Neoadjuvant chemotherapy with MRI monitoring for breast cancer

Dave, Rajiv; Millican-Slater, Rebecca; Horgan, Kieran; Sharma, Nisha

doi:10.1002/bjs.10544

Cited by 22 publications

(7 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While several studies use radiomic MRI features to monitor response 15,18,35,36 , our goal was to use MRI to predict tumor response . Published studies with this goal are limited by small cohort sizes 18,20–22,24,25 .…”

Section: Discussionmentioning

confidence: 99%

Multivariate machine learning models for prediction of pathologic response to neoadjuvant therapy in breast cancer using MRI features: a study using an independent validation set

Cain

Saha

Harowicz

et al. 2018

Breast Cancer Res Treat

146

116

View full text Add to dashboard Cite

Purpose To determine whether a multivariate machine learning-based model using computer-extracted features of pre-treatment dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) can predict pathologic complete response (pCR) to neoadjuvant therapy (NAT) in breast cancer patients. Methods Institutional review board approval was obtained for this retrospective study of 288 breast cancer patients at our institution who received NAT and had a pre-treatment breast MRI. A comprehensive set of 529 radiomic features was extracted from each patient’s pretreatment MRI. The patients were divided into equal groups to form a training set and an independent test set. Two multivariate machine learning models (logistic regression and a support vector machine) based on imaging features were trained to predict pCR in (a) all patients with NAT, (b) patients with neoadjuvant chemotherapy (NACT), and (c) triple negative or human epidermal growth factor receptor 2-positive (TN/HER2+) patients who had NAT. The multivariate models were tested using the independent test set, and the area under the receiver operating characteristics (ROC) curve (AUC) was calculated. Results Out of the 288 patients, 64 achieved pCR. The AUC values for predicting pCR in TN/HER+ patients who received NAT were significant (.707, 95%CI: 0.582–0.833, p < 0.002). Conclusions The multivariate models based on pre-treatment MRI features were able to predict pCR in TN/HER2+ patients.

show abstract

Section: Discussionmentioning

confidence: 99%

Multivariate machine learning models for prediction of pathologic response to neoadjuvant therapy in breast cancer using MRI features: a study using an independent validation set

Cain

Saha

Harowicz

et al. 2018

Breast Cancer Res Treat

146

116

View full text Add to dashboard Cite

show abstract

“…In addition, some of them underwent mammography, magnetic resonance imaging, fine‐needle aspiration biopsy (FNAB), or a combination for confirmation of the diagnosis. A total of 39 patients who received neoadjuvant chemotherapy before breast surgery were excluded, in addition to 33 patients in whom cancer was diagnosed by excisional biopsy and 35 patients without complete US reports because we were unable to retrieve the primary data for the cancer, such as the tumor size, aspect ratio, tumor margin, estrogen receptor and progesterone receptor status, and Ki‐67 status . Eventually, 527 patients were included in the study.…”

Section: Methodsmentioning

confidence: 99%

Correlation of Conventional Ultrasound Characteristics of Breast Tumors With Axillary Lymph Node Metastasis and Ki‐67 Expression in Patients With Breast Cancer

Zhang

Sui

Zhou

et al. 2018

J of Ultrasound Medicine

View full text Add to dashboard Cite

Objectives-To explore the association between the ultrasound (US) characteristics of breast tumors with axillary lymph node metastasis (ALNM) and Ki-67 expression in patients with breast cancer.Methods-In total, 527 consecutive patients with breast cancer who had undergone US examinations and curative surgery with axillary lymph node evaluations were included. The size, shape, aspect ratio, margin, internal echo, internal calcification, posterior echo attenuation, lymphatic hilar structure, cortical thickness, and blood flow of the axillary lymph nodes or primary breast lesions were observed with conventional US. Pathologic prognostic factors, including the histologic type of the tumor, histologic grade, estrogen and progesterone receptor status, lymph node status, and Ki-67 expression were determined. A logistic regression model was used to evaluate whether the US characteristics of primary breast lesions were associated with ALNM and Ki-67 expression.Results-The maximum tumor diameter (odds ratio [OR], 1.54; 95% confidence interval [CI], 1.05-2.27; P = .028), tumor margin (OR, 2.89; 95% CI, 1.69-4.94; P < .001), internal echo (OR, 2.17; 95% CI, 1.47-3.20; P < .001), and Ki-67 status (OR, 3.57; 95% CI, 2.29-5.58; P < .001) had significant value as independent predictors of ALNM. Only the internal echo (OR, 1.95; 95% CI, 1.28-2.95; P = .002) of breast cancer was an independent predictor of the Ki-67 status. The heterogeneity in the internal echo indicated faster cancer cell proliferation and was associated with a worse prognosis in patients with breast carcinoma.Conclusions-Certain conventional US characteristics may be useful predictors of ALNM and the Ki-67 status in patients with breast cancer.

show abstract

“…[ 9 , 14 ] NAC can affect the BPE levels of normal breast and breast cancer tissues; thus, BPE levels may reflect the therapeutic response or prognosis of patients with cancer. [ 15 – 17 ] Patients with higher pre-NAC BPE levels have been shown to have poor recurrence-free survival. [ 16 ] The higher degree of BPE reduction after NAC is associated with good tumor response (Response Evaluation Criteria in Solid Tumors 1.1 criteria).…”

Section: Introductionmentioning

confidence: 99%

Changes in background parenchymal enhancement in HER2-positive breast cancer before and after neoadjuvant chemotherapy

et al. 2018

View full text Add to dashboard Cite

This study aimed to analyze the relationship between pathologic complete response (pCR) and changes in background parenchymal enhancement (BPE) levels in patients with human epidermal growth factor receptor 2 (HER2)-positive breast cancer and who received neoadjuvant chemotherapy (NAC).The pre- and post-NAC magnetic resonance imaging results of 51 patients with confirmed unilateral HER2-positive breast cancer were retrospectively analyzed by 2 experienced radiologists. Pre- and post-NAC of contralateral BPE levels were classified into 4 categories (1 = minimal, 2 = mild, 3 = moderate, and 4 = marked). The 4 categories of BPE were defined by the visually estimated enhancement of fibroglandular tissue of the breast. Changes in BPE before and after NAC were compared between the premenopausal and postmenopausal groups and between the pCR and non-pCR groups. The associations between BPE and pCR and between BPE and tumor size were analyzed before and after NAC.Twenty-three patients achieved pCR, and 28 patients achieved non-pCR. Premenopausal patients had significantly higher baseline BPE levels than postmenopausal women (P = .023). The post-NAC BPE levels of premenopausal patients significantly decreased relative to those of postmenopausal patients (P = .027). The baseline BPE levels of the pCR group were not significantly different from those of the non-pCR group (P = .892). However, the decrease in BPE levels in the pCR group was more drastic than that in the non-pCR group (P < .001). Decreased BPE levels were directly associated with pCR and tumor size reduction (P < .05). Women with hormone receptor (HR)-negative tumors were more likely to exhibit pCR than those with HR-positive tumors (P = .007).Decreased BPE of patients with HER2-positive breast cancer may serve as an indicator of NAC effectiveness. Furthermore, women with HR-negative tumors were more likely to exhibit pCR than women with HR-positive tumors.

show abstract

Neoadjuvant chemotherapy with MRI monitoring for breast cancer

Abstract: NACT allows identification of patient subgroups within TNBC and Her2-positive cohorts with a good prognosis. MRI can be used to identify patients who are responding to treatment.

Cited by 22 publications

References 30 publications

Multivariate machine learning models for prediction of pathologic response to neoadjuvant therapy in breast cancer using MRI features: a study using an independent validation set

Multivariate machine learning models for prediction of pathologic response to neoadjuvant therapy in breast cancer using MRI features: a study using an independent validation set

Correlation of Conventional Ultrasound Characteristics of Breast Tumors With Axillary Lymph Node Metastasis and Ki‐67 Expression in Patients With Breast Cancer

Changes in background parenchymal enhancement in HER2-positive breast cancer before and after neoadjuvant chemotherapy

Contact Info

Product

Resources

About