Nomograms predicting recurrence in patients with triple negative breast cancer based on ultrasound and clinicopathological features

Zhang, Lei; Zhang, Xudong; Han, Peng; Zhao, Dantong; Hu, Nana; Fan, Wei; Wang, Panting; Zuo, Xiaoxuan; Kong, Hanqing; Peng, Fuhui; Tian, Jing; Cui, Hao

doi:10.1259/bjr.20220305

Cited by 3 publications

(1 citation statement)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Meanwhile, ultrasound has a relatively high sensitivity and speci city for diagnosing breast cancer [14]. The relationship between the risk of breast cancer recurrence and ultrasound features has already been identi ed [15,16]. Breast cancer at high risk of recurrence is associated with HER2 status, vascularity, and breast imaging reporting and data system (BI-RADS) grade [17].…”

Section: Introduction Page 3/27mentioning

confidence: 99%

Ultrasound-based radiomics score to predict the risk of breast cancer recurrence

Fan,

Cui,

Wang

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

Background To develop a radiomics model based on ultrasound images for predicting recurrence risk in breast cancer patients. Methods In this retrospective study, 420 patients with pathologically confirmed breast cancer were included. According to St. Gallen risk criteria, patients were categorised into low-medium and high-risk recurrence groups. All patients were randomly assigned to training and test cohorts at a ratio of 7:3. Radiomics features were extracted from a radiomics analysis set using Pyradiomics. The informative radiomics features were screened using the minimum redundancy maximum relevance (mRMR) and the least absolute shrinkage and selection operator (LASSO) algorithms. Subsequently, radiomics models were constructed with seven machine learning algorithms. Three distinct nomogram models were created using the features selected through multivariate logistic regression, including the clinic-ultrasound (Clin-US), clinic-radiomics (Clin-Rad), and clinic-ultrasound-radiomics (Clin-US-Rad) models. The receiver operating characteristic (ROC), calibration, and decision curve analysis (DCA) curves were used to evaluate the model’s clinical applicability and predictive performance. Results Overall, 12 ultrasound radiomics features were screened, such as wavelet.LHL_firstorder_median, original_shape_majoraxislength, square_glszm_graylevelcariance, etc. The higher the risk of recurrence, the higher the radiomics score (Rad-score) in training and test cohorts (both p < 0.05). According to the above screening features, we selected seven different classifiers, among which logistic regression was used to establish the best radiomics model. In the test cohort, the Clin-US-Rad model performed best and had the highest significant areaunder the curve (AUC) values (AUC = 0.873) compared to the Clin-Rad and Clin-US models. The calibration and DCA curves also demonstrated the combined model’s good clinical utility. Conclusions The ultrasound radiomics features were useful for predicting the risk of breast cancer recurrence. The nomograms developed by the above-described features are reliable tools for assessing the risk of breast cancer recurrence.

show abstract

Section: Introduction Page 3/27mentioning

confidence: 99%