Vector Quantization for Reversed Disease Progression: Further Investigations

Chih-Chieh Chen, Chang-Fu Kuo
Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, PMLR 315:594-619, 2026.

Abstract

Interpretability plays a pivotal role in the collaboration between artificial intelligence (AI) systems and clinicians. It enables clinicians to critically reassess the rationale underlying AI-generated predictions. Moreover, translating these interpretations into clinically meaningful quantifications is feasible even for more granular algorithms, thereby potentially reducing the extensive annotation efforts typically required. Recently, a novel approach was introduced to generate reversed disease progression trajectories by applying conditional flow matching within the latent space of an autoencoder, jointly training a linear classifier. However, the architectural design, training procedures, and objective functions associated with the flow matching network warrant further investigation and refinement. In the present study, we implement this concept utilizing a recently proposed vector-quantized autoencoder framework incorporating Sinkhorn-based quantization. Our findings indicate that reversed disease progression can be consistently generated even in the absence of joint classifier training. Additionally, the method preserves strong spatial correspondences between the pixel domain and latent representations, enabling the synthesis of desired images through a CutMix-inspired algorithm. We demonstrate the efficacy of our approach by applying it to the weakly supervised quantization of midline shift distances.

Cite this Paper

BibTeX
@InProceedings{pmlr-v315-chen26b, title = {Vector Quantization for Reversed Disease Progression: Further Investigations}, author = {Chen, Chih-Chieh and Kuo, Chang-Fu}, booktitle = {Proceedings of The 9th International Conference on Medical Imaging with Deep Learning}, pages = {594--619}, year = {2026}, editor = {Huo, Yuankai and Gao, Mingchen and Kuo, Chang-Fu and Jin, Yueming and Deng, Ruining}, volume = {315}, series = {Proceedings of Machine Learning Research}, month = {08--10 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v315/main/assets/chen26b/chen26b.pdf}, url = {https://proceedings.mlr.press/v315/chen26b.html}, abstract = {Interpretability plays a pivotal role in the collaboration between artificial intelligence (AI) systems and clinicians. It enables clinicians to critically reassess the rationale underlying AI-generated predictions. Moreover, translating these interpretations into clinically meaningful quantifications is feasible even for more granular algorithms, thereby potentially reducing the extensive annotation efforts typically required. Recently, a novel approach was introduced to generate reversed disease progression trajectories by applying conditional flow matching within the latent space of an autoencoder, jointly training a linear classifier. However, the architectural design, training procedures, and objective functions associated with the flow matching network warrant further investigation and refinement. In the present study, we implement this concept utilizing a recently proposed vector-quantized autoencoder framework incorporating Sinkhorn-based quantization. Our findings indicate that reversed disease progression can be consistently generated even in the absence of joint classifier training. Additionally, the method preserves strong spatial correspondences between the pixel domain and latent representations, enabling the synthesis of desired images through a CutMix-inspired algorithm. We demonstrate the efficacy of our approach by applying it to the weakly supervised quantization of midline shift distances.} }
Endnote
%0 Conference Paper %T Vector Quantization for Reversed Disease Progression: Further Investigations %A Chih-Chieh Chen %A Chang-Fu Kuo %B Proceedings of The 9th International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2026 %E Yuankai Huo %E Mingchen Gao %E Chang-Fu Kuo %E Yueming Jin %E Ruining Deng %F pmlr-v315-chen26b %I PMLR %P 594--619 %U https://proceedings.mlr.press/v315/chen26b.html %V 315 %X Interpretability plays a pivotal role in the collaboration between artificial intelligence (AI) systems and clinicians. It enables clinicians to critically reassess the rationale underlying AI-generated predictions. Moreover, translating these interpretations into clinically meaningful quantifications is feasible even for more granular algorithms, thereby potentially reducing the extensive annotation efforts typically required. Recently, a novel approach was introduced to generate reversed disease progression trajectories by applying conditional flow matching within the latent space of an autoencoder, jointly training a linear classifier. However, the architectural design, training procedures, and objective functions associated with the flow matching network warrant further investigation and refinement. In the present study, we implement this concept utilizing a recently proposed vector-quantized autoencoder framework incorporating Sinkhorn-based quantization. Our findings indicate that reversed disease progression can be consistently generated even in the absence of joint classifier training. Additionally, the method preserves strong spatial correspondences between the pixel domain and latent representations, enabling the synthesis of desired images through a CutMix-inspired algorithm. We demonstrate the efficacy of our approach by applying it to the weakly supervised quantization of midline shift distances.
APA
Chen, C. & Kuo, C.. (2026). Vector Quantization for Reversed Disease Progression: Further Investigations. Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 315:594-619 Available from https://proceedings.mlr.press/v315/chen26b.html.

Related Material