Search for: All records

This project studied the effects of a class (N=25) on additive manufacturing in a point-of-care healthcare setting funded by NSF IUSE (2337087 and 2337088). This class was run simultaneously with the same curriculum and research methodology at two large public universities. Data were pooled. We focused on two main areas of growth for the engineering undergraduates enrolled in the class: i) knowledge and skills in additive manufacturing in a healthcare setting, ii) skills in communicating with other engineering undergraduates and with healthcare professionals. To determine growth over the course of the semester, we employed both objective and subjective metrics using both qualitative and quantitative methodologies developed by the team. Specifically, we measured content area knowledge through a quiz containing both multiple choice and essay responses at the beginning and end of the semester. This was a statistically significant increase (+10.12, p<. 001). We measured formal written skills through students’ responses to hypothetical email prompts at the beginning and end of the semester. We saw a statistically significant increase in their ability to take another’s perspective during problem solving (+ .48, p<.05). We measured formal spoken skills through mock job interviews conducted at the end of the semester in which the theme of perspective-taking continued: students used many of the skills practiced during the semester to deal with hypothetical scenarios during the semester. When looked at in alignment with the results concerning students’ ability to take another’s perspective, this leads us to conclude that the majority of the growth in communication skills was about the ability to understand another person's goals, motivations, and behaviors in micro-level communication. 

Modeling group actions on latent representations enables controllable transformations of high-dimensional image data. Prior works applying group-theoretic priors or modeling transformations typically operate in the high-dimensional data space, where group actions apply uniformly across the entire input, making it difficult to disentangle the subspace that varies under transformations. While latent-space methods offer greater flexibility, they still require manual partitioning of latent variables into equivariant and invariant subspaces, limiting the ability to robustly learn and operate group actions within the representation space. To address this, we introduce a novel end-to-end framework that for the first time learns group actions on latent image manifolds, automatically discovering transformation-relevant structures without manual intervention. Our method uses learnable binary masks with straight-through estimation to dynamically partition latent representations into transformation-sensitive and invariant components. We formulate this within a unified optimization framework that jointly learns latent disentanglement and group transformation mappings. The framework can be seamlessly integrated with any standard encoder-decoder architecture. We validate our approach on five 2D/3D image datasets, demonstrating its ability to automatically learn disentangled latent factors for group actions in diverse data, while downstream classification tasks confirm the effectiveness of the learned representations. 

Identification and quantification of myocardial scar is important for diagnosis and prognosis of cardiovascular diseases. However, reliable scar segmentation from Late Gadolinium Enhancement Cardiac Magnetic Resonance (LGE-CMR) images remains a challenge due to variations in contrast enhancement across patients, suboptimal imaging conditions such as post-contrast washout, and inconsistencies in ground-truth annotations on diffuse scars caused by interobserver variability. In this work, we propose a curriculum learning-based framework designed to improve segmentation performance under these challenging conditions. The method introduces a progressive training strategy that guides the model from high-confidence, clearly defined scar regions to low-confidence or visually ambiguous samples with limited scar burden. By structuring the learning process in this manner, the network develops robustness to uncertain labels and subtle scar appearances that are often underrepresented in conventional training pipelines. Experimental results show that the proposed approach enhances segmentation accuracy and consistency, particularly for cases with minimal or diffuse scar, outperforming standard training baselines. This strategy provides a principled way to leverage imperfect data for improved myocardial scar quantification in clinical applications. Our code is publicly available on Github. 

This paper presents a novel motion feature guided diffusion model for unpaired video-to-video translation (MFD-V2V), designed to synthesize dynamic, high-contrast cine cardiac magnetic resonance (CMR) from lower-contrast, artifact-prone displacement encoding with stimulated echoes (DENSE) CMR sequences. To achieve this, we first introduce a Latent Temporal Multi-Attention (LTMA) registration network that effectively learns more accurate and consistent cardiac motions from cine CMR image videos. A multi-level motion feature guided diffusion model, equipped with a specialized Spatio-Temporal Motion Encoder (STME) to extract hierarchical coarse-to-fine motion conditioning, is then developed to improve synthesis quality and fidelity. We evaluate our method, MFD-V2V, on a comprehensive cardiac dataset, demonstrating superior performance over the state-of-the-art in both quantitative metrics and qualitative assessments. Furthermore, we show the benefits of our synthesized cine CMRs improving downstream clinical and analytical tasks, underscoring the broader impact of our approach. Our code is publicly available at https://github.com/SwaksharDeb/MFD-V2V.