Mandelkow Tim, Bady Elena, Lurati Magalie C J, Raedler Jonas B, Müller Jan H, Huang Zhihao, Vettorazzi Eik, Lennartz Maximilian, Clauditz Till S, Lebok Patrick, Steinhilper Lisa, Woelber Linn, Sauter Guido, Berkes Enikö, Bühler Simon, Paluchowski Peter, Heilenkötter Uwe, Müller Volkmar, Schmalfeldt Barbara, von der Assen Albert, Jacobsen Frank, Krech Till, Krech Rainer H, Simon Ronald, Bernreuther Christian, Steurer Stefan, Burandt Eike, Blessin Niclas C
Institute of Pathology, University Medical Center Hamburg-Eppendorf, 20246 Hamburg, Germany.
College of Arts and Sciences, Boston University, Boston, MA 02215, USA.
Biomedicines. 2023 Nov 29;11(12):3175. doi: 10.3390/biomedicines11123175.
Prognostic markers in routine clinical management of breast cancer are often assessed using RNA-based multi-gene panels that depend on fluctuating tumor purity. Multiplex fluorescence immunohistochemistry (mfIHC) holds the potential for an improved risk assessment. To enable automated prognosis marker detection (i.e., progesterone receptor [PR], estrogen receptor [ER], androgen receptor [AR], GATA3, TROP2, HER2, PD-L1, Ki67, TOP2A), a framework for automated breast cancer identification was developed and validated involving thirteen different artificial intelligence analysis steps and an algorithm for cell distance analysis using 11+1-marker-BLEACH&STAIN-mfIHC staining in 1404 invasive breast cancers of no special type (NST). The framework for automated breast cancer detection discriminated normal glands from malignant glands with an accuracy of 98.4%. This approach identified that five (PR, ER, AR, GATA3, PD-L1) of nine biomarkers were associated with prolonged overall survival ( ≤ 0.0095 each) and two of these (PR, AR) were found to be independent risk factors in multivariate analysis ( ≤ 0.0151 each). The combined assessment of PR-ER-AR-GATA3-PD-L1 as a five-marker prognosis score showed strong prognostic relevance ( < 0.0001) and was an independent risk factor in multivariate analysis ( = 0.0034). Automated breast cancer detection in combination with an artificial intelligence-based analysis of mfIHC enables a rapid and reliable analysis of multiple prognostic parameters. The strict limitation of the analysis to malignant cells excludes the impact of fluctuating tumor purity on assay precision.
在乳腺癌的常规临床管理中，预后标志物通常使用依赖于波动的肿瘤纯度的基于RNA的多基因检测板进行评估。多重荧光免疫组织化学（mfIHC）具有改善风险评估的潜力。为了实现自动预后标志物检测（即孕激素受体[PR]、雌激素受体[ER]、雄激素受体[AR]、GATA3、TROP2、HER2、PD-L1、Ki67、TOP2A），开发并验证了一个自动乳腺癌识别框架，该框架涉及13个不同的人工智能分析步骤以及一种细胞距离分析算法，使用11 + 1标记的BLEACH&STAIN - mfIHC染色对1404例非特殊类型（NST）的浸润性乳腺癌进行分析。自动乳腺癌检测框架区分正常腺体和恶性腺体的准确率为98.4%。该方法确定9种生物标志物中的5种（PR、ER、AR、GATA3、PD-L1）与总生存期延长相关（每种均≤0.0095），其中2种（PR、AR）在多变量分析中被发现是独立危险因素（每种均≤0.0151）。将PR-ER-AR-GATA3-PD-L1作为五标志物预后评分进行联合评估显示出很强的预后相关性（<0.0001），并且在多变量分析中是独立危险因素（=0.0034）。结合基于人工智能的mfIHC分析进行自动乳腺癌检测能够快速可靠地分析多个预后参数。将分析严格限制在恶性细胞上排除了波动的肿瘤纯度对检测精度的影响。
