Discrimination between HER2-overexpressing, -low-expressing, and -zero-expressing statuses in breast cancer using multiparametric MRI-based radiomics.

OBJECTIVES: To explore the performance of multiparametric MRI-based radiomics in discriminating different human epidermal growth factor receptor 2 (HER2) expressing statuses (i.e., HER2-overexpressing, HER2-low-expressing, and HER2-zero-expressing) in breast cancer. METHODS: A total of 771 breast cancer patients from two institutions were retrospectively studied. Five-hundred-eighty-one patients from Institution I were divided into a training dataset (n1 = 407) and an independent validation dataset (n1 = 174); 190 patients from Institution II formed the external validation dataset. All patients were categorized into HER2-overexpressing, HER2-low-expressing, and HER2-zero-expressing groups based on pathologic examination. Multiparametric (including T2-weighted imaging with fat suppression [T2WI-FS], diffusion-weighted imaging [DWI], apparent diffusion coefficient [ADC], and dynamic contrast-enhanced [DCE]) MRI-based radiomics features were extracted and then selected from the training dataset using the least absolute shrinkage and selection operator (LASSO) regression. Three predictive models to discriminate HER2-overexpressing vs. others, HER2-low expressing vs. others, and HER2-zero-expressing vs. others were developed based on the selected features. The model performance was evaluated using the area under the receiver operating characteristic curve (AUC). RESULTS: Eleven radiomics features from DWI, ADC, and DCE; one radiomics feature from DWI; and 17 radiomics features from DWI, ADC, and DCE were selected to build three predictive models, respectively. In training, independent validation, and external validation datasets, radiomics models achieved AUCs of 0.809, 0.737, and 0.725 in differentiating HER2-overexpressing from others; 0.779, 0.778, and 0.782 in differentiating HER2-low-expressing from others; and 0.889, 0.867, and 0.813 in differentiating HER2-zero-expressing from others, respectively. CONCLUSIONS: Multiparametric MRI-based radiomics model may preoperatively predict HER2 statuses in breast cancer patients. CLINICAL RELEVANCE STATEMENT: The MRI-based radiomics models could be used to noninvasively identify the new three-classification of HER2 expressing status in breast cancer, which is helpful to the decision-making for HER2-target therapies. KEY POINTS: • Detecting HER2-overexpressing, HER2-low-expressing, and HER2-zero-expressing status in breast cancer patients is crucial for determining candidates for anti-HER2 therapy. • Radiomics features from multiparametric MRI significantly differed among HER2-overexpressing, HER2-low expressing, and HER2-zero-expressing breast cancers. • Multiparametric MRI-based radiomics could preoperatively evaluate three different HER2-expressing statuses and help to determine potential candidates for anti-HER2 therapy in breast cancer patients.

Histological Classification and Invasion Prediction of Thymoma by Machine Learning-Based Computed Tomography Imaging.

Purpose: The values of machine learning-based computed tomography (CT) imaging in histological classification and invasion prediction of thymoma were investigated. Methods: 181 patients diagnosed with thymoma by surgery or biopsy in Shantou Central Hospital between February 2017 and March 2022 were selected. According to the concept of simplified histological classification and the latest histological classification by the WHO, thymoma was divided into two groups, including low-risk (types A, AB, B1, and metaplastic type) and high-risk groups (types B2 and B3). CT images were reconstructed by filtering back projection (FBP) algorithm. CT image features were collected for statistical analysis. Results: The main symptoms of patients diagnosed with thymoma included respiratory tract infection, chest distress and shortness of breath, and chest pain. 35.91% of them suffered from complicated myasthenia gravis. Tumor size and position in low-risk and high-risk groups showed no statistical significance (P > 0.05). Tumor morphology and boundary between the two groups suggested statistical difference (P < 0.05). Whether tumor invaded adjacent tissues was apparently correlated with simplified histological classification (P < 0.01). The sensitivity and specificity of CT images for the invasion of mediastinal pleura or pericardium were around 90% and negative predictive values both reached above 95%. Those of the CT images for lung invasion were over 80%. The negative and positive predictive values were 93.54% and 63.82%, respectively. Those of the CT images for blood vessel invasion were 67.32% and 97.93%. The negative and positive predictive values were 98.21% and 83%, respectively. Conclusion: The machine learning-based CT image had significant values in the prediction of different histological classification and even invasion level.