Toward Computer-Assisted Triaging of Magnetic Resonance Imaging‐Guided Biopsy in Preoperative Breast Cancer Patients

Abstract

ObjectivesIncidental MR-detected breast lesions (ie, additional lesions to the index cancer) pose challenges in the preoperative workup of patients with early breast cancer. We pursue computer-assisted triaging of magnetic resonance imaging (MRI)‐guided breast biopsy of additional lesions at high specificity.Materials and MethodsWe investigated 316 consecutive female patients (aged 26 to 76 years; mean, 54 years) with early breast cancer who received preoperative multiparametric breast MRI between 2013 and 2016. In total, 82 (26%) of 316 patients had additional breast lesions on MRI. These 82 patients had 101 additional lesions in total, 51 were benign and 50 were malignant. We collected 4 clinical features and 46 MRI radiomic features from T1-weighted dynamic contrast-enhanced imaging, high-temporal-resolution dynamic contrast-enhanced imaging, T2-weighted imaging, and diffusion-weighted imaging. A multiparametric computer-aided diagnosis (CAD) model using 10-fold cross-validated ridge regression was constructed. The sensitivities were calculated at operating points corresponding to 98%, 95%, and 90% specificity. The model calibration performance was evaluated by calibration plot analysis and goodness-of-fit tests. The model was tested in an independent testing cohort of 187 consecutive patients from 2017 and 2018 (aged 35 to 76 years; mean, 59 years). In this testing cohort, 45 (24%) of 187 patients had 55 additional breast lesions in total, 23 were benign and 32 were malignant.ResultsThe multiparametric CAD model correctly identified 48% of the malignant additional lesions with a specificity of 98%. At specificity 95% and 90%, the sensitivity was 62% and 72%, respectively. Calibration plot analysis and goodness-of-fit tests indicated that the model was well fitted.In the independent testing cohort, the specificity was 96% and the sensitivity 44% at the 98% specificity operating point of the training set. At operating points 95% and 90%, the specificity was 83% at 69% sensitivity and the specificity was 78% at 81% sensitivity, respectively.ConclusionsThe multiparametric CAD model showed potential to identify malignant disease extension with near-perfect specificity in approximately half the population of preoperative patients originally indicated for a breast biopsy. In the other half, patients would still proceed to MRI-guided biopsy to confirm absence of malignant disease. These findings demonstrate the potential to triage MRI-guided breast biopsy.

Medical education and artificial intelligence: Question answering for medical questions based on intelligent interaction

“…By using the combined attention mechanism, we can obtain answer aware question representation ⌢ Q i and question aware answer representation ⌢ A i . In the comparison module, it compares the representation of answers before and after the interaction as a new feature of the current interaction, as shown in Equation (7).…”

“…The experiment illustrates that approximately half of the preoperative patients who were originally scheduled for breast biopsy have the potential for nearly perfect specificity in identifying the spread of malignant diseases. In the other half of the patients, they will still undergo MRI guided biopsy to confirm the absence of malignant diseases 7 . Since the birth of artificial intelligence, its theory and technology have become increasingly mature, and its application fields have also continued to expand.…”

Automated Triage of Screening Breast MRI Examinations in High-Risk Women Using an Ensemble Deep Learning Model

“…26 Deep learning has also been used to triage cancer patients with additional MRI lesions directly to surgery, potentially eliminating need for additional preoperative biopsies that have a very high likelihood of malignancy. 27 However, no study to date has evaluated the use of DL for automated triage of screening breast MRI examinations in a large population of high-risk women (ie, women with greater than 20% lifetime risk of breast cancer), which constitutes the clinically relevant scenario.…”

“…Deep learning has also been explored to reduce the clinical workload of screening breast MRI examinations in women with extremely dense breasts, 25 or as an initial triage step before computer-aided detection in an effort to decrease the number of biopsies on benign lesions 26 . Deep learning has also been used to triage cancer patients with additional MRI lesions directly to surgery, potentially eliminating need for additional preoperative biopsies that have a very high likelihood of malignancy 27 . However, no study to date has evaluated the use of DL for automated triage of screening breast MRI examinations in a large population of high-risk women (ie, women with greater than 20% lifetime risk of breast cancer), which constitutes the clinically relevant scenario.…”

Personalizing endocrine therapy for breast cancer using MRI

“…AI is an exciting field with current uses mainly in the field of diagnostic imaging (e.g. diagnosis of benign versus malignant breast tumors [205][206][207] ) 208,209 , but is extending to find patterns that predict survival, for example in amyotrophic lateral sclerosis in MRI data 209,210 . In breast imaging, additional imaging features beyond only parenchymal enhancement, such as tumor-derived features, can also be considered with AI.…”