发表机构
American University of Beirut; Centre de Visió per Computador (CVC); Ingenii Inc.; Hamad Bin Khalifa University（贝鲁特美国大学; 计算机视觉中心 (CVC); 英格尼公司; 哈马德·本·哈利法大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对QUBO用于医学图像分割时的可扩展性挑战，提出基于超像素的QUBO框架，用简单线性迭代聚类分组像素，在区域邻接图上公式化分割。实验表明该方法提升了分割质量、计算速度并减小问题规模，还符合量子退火器连接限制。
AI 中文摘要
二次无约束二进制优化（QUBO）已成为解决医学计算问题的强大框架。二进制决策变量自然地代表临床选择，使QUBO公式非常适合量子退火硬件。然而，一个基本的可扩展性挑战限制了实际部署：问题规模随着输入维度迅速增长，造成计算瓶颈，将应用限制在简化场景。本文通过分层问题约简解决这一挑战，如在医学图像分割中所示，像素级QUBO公式为256x256图像创建超过65000个变量，迫使现有方法下采样到42x42分辨率并丢弃97%的像素信息。提出了基于超像素的QUBO框架，使用简单线性迭代聚类（SLIC）将像素分组为有感知意义的区域，然后在结合最小割和平滑度目标的区域邻接图（RAG）上把分割公式化为QUBO。在INbreast乳腺钼靶乳腺癌图像上的验证表明，分割质量提高了4.2%（平均交并比从0.73提高到0.76），计算速度提高了33倍（从21.97秒降至0.67秒），问题规模减少了97.3%（从1764个变量降至48个变量），所有这些都是在处理全分辨率图像而非下采样版本时实现的。减少的问题规模也很好地符合当前量子退火器的连接限制，消除了历史上阻碍像素级QUBO分割在量子硬件上直接部署的嵌入开销。
英文摘要
Quadratic unconstrained binary optimization (QUBO) has emerged as a powerful framework for medical computing problems. Binary decision variables naturally represent clinical choices, making QUBO formulations well-suited for quantum annealing hardware. However, a fundamental scalability challenge limits practical deployment: problem size grows rapidly with input dimensionality, creating computational bottlenecks that restrict applications to simplified scenarios. This paper addresses this challenge through hierarchical problem reduction, as demonstrated in medical image segmentation, where pixel-level QUBO formulations create over 65,000 variables for a 256x256 image, forcing existing approaches to downsample to 42x42 resolution and discard 97% of pixel information. A superpixel-based QUBO framework is proposed using simple linear iterative clustering (SLIC) to group pixels into perceptually meaningful regions, then formulate segmentation as QUBO over a region adjacency graph (RAG) combining min-cut and smoothness objectives. Validation on INbreast mammography breast cancer images demonstrates a 4.2% improvement in segmentation quality (mean IoU 0.76 vs 0.73) with 33 computational speedup (0.67s vs 21.97s) and a 97.3% reduction in problem size (1764 to 48 variables), all achieved while processing full-resolution images rather than downsampled versions. The reduced problem size also fits well within current quantum annealer connectivity limits, removing the embedding overhead that has historically blocked direct deployment of pixel-level QUBO segmentation on quantum hardware.
Comments7 pages, 2 figures
