Dataset Information

An AI-Ready Multiplex Staining Dataset for Reproducible and Accurate Characterization of Tumor Immune Microenvironment.

ABSTRACT: We introduce a new AI-ready computational pathology dataset containing restained and co-registered digitized images from eight head-and-neck squamous cell carcinoma patients. Specifically, the same tumor sections were stained with the expensive multiplex immunofluorescence (mIF) assay first and then restained with cheaper multiplex immunohistochemistry (mIHC). This is a first public dataset that demonstrates the equivalence of these two staining methods which in turn allows several use cases; due to the equivalence, our cheaper mIHC staining protocol can offset the need for expensive mIF staining/scanning which requires highly-skilled lab technicians. As opposed to subjective and error-prone immune cell annotations from individual pathologists (disagreement > 50%) to drive SOTA deep learning approaches, this dataset provides objective immune and tumor cell annotations via mIF/mIHC restaining for more reproducible and accurate characterization of tumor immune microenvironment (e.g. for immunotherapy). We demonstrate the effectiveness of this dataset in three use cases: (1) IHC quantification of CD3/CD8 tumor-infiltrating lymphocytes via style transfer, (2) virtual translation of cheap mIHC stains to more expensive mIF stains, and (3) virtual tumor/immune cellular phenotyping on standard hematoxylin images. The dataset is available at https://github.com/nadeemlab/DeepLIIF.

SUBMITTER: Ghahremani P

PROVIDER: S-EPMC10571229 | biostudies-literature | 2023 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

An AI-Ready Multiplex Staining Dataset for Reproducible and Accurate Characterization of Tumor Immune Microenvironment.

Ghahremani Parmida P Marino Joseph J Hernandez-Prera Juan J de la Iglesia Janis V JV Slebos Robbert Jc RJ Chung Christine H CH Nadeem Saad S

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention 20231001

We introduce a new AI-ready computational pathology dataset containing restained and co-registered digitized images from eight head-and-neck squamous cell carcinoma patients. Specifically, the same tumor sections were stained with the expensive multiplex immunofluorescence (mIF) assay first and then restained with cheaper multiplex immunohistochemistry (mIHC). This is a first public dataset that demonstrates the equivalence of these two staining methods which in turn allows several use cases; du ...[more]

PMID: 37841230

Similar Datasets

Project description:BackgroundEmerging evidence has underscored the crucial role of infiltrating immune cells in the tumor immune microenvironment (TIME) of non-small cell lung cancer (NSCLC) development and progression. With the implementation of screening programs, the incidence of early-stage NSCLC is rising. However, the high risk of recurrence and poor survival rates associated with this disease necessitate a deeper understanding of the TIME and its relationship with driver alterations. The aim of this study was to provide an in-depth analysis of immune changes in early-stage NSCLC, highlighting the significant transitions in immune response during disease progression.MethodsTumor tissues were collected from 105 patients with precancerous lesions or stage I-III NSCLC. Next-generation sequencing (NGS) was used to detect cancer driver alterations. Multiplex immunofluorescence (mIF) was performed to evaluate immune cell density, percentage, and spatial proximity to cancer cells in the TIME. Next Among these patients, 64 had NGS results, including three with adenocarcinoma in situ (AIS), 10 with minimally invasive adenocarcinoma (MIA), and 51 with stage I invasive cancers. Additionally, three patients underwent neoadjuvant immuno-chemotherapy and tumor tissue specimens before and after treatment were obtained.ResultsPatients with stage I invasive cancer had significantly higher density (P=0.01) and percentage (P=0.02) of CD8+ T cells and higher percentages of M1 macrophages (P=0.04) and immature natural killer (NK) cells (P=0.041) in the tumor parenchyma compared to those with AIS/MIA. Patients with mutated epidermal growth factor receptor (EGFR) gene exhibited decreased NK cell infiltration, increased M2 macrophage infiltration, and decreased aggregation of CD4+ T cells near tumor cells compared to EGFR wild-type patients. As NSCLC progressed from stage I to III, CD8+ T cell density and proportion increased, while PD-L1+ tumor cells were in closer proximity to PD-1+CD8+ T cells, potentially inhibiting CD8+ T cell function. Furthermore, M1 macrophages decreased in density and proportion, and the number of NK cells, macrophages, and B cells around tumor cells decreased. Additionally, patients with tertiary lymphoid structures (TLSs) had significantly higher proportion of M1 macrophages and lymphocytes near tumor cells, whereas those without TLS had PD-L1+ tumor cells more densely clustered around PD-1+CD8+ T cells. Notably, neoadjuvant immuno-chemotherapy induced the development of TLS.ConclusionsThis study offers an in-depth analysis of immune changes in NSCLC, demonstrating that the transition from AIS/MIA to invasive stage I NSCLC leads to immune activation, while the advancement from stage I to stage III cancer results in immune suppression. These findings contribute to our understanding of the molecular mechanisms underlying early-stage NSCLC progression and pave the way for the identification of potential treatment options.

Dataset Information

An AI-Ready Multiplex Staining Dataset for Reproducible and Accurate Characterization of Tumor Immune Microenvironment.

Publications

An AI-Ready Multiplex Staining Dataset for Reproducible and Accurate Characterization of Tumor Immune Microenvironment.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets