Radiomics Analysis on Digital Breast Tomosynthesis: Preoperative Evaluation of Lymphovascular Invasion Status in Invasive Breast Cancer

Wang, Dongqing; Liu, Mengsi; Zhuang, Zijian; Wu, Shuting; Zhou, Peng; Chen, Xingchi; Zhu, Hai‐Tao; Liu, Huihui; Zhang, Lirong

doi:10.1016/j.acra.2022.03.011

Cited by 12 publications

(18 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As another independent predictor for LVI in the clinic_CUS model, US_LNM was more common in LVI-positive than LVI-negative breast cancers. Previous studies (6)(7)(8)(9) had also demonstrated that the presence of LVI was closely associated with axillary lymph node involvement, which were consistent with our study. Similarly, ZHOU et al (12) and Tong et al (8) all thought that suspicious findings on axillary US imaging were independent predictor for the presence of LVI.…”

Section: Discussionsupporting

confidence: 93%

“…According to previous study ( 27 ), patients were classified into the following four breast cancer subtypes: luminal A, luminal B, HER-2-positive, and triple-negative. LVI was defined as the presence of tumor cells within the lymphatic or vascular channels at the peritumoral region ( 6 , 7 ), which was also identified by examining the primary tumor stained with endothelial-specific markers, including anti-CD34 and anti-D2-40 antibodies ( 6 ). The status of tumor LVI was defined as LVI-positive and LVI-negative.…”

Section: Methodsmentioning

confidence: 99%

“…Therefore, LVI has been considered as a major criteria for tumor staging, prognostic prediction, and the treatment choice (3,4). Treatment decisions for T1 breast cancer usually need refer to the presence or absence of lymph node metastasis (5), which is often associated with LVI (1,(5)(6)(7)(8)(9). LVI had been proved as an independent prognostic factor in T1 breast cancer (9,10), and patients with LVI may require more clinical decisions, including surgical type, the margin determination of surgery, and guiding more aggressive neoadjuvant treatment protocols for breast cancer patients (9,11).…”

Section: Introductionmentioning

confidence: 99%

“…Previous studies have demonstrated that preoperative breast mammography, digital breast tomosynthesis (DBT) or MRI can be effectively used for the prediction of LVI ( 1 , 3 , 6 , 7 , 15 ). Different from other imaging methods, US has the advantages of relatively low price, real-time, and reproducible operation, and is a reliable examination method for breast tumors in clinical work ( 16 ).…”

Section: Introductionmentioning

confidence: 99%

“…Radiomics is a relatively new machine learning approach that provides high-throughput quantitative information on tumor shape, intensity, and texture ( 3 , 6 ), which fail to be detected by naked eyes ( 17 ). Advances in radiomics-based US have increasingly highlighted its potential value for improving diagnosis, evaluating prognosis, and predicting response to treatment in breast carcinoma ( 18 – 21 ).…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Preoperative prediction of lymphovascular invasion in patients with T1 breast invasive ductal carcinoma based on radiomics nomogram using grayscale ultrasound

Zeng

et al. 2022

Front. Oncol.

View full text Add to dashboard Cite

PurposeThe aim of this study was to develop a radiomics nomogram based on grayscale ultrasound (US) for preoperatively predicting Lymphovascular invasion (LVI) in patients with pathologically confirmed T1 (pT1) breast invasive ductal carcinoma (IDC).MethodsOne hundred and ninety-two patients with pT1 IDC between September 2020 and August 2022 were analyzed retrospectively. Study population was randomly divided in a 7: 3 ratio into a training dataset of 134 patients (37 patients with LVI-positive) and a validation dataset of 58 patients (19 patients with LVI-positive). Clinical information and conventional US (CUS) features (called clinic_CUS features) were recorded and evaluated to predict LVI. In the training dataset, independent predictors of clinic_CUS features were obtained by univariate and multivariate logistic regression analyses and incorporated into a clinic_CUS prediction model. In addition, radiomics features were extracted from the grayscale US images, and the radiomics score (Radscore) was constructed after radiomics feature selection. Subsequent multivariate logistic regression analysis was also performed for Radscore and the independent predictors of clinic_CUS features, and a radiomics nomogram was developed. The performance of the nomogram model was evaluated via its discrimination, calibration, and clinical usefulness.ResultsThe US reported axillary lymph node metastasis (LNM) (US_LNM) status and tumor margin were determined as independent risk factors, which were combined for the construction of clinic_CUS prediction model for LVI in pT1 IDC. Moreover, tumor margin, US_LNM status and Radscore were independent predictors, incorporated as the radiomics nomogram model, which achieved a superior discrimination to the clinic_CUS model in the training dataset (AUC: 0.849 vs. 0.747; P < 0.001) and validation dataset (AUC: 0.854 vs. 0.713; P = 0.001). Calibration curve for the radiomic nomogram showed good concordance between predicted and actual probability. Furthermore, decision curve analysis (DCA) confirmed that the radiomics nomogram had higher clinical net benefit than the clinic_CUS model.ConclusionThe US-based radiomics nomogram, incorporating tumor margin, US_LNM status and Radscore, showed a satisfactory preoperative prediction of LVI in pT1 IDC patients.

show abstract