TMCnet News

Lunit Demonstrates Predictive Value of AI-Biomarker Platform at the 2023 ASCO Annual Meeting
[May 25, 2023]

Lunit Demonstrates Predictive Value of AI-Biomarker Platform at the 2023 ASCO Annual Meeting


- New studies reveal Lunit SCOPE's impact on predicting clinical outcomes, analyzing tumor microenvironment, and enhancing personalized cancer treatment

SEOUL, South Korea, May 25, 2023 /PRNewswire/ -- Lunit (KRX:328130.KQ), a global leader of AI-powered cancer diagnostics and therapeutics solutions, is set to make a significant impact at the American Society of Clinical Oncology (ASCO) Annual Meeting in Chicago, Illinois. This year, Lunit will present 16 abstracts at the conference, showcasing the groundbreaking capabilities of its AI-biomarker platform, Lunit SCOPE. This comprehensive collection of studies includes 10 poster presentations and 6 online publications, covering a wide spectrum of topics. From predicting clinical outcomes to exploring the complex dynamics of tumor microenvironments, these advancements highlight Lunit's unwavering commitment to advancing AI pathology research and personalized cancer care.

A breakthrough joint study conducted with the Japan National Cancer Center East (NCCE), investigated microsatellite stable (MSS) locally advanced rectal cancer (LARC), using Lunit SCOPE IO, an AI-powered tumor-infiltrating lymphocyte (TIL) analyzer. The study measured TIL density in the tumor microenvironment (TME) of MSS LARC samples during chemoradiotherapy (CRT) and found a strong correlation between the change in TIL density and the pathologic complete response (pCR) rate. This finding indicates the potential of AI-powered spatial TIL analysis in predicting favorable clinical outcomes.

Another study using Lunit SCOPE IO in head and neck squamous cell carcinoma (HNSCC) patients undergoing immunotherapy demonstrated a shift towards an inflamed immune phenotype, leading to improved outcomes in patients treated with neoadjuvant durvalumab, with or without tremelimumab. Another clinical trial, evaluating the efficacy of neoadjuvant therapy in HPV-positive HNSCC patients, revealed treatment-induced immune changes are strongly associated with treatment outcomes.

Both studies observed a shift from non-inflamed to inflamed immune phenotype with immunotherapy, which was correlated with treatment effectiveness. Notably, patients treated with neoadjuvant durvalumab, with or without tremelimumab achieved a remarkable 93.1% 12-month disease-free survival rate. These results underscore Lunit SCOPE IO's potential in guiding personalized cancer care by revealing immune changes induced by treatment and their impact on clinical outcomes.

A comprehensive analysis of cancer images from The Cancer Genome Atlas (TCGA) using Lunit SCOPE IO unveiled the close correlation between fibroblast density and Transforming growth factor-beta (TGFß) signaling, a factor associated with resistance to cancer immunotherapy. The finding emphasized that analyzing various cells within the tumor can be applied to the development of personalized therapies targeting specific tumor microenvironments. This study was proved by more than 1,800 real-world dataset consisting of multiple cancer types, treated with immune checkpoint inhibitors (ICI).

Another TCGA pan-cancer-based analysis with Lunit SCOPE IO investigated the association between spatial residue of macrophage and anti-tumor activity in the tumor microenvironment, revealing that intra-tumoral macrophage density was strongly correlated with immune phenotypes and genomic signatures.

Another study showcased the utility of Lunit SCOPE uIHC (Universal Immunohistochemistry) model in analyzing the expression of tumor-associated antigens (TAA) in various tumors. By accurately predicting responses to novel TAA-targeted agents, this AI-powered analyzer has the potential to guide personalized treatment decisions and facilitate the exploration of target cancer types.

The last study validated the Lunit SCOPE genotype analyzer's capability to enhance the accuracy and robustness of MET pathogenic mutation prediction model in non-small cell lung cancer (NSCLC), offering a cost-effective screening method for MET alterations in lung cancer. Area Under the Curve (AUC) of the predictive model recorded a significantly high level at 0.837.

"I am excited to present the groundbreaking results from our studies at ASCO, showcasing the immense impact of the Lunit SCOPE suite," said Brandon Suh, CEO of Lunit. "Through our AI-biomarker platform, we are paving the way to provide valuable insights into cancer progression, immune responses, and treatment efficacy. These findings exemplify our dedication to transforming cancer diagnostics and treatment, empowering healthcare professionals to make informed decisions and ultimately improve patient outcomes."

Visit team Lunit at Booth IH21. Reach out to schedule a meeting at ([email protected]).

###

Lunit's Abstracts at ASCO 2023





No.

Abstract No. #

Title

Type

1

3608

Predictive value of tumor-infiltrating lymphocyte (TIL) dynamics in the tumor microenvironment (TME) during preoperative chemoradiotherapy (CRT) on pathologic complete response (pCR) in microsatellite-stable (MSS) locally advanced rectal cancer (LARC)

Poster

2

2578

Dynamic change of immune phenotype assessed by artificial intelligence (AI)-powered tumor-infiltrating lymphocytes (TILs) analysis during neoadjuvant durvalumab with or without tremelimumab (D+/-T) in head and neck squamous cell carcinoma (HNSCC)

Poster

3

6075

Neoadjuvant pembrolizumab, GX-188E, and GX-I7 in patients with human papilloma virus-16- and/or 18-positive head and neck squamous cell carcinoma: single-arm, phase 2 trial with single cell transcriptomic analysis and artificial intelligence-powered spatial analysis

Poster

4

3542

Artificial Intelligence-Derived Immune Phenotypes for Prediction of Prognosis in Patients with Stage III Colon Cancer (NCCTG N0147) [Alliance]

Poster

5

2585

Tumor microenvironment (TME)-based histomic TGFß signature (TGFBs) reveals stromal fibroblast recruitment and exclusion of immune cells as immunotherapy resistance mechanisms

Poster

6

3135

Exploring expression levels of HER2, HER3, MET, Claudin18.2, and MUC16 across 16 cancer types using an artificial intelligence-powered immunohistochemistry analyzer

Poster

7

2621

Artificial intelligence (AI) –powered spatial analysis of macrophages in tumor microenvironment and its association with interferon-gamma (IFNG) signature and immune phenotype (IP) in pan-cancer dataset

Poster

8

1049

Artificial intelligence–powered tumor-infiltrating lymphocytes analyzer to reveal distinct immune landscapes in breast cancer by molecular subtype and HER2 score

Poster

9

4162

Artificial intelligence (AI) –powered spatial analysis of tumor-infiltrating lymphocytes (TILs) for prediction of prognosis in resectable pancreatic adenocarcinoma (PDAC)

Poster

10

6100

Artificial intelligence (AI) analysis of tumor-infiltrating lymphocytes (TILs) in hematoxylin and eosin (H&E) slides to explore immune phenotypes in papillary thyroid cancer

Poster

11

e13578

Deep learning-based ensemble model using hematoxylin and eosin (H&E) whole slide images (WSIs) for the prediction of MET mutations in non-small cell lung cancer (NSCLC)

Online Publication

12

e20520

Artificial intelligence (AI) –powered H&E whole-slide image (WSI) analysis of tertiary lymphoid structure (TLS) correlates with immune phenotype and related molecular signatures in non–small-cell lung cancer

Online Publication

13

e21179

Immune phenotype-driven treatment outcome of IO-only versus chemo-IO in PD-L1-high, first-line, advanced non-small cell lung cancer (NSCLC)

Online Publication

14

e14657

Correlation of fragmented pattern of tumor mass captured by artificial intelligence (AI)-powered whole-slide image (WSI) analysis with biased fibroblast expansion over tumor growth and distinct mutational signatures

Online Publication

15

e13553

Performance validation of an artificial intelligence-powered PD-L1 combined positive score analyzer in six cancer types

Online Publication

16

e13546

Effect of an artificial intelligence–powered programmed death-ligand 1 combined positive score analyzer in urothelial cancer on inter-observer and inter-site variability

Online Publication




About Lunit

With AI, Lunit aims to 'conquer cancer,' one of the leading causes of death worldwide. Lunit is an AI software company devoted to developing AI solutions for precision diagnostics and therapeutics, to find the right diagnosis at the right cost, and the right treatment for the right patients. Lunit, a portmanteau of 'learning unit,' is a deep learning-based medical AI company devoted to developing advanced medical image analytics and data-driven imaging biomarkers via cutting-edge technology.

Founded in 2013, Lunit has been acknowledged around the world for its advanced, state-of-the-art technology and its application in medical images. Its technology has been recognized at international AI competitions surpassing top companies like Google, IBM, and Microsoft. As a medical AI company with a focus on clinical evidence, the company's findings are presented in major peer-reviewed journals such as the Journal of Clinical Oncology and JAMA Network Open, and global conferences including ASCO and AACR.

After receiving FDA clearance and the CE Mark, Lunit INSIGHT CXR and MMG are clinically used in approximately 2,000 hospitals and medical institutions across more than 40 countries. Lunit SCOPE PD-L1 is CE marked in Europe and has not been cleared or approved by the US Food and Drug Administration (FDA) and is intended for Research Use Only. Lunit is headquartered in Seoul, South Korea with offices and representatives around the world.

About Lunit SCOPE

Lunit SCOPE is a suite of AI-powered software that analyzes tissue slide images for digital pathology and AI biomarker development, with the aim of optimizing workflow and facilitating more accurate and predictive clinical data for clinicians and researchers.

Lunit SCOPE platform offers multiple tissue analysis AI software products and assays that can streamline digital pathology workflow and diagnostics, as well as enhance the drug development process.

Lunit SCOPE IO analyzes the tumor microenvironment (TME) based on H&E analysis and provides AI-based predictive clinical outcome information. In addition, AI-driven Immunohistochemistry (IHC) slide analysis services are offered, through products such as Lunit SCOPE PD-L1, Lunit SCOPE HER2, Lunit SCOPE ER/PR, and others.

 

Cision View original content to download multimedia:https://www.prnewswire.com/news-releases/lunit-demonstrates-predictive-value-of-ai-biomarker-platform-at-the-2023-asco-annual-meeting-301835011.html

SOURCE Lunit


[ Back To TMCnet.com's Homepage ]