乳腺癌反內(nèi)卷分型療效預(yù)測(cè)新方法

過(guò)去，乳腺癌通常被分為HR陽(yáng)性HER2陰性、HR陽(yáng)性HER2陰性、HR陰性HER2陽(yáng)性、三陰性等若干大類(lèi)進(jìn)行分類(lèi)治療，但是同一大類(lèi)患者治療效果有好有壞、相差懸殊。隨后，同一大類(lèi)乳腺癌又被進(jìn)一步細(xì)分為若干亞型進(jìn)行分型治療，但是同一亞型患者治療效果仍然有好有壞、相差懸殊。雖然這些分類(lèi)分型越來(lái)越內(nèi)卷，但是都將乳腺癌視為均勻物，其實(shí)大多數(shù)乳腺癌為混合物，可能由一部分HR陽(yáng)性或陰性細(xì)胞、一部分HER2陽(yáng)性或陰性細(xì)胞、一部分其他靶點(diǎn)陽(yáng)性或陰性細(xì)胞組成，不同比例的多種惡性亞型細(xì)胞可能共存于同一腫瘤內(nèi)，并影響療效，也就是說(shuō)可以將乳腺癌細(xì)胞分類(lèi)分型，但是難以將乳腺癌及其患者分為某一類(lèi)某一型采用一刀切的治療方案。

2026年5月26日，歐洲腫瘤內(nèi)科學(xué)會(huì)官方期刊《腫瘤學(xué)年鑒》在線發(fā)表美國(guó)國(guó)家癌癥研究所、西達(dá)賽奈醫(yī)學(xué)中心、以色列特拉維夫大學(xué)、拉賓醫(yī)學(xué)中心、韓國(guó)成均館大學(xué)、英國(guó)倫敦癌癥研究院、皇家馬斯登醫(yī)院、劍橋大學(xué)、中國(guó)臺(tái)灣成功大學(xué)的研究報(bào)告，利用人工智能技術(shù)，根據(jù)腫瘤基因轉(zhuǎn)錄組學(xué)和組織病理學(xué)，對(duì)乳腺癌進(jìn)行反卷積分析，以量化其不同亞型組成比例，并預(yù)測(cè)術(shù)前治療效果。

該研究首先開(kāi)發(fā)了計(jì)算機(jī)軟件BRIDGE對(duì)治療前混合腫瘤組織基因轉(zhuǎn)錄組數(shù)據(jù)進(jìn)行解卷積，以估計(jì)不同分子亞型組成比例，并預(yù)測(cè)術(shù)前治療后的病理完全緩解。該研究采用10個(gè)轉(zhuǎn)錄組數(shù)據(jù)集進(jìn)行訓(xùn)練，并采用涵蓋不同亞型的24個(gè)獨(dú)立多中心數(shù)據(jù)集進(jìn)行測(cè)試。此外，還分析了6個(gè)包含治療前蘇木精伊紅染色切片和治療效果數(shù)據(jù)的額外數(shù)據(jù)集，以評(píng)價(jià)根據(jù)腫瘤組織病理學(xué)的預(yù)測(cè)結(jié)果。

結(jié)果，通過(guò)對(duì)實(shí)測(cè)轉(zhuǎn)錄組學(xué)數(shù)據(jù)進(jìn)行分析，BRIDGE對(duì)ER陽(yáng)性HER2陰性乳腺癌術(shù)前治療病理完全緩解的預(yù)測(cè)能力優(yōu)于現(xiàn)有商業(yè)化21基因、70基因、50基因檢測(cè)，并對(duì)HER2陽(yáng)性和三陰性乳腺癌術(shù)前治療病理完全緩解的預(yù)測(cè)能力超越其他轉(zhuǎn)錄組學(xué)預(yù)測(cè)方法。

BRIDGE預(yù)測(cè)病理完全緩解真假陽(yáng)性率曲線下面積：

• ER陽(yáng)性HER2陰性乳腺癌：0.84（比值比：8）

• HER2陽(yáng)性乳腺癌：0.77（比值比：8.3）

• 三陰性乳腺癌：0.73（比值比：3.1）

該研究隨后通過(guò)人工智能深度學(xué)習(xí)推斷轉(zhuǎn)錄組學(xué)，將BRIDGE用于治療前腫瘤組織病理切片，開(kāi)發(fā)了BRIDGE切片版，性能優(yōu)于直接的切片預(yù)測(cè)治療效果模型，凸顯其作為首個(gè)此類(lèi)快速低成本生物標(biāo)志物的潛力。

對(duì)采用不同術(shù)前治療方案的數(shù)據(jù)集進(jìn)行探索性留一交叉驗(yàn)證分析表明，該方法可推廣至接受免疫檢查點(diǎn)抑制劑治療的ER陽(yáng)性HER2陰性腫瘤，但是仍然需要在更大規(guī)模的隊(duì)列中進(jìn)行驗(yàn)證。

最后，空間轉(zhuǎn)錄組學(xué)分析表明，BRIDGE亞型分類(lèi)形成與典型分子特征相一致的空間聚集區(qū)域，進(jìn)一步增強(qiáng)其生物學(xué)解釋能力。

因此，該研究結(jié)果表明，基于生物學(xué)原理的術(shù)前乳腺癌治療效果預(yù)測(cè)軟件BRIDGE已在大量不同患者隊(duì)列中得到驗(yàn)證，其組織病理學(xué)切片版有望在術(shù)前治療中實(shí)現(xiàn)快速、低成本的治療效果預(yù)測(cè)，但是仍然需要進(jìn)一步的前瞻測(cè)試和驗(yàn)證，尤其對(duì)于中國(guó)大陸患者。

Ann Oncol. 2026 May 26. IF: 65.4

Predicting neoadjuvant breast cancer therapy response using BRIDGE from tumor transcriptomics and histopathology.

Cantore T, Hoang DT, Pal LR, Stemmer A, Chang TG, Dhruba SR, Shulman E, Campagnolo E, Lee JS, Levy J, Yao K, Liao I, Stemmer SM, Sammut SJ, Lipkowitz S, Rajagopal PS, Filipits M, Caldas C, Yuan Y, Nair NU, Ruppin E.

National Cancer Institute (NCI), National Institutes of Health (NIH), Bethesda, MD, USA; Cedars-Sinai Medical Center, Los Angeles, CA, USA; Tel Aviv University, Tel Aviv, Israel; Rabin Medical Center, Petah Tikva, Israel; Sungkyunkwan University, Suwon, Korea; The Institute of Cancer Research, London, UK; The Royal Marsden Hospital NHS Foundation Trust, London, UK; University of Cambridge, Cambridge, UK; Medical University of Vienna, Vienna, Austria; National Cheng Kung University, Tainan, Taiwan, China.

HIGHLIGHTS

• BRIDGE deconvolves transcriptomes of breast tumors to quantify their subtype composition and predict neo-adjuvant response.

• Validated across 24 independent multi-center cohorts, BRIDGE outperforms established molecular biomarkers.

• BRIDGE-Slide extends BRIDGE to pre-treatment histopathology by using deep learning to infer the tumor transcriptome.

BACKGROUND: While expression-based signatures inform adjuvant therapy in breast cancer (BC), no approved molecular biomarkers exist for the neoadjuvant setting, where early response prediction could inform treatment decisions. This challenge is compounded by intratumoral heterogeneity, as multiple malignant subtypes may coexist within a tumor and influence therapy sensitivity.

METHODS: We developed BRIDGE, a computational framework that deconvolves the pre-treatment bulk tumor transcriptome to estimate molecular subtype composition and predict pathological complete response (pCR) to neoadjuvant therapy. BRIDGE was trained on 10 transcriptomics datasets and tested on 24 independent ones spanning different sub-types. Six additional datasets with pre-treatment H&E slides and response data were analyzed to evaluate histology-based predictions.

RESULTS: Analyzing measured transcriptomics, BRIDGE outperformed surrogate implementations of established commercial signatures (Oncotype DX, MammaPrint, ROR-S) in ER+/HER2- tumors, and exceeded other transcriptomic predictors in HER2+ and TNBC disease. In ER+/HER2- patients, it yields an ROC-AUC of 0.84 with a high Odds Ratio (OR = 8); in HER2+ disease, an AUC of 0.77 (OR = 8.3); and in TNBC, an AUC of 0.73 (OR = 3.1). We further developed BRIDGE-Slide, which applies BRIDGE to pre-treatment histopathology slides via deep learning-inferred transcriptomics. BRIDGE-Slide outperforms direct slide-to-response models, underscoring its potential as a first-of-its-kind, fast, low-cost biomarker. Exploratory leave-one-dataset-out analyses across datasets treated with alternative neoadjuvant regimens suggest generalizability to ICB-treated ER+/HER2- tumors, pending validation in larger cohorts. Finally, spatial transcriptomics shows that BRIDGE-derived subtype assignments form spatially cohesive regions aligned with canonical molecular features, reinforcing its biological interpretability.

CONCLUSIONS: BRIDGE is a biologically grounded framework for neoadjuvant BC response prediction, validated on a rich set of different patients' cohorts. Its histopathology-based version opens the door for fast and low-cost prediction in the neoadjuvant setting, upon further prospective testing and validation.

KEYWORDS: Breast Tumors, gene expression, PRECISION MEDICINE, AI in Oncology

DOI: 10.1016/j.annonc.2026.05.700

來(lái)源：SIBCS

免責(zé)聲明：本公眾號(hào)旨在為醫(yī)療衛(wèi)生專(zhuān)業(yè)人士提供腫瘤領(lǐng)域資訊參考，促進(jìn)專(zhuān)業(yè)交流。內(nèi)容僅供信息交流，不可替代專(zhuān)業(yè)醫(yī)療指導(dǎo)，亦非診療建議。 據(jù)此操作，風(fēng)險(xiǎn)自擔(dān)。轉(zhuǎn)載內(nèi)容均已標(biāo)注來(lái)源及作者。如有版權(quán)問(wèn)題，請(qǐng)留言聯(lián)系，我們將及時(shí)處理。