Ramya Muthukrishnan

32-D474

32 Vassar St

Cambridge, MA 01239

I’m a second-year PhD student at MIT CSAIL in Dr. Polina Golland’s Medical Vision Group. I have been supported by the MIT-Takeda Program and the Abdul Latif Jameel Fellowships. My current research uses equivariant neural networks to track fetal brain motion in MRI, with the aim of enabling a fully auto-navigated imaging system that mitigates motion artifacts in fetal neuroimaging. More broadly, I am interested in modeling and leveraging symmetries in medical imaging data to make learning more efficient.

I obtained my bachelors degree in computer science from the University of Pennsylvania, during which I worked with Dr. Brian Litt at the Center for Neuroengineering and Therapeutics and Drs. Spyros Bakas and Despina Kontos at the Center for Biomedical Image Computing & Analytics on deep learning solutions to automating 3D lesion segmentation in postsurgical epilepsy MRI and quantitative breast density estimation in mammography, respectively. I also received my masters degree in data science from Penn, where I completed my thesis on deploying graph neural networks for distributed control of multi-robot systems under the supervision of Dr. Alejandro Ribeiro. Additionally, I was fortunate enough to intern at MIT Lincoln Laboratory, where I researched neural networks for solving forward and inverse physics problems in the radar domain.

Outside of work, I enjoy staying active, spending time outdoors, traveling, and reading :)

news

May 14, 2025	I presented my poster, titled 3D fetal head pose estimation from MRI navigators with equivariant neural networks, at the 2025 ISMRM Annual Meeting. Video
Mar 6, 2025	Our new preprint on improved keypoint estimation for rigid motion tracking in neuroimaging, Spatial regularisation for improved accuracy and interpretability in keypoint-based registration, is now available on arXiV.
Jan 10, 2025	Our preprint on graph neural networks for distributed coverage control in robot swarms, LPAC: learnable perception-action-communication loops with applications to coverage control, is now available on arXiV.
Nov 28, 2023	Our work on SO(3)-equivariant radar modeling, Symmetric Models for Radar Response Modeling, was presented at the 2023 NeurIPS workshop on Symmetry and Geometry in Neural Representations.
Sep 6, 2023	I started my PhD at MIT CSAIL in the Medical Vision Group, directed by Dr. Polina Golland.

selected publications

2025

E3-Pose: equivariant symmetry-aware rigid pose estimation in fetal brain MRI

Ramya Muthukrishnan, Benjamin Billot, Borjan Gagoski, and 3 more authors

2025

Abs Code

Rigid pose estimation relative to a canon- ical coordinate frame is paramount in medical imaging. It provides consistent anatomical alignment across time, modalities, and subjects, enabling tasks such as regis- tration and motion tracking. Here we present E3-Pose, a method that estimates a canonical 3D pose from volumetric brain MRI. Importantly, E3-Pose uses a E(3)-equivariant convolutional neural network that exploits intrinsic spa- tial symmetries in rigid pose estimation. In turn, this formulation enables us to introduce a novel 9D rotation parametrization, which uses regular and pseudovectors to tackle ambiguities in contralateral brain symmetry. We show that E3-Pose outperforms state-of-the-art methods on motion quantification in fetal brain MRI, and that its symmetry-driven architectural constraints enable it to gen- eralize to challenging and out-of-distribution samples, such as younger fetuses with underdeveloped anatomy. Finally, we demonstrate utility for the clinical application of auto- navigated slice prescription, where extensive simulations show that E3-Pose significantly improves brain coverage and slice readability. Our code and model are available at https://github.com/ramyamut/E3-Pose.
arXiV

Spatial regularisation for improved accuracy and interpretability in keypoint-based registration

Benjamin Billot, Ramya Muthukrishnan, Esra Abaci-Turk, and 4 more authors

2025

Abs HTML PDF Code

Unsupervised registration strategies bypass requirements in ground truth transforms or segmentations by optimising similarity metrics between fixed and moved volumes. Among these methods, a recent subclass of approaches based on unsupervised keypoint detection stand out as very promising for interpretability. Specifically, these methods train a network to predict feature maps for fixed and moving images, from which explainable centres of mass are computed to obtain point clouds, that are then aligned in closed-form. However, the features returned by the network often yield spatially diffuse patterns that are hard to interpret, thus undermining the purpose of keypoint-based registration. Here, we propose a three-fold loss to regularise the spatial distribution of the features. First, we use the KL divergence to model features as point spread functions that we interpret as probabilistic keypoints. Then, we sharpen the spatial distributions of these features to increase the precision of the detected landmarks. Finally, we introduce a new repulsive loss across keypoints to encourage spatial diversity. Overall, our loss considerably improves the interpretability of the features, which now correspond to precise and anatomically meaningful landmarks. We demonstrate our three-fold loss in foetal rigid motion tracking and brain MRI affine registration tasks, where it not only outperforms state-of-the-art unsupervised strategies, but also bridges the gap with state-of-the-art supervised methods. Our code is available at https://github.com/BenBillot/spatial regularisation.
arXiV

LPAC: Learnable perception-action-communication loops with applications to coverage control

Saurav Agarwal, Ramya Muthukrishnan, Walker Gosrich, and 2 more authors

2025

Abs HTML PDF Code

Coverage control is the problem of navigating a robot swarm to collaboratively monitor features or a phenomenon of interest not known a priori. The problem is challenging in decentralized settings with robots that have limited communication and sensing capabilities. We propose a learnable Perception-Action-Communication (LPAC) architecture for the problem, wherein a convolution neural network (CNN) processes localized perception; a graph neural network (GNN) facilitates robot communications; finally, a shallow multi-layer perceptron (MLP) computes robot actions. The GNN enables collaboration in the robot swarm by computing what information to communicate with nearby robots and how to incorporate received information. Evaluations show that the LPAC models—trained using imitation learning—outperform standard decentralized and centralized coverage control algorithms. The learned policy generalizes to environments different from the training dataset, transfers to larger environments with more robots, and is robust to noisy position estimates. The results indicate the suitability of LPAC architectures for decentralized navigation in robot swarms to achieve collaborative behavior.

2023

AAAI

InvRT: Solving Radar Inverse Problems with Transformers

Ramya Muthukrishnan, Justin Goodwin, Adam Kern, and 2 more authors

2023

Abs HTML PDF

A wide variety of applications rely on the characterization of objects from radar observations. Existing approaches in this space primarily focus on inferring object type. In this work, we focus on inferring the input parameters of a physics-based radar simulator from its output, a temporal sequence of radar observations. Sequential radar observations inherently have a complex spatio-temporal structure that is difficult to capture with many standard vision-based deep learning architectures. We model such complex phenomena as a sequence to sequence prediction problem and use a transformer architecture, taking advantage of its ability to capture contextual temporal dependencies. We demonstrate that our method, Inverse Radar Transformer (InvRT), outperforms baseline approaches in predicting object properties, for both high and low observability settings. Furthermore, its errors are highly correlated with the level of object observability, highlighting its potential to learn the geometric limitations of radar sensing.

2022

NeuroImage Clin

Deep learning-based automated segmentation of resection cavities on postsurgical epilepsy MRI

T. Campbell Arnold, Ramya Muthukrishnan, Akash R. Pattnaik, and 9 more authors

NeuroImage: Clinical, 2022

Abs HTML PDF Code

Accurate segmentation of surgical resection sites is critical for clinical assessments and neuroimaging research applications, including resection extent determination, predictive modeling of surgery outcome, and masking image processing near resection sites. In this study, an automated resection cavity segmentation algorithm is developed for analyzing postoperative MRI of epilepsy patients and deployed in an easy-to-use graphical user interface (GUI) that estimates remnant brain volumes, including postsurgical hippocampal remnant tissue. This retrospective study included postoperative T1-weighted MRI from 62 temporal lobe epilepsy (TLE) patients who underwent resective surgery. The resection site was manually segmented and reviewed by a neuroradiologist (JMS). A majority vote ensemble algorithm was used to segment surgical resections, using 3 U-Net convolutional neural networks trained on axial, coronal, and sagittal slices, respectively. The algorithm was trained using 5-fold cross validation, with data partitioned into training (N = 27) testing (N = 9), and validation (N = 9) sets, and evaluated on a separate held-out test set (N = 17). Algorithm performance was assessed using Dice-Sørensen coefficient (DSC), Hausdorff distance, and volume estimates. Additionally, we deploy a fully-automated, GUI-based pipeline that compares resection segmentations with preoperative imaging and reports estimates of resected brain structures. The cross-validation and held-out test median DSCs were 0.84 ± 0.08 and 0.74 ± 0.22 (median ± interquartile range) respectively, which approach inter-rater reliability between radiologists (0.84–0.86) as reported in the literature. Median 95% Hausdorff distances were 3.6 mm and 4.0 mm respectively, indicating high segmentation boundary confidence. Automated and manual resection volume estimates were highly correlated for both cross-validation (r = 0.94, p < 0.0001) and held-out test subjects (r = 0.87, p < 0.0001). Automated and manual segmentations overlapped in all 62 subjects, indicating a low false negative rate. In control subjects (N = 40), the classifier segmented no voxels (N = 33), <50 voxels (N = 5), or a small volumes<0.5 cm3 (N = 2), indicating a low false positive rate that can be controlled via thresholding. There was strong agreement between postoperative hippocampal remnant volumes determined using automated and manual resection segmentations (r = 0.90, p < 0.0001, mean absolute error = 6.3 %), indicating that automated resection segmentations can permit quantification of postoperative brain volumes after epilepsy surgery. Applications include quantification of postoperative remnant brain volumes, correction of deformable registration, and localization of removed brain regions for network modeling.