A Multi-Granularity Approach to Similarity Search in Multiplexed Immunofluorescence Images

Jennifer Yu, Zhenqin Wu, Aaron Mayer, Alexandro Trevino, James Zou
Proceedings of the 18th Machine Learning in Computational Biology meeting, PMLR 240:135-147, 2024.

Abstract

Due to the rapid increase and importance of multiplexed immunofluorescence (mIF) imaging data in spatial biology, there is a pressing need to develop efficient image-to-image search pipelines for both diagnostic and research purposes. While several image search methods have been introduced for conventional images and digital pathology, mIF images present three main challenges: (1) high dimensionality, (2) domain-specificity, and (3) complex additional molecular information. To address this gap, we introduce the MIISS framework, a Multi-granularity mIF Image Similarity Search pipeline that employs self-supervised learning models to extract features from mIF image patches and an entropy-based aggregation method to enable similarity searches at higher, multi-granular levels. We then benchmarked various feature generation approaches to handle high dimensional images and tested them on various foundation models. We conducted evaluations using datasets from different tissues on both patch- and patient-level, which demonstrate the framework’s effectiveness and generalizability. Notably, we found that domain-specific models consistently outperformed other models, further showing their robustness and generalizability across different datasets. The MIISS framework offers an effective solution for navigating the growing landscape of mIF images, providing tangible clinical benefits and opening new avenues for pathology research.

Cite this Paper

BibTeX
@InProceedings{pmlr-v240-yu24a, title = {A Multi-Granularity Approach to Similarity Search in Multiplexed Immunofluorescence Images}, author = {Yu, Jennifer and Wu, Zhenqin and Mayer, Aaron and Trevino, Alexandro and Zou, James}, booktitle = {Proceedings of the 18th Machine Learning in Computational Biology meeting}, pages = {135--147}, year = {2024}, editor = {Knowles, David A. and Mostafavi, Sara}, volume = {240}, series = {Proceedings of Machine Learning Research}, month = {30 Nov--01 Dec}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v240/yu24a/yu24a.pdf}, url = {https://proceedings.mlr.press/v240/yu24a.html}, abstract = {Due to the rapid increase and importance of multiplexed immunofluorescence (mIF) imaging data in spatial biology, there is a pressing need to develop efficient image-to-image search pipelines for both diagnostic and research purposes. While several image search methods have been introduced for conventional images and digital pathology, mIF images present three main challenges: (1) high dimensionality, (2) domain-specificity, and (3) complex additional molecular information. To address this gap, we introduce the MIISS framework, a Multi-granularity mIF Image Similarity Search pipeline that employs self-supervised learning models to extract features from mIF image patches and an entropy-based aggregation method to enable similarity searches at higher, multi-granular levels. We then benchmarked various feature generation approaches to handle high dimensional images and tested them on various foundation models. We conducted evaluations using datasets from different tissues on both patch- and patient-level, which demonstrate the framework’s effectiveness and generalizability. Notably, we found that domain-specific models consistently outperformed other models, further showing their robustness and generalizability across different datasets. The MIISS framework offers an effective solution for navigating the growing landscape of mIF images, providing tangible clinical benefits and opening new avenues for pathology research.} }
Endnote
%0 Conference Paper %T A Multi-Granularity Approach to Similarity Search in Multiplexed Immunofluorescence Images %A Jennifer Yu %A Zhenqin Wu %A Aaron Mayer %A Alexandro Trevino %A James Zou %B Proceedings of the 18th Machine Learning in Computational Biology meeting %C Proceedings of Machine Learning Research %D 2024 %E David A. Knowles %E Sara Mostafavi %F pmlr-v240-yu24a %I PMLR %P 135--147 %U https://proceedings.mlr.press/v240/yu24a.html %V 240 %X Due to the rapid increase and importance of multiplexed immunofluorescence (mIF) imaging data in spatial biology, there is a pressing need to develop efficient image-to-image search pipelines for both diagnostic and research purposes. While several image search methods have been introduced for conventional images and digital pathology, mIF images present three main challenges: (1) high dimensionality, (2) domain-specificity, and (3) complex additional molecular information. To address this gap, we introduce the MIISS framework, a Multi-granularity mIF Image Similarity Search pipeline that employs self-supervised learning models to extract features from mIF image patches and an entropy-based aggregation method to enable similarity searches at higher, multi-granular levels. We then benchmarked various feature generation approaches to handle high dimensional images and tested them on various foundation models. We conducted evaluations using datasets from different tissues on both patch- and patient-level, which demonstrate the framework’s effectiveness and generalizability. Notably, we found that domain-specific models consistently outperformed other models, further showing their robustness and generalizability across different datasets. The MIISS framework offers an effective solution for navigating the growing landscape of mIF images, providing tangible clinical benefits and opening new avenues for pathology research.
APA
Yu, J., Wu, Z., Mayer, A., Trevino, A. & Zou, J.. (2024). A Multi-Granularity Approach to Similarity Search in Multiplexed Immunofluorescence Images. Proceedings of the 18th Machine Learning in Computational Biology meeting, in Proceedings of Machine Learning Research 240:135-147 Available from https://proceedings.mlr.press/v240/yu24a.html.

Related Material