Magda Marcon

In DCE-MRI, the degree of contrast uptake in normal fibroglandular tissue, i.e., background parenchymal enhancement (BPE), is a crucial biomarker linked to breast cancer risk and treatment outcome. In accordance with the Breast Imaging Reporting & Data System (BI-RADS), it should be visually classified into four classes. The susceptibility of such an assessment to inter-reader variability highlights the urgent need for a standardized classification algorithm. In this retrospective study, the first post-contrast subtraction images for 27 healthy female subjects were included. The BPE was classified slice-wise by two expert radiologists. The extraction of radiomic features from segmented BPE was followed by dataset splitting and dimensionality reduction. The latent representations were then utilized as inputs to a deep neural network classifying BPE into BI-RADS classes. The network’s predictions were elucidated at the radiomic feature level with Shapley values. The deep neural network achieved a BPE classification accuracy of 84 ± 2% (p-value < 0.00001). Most of the misclassifications involved adjacent classes. Different radiomic features were decisive for the prediction of each BPE class underlying the complexity of the decision boundaries. A highly precise and explainable pipeline for BPE classification was achieved without user- or algorithm-dependent radiomic feature selection.

Breast cancer is the most frequently diagnosed cancer in women accounting for about 30% of all new cancer cases and the incidence is constantly increasing. Implementation of mammographic screening has contributed to a reduction in breast cancer mortality of at least 20% over the last 30 years. Screening programs usually include all women irrespective of their risk of developing breast cancer and with age being the only determining factor. This approach has some recognized limitations, including underdiagnosis, false positive cases, and overdiagnosis. Indeed, breast cancer remains a major cause of cancer-related deaths in women undergoing cancer screening. Supplemental imaging modalities, including digital breast tomosynthesis, ultrasound, breast MRI, and, more recently, contrast-enhanced mammography, are available and have already shown potential to further increase the diagnostic performances. Use of breast MRI is recommended in high-risk women and women with extremely dense breasts. Artificial intelligence has also shown promising results to support risk categorization and interval cancer reduction. The implementation of a risk-stratified approach instead of a “one-size-fits-all” approach may help to improve the benefit-to-harm ratio as well as the cost-effectiveness of breast cancer screening. Key Points: Regular mammography should still be considered the mainstay of the breast cancer screening. High-risk women and women with extremely dense breast tissue should use MRI for supplemental screening or US if MRI is not available. Women need to participate actively in the decision to undergo personalized screening. Key recommendations: Mammography is an effective imaging tool to diagnose breast cancer in an early stage and to reduce breast cancer mortality (evidence level I). Until more evidence is available to move to a personalized approach, regular mammography should be considered the mainstay of the breast cancer screening. High-risk women should start screening earlier; first with yearly breast MRI which can be supplemented by yearly or biennial mammography starting at 35–40 years old (evidence level I). Breast MRI screening should be also offered to women with extremely dense breasts (evidence level I). If MRI is not available, ultrasound can be performed as an alternative, although the added value of supplemental ultrasound regarding cancer detection remains limited. Individual screening recommendations should be made through a shared decision-making process between women and physicians.

Purpose: To compare the positive predictive values (PPVs) of BI-RADS categories used to assess pure mammographic calcifications in women with and without a previous history of breast cancer (PHBC). Materials and methods: In this retrospective study, all consecutive pure mammographic calcifications (n = 320) undergoing a stereotactic biopsy between 2016 and 2018 were identified. Mammograms were evaluated in consensus by two radiologists according to BI-RADS and blinded to patient history and pathology results. Final pathologic results were used as the standard of reference. PPV of BI-RADS categories were compared between the two groups. Data were evaluated using standard statistics, Mann–Whitney U tests and Chi-square tests. Results: Two hundred sixty-eight patients (274 lesions, median age 54 years, inter-quartile range, 50–65 years) with a PHBC (n = 46) and without a PHBC (n = 222) were included. Overall PPVs were the following: BI-RADS 2, 0% (0 of 56); BI-RADS 3, 9.1% (1 of 11); BI-RADS 4a, 16.2% (6 of 37); BI-RADS 4b, 37.5% (48 of 128); BI-RADS 4c, 47.3% (18 of 38) and BI-RADS 5, 100% (4 of 4). The PPV of BI-RADS categories was similar in patients with and without a PHBC (P = .715). Calcifications were more often malignant in patients with a PHBC older than 10 years (47.3%, 9 of 19) compared to 1–2 years (25%, 1 of 4), 2–5 years (20%, 2 of 10) and 5–10 years (0%, of 13) from the first breast cancer (P = .005). Conclusion: PPV of mammographic calcifications is similar in women with or without PHBC when BI-RADS classification is strictly applied. A higher risk of malignancy was observed in patients with a PHBC longer than 10 years.

The aim of this study was to investigate the potential of a machine learning algorithm to classify breast cancer solely by the presence of soft tissue opacities in mammograms, independent of other morphological features, using a deep convolutional neural network (dCNN). Soft tissue opacities were classified based on their radiological appearance using the ACR BI-RADS atlas. We included 1744 mammograms from 438 patients to create 7242 icons by manual labeling. The icons were sorted into three categories: “no opacities” (BI-RADS 1), “probably benign opacities” (BI-RADS 2/3) and “suspicious opacities” (BI-RADS 4/5). A dCNN was trained (70% of data), validated (20%) and finally tested (10%). A sliding window approach was applied to create colored probability maps for visual impression. Diagnostic performance of the dCNN was compared to human readout by experienced radiologists on a “real-world” dataset. The accuracies of the models on the test dataset ranged between 73.8% and 89.8%. Compared to human readout, our dCNN achieved a higher specificity (100%, 95% CI: 85.4–100%; reader 1: 86.2%, 95% CI: 67.4–95.5%; reader 2: 79.3%, 95% CI: 59.7–91.3%), and the sensitivity (84.0%, 95% CI: 63.9–95.5%) was lower than that of human readers (reader 1:88.0%, 95% CI: 67.4–95.4%; reader 2:88.0%, 95% CI: 67.7–96.8%). In conclusion, a dCNN can be used for the automatic detection as well as the standardized and observer-independent classification of soft tissue opacities in mammograms independent of the presence of microcalcifications. Human decision making in accordance with the BI-RADS classification can be mimicked by artificial intelligence.

Objectives: This study aimed to evaluate the diagnostic performance of the maximum intensity projection (MIP) reformations of breast computed tomography (B-CT) images as a stand-alone method for the detection and characterization of breast imaging findings. Materials and Methods: A total of 160 women undergoing B-CT between August 2018 and December 2020 were retrospectively included; 80 patients with known breast imaging findings were matched with 80 patients without imaging findings according to age and amount of fibroglandular tissue (FGT). A total of 71 benign and 9 malignant lesions were included. Images were evaluated using 15-mm MIP in 3 planes by 2 radiologists with experience in B-CT. The presence of lesions and FGT were evaluated, using the BI-RADS classification. Interreader agreement and descriptive statistics were calculated. Results: The interreader agreement of the 2 readers for finding a lesion (benign or malignant) was 0.86 and for rating according to BI-RADS classification was 0.82. One of 9 cancers (11.1%) was missed by both readers due to dense breast tissue. BI-RADS 1 was correctly applied to 73 of 80 patients (91.3%) by reader 1 and to 74 of 80 patients (92.5%) by reader 2 without recognizable lesions. BI-RADS 2 or higher with a lesion in at least one of the breasts was correctly applied in 69 of 80 patients (86.3%) by both readers. For finding a malignant lesion, sensitivity was 88.9% (95% confidence interval [CI], 51.75%–99.72%) for both readers, and specificity was 99.3% (95% CI, 96.4%–100%) for reader 1 and 100% (95% CI, 97.20%–100.00%) for reader 2. Conclusions: Evaluation of B-CT images using the MIP reformations may help to reduce the reading time with high diagnostic performance and confidence.

Background: Legg–Calvé–Perthes (LCP) is a common orthopedic childhood disease that causes a deformity of the femoral head and to an adaptive deformity of the acetabulum. The altered joint biomechanics can result in early joint degeneration that requires total hip arthroplasty. In 2002, Ganz et al. introduced the femoral head reduction osteotomy (FHRO) as a direct joint-preserving treatment. The procedure remains one of the most challenging in hip surgery. Computer-based 3D preoperative planning and patient-specific navigation instruments have been successfully used to reduce technical complexity in other anatomies. The purpose of this study was to report the first results in the treatment of 6 patients to investigate whether our approach is feasible and safe.Methods: In this retrospective pilot study, 6 LCP patients were treated with FHRO in multiple centers between May 2017 and June 2019. Based on patient-specific 3D-models of the hips, the surgeries were simulated in a step-wise fashion. Patient-specific instruments tailored for FHRO were designed, 3D-printed and used in the surgeries for navigating the osteotomies. The results were assessed radiographically [diameter index, sphericity index, Stulberg classification, extrusion index, LCE-, Tönnis-, CCD-angle and Shenton line] and the time and costs were recorded. Radiologic values were tested for normal distribution using the Shapiro–Wilk test and for significance using Wilcoxon signed-rank test.Results: The sphericity index improved postoperatively by 20% (p = 0.028). The postoperative diameter of the femoral head differed by only 1.8% (p = 0.043) from the contralateral side and Stulberg grading improved from poor coxarthrosis outcome to good outcome (p = 0.026). All patients underwent acetabular reorientation by periacetabular osteotomy. The average time (in minutes) for preliminary analysis, computer simulation and patient-specific instrument design was 63 (±48), 156 (±64) and 105 (±68.5), respectively.Conclusion: The clinical feasibility of our approach to FHRO has been demonstrated. The results showed significant improvement compared to the preoperative situation. All operations were performed by experienced surgeons; nevertheless, three complications occurred, showing that FHRO remains one of the most complex hip surgeries even with computer assistance. However, none of the complications were directly related to the simulation or the navigation technique.