Ultrasound-based radiomics nomogram for differentiation of triple-negative breast cancer from fibroadenoma

Abstract

Objective: This study aimed to develop a radiomics nomogram that incorporates radiomics, conventional ultrasound (US) and clinical features in order to differentiate triple-negative breast cancer (TNBC) from fibroadenoma. Methods: A total of 182 pathology-proven fibroadenomas and 178 pathology-proven TNBCs, which underwent preoperative US examination, were involved and randomly divided into training (n = 253) and validation cohorts (n = 107). The radiomics features were extracted from the regions of interest of all lesions, which were delineated on the basis of preoperative US examination. The least absolute shrinkage and selection operator model and the maximum relevance minimum redundancy algorithm were established for the selection of tumor status-related features and construction of radiomics signature (Rad-score). Then, multivariate logistic regression analyses were utilized to develop a radiomics model by incorporating the radiomics signature and clinical findings. Finally, the usefulness of the combined nomogram was assessed by using the receiver operator characteristic curve, calibration curve, and decision curve analysis (DCA). Results: The radiomics signature, composed of 12 selected features, achieved good diagnostic performance. The nomogram incorporated with radiomics signature and clinical data showed favorable diagnostic efficacy in the training cohort (AUC 0.986, 95% CI, 0.975–0.997) and validation cohort (AUC 0.977, 95% CI, 0.953–1.000). The radiomics nomogram outperformed the Rad-score and clinical models (p < 0.05). The calibration curve and DCA demonstrated the good clinical utility of the combined radiomics nomogram. Conclusion: The radiomics signature is a potential predictive indicator for differentiating TNBC and fibroadenoma. The radiomics nomogram associated with Rad-score, US conventional features, and clinical data outperformed the Rad-score and clinical models. Advances in knowledge: Recent advances in radiomics-based US are increasingly showing potential for improved diagnosis, assessment of therapeutic response and disease prediction in oncology. Rad-score is an independent predictive indicator for differentiating TNBC and fibroadenoma. The radiomics nomogram associated with Rad-score, US conventional features, and clinical data outperformed the Rad-score and clinical models.

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

“…The clearest and most complete US images were obtained in DICOM format. The following conventional ultrasound (CUS) features of breast tumors were recorded in concordance with prior studies ( 12 , 18 ): (1) tumor location: upper outer quadrant, upper inner quadrant, lower outer quadrant, lower inner quadrant or other positions; (2) tumor size: maximum diameter; (3) tumor shape: regular (round or oval) or irregular; (4) tumor margin: circumscribed or not circumscribed (indistinct, angular, microlobulated, or spiculated); (5) tumor orientation: parallel or not parallel; (6) tumor echo pattern: hypoechoic, isoechoic, hyperechoic or heterogeneous; (7) microcalcifications: present or absent; (8) tumor posterior features: no posterior acoustic features, enhancement, shadowing or combined pattern. In addition, suspicious CUS features of axillary lymph node metastasis (LNM) were also evaluated, including rounded hypoechoic node complete or partial effacement of the fatty hilum, the ratio of long axis diameter to short axis diameter < 2, cortical thickening > 3 mm, nonhilar cortical blood flow on color Doppler images, complete or partial replacement of the node with an ill-defined or irregular mass and microcalcifications in the node ( 25 ).…”

“…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 ). As a tool to determine the appropriate treatment for patients, nomogram was developed based on comprehensive data to allow the clinician to assess the associated clinical risk more accurately ( 18 , 22 ).…”

“…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 ). As a tool to determine the appropriate treatment for patients, nomogram was developed based on comprehensive data to allow the clinician to assess the associated clinical risk more accurately ( 18 , 22 ). The nomogram incorporating US radiomics score had showed potential diagnostic capabilities for triple-negative breast cancer and fibroadenoma ( 18 ).…”

“…As a tool to determine the appropriate treatment for patients, nomogram was developed based on comprehensive data to allow the clinician to assess the associated clinical risk more accurately ( 18 , 22 ). The nomogram incorporating US radiomics score had showed potential diagnostic capabilities for triple-negative breast cancer and fibroadenoma ( 18 ). On the other hand, nomogram based on US radiomics analysis exhibited high accuracy in predicting axillary lymph node (ALN) tumor burden in breast cancer patients ( 21 ).…”

Imaging of fibroadenoma: Be careful with imaging follow-up

“…Novel radiologic studies continue to emphasize the critical distinction between fibroadenomas and malignant tumors. Radiomics—a diagnostic tool based on artificial intelligence—has been evaluated for the aforementioned purpose using sonographic and magnetic resonance images; it is stated that the radiomics signature may be a useful predictive parameter for the differentiation of fibroadenomas from malignant lesions and phyllodes tumors[ 16 , 17 ]. Additionally, novel MRI approaches have been developed to distinguish fibradenomas from malignant lesions, one of which is three-dimensional amide proton transfer weighted magnetic resonance imaging.…”