Pros and cons for breast cancer screening with tomosynthesis - a review of the literature

Detection of breast cancer in digital breast tomosynthesis with vision transformers

Digital Breast Tomosynthesis (DBT) has revolutionized more traditional breast imaging through its three-dimensional (3D) visualization capability that significantly enhances lesion discernibility, reduces tissue overlap, and improves diagnostic precision as compared to conventional two-dimensional (2D) mammography. In this study, we propose an advanced Computer-Aided Detection (CAD) system that harnesses the power of vision transformers to augment DBT's diagnostic efficiency. This scheme uses a neural network to glean attributes from the 2D slices of DBT followed by post-processing that considers features from neighboring slices to categorize the entire 3D scan. By leveraging a transfer learning technique, we trained and validated our CAD framework on a unique dataset consisting of 3,831 DBT scans and subsequently tested it on 685 scans. Of the architectures tested, the Swin Transformer outperformed the ResNet101 and vanilla Vision Transformer. It achieved an impressive AUC score of 0.934 ± 0.026 at a resolution of 384 × 384. Increasing the image resolution from 224 to 384 not only maintained vital image attributes but also led to a marked improvement in performance (p-value = 0.0003). The Mean Teacher algorithm, a semi-supervised method using both labeled and unlabeled DBT slices, showed no significant improvement over the supervised approach. Comprehensive analyses across different lesion types, sizes, and patient ages revealed consistent performance. The integration of attention mechanisms yielded a visual narrative of the model's decision-making process that highlighted the prioritized regions during assessments. These findings should significantly propel the methodologies employed in DBT image analysis by setting a new benchmark for breast cancer diagnostic precision.

[Digital 3D tomosynthesis in the diagnosis and screening of breast cancer]

Az emlőrák mortalitása és morbiditása a mammográfiás szűrőprogram bevezetésével szignifikánsan csökkent. A teljes gyógyulás szempontjából rendkívül nagy jelentősége van a korai felismerésnek. A 2011-ben az FDA által is elfogadott digitális 3D tomoszintézis a digitális mammográfiát (full-field digital mammography – FFDM) kiegészítő modalitás, mely jól alkalmazható az emlőbetegségek diagnosztikájában és az emlőrák szűrésében. A digitális 3D tomoszintézis alapelve: a vizsgálat során egy adott köríven mozgó röntgencső az emlőről – kis sugárdózissal – rövid idő alatt 10–15 átfedő digitális képet készít. Az így nyert adathalmazból számítógépes feldolgozással vékony szeletvastagságú rétegképek (3D tomoszintézis), valamint rekonstruált, a hagyományos mammográfiás képhez hasonló, ún. szintetikus 2D képek is készülnek. Az előnyök mellett (nagyobb rákfelismerési arány, a kóros képletek, szerkezeti disztorzió, aszimmetrikus denzitás pontosabb megítélése, a felesleges mintavételek számának csökkenése, a szűrésben kisebb visszahívási arány) a hátrányokkal kapcsolatos dilemmák (például sugárterhelés, nagyobb tárhelyigény) ismerete is fontos. Orv Hetil. 2024; 165(37): 1443–1451.

Does Breast-Conserving Surgery with Radiotherapy have a Better Survival than Mastectomy? A Meta-Analysis of More than 1,500,000 Patients

BACKGROUND

There have been conflicting studies reporting on survival advantages between breast-conserving surgery with radiotherapy (BCS) in comparison with mastectomy. Our aim was to compare the efficacy of BCS and mastectomy in terms of overall survival (OS) comparing all past published studies.

METHODS

We performed a comprehensive review of literature through October 2021 in PubMed, Scopus, and EMBASE. The studies included were randomized controlled trials (RCTs) and cohorts that compare BCS versus mastectomy. We excluded studies that included male sex, stage 0, distant metastasis at diagnosis, bilateral synchronous cancer, neoadjuvant radiation/chemotherapy, and articles with incomplete data. We performed a meta-analysis following the random-effect model with the inverse variance method.

RESULTS

From 18,997 publications, a total of 30 studies were included in the final analysis: 6 studies were randomized trials, and 24 were retrospective cohorts. A total of 1,802,128 patients with a follow-up ranging from 4 to 20 years were included, and 1,075,563 and 744,565 underwent BCS and mastectomy, respectively. Among the population, BCS is associated with improved OS compared with mastectomy [relative risk (RR) 0.64, 95% confidence interval (CI) 0.55-0.74]. This effect was similar when analysis was performed in cohorts and multi-institutional databases (RR 0.57, 95% CI 0.49-0.67). Furthermore, the benefit of BCS was stronger in patients who had less than 10 years of follow-up (RR 0.54, 95% CI 0.46-0.64).

CONCLUSIONS

Patients who underwent BCS had better OS compared with mastectomy. Such results depicting survival advantage, especially using such a large sample of patients, may need to be included in the shared surgical decision making when discussing breast cancer treatment with patients.