arXiv subjects

Laxmi Gewali

Publications and source records attributed to Laxmi Gewali.

4 recordsLinked to original sources

arXiv2026

The segmentation ceiling: why explicit left-ventricular masks do not improve learned ejection-fraction regression

Accurate estimation of left ventricular ejection fraction (EF) from echocardiography is central to cardiovascular care, and deep learning enables automated EF prediction from echocardiographic video. Because EF is clinically derived from left-ventricular (LV) volumes, a widely held intuition is that explicit LV segmentation should improve prediction. We introduce a quantitative criterion, the segmentation ceiling, that makes this testable: from EF as a normalized difference of end-diastolic and end-systolic volumes, we derive in closed form how per-frame segmentation area error propagates into EF error, and thus the accuracy a mask must reach before it can improve on direct regression. Using EchoNet-Dynamic, a UniFormer-S backbone, and the empirically measured within-patient error correlation, the criterion places the break-even near 10% per-frame area error, whereas a representative segmenter operates at roughly 14%, above the ceiling. Consistent with this, four strategies for injecting segmentation or area information (a predicted-mask channel, end-diastolic/end-systolic clip sampling, and per-bin and amplitude area-consistency objectives) fail to beat a raw-video baseline; ground-truth masks help only through label leakage. Input representation thus not being the limit, we identify generalization as the practical lever: weight averaging with strong augmentation attains a test R^2 of 0.806 (MAE 4.08) under a matched dense-clip protocol, comparable to an R(2+1)D baseline (0.811) while tightening the validation-to-test gap. Finally, a heteroscedastic beta-NLL formulation yields informative, well-calibrated per-prediction uncertainty, larger for clinically harder low-EF cases, where Monte-Carlo dropout does not. The segmentation ceiling gives a concrete design criterion for when mask-guided EF estimation is worthwhile, plus a simple, uncertainty-aware recipe for EF regression.

eess.IV↗

arXiv2026

BUSTR: Descriptor-Aware Vision-Language Learning for Breast Ultrasound Report Generation

Breast ultrasound (BUS) reporting relies on clinically meaningful lesion descriptors, including BI-RADS category, lesion shape, margin, echogenicity, posterior features, pathology, and histology. However, many public BUS datasets provide structured annotations and lesion masks without paired radiologist-written reports, limiting the development of vision--language models for BUS report generation. We propose BUSTR, a descriptor-aware vision--language framework that uses structured lesion information to enable report generation under limited report supervision. BUSTR first constructs descriptor-derived reports from available annotations and radiomics features extracted from lesion masks. It then trains a multi-head Swin Transformer encoder with multitask supervision to learn descriptor-aware visual representations across datasets with partially overlapping annotation sets. The projected visual tokens condition a frozen LLaMA-based language model, and training is guided by a dual-level objective combining token-level cross-entropy with representation-level cosine alignment. At inference, BUSTR generates reports from BUS images without access to structured descriptors, lesion masks, or radiomics features. We evaluate BUSTR on the public BrEaST and BUS-BRA datasets using natural language generation and clinical efficacy metrics. BUSTR improves report similarity and descriptor recovery compared with representative report-generation baselines, with notable gains for lesion shape, margin, posterior features, and pathology, as well as improved BI-RADS sensitivity and F1-score on BrEaST. These results suggest that structured BUS descriptors, lesion masks, and radiomics features can provide useful supervision for descriptor-aware BUS report generation when paired radiologist-written reports are unavailable.

cs.CV↗

arXiv2026

Machine Learning-Driven Analysis of kSZ Maps to Predict CMB Optical Depth $τ$

Upcoming measurements of the kinetic Sunyaev-Zel'dovich (kSZ) effect, which results from Cosmic Microwave Background (CMB) photons scattering off moving electrons, offer a powerful probe of the Epoch of Reionization (EoR). The kSZ signal contains key information about the timing, duration, and spatial structure of the EoR. A precise measurement of the CMB optical depth $τ$, a key parameter that characterizes the universe's integrated electron density, would significantly constrain models of early structure formation. However, the weak kSZ signal is difficult to extract from CMB observations due to significant contamination from astrophysical foregrounds. We present a machine learning approach to extract $τ$ from simulated kSZ maps. We train advanced machine learning models, including swin transformers, on high-resolution seminumeric simulations of the kSZ signal. To robustly quantify prediction uncertainties of $τ$, we employ the Laplace Approximation (LA). This approach provides an efficient and principled Gaussian approximation to the posterior distribution over the model's weights, allowing for reliable error estimation. We investigate and compare two distinct application modes: a post-hoc LA applied to a pre-trained model, and an online LA where model weights and hyperparameters are optimized jointly by maximizing the marginal likelihood. This approach provides a framework for robustly constraining $τ$ and its associated uncertainty, which can enhance the analysis of upcoming CMB surveys like the Simons Observatory and CMB-S4.

astro-ph.CO↗

arXiv2025

CMA-ES with Radial Basis Function Surrogate for Black-Box Optimization

Evolutionary optimization algorithms often face defects and limitations that complicate the evolution processes or even prevent them from reaching the global optimum. A notable constraint pertains to the considerable quantity of function evaluations required to achieve the intended solution. This concern assumes heightened significance when addressing costly optimization problems. However, recent research has shown that integrating machine learning methods, specifically surrogate models, with evolutionary optimization can enhance various aspects of these algorithms. Among the evolutionary algorithms, the Covariance Matrix Adaptation Evolutionary Strategy (CMA-ES) is particularly favored. This preference is due to its use of Gaussian distribution for calculating evolution and its ability to adapt optimization parameters, which reduces the need for user intervention in adjusting initial parameters. In this research endeavor, we propose the adoption of surrogate models within the CMA-ES framework called CMA-SAO to develop an initial surrogate model that facilitates the adaptation of optimization parameters through the acquisition of pertinent information derived from the associated surrogate model. Empirical validation reveals that CMA-SAO algorithm markedly diminishes the number of function evaluations in comparison to prevailing algorithms, thereby providing a significant enhancement in operational efficiency.

cs.NE↗