Abstract
ObjectivesThe probability of Breast Imaging Reporting and Data Systems (BI-RADS) 4 lesions being malignant is 2%–95%, which shows the difficulty to make a diagnosis. Radiomics models based on magnetic resonance imaging (MRI) can replace clinicopathological diagnosis with high performance. In the present study, we developed and tested a radiomics model based on MRI images that can predict the malignancy of BI-RADS 4 breast lesions.MethodsWe retrospective enrolled a total of 216 BI-RADS 4 patients MRI and clinical information. We extracted 3,474 radiomics features from dynamic contrast-enhanced (DCE), T2-weighted images (T2WI), and diffusion-weighted imaging (DWI) MRI images. Least absolute shrinkage and selection operator (LASSO) and logistic regression were used to select features and build radiomics models based on different sequence combinations. We built eight radiomics models which were based on DCE, DWI, T2WI, DCE+DWI, DCE+T2WI, DWI+T2WI, and DCE+DWI+T2WI and a clinical predictive model built based on the visual assessment of radiologists. A nomogram was constructed with the best radiomics signature combined with patient characteristics. The calibration curves for the radiomics signature and nomogram were conducted, combined with the Hosmer-Lemeshow test.ResultsPearson’s correlation was used to eliminate 3,329 irrelevant features, and then LASSO and logistic regression were used to screen the remaining feature coefficients for each model we built. Finally, 12 related features were obtained in the model which had the best performance. These 12 features were used to build a radiomics model in combination with the actual clinical diagnosis of benign or malignant lesion labels we have obtained. The best model built by 12 features from the 3 sequences has an AUC value of 0.939 (95% CI, 0.884-0.994) and an accuracy of 0.931 in the testing cohort. The sensitivity, specificity, precision and Matthews correlation coefficient (MCC) of testing cohort are 0.932, 0.923, 0.982, and 0.791, respectively. The nomogram has also been verified to have calibration curves with good overlap.ConclusionsRadiomics is beneficial in the malignancy prediction of BI-RADS 4 breast lesions. The radiomics predictive model built by the combination of DCE, DWI, and T2WI sequences has great application potential.
Highlights
The 2020 Global Cancer Report released by the International Agency for Research on Cancer (IARC) shows that female breast cancer has replaced lung cancer as the most common cancer in the world with an increase of approximately 2.3 million new cases (11.7%) throughout the year [1]
The probability of being malignant is 2%–95%, this type of breast disease has a further classification of 4a, 4b, and 4c, because of the large range of the possibility of the existence of malignant lesion, all patients with BI-RADS 4 breast diseases are recommended to undergo biopsy of suspicious areas to clarify their pathological properties [3]
The criteria for inclusion in the group were as follows: (i) Patients have been diagnosed with a BI-RADS type IV breast lesion. (ii) The pathological diagnoses results were confirmed by puncture pathology diagnoses. (iii) Patients have complete MRI images in picture archiving and communication system (PACS) with axial DCE, DWI, and T2WI sequences obtained before patients underwent biopsy
Summary
The 2020 Global Cancer Report released by the International Agency for Research on Cancer (IARC) shows that female breast cancer has replaced lung cancer as the most common cancer in the world with an increase of approximately 2.3 million new cases (11.7%) throughout the year [1]. The diagnosis of benign or malignant breast lesions has become the most basic and important step in the treatment of breast diseases. The fourth category of breast disease is defined as a type of breast lesions with suspicious malignancy and uncertain pathological types. The probability of being malignant is 2%–95%, this type of breast disease has a further classification of 4a, 4b, and 4c, because of the large range of the possibility of the existence of malignant lesion, all patients with BI-RADS 4 breast diseases are recommended to undergo biopsy of suspicious areas to clarify their pathological properties [3]. We propose a hypothesis to establish a predictive radiomics model based on the patients’ preoperative imaging information, thereby avoiding patients with benign breast lesions from undergoing invasive pathological testing
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
