潛在擴散自編碼器：邁向醫學影像中高效且有意義的無監督表徵學習

Latent Diffusion Autoencoders: Toward Efficient and Meaningful Unsupervised Representation Learning in Medical Imaging

April 11, 2025

作者: Gabriele Lozupone, Alessandro Bria, Francesco Fontanella, Frederick J. A. Meijer, Claudio De Stefano, Henkjan Huisman

cs.AI

摘要

本研究提出了潛在擴散自編碼器（Latent Diffusion Autoencoder, LDAE），這是一種新穎的基於擴散過程的編碼-解碼框架，專為醫學影像中的高效且有意義的無監督學習而設計，並以阿爾茨海默病（AD）為例，利用來自ADNI數據庫的腦部磁共振影像進行案例研究。與傳統在影像空間運作的擴散自編碼器不同，LDAE將擴散過程應用於壓縮後的潛在表示中，從而提升計算效率，使三維醫學影像的表示學習變得可行。為驗證所提方法，我們探討了兩個關鍵假設：(i) LDAE能有效捕捉與AD及老化相關的三維腦部磁共振影像中的有意義語義表示；(ii) LDAE在保持計算效率的同時，能實現高質量的影像生成與重建。實驗結果支持了這兩項假設：(i) 線性探針評估顯示出對AD診斷（ROC-AUC：90%，ACC：84%）及年齡預測（MAE：4.1年，RMSE：5.2年）的優異性能；(ii) 學習到的語義表示支持屬性操控，產生解剖學上合理的修改；(iii) 語義插值實驗展示了對缺失掃描的強重建能力，對於6個月間隔的掃描，SSIM達0.969（MSE：0.0019）。即使對於更長的間隔（24個月），模型仍保持穩健性能（SSIM > 0.93，MSE < 0.004），表明其能捕捉時間進展趨勢；(iv) 與傳統擴散自編碼器相比，LDAE顯著提升了推理吞吐量（快20倍），同時也提高了重建質量。這些發現使LDAE成為可擴展醫學影像應用的有前景框架，並有潛力作為醫學影像分析的基礎模型。代碼可於https://github.com/GabrieleLozupone/LDAE獲取。

English

This study presents Latent Diffusion Autoencoder (LDAE), a novel encoder-decoder diffusion-based framework for efficient and meaningful unsupervised learning in medical imaging, focusing on Alzheimer disease (AD) using brain MR from the ADNI database as a case study. Unlike conventional diffusion autoencoders operating in image space, LDAE applies the diffusion process in a compressed latent representation, improving computational efficiency and making 3D medical imaging representation learning tractable. To validate the proposed approach, we explore two key hypotheses: (i) LDAE effectively captures meaningful semantic representations on 3D brain MR associated with AD and ageing, and (ii) LDAE achieves high-quality image generation and reconstruction while being computationally efficient. Experimental results support both hypotheses: (i) linear-probe evaluations demonstrate promising diagnostic performance for AD (ROC-AUC: 90%, ACC: 84%) and age prediction (MAE: 4.1 years, RMSE: 5.2 years); (ii) the learned semantic representations enable attribute manipulation, yielding anatomically plausible modifications; (iii) semantic interpolation experiments show strong reconstruction of missing scans, with SSIM of 0.969 (MSE: 0.0019) for a 6-month gap. Even for longer gaps (24 months), the model maintains robust performance (SSIM > 0.93, MSE < 0.004), indicating an ability to capture temporal progression trends; (iv) compared to conventional diffusion autoencoders, LDAE significantly increases inference throughput (20x faster) while also enhancing reconstruction quality. These findings position LDAE as a promising framework for scalable medical imaging applications, with the potential to serve as a foundation model for medical image analysis. Code available at https://github.com/GabrieleLozupone/LDAE