Predicting breast cancer response to neoadjuvant treatment using multi-feature MRI: results from the I-SPY 2 TRIAL

被引：55

作者：

Li, Wen ^{[1
]}

Newitt, David C. ^{[1
]}

Gibbs, Jessica ^{[1
]}

Wilmes, Lisa J. ^{[1
]}

Jones, Ella F. ^{[1
]}

Arasu, Vignesh A. ^{[1
]}

Strand, Fredrik ^{[1
,2
]}

Onishi, Natsuko ^{[1
]}

Nguyen, Alex Anh-Tu ^{[1
]}

Kornak, John ^{[1
]}

Joe, Bonnie N. ^{[1
]}

Price, Elissa R. ^{[1
]}

Ojeda-Fournier, Haydee ^{[3
]}

Eghtedari, Mohammad ^{[3
]}

Zamora, Kathryn W. ^{[4
]}

Woodard, Stefanie A. ^{[4
]}

Umphrey, Heidi ^{[4
]}

Bernreuter, Wanda ^{[4
]}

Nelson, Michael ^{[5
]}

Church, An Ly ^{[5
]}

Bolan, Patrick ^{[5
]}

Kuritza, Theresa ^{[6
]}

Ward, Kathleen ^{[6
]}

Morley, Kevin ^{[6
]}

Wolverton, Dulcy ^{[7
]}

Fountain, Kelly ^{[7
]}

Lopez-Paniagua, Dan ^{[7
]}

Hardesty, Lara ^{[7
]}

Brandt, Kathy ^{[8
]}

McDonald, Elizabeth S. ^{[9
]}

Rosen, Mark ^{[9
]}

Kontos, Despina ^{[9
]}

Abe, Hiroyuki ^{[10
]}

Sheth, Deepa ^{[10
]}

Crane, Erin P. ^{[11
]}

Dillis, Charlotte ^{[11
]}

Sheth, Pulin ^{[12
]}

Hovanessian-Larsen, Linda ^{[12
]}

Bang, Dae Hee ^{[13
]}

Porter, Bruce ^{[13
]}

Oh, Karen Y. ^{[14
]}

Jafarian, Neda ^{[14
]}

Tudorica, Alina ^{[14
]}

Niell, Bethany L. ^{[15
]}

Drukteinis, Jennifer ^{[15
]}

Newell, Mary S. ^{[16
]}

Cohen, Michael A. ^{[16
]}

Giurescu, Marina ^{[17
]}

Berman, Elise ^{[18
]}

Lehman, Constance ^{[19
]}

机构：

[1] Univ Calif San Francisco, San Francisco, CA 94143 USA

[2] Karolinska Inst, Stockholm, Sweden

[3] Univ Calif San Diego, San Diego, CA 92103 USA

[4] Univ Alabama Birmingham, Birmingham, AL USA

[5] Univ Minnesota, Minneapolis, MN USA

[6] Loyola Univ, Maywood, IL 60153 USA

[7] Univ Colorado, Denver, CO 80202 USA

[8] Mayo Clin, Rochester, NY USA

[9] Univ Penn, Philadelphia, PA 19104 USA

[10] Univ Chicago, Chicago, IL 60637 USA

[11] Georgetown Univ, Georgetown, DC USA

[12] Univ Southern Calif, Los Angeles, CA 90007 USA

[13] Swedish Canc Inst, Seattle, WA USA

[14] Oregon Hlth & Sci Univ, Portland, OR 97201 USA

[15] H Lee Moffitt Canc Ctr & Res Inst, Tampa, FL USA

[16] Emory Univ, Atlanta, GA 30322 USA

[17] Mayo Clin, Scottsdale, AZ USA

[18] Inova Hlth Syst, Falls Church, VA USA

[19] Univ Washington, Seattle, WA 98195 USA

[20] Univ Arizona, Tucson, AZ USA

[21] Univ Texas MD Anderson Canc Ctr, Houston, TX 77030 USA

[22] Univ Texas Southwestern, Dallas, TX USA

[23] Univ Michigan, Ann Arbor, MI 48109 USA

[24] Berry Consultants LLC, Austin, TX USA

来源：

NPJ BREAST CANCER | 2020年 / 6卷 / 01期

关键词：

BACKGROUND PARENCHYMAL ENHANCEMENT; FUNCTIONAL TUMOR VOLUME; ADAPTIVE RANDOMIZATION; CHEMOTHERAPY; HER2;

D O I：

10.1038/s41523-020-00203-7

中图分类号：

R73 [肿瘤学];

学科分类号：

100214 ;

摘要：

Dynamic contrast-enhanced (DCE) MRI provides both morphological and functional information regarding breast tumor response to neoadjuvant chemotherapy (NAC). The purpose of this retrospective study is to test if prediction models combining multiple MRI features outperform models with single features. Four features were quantitatively calculated in each MRI exam: functional tumor volume, longest diameter, sphericity, and contralateral background parenchymal enhancement. Logistic regression analysis was used to study the relationship between MRI variables and pathologic complete response (pCR). Predictive performance was estimated using the area under the receiver operating characteristic curve (AUC). The full cohort was stratified by hormone receptor (HR) and human epidermal growth factor receptor 2 (HER2) status (positive or negative). A total of 384 patients (median age: 49 y/o) were included. Results showed analysis with combined features achieved higher AUCs than analysis with any feature alone. AUCs estimated for the combined versus highest AUCs among single features were 0.81 (95% confidence interval [CI]: 0.76, 0.86) versus 0.79 (95% CI: 0.73, 0.85) in the full cohort, 0.83 (95% CI: 0.77, 0.92) versus 0.73 (95% CI: 0.61, 0.84) in HR-positive/HER2-negative, 0.88 (95% CI: 0.79, 0.97) versus 0.78 (95% CI: 0.63, 0.89) in HR-positive/HER2-positive, 0.83 (95% CI not available) versus 0.75 (95% CI: 0.46, 0.81) in HR-negative/HER2-positive, and 0.82 (95% CI: 0.74, 0.91) versus 0.75 (95% CI: 0.64, 0.83) in triple negatives. Multi-feature MRI analysis improved pCR prediction over analysis of any individual feature that we examined. Additionally, the improvements in prediction were more notable when analysis was conducted according to cancer subtype.

引用

页数：6

共 34 条

[1] Current and emerging quantitative magnetic resonance imaging methods for assessing and predicting the response of breast cancer to neoadjuvant therapy [J].