术前全身新辅助治疗后，大约40%～70%的早期乳腺癌患者乳房和腋窝术后病理检查发现肿瘤和淋巴结残癌完全消失。这些患者可能并不需要手术，因为全身新辅助治疗已经清除所有局部肿瘤。不过，影像学或真空辅助活检等非手术方法无法准确识别乳房或腋窝没有残癌的患者。
2022年2月2日，美国临床肿瘤学会《临床肿瘤学杂志》在线发表德国海德堡大学医院、柏林大学医学院、埃森中心医院、罗斯托克大学医院、图宾根大学医院、法兰克福阿加普莱西恩马库斯医院、法兰克福霍赫斯特医院、马里恩医院、科隆大学、乌尔姆大学医院、汉堡耶路撒冷医院、汉堡放疗联盟、比勒费尔德中心医院、慕尼黑理工大学伊萨尔河右岸医院、慕尼黑大学医院、石勒苏益格荷尔斯泰因大学医院、杜塞尔多夫海因里希海涅大学、哈雷大学医院、美国德克萨斯大学MD安德森癌症中心的研究报告，探讨了人工智能机器学习算法用于真空辅助活检确定早期乳腺癌术前全身新辅助治疗后病理完全缓解的可行性。
该研究开发、测试并验证了一种人工智能机器学习算法，可利用患者、影像学、肿瘤和真空辅助活检的变量，检测术前全身新辅助治疗后残癌（病理肿瘤或原位癌或淋巴结阳性）。开发数据来自RESPONDER研究（NCT02948764）318例cT1-3、cN0或+、HER2阳性或三阴性或高增殖指数管腔B型乳腺癌术前真空辅助活检女性。通过十等分交叉验证对该算法进行开发和测试，随后利用其他研究（NCT02575612）45例患者数据进行外部验证，将结果与手术标本组织病理报告进行比较，主要结局为假阴性率和真阴性率。
结果，智能真空辅助活检对于开发测试组318例和外部验证组45例患者全身新辅助治疗后残癌：
假阴性率：0.0%～5.2%
真阴性率：37.5%～40.0%
真假阴性率曲线下面积：0.91～0.92
斯皮格霍尔特检验评分：-0.746（P=0.228）
智能真空辅助活检与全身新辅助治疗后影像学±真空辅助活检相比，假阴性率显著较低。
因此，该小样本初步研究结果表明，智能真空辅助活检算法能够可靠地排除早期乳腺癌术前全身新辅助治疗后残癌，故有必要开展进一步研究探讨对这些病理完全缓解患者避免乳房和腋窝手术。
J Clin Oncol. 2022 Feb 2. Online ahead of print.
Intelligent Vacuum-Assisted Biopsy to Identify Breast Cancer Patients With Pathologic Complete Response (ypT0 and ypN0) After Neoadjuvant Systemic Treatment for Omission of Breast and Axillary Surgery.
Pfob A, Sidey-Gibbons C, Rauch G, Thomas B, Schaefgen B, Kuemmel S, Reimer T, Hahn M, Thill M, Blohmer JU, Hackmann J, Malter W, Bekes I, Friedrichs K, Wojcinski S, Joos S, Paepke S, Degenhardt T, Rom J, Rody A, van Mackelenbergh M, Banys-Paluchowski M, Grobe R, Reinisch M, Karsten M, Golatta M, Heil J.
Heidelberg University Hospital, Heidelberg, Germany; University Heidelberg, Heidelberg, Germany; Charité—Universitatsmedizin Berlin, Freie Universitat Berlin, Humboldt Universitat zu Berlin, Berlin, Germany; Kliniken Essen-Mitte, Essen, Germany; University Hospital Rostock, Rostock, Germany; University Hospital Tuebingen, Tuebingen, Germany; Agaplesion Markus Hospital Frankfurt, Frankfurt, Germany; Klinikum Frankfurt-Hochst, Frankfurt, Germany; Marienhospital, Witten, Germany; University of Cologne, Cologne, Germany; University Hospital Ulm, Ulm, Germany; Jerusalem Hospital Hamburg, Hamburg, Germany; Radiologische Allianz Hamburg, Hamburg, Germany; Klinikum Bielefeld Mitte GmbH, Bielefeld, Germany; Hospital rechts der Isar, Munich, Germany; University Hospital Munich, Munich, Germany; University Hospital Schleswig-Holstein, Luebeck, Germany; Heinrich Heine University Düsseldorf, Düsseldorf, Germany; University Hospital Halle, Halle, Germany; The University of Texas MD Anderson Cancer Center, Houston, TX.
PURPOSE: Neoadjuvant systemic treatment (NST) elicits a pathologic complete response in 40%-70% of women with breast cancer. These patients may not need surgery as all local tumor has already been eradicated by NST. However, nonsurgical approaches, including imaging or vacuum-assisted biopsy (VAB), were not able to accurately identify patients without residual cancer in the breast or axilla. We evaluated the feasibility of a machine learning algorithm (intelligent VAB) to identify exceptional responders to NST.
METHODS: We trained, tested, and validated a machine learning algorithm using patient, imaging, tumor, and VAB variables to detect residual cancer after NST (ypT+ or in situ or ypN+) before surgery. We used data from 318 women with cT1-3, cN0 or +, human epidermal growth factor receptor 2-positive, triple-negative, or high-proliferative Luminal B-like breast cancer who underwent VAB before surgery (NCT02948764, RESPONDER trial). We used 10-fold cross-validation to train and test the algorithm, which was then externally validated using data of an independent trial (NCT02575612). We compared findings with the histopathologic evaluation of the surgical specimen. We considered false-negative rate (FNR) and specificity to be the main outcomes.
RESULTS: In the development set (n = 318) and external validation set (n = 45), the intelligent VAB showed an FNR of 0.0%-5.2%, a specificity of 37.5%-40.0%, and an area under the receiver operating characteristic curve of 0.91-0.92 to detect residual cancer (ypT+ or in situ or ypN+) after NST. Spiegelhalter's Z confirmed a well-calibrated model (z score -0.746, P = .228). FNR of the intelligent VAB was lower compared with imaging after NST, VAB alone, or combinations of both.
CONCLUSION: An intelligent VAB algorithm can reliably exclude residual cancer after NST. The omission of breast and axillary surgery for these exceptional responders may be evaluated in future trials.
KEY OBJECTIVE: Neoadjuvant systemic treatment elicits a pathologic complete response in many women with breast cancer. These patients may not need therapeutic surgery as all local tumor has already been eradicated by neoadjuvant treatment. We evaluated whether a machine learning algorithm (intelligent vacuum-assisted biopsy [VAB]) can identify patients without residual cancer in the breast or axilla.
KNOWLEDGE GENERATED: In the development (n = 318) and external validation sets (n = 45), the intelligent VAB showed an false-negative rate of 0.0%-5.2%, a specificity of 37.5%-40.0%, and an area under the receiver operating characteristic curve of 0.91-0.92 to detect residual cancer (ypT+ or in situ or ypN+) after neoadjuvant treatment. The false-negative rate of the intelligent VAB was lower compared with imaging after neoadjuvant treatment, VAB alone, or combinations of both.
RELEVANCE: An intelligent VAB algorithm can reliably exclude residual cancer after neoadjuvant treatment. These findings pave the way for the omission of breast and axillary surgery for these exceptional responders in future trials.
PMID: 35108029
DOI: 10.1200/JCO.21.02439
2021版CBCS指南与规范完整版
2021版CBCS指南与规范精编版
2021版CBCS指南与规范小程序
联系客服
