Imai Mitsuho, Nakamura Yoshiaki, Shin Sangwon, Okamoto Wataru, Kato Takeshi, Esaki Taito, Kato Ken, Komatsu Yoshito, Yuki Satoshi, Masuishi Toshiki, Nishina Tomohiro, Sawada Kentaro, Sato Akihiro, Kuwata Takeshi, Yamashita Riu, Fujisawa Takao, Bando Hideaki, Ock Chan-Young, Fujii Satoshi, Yoshino Takayuki
Translational Research Support Office, National Cancer Center Hospital East, Chiba, Japan.
Department of Genetic Medicine and Services, National Cancer Center Hospital East, Chiba, Japan.
JCO Precis Oncol. 2025 Jan;9:e2400385. doi: 10.1200/PO-24-00385. Epub 2025 Jan 17.
Human epidermal growth factor receptor 2 (HER2)-targeted therapies have shown promise in treating -amplified metastatic colorectal cancer (mCRC). Identifying optimal biomarkers for treatment decisions remains challenging. This study explores the potential of artificial intelligence (AI) in predicting treatment responses to trastuzumab plus pertuzumab (TP) in patients with -amplified mCRC from the phase II TRIUMPH trial.
AI-powered HER2 quantification continuous score (QCS) and tumor microenvironment (TME) analysis were applied to the prescreening cohort (n = 143) and the TRIUMPH cohort (n = 30). AI analyzers determined the proportions of tumor cells (TCs) with HER2 staining intensity and the densities of various cells in TME, examining their associations with clinical outcomes of TP.
The AI-powered HER2 QCS for HER2 immunohistochemistry (IHC) achieved an accuracy of 86.7% against pathologist evaluations, with a 100% accuracy for HER2 IHC 3+ patients. Patients with ≥50% of TCs showing HER2 3+ staining intensity (AI-H3-high) exhibited significantly prolonged progression-free survival (PFS; median PFS, 4.4 1.4 months; hazard ratio [HR], 0.12 [95% CI, 0.04 to 0.38]) and overall survival (OS; median OS, 16.5 4.1 months; HR, 0.13 [95% CI, 0.05 to 0.38]) compared with the AI-H3-low (<50% group). Stratification among patients with AI-H3-high included TME-high (all lymphocyte, fibroblast, and macrophage densities in the cancer stroma above the median) and TME-low (anything below the median), showing a median PFS of 1.3 and 5.6 months for TME-high and TME-low respectively, with an HR of 0.04 (95% CI, 0.01 to 0.19) for AI-H3-high with TME-low compared with AI-H3-low.
AI-powered HER2 QCS and TME analysis demonstrated potential in enhancing treatment response predictions in patients with -amplified mCRC undergoing TP therapy.
人表皮生长因子受体2（HER2）靶向治疗已显示出治疗HER2扩增的转移性结直肠癌（mCRC）的前景。确定用于治疗决策的最佳生物标志物仍然具有挑战性。本研究从II期TRIUMPH试验中探索人工智能（AI）在预测HER2扩增的mCRC患者对曲妥珠单抗加帕妥珠单抗（TP）治疗反应方面的潜力。
将人工智能驱动的HER2定量连续评分（QCS）和肿瘤微环境（TME）分析应用于预筛选队列（n = 143）和TRIUMPH队列（n = 30）。人工智能分析仪确定HER2染色强度的肿瘤细胞（TCs）比例以及TME中各种细胞的密度，研究它们与TP临床结果的关联。
针对HER2免疫组织化学（IHC）的人工智能驱动的HER2 QCS相对于病理学家评估的准确率为86.7%，HER2 IHC 3+患者的准确率为100%。≥50%的TCs显示HER2 3+染色强度（AI-H3高）的患者与AI-H3低（<50%组）相比，无进展生存期（PFS）显著延长（中位PFS，4.4±1.4个月；风险比[HR]，0.12[95%CI，0.04至0.38]），总生存期（OS）也显著延长（中位OS，16.5±4.1个月；HR，0.13[95%CI，0.05至0.38]）。AI-H3高的患者分层包括TME高（癌基质中所有淋巴细胞、成纤维细胞和巨噬细胞密度高于中位数）和TME低（任何低于中位数的情况），TME高和TME低的中位PFS分别为1.3和5.6个月，与AI-H3低相比，AI-H3高且TME低的HR为0.04（95%CI，0.01至0.19）。
人工智能驱动的HER2 QCS和TME分析显示出在增强接受TP治疗的HER2扩增mCRC患者治疗反应预测方面的潜力。
Zotero 插件
