Institution profile

Morgan State University

Academic institutionnorthamerica · us
Official website
Research library21linked papers
Opportunities0open roles
Selected work

Representative Papers

Advancing AI-Powered Medical Image Synthesis: Insights from MedVQA-GI Challenge Using CLIP, Fine-Tuned Stable Diffusion, and Dream-Booth + LoRA

Feb 28, 2025Conference and Labs of the Evaluation Forum

This work addresses the critical bottleneck in medical diagnosis: the absence of methods for dynamically generating high-fidelity images from clinical text. We propose the first dual-task text-to-image framework tailored for gastrointestinal imaging—comprising Image Synthesis (IS) and Optimal Prompt Generation (OPG). Methodologically, we systematically integrate fine-tuned Stable Diffusion, DreamBooth-based personalization, and LoRA-based low-rank adaptation, coupled with a CLIP text encoder to jointly optimize generation quality, class controllability, and diversity. Evaluated on multi-center data, our approach achieves FID = 0.064 and Inception Score = 2.327, significantly outperforming baseline models. Key contributions include: (1) transcending traditional static image analysis by enabling dynamic, natural-language-driven medical image synthesis; (2) establishing a scalable, high-precision prompt optimization mechanism; and (3) providing a reproducible technical pipeline and standardized evaluation benchmark for clinical-oriented generative AI.

1 citationsRead paper

Complementary Feature Domains: Information Preservation Does Not Imply Predictive-Contribution Preservation

Oct 05, 2026

This study addresses the paradox that while invertible transformations preserve information, they alter the distribution of feature contributions to predictions, yielding a fundamental divergence between information preservation and contribution preservation. To resolve this, we decouple intrinsic information from implementation-dependent contributions and propose quantitative transition laws for multi-representation prediction. By integrating cooperative game-theoretic frameworks with Lipschitz utility analysis, we formalize this deficiency and demonstrate that behavioral distance governs the magnitude of its impact, which is further validated through electrocardiogram experiments. This work elucidates the mechanism by which nonlinear recoding degrades predictive accuracy and establishes that exact inverse mappings can fully recover coalition-wise accuracy across all feature subsets. These findings provide a rigorous theoretical foundation for ensuring contribution consistency in representation learning.

0 citationsRead paper

Representation Bias, Correction Transfer, and Resolution Sensitivity in Three-Dimensional Mitochondrial Morphometry

Oct 05, 2026

This study addresses systematic measurement biases introduced by processing pipelines in quantitative imaging and the failure of cross-condition calibration, systematically evaluating the reliability of three-dimensional mitochondrial morphometry. Methodologically, leveraging a 3D mitochondrial shape library and reimplemented labeling pipelines, empirical analyses were conducted via frozen regression and boundary displacement quantification. Notably, this work innovatively decouples precision from uncertainty transfer for the first time, revealing the risk of insufficient coverage of calibration errors within low-occupancy subpopulations. Results demonstrate that eliminating depth bias reduces volumetric error by 45%, while the regression model lowers the median absolute error to 0.66%; however, overall coverage reaches only 92%.

0 citationsRead paper
Recent publications

Latest Papers

Complementary Feature Domains: Information Preservation Does Not Imply Predictive-Contribution Preservation

Oct 05, 2026

This study addresses the paradox that while invertible transformations preserve information, they alter the distribution of feature contributions to predictions, yielding a fundamental divergence between information preservation and contribution preservation. To resolve this, we decouple intrinsic information from implementation-dependent contributions and propose quantitative transition laws for multi-representation prediction. By integrating cooperative game-theoretic frameworks with Lipschitz utility analysis, we formalize this deficiency and demonstrate that behavioral distance governs the magnitude of its impact, which is further validated through electrocardiogram experiments. This work elucidates the mechanism by which nonlinear recoding degrades predictive accuracy and establishes that exact inverse mappings can fully recover coalition-wise accuracy across all feature subsets. These findings provide a rigorous theoretical foundation for ensuring contribution consistency in representation learning.

0 citationsRead paper

Representation Bias, Correction Transfer, and Resolution Sensitivity in Three-Dimensional Mitochondrial Morphometry

Oct 05, 2026

This study addresses systematic measurement biases introduced by processing pipelines in quantitative imaging and the failure of cross-condition calibration, systematically evaluating the reliability of three-dimensional mitochondrial morphometry. Methodologically, leveraging a 3D mitochondrial shape library and reimplemented labeling pipelines, empirical analyses were conducted via frozen regression and boundary displacement quantification. Notably, this work innovatively decouples precision from uncertainty transfer for the first time, revealing the risk of insufficient coverage of calibration errors within low-occupancy subpopulations. Results demonstrate that eliminating depth bias reduces volumetric error by 45%, while the regression model lowers the median absolute error to 0.66%; however, overall coverage reaches only 92%.

0 citationsRead paper

CFD-Guided Detection of Concept Drift in Multimodal Physiologic Signals

Aug 07, 2026

This study addresses the unreliability of cardiovascular signal predictions from wearable devices due to interference from motion, respiration, and posture changes. To mitigate this, the authors propose PECS, a physiological stability framework that innovatively adapts concepts from computational fluid dynamics to detect concept drift and enable interpretable trust routing. PECS achieves this by comparing internal model variations against observable changes in multimodal signals—primarily ECG, supplemented by PPG, with respiratory signals selectively incorporated in ambiguous scenarios. The framework integrates domain-pair selection strategies with multimodal fusion to dynamically guide model decisions. Evaluated on the BIDMC and MIMIC datasets, PECS achieves concept drift classification accuracies of 0.8786 and 0.9560, respectively, demonstrating its effectiveness and highlighting the selective utility of respiratory signals in resolving prediction discrepancies.

0 citationsRead paper