🤖 AI Summary
Medical imaging data suffer from high dimensionality and multimodality, leading to inefficiencies in storage, transmission, and processing. To address this, this work systematically reviews low-rank matrix approximation (LRMA) and its localized variant—localized LRMA (LLRMA)—in medical imaging, noting that since 2015, LLRMA has consistently outperformed conventional LRMA in compression accuracy and reconstruction quality. However, existing methods exhibit limitations in structural modeling, cross-modal adaptability, and hyperparameter robustness. We propose three key innovations: (1) a semantic segmentation–driven patch similarity metric to enhance local structural fidelity; (2) a generalized LLRMA framework tailored for structured and semi-structured medical data; and (3) an adaptive patch-size selection strategy integrating Bayesian optimization with random search. Extensive experiments on multi-center imaging datasets demonstrate superior efficiency and robustness. Our approach provides a reproducible, practical pathway for deploying LRMA/LLRMA on heterogeneous medical data.
📝 Abstract
The large volume and complexity of medical imaging datasets are bottlenecks for storage, transmission, and processing. To tackle these challenges, the application of low-rank matrix approximation (LRMA) and its derivative, local LRMA (LLRMA) has demonstrated potential. A detailed analysis of the literature identifies LRMA and LLRMA methods applied to various imaging modalities, and the challenges and limitations associated with existing LRMA and LLRMA methods are addressed. We note a significant shift towards a preference for LLRMA in the medical imaging field since 2015, demonstrating its potential and effectiveness in capturing complex structures in medical data compared to LRMA. Acknowledging the limitations of shallow similarity methods used with LLRMA, we suggest advanced semantic image segmentation for similarity measure, explaining in detail how it can be used to measure similar patches and its feasibility. We note that LRMA and LLRMA are mainly applied to unstructured medical data, and we propose extending their application to different medical data types, including structured and semi-structured. This paper also discusses how LRMA and LLRMA can be applied to regular data with missing entries and the impact of inaccuracies in predicting missing values and their effects. We discuss the impact of patch size and propose the use of random search (RS) to determine the optimal patch size. To enhance feasibility, a hybrid approach using Bayesian optimization and RS is proposed, which could improve the application of LRMA and LLRMA in medical imaging.