arXiv subjects

Nikolas Pontikos

Publications and source records attributed to Nikolas Pontikos.

3 recordsLinked to original sources

arXiv2026

The Quantum Cliff: A Critical Proton Tunneling Threshold Determines Clinical Severity in RPE65-Mediated Retinal Disease

Predicting clinical severity from genotype remains a fundamental challenge in molecular medicine, particularly for enzymes whose function depends on sub-atomic-scale geometry. Mutations in the \textit{RPE65} isomerohydrolase cause Leber Congenital Amaurosis (LCA) and related retinal diseases; however, the kinetic mechanisms connecting sub-atomic-scale perturbations to blindness remain unclear. In this study, we demonstrate that mutations in the human visual isomerase RPE65 are governed by a quantum-mechanical threshold effect arising from proton tunneling in the active site. We established a hybrid quantum-classical structure-to-phenotype pipeline combining AlphaFold structure prediction with \textit{ab initio} quantum simulation using the Variational Quantum Eigensolver (VQE) to analyze minimal proton-coupled electron transfer in the visual cycle. Our analysis reveals that many pathogenic mutations do not merely occlude the active site, but rather strongly reduce the quantum probability of proton tunneling. We observed a sharp non-linear effect, termed the "Quantum Cliff," where minute structural changes (below 0.1 \AA) reduce the reaction rate by multiple orders of magnitude. Based on these findings, we introduce a dimensionless Relative Quantum Activity Score (RQAS) that isolates the geometry-controlled exponential sensitivity of the reaction rate and successfully distinguishes between mild and severe patient phenotypes. These results suggest that RPE65 operates near a quantum-critical point, where sub-Angstrom structural perturbations induce a catastrophic loss of function. Furthermore, our findings establish quantum tunneling as a predictive mechanistic link between atomic structure and clinical phenotype, proposing a general framework for quantum-structural disease modeling.

cs.ET↗

arXiv2025

Hierarchical Attention for Sparse Volumetric Anomaly Detection in Subclinical Keratoconus

The detection of weak, spatially distributed anomalies in volumetric medical imaging remains challenging due to the difficulty of integrating subtle signals across non-adjacent regions. This study presents a controlled comparison of sixteen architectures spanning convolutional, hybrid, and transformer families for subclinical keratoconus detection from three-dimensional anterior segment optical coherence tomography (AS-OCT). The results demonstrate that hierarchical architectures achieve 21-23% higher sensitivity and specificity, particularly in the difficult subclinical regime, outperforming both convolutional neural networks (CNNs) and global-attention Vision Transformer (ViT) baselines. Mechanistic analyses indicate that this advantage arises from spatial scale alignment: hierarchical windowing produces effective receptive fields matched to the intermediate extent of subclinical abnormalities, avoiding the excessive locality observed in convolutional models and the diffuse integration characteristic of pure global attention. Attention-distance measurements show that subclinical cases require longer spatial integration than healthy or overtly pathological volumes, with hierarchical models exhibiting lower variance and more anatomically coherent focus. Representational similarity further indicates that hierarchical attention learns a distinct feature space that balances local structure sensitivity with flexible long-range interactions. Auxiliary age and sex prediction tasks demonstrate moderately high cross-task consistency, supporting the generalizability of these inductive principles. The findings provide design guidance for volumetric anomaly detection and highlight hierarchical attention as a principled approach for early pathological change analysis in medical imaging.

cs.CV↗

arXiv2023

Exploring Multimodal Large Language Models for Radiology Report Error-checking

This paper proposes one of the first clinical applications of multimodal large language models (LLMs) as an assistant for radiologists to check errors in their reports. We created an evaluation dataset from real-world radiology datasets (including X-rays and CT scans). A subset of original reports was modified to contain synthetic errors by introducing three types of mistakes: "insert", "remove", and "substitute". The evaluation contained two difficulty levels: SIMPLE for binary error-checking and COMPLEX for identifying error types. At the SIMPLE level, our fine-tuned model significantly enhanced performance by 47.4% and 25.4% on MIMIC-CXR and IU X-ray data, respectively. This performance boost is also observed in unseen modality, CT scans, as the model performed 19.46% better than the baseline model. The model also surpassed the domain expert's accuracy in the MIMIC-CXR dataset by 1.67%. Notably, among the subsets (N=21) of the test set where a clinician did not achieve the correct conclusion, the LLaVA ensemble mode correctly identified 71.4% of these cases. However, all models performed poorly in identifying mistake types, underscoring the difficulty of the COMPLEX level. This study marks a promising step toward utilizing multimodal LLMs to enhance diagnostic accuracy in radiology. The ensemble model demonstrated comparable performance to clinicians, even capturing errors overlooked by humans.

cs.CL↗