A deep learning model for breast ductal carcinoma in situ classification in whole slide images

The pathological differential diagnosis between breast ductal carcinoma in situ (DCIS) and invasive ductal carcinoma (IDC) is of pivotal importance for determining optimum cancer treatment(s) and clinical outcomes. Since conventional diagnosis by pathologists using microscopes is limited in terms of human resources, it is necessary to develop new techniques that can rapidly and accurately diagnose large numbers of histopathological specimens. Computational pathology tools which can assist pathologists in detecting and classifying DCIS and IDC from whole slide images (WSIs) would be of great benefit for routine pathological diagnosis. In this paper, we trained deep learning models capable of classifying biopsy and surgical histopathological WSIs into DCIS, IDC, and benign. We evaluated the models on two independent test sets (n=1,382, n=548), achieving ROC areas under the curves (AUCs) up to 0.960 and 0.977 for DCIS and IDC, respectively.

Ductal carcinoma in situ: a risk prediction model for the underestimation of invasive breast cancer

Patients with a biopsy diagnosis of ductal carcinoma in situ (DCIS) may be diagnosed with invasive breast cancer after excision. We evaluated the preoperative clinical and imaging predictors of DCIS that were associated with an upgrade to invasive carcinoma on final pathology and also compared the diagnostic performance of various statistical models. We reviewed the medical records; including mammography, ultrasound (US), and magnetic resonance imaging (MRI) findings; of 644 patients who were preoperatively diagnosed with DCIS and who underwent surgery between January 2012 and September 2018. Logistic regression and three machine learning methods were applied to predict DCIS underestimation. Among 644 DCIS biopsies, 161 (25%) underestimated invasive breast cancers. In multivariable analysis, suspicious axillary lymph nodes (LNs) on US (odds ratio [OR], 12.16; 95% confidence interval [CI], 4.94–29.95; P < 0.001) and high nuclear grade (OR, 1.90; 95% CI, 1.24–2.91; P = 0.003) were associated with underestimation. Cases with biopsy performed using vacuum-assisted biopsy (VAB) (OR, 0.42; 95% CI, 0.27–0.65; P < 0.001) and lesion size <2 cm on mammography (OR, 0.45; 95% CI, 0.22–0.90; P = 0.021) and MRI (OR, 0.29; 95% CI, 0.09–0.94; P = 0.037) were less likely to be upgraded. No significant differences in performance were observed between logistic regression and machine learning models. Our results suggest that biopsy device, high nuclear grade, presence of suspicious axillary LN on US, and lesion size on mammography or MRI were independent predictors of DCIS underestimation.

A Model to Predict Upstaging to Invasive Carcinoma in Patients Preoperatively Diagnosed with Low-Grade Ductal Carcinoma In Situ of the Breast

Background: We aimed to create a model of radiological and pathological criteria able to predict the upgrade rate of low-grade ductal carcinoma in situ (DCIS) to invasive carcinoma, in patients undergoing vacuum-assisted breast biopsy (VABB) and subsequent surgical excision. Methods: A total of 3100 VABBs were retrospectively reviewed, among which we reported 295 low-grade DCIS who subsequently underwent surgery. The association between patients’ features and the upgrade rate to invasive breast cancer (IBC) was evaluated by univariate and multivariate analysis. Finally, we developed a nomogram for predicting the upstage at surgery, according to the multivariate logistic regression model. Results: The overall upgrade rate to invasive carcinoma was 10.8%. At univariate analysis, the risk of upgrade was significantly lower in patients with greater age (p = 0.018), without post-biopsy residual lesion (p < 0.001), with a smaller post-biopsy residual lesion size (p < 0.001), and in the presence of low-grade DCIS only in specimens with microcalcifications (p = 0.002). According to the final multivariable model, the predicted probability of upstage at surgery was lower than 2% in 58 patients; among these 58 patients, only one (1.7%) upstage was observed, showing a good calibration of the model. Conclusions: An easy-to-use nomogram for predicting the upstage at surgery based on radiological and pathological criteria is able to identify patients with low-grade carcinoma in situ with low risk of upstaging to infiltrating carcinomas.

Modelling a new approach for radio-ablation after resection of breast ductal carcinoma in-situ based on the BAT-90 medical device

The majority of local recurrences, after conservative surgery of breast cancer, occurs in the same anatomical area where the tumour was originally located. For the treatment of ductal carcinoma in situ (DCIS), a new medical device, named BAT-90, (BetaGlue Technologies SpA) has been proposed. BAT-90 is based on the administration of 90Y β-emitting microspheres, embedded in a bio-compatible matrix. In this work, the Geant4 simulation toolkit is used to simulate BAT-90 as a homogenous cylindrical 90Y layer placed in the middle of a bulk material. The activity needed to deliver a 20 Gy isodose at a given distance z from the BAT-90 layer is calculated for different device thicknesses, tumour bed sizes and for water and adipose bulk materials. A radiobiological analysis has been performed using both the Poisson and logistic Tumour Control Probability (TCP) models. A range of radiobiological parameters (α and β), target sizes, and densities of tumour cells were considered. Increasing α values, TCP increases too, while, for a fixed α value, TCP decreases as a function of clonogenic cell density. The models predict very solid results in case of limited tumour burden while the activity/dose ratio could be further optimized in case of larger tumour beds.