Addressing persistent challenges in digital image analysis of cancer tissue - resources developed from a hackathon

Sep 23, 2026

Summary of a virtual hackathon organized by the Image Analysis Working Group (IAWG) in 2022 to confront persistent computational and data-processing barriers in digital image analysis of fixed cancer tissues. The work targets three core problem areas: robust cell type classification and assessment, spatial data visualization and translation, and scaling image analysis to large multi-terabyte datasets. Participants evaluated limitations of existing automated tools, proposed practical solutions, and produced resources while outlining remaining challenges for research as new imaging modalities and analysis platforms emerge.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages17

Reading Time43 min

AccessFree to download

Introduction

Background and rationale

Hackathon focus areas and outcomes

A GUIDE TO . . . Addressing persistent challenges in digital image analysis of cancer tissue: resources developed from a hackathon Sandhya Prabhakaran 1 , Clarence Yapp2 , Gregory J. Baker2 , Johanna Beyer3, Young Hwan Chang4 , Allison L. Creason4 , Robert Krueger5, Jeremy Muhlich6, Nathan Heath Patterson7 , Kevin Sidak5, Damir Sudar8 , Adam J. Taylor9 , Luke Ternes4 , Jakob Troidl3, Xie Yubin 10, Artem Sokolov2 and Darren R. Tyson 11 1 Mofﬁtt Cancer Center, Tampa, FL, USA 2 Laboratory of Systems Pharmacology, Harvard Medical School, Boston, MA, USA 3 School of Engineering and Applied Sciences, Harvard University, Cambridge, MA, USA 4 Department of Biomedical Engineering, Oregon Health & Science University, Portland, OR, USA 5 Harvard University, Cambridge, MA, USA 6 Harvard Medical School, Boston, MA, USA 7 Aspect Analytics, Genk, Belgium 8 Quantitative Imaging Systems, Monroeville, PA, USA 9 Sage Bionetworks, Seattle, WA, USA 10 Memorial Sloan Kettering Cancer Center, New York, NY, USA 11 Vanderbilt University School of Medicine, Nashville, TN, USA Keywords artifact removal; artifacts; cancer; computational scalability; domain representation; image analysis Correspondence D. R. Tyson, Vanderbilt University School of Medicine, 2220 Pierce Ave.– PRB 715B, Nashville, TN 37232, USA Tel: +1 615 936 1975 E-mail: [darren.tyson@vanderbilt.edu](darren.tyson@vanderbilt.edu), darren. [tyson@duke.edu](tyson@duke.edu) Sandhya Prabhakaran and Clarence Yapp contributed equally to this work. Artem Sokolov and Darren R. Tyson share senior authorship. (Received 28 May 2024, revised 17 October 2024, accepted 11 November 2024, available online 10 February 2025) doi:10 . 1002/1878-0261 .13783 The National Cancer Institute (NCI) supports numerous research consortia that rely on imaging technologies to study cancerous tissues. To foster collaboration and innovation in this ﬁeld, the Image Analysis Working Group (IAWG) was created in 2019 . As multiplexed imaging techniques grow in scale and complexity, more advanced computational methods are required beyond traditional approaches like segmentation and pixel intensity quantiﬁcation. In 2022, the IAWG held a virtual hackathon focused on addressing challenges in analyzing complex, high-dimensional datasets from ﬁxed cancer tissues. The hackathon addressed key challenges in three areas: (1) cell type classiﬁcation and assessment, (2) spatial data visualization and translation, and (3) scaling image analysis for large, multi-terabyte datasets. Participants explored the limitations of current automated analysis tools, developed potential solutions, and made signiﬁcant progress during the hackathon. Here we provide a summary of the efforts and resultant resources and highlight remaining challenges facing the research community as emerging technologies are integrated into diverse imaging modalities and data analysis platforms. Abbreviations API, application programming interface; CSBC, Cancer Systems Biology Consortium; C-VAE, conditional variational autoencoder; CyCIF, cyclic immunoﬂuorescence; FS, feature set; GMM, Gaussian mixture model; H&E, hematoxylin and eosin; HTAN, Human Tumor Atlas Network; HuBMAP, human biomolecular atlas project; I/O, digital ﬁle input/output; IAWG, image analysis working group; IF, immunoﬂuorescence; MCMICRO, multiple-choice microscopy pipeline; MERFISH, multiplexed error-robust ﬂuorescence in situ hybridization; ME-VAE, multi-encoder variational autoencoder; NCI, National Cancer Institute; PALOM, piecewise alignment for layers of mosaics; PBS, phosphate-buffered saline; QC, quality control; REDSEA, reinforcement dynamic spillover elimination; RGB, red/green/blue colorspace; SHIFT, speedy histological-to-immunoﬂuorescent translation; TGF-b, transforming growth factor beta; UMAP, uniform manifold approximation and projection; VAE, variational autoencoder; a-SMA, alpha smooth muscle Actin. Molecular Oncology 19 (2025) 15

FAQs

What prompted the 2022 IAWG hackathon on cancer tissue image analysis?

The hackathon was created to foster collaboration and innovation as multiplexed imaging techniques expanded in scale and complexity, requiring computational approaches beyond standard segmentation and pixel intensity quantification.

Which three challenge areas did the hackathon address?

It addressed (1) cell type classification and assessment, (2) spatial data visualization and translation, and (3) scaling image analysis for large, multi-terabyte datasets.

What did participants do during the hackathon?

Participants explored limitations of current automated analysis tools, developed potential solutions, and made significant progress toward resources and summarized efforts.

Sep 23, 2026

Uploaded by นรินทร์