI data. Our results show that the proposed model achieves state of the art results on single sites with F1-scores of 0.78 and 0.7 on NYU and UM sites, respectively.

Ahmed El Gazzar, Leonardo Cerliani, Guido van Wingen et al.

Deep learning methods are increasingly being used with neuroimaging data like structural and function magnetic resonance imaging (MRI) to predict the diagnosis of neuropsychiatric and neurological disorders. For psychiatric disorders in particular, it is believed that one of the most promising modality is the resting-state functional MRI (rsfMRI), which captures the intrinsic connectivity between regions in the brain. Because rsfMRI data points are inherently high-dimensional (~1M), it is impossible to process the entire input in its raw form. In this paper, we propose a very simple transformation of the rsfMRI images that captures all of the temporal dynamics of the signal but sub-samples its spatial extent. As a result, we use a very simple 1-D convolutional network which is fast to train, requires minimal preprocessing and performs at par with the state-of-the-art on the classification of Autism spectrum disorders.

Richard Galvez, David F. Fouhey, Meng Jin et al.

In this paper we present a curated dataset from the NASA Solar Dynamics Observatory (SDO) mission in a format suitable for machine learning research. Beginning from level 1 scientific products we have processed various instrumental corrections, downsampled to manageable spatial and temporal resolutions, and synchronized observations spatially and temporally. We illustrate the use of this dataset with two example applications: forecasting future EVE irradiance from present EVE irradiance and translating HMI observations into AIA observations. For each application we provide metrics and baselines for future model comparison. We anticipate this curated dataset will facilitate machine learning research in heliophysics and the physical sciences generally, increasing the scientific return of the SDO mission. This work is a direct result of the 2018 NASA Frontier Development Laboratory Program. Please see the appendix for access to the dataset.