Screening for Breast Cancer

In many fields, including bioinformatics, ensemble methods have been often employed to perform prediction tasks such as classification and regression due to their ability to improve the accuracy and robustness of machine learning models. Given that the most prevalent cancer and the primary cause of death for women is breast cancer, researchers have started using ensemble approaches to advance their studies in this area. Effectively, ensemble methods can be used to develop clinical decision support systems that can help healthcare providers make more accurate judgements.

In the present study, we construct and evaluate bagging and boosting ensemble methods for the binary classification of breast cancer screening images from the CBIS-DDSM dataset. To build the bagging ensembles, a hybrid architecture consisting of three feature extractors (Inception V3, MobileNet V2, DenseNet 201) and four classifiers (K-nearest neighbors, Multilayer perceptron, Support vector machine, Decision trees) was chosen. As for the boosting ensembles, the method consists of the same three feature extractors with a decision trees-based classifier and the four boosting methods (AdaBoost, GBM, XGboost, LightGBM).

The evaluation of both ensemble methods over the mammography dataset was made using four performance metrics (accuracy, sensitivity, F1-score, and recall), as well as the Skott–Knott statistical test and the Borda count voting system to rank all the possible model combinations. Results proved that bagging and boosting ensembles generally outperformed both their base learners and single models, and that the best performing ensemble overall was Gradient boosting with DenseNet 201 as feature extractor and 200 trees which scored an accuracy of 85.50 %.

The purpose of this research was to use hybrid learning based ensembles to maximize the potent performance of numerous models. It effectively illustrated the prospective potential of using ML approaches for the binary classification of mammography data used for breast cancer screening.

Supplemental screening with breast MRI is recommended annually for patients who have greater than 20% lifetime risk for breast cancer. While there is robust data regarding features of mammographic screen-detected breast cancers, there is limited data regarding MRI-screen-detected cancers.

Screening breast MRIs performed between August 1, 2016 and July 30, 2022 identified 50 screen-detected breast cancers in 47 patients. Clinical and imaging features of all eligible cancers were recorded.

During the study period, 50 MRI-screen detected cancers were identified in 47 patients. The majority of MRI-screen detected cancers (32/50, 64%) were invasive. Pathology revealed ductal carcinoma in situ (DCIS) in 36% (18/50), invasive ductal carcinoma (IDC) in 52% (26/50), invasive lobular carcinoma in 10% (5/50), and angiosarcoma in 2% (1/50). The majority of patients (43/47, 91%) were stage 0 or 1 at diagnosis and there were no breast cancer-related deaths during the follow-up periods. Cancers presented as masses in 50% (25/50), nonmass enhancement in 48% (25/50), and a focus in 2% (1/50). DCIS was more likely to present as nonmass enhancement (94.4%, 17/18), whereas invasive cancers were more likely to present as masses (75%, 24/32) (P < .001). All cancers that were stage 2 at diagnosis were detected either on a baseline exam or more than 4 years since the prior MRI exam.

MRI screen-detected breast cancers were most often invasive cancers. Cancers detected by MRI screening had an excellent prognosis in our study population. Invasive cancers most commonly presented as a mass.

Several breast reduction techniques have been introduced, and the reliability of these techniques has been demonstrated in clinical practice. However, it is still controversial how patients should be evaluated radiologically both preoperative and postoperative. This study aims to compare the radiological findings seen following reduction mammoplasty with two different techniques (inferior pedicle and superomedial pedicle), in connection with the surgical steps.

Medical records of 141 patients and a total of 278 breasts who underwent breast reduction with the diagnosis of macromastia were retrospectively analyzed. Demographic and operative data such as age, type of pedicle, preoperative and postoperative nipple-areola complex (NAC) position, and NAC transfer distance were recorded. Radiological evaluation was performed by two radiologists experienced in breast imaging by reinterpreting preoperative and postoperative mammography images.

The rate of postoperative structural distortion (p < 0.001), thickened areola (p = 0.011), and retroareolar fibrotic band (p < 0.001) were observed to be significantly higher in the superomedial group. The risk of fat necrosis increases as the NAC transfer distance increases and a value of >9.5 cm in the NAC transfer distance can be considered as the cutoff value in terms of fat necrosis development, especially in those using superomedial pedicle technique.

Surgical technique-specific benign radiological changes occur following reduction mammoplasty. However, these changes do not significantly affect the Breast imaging, reporting, and data system category. The localization of fat necrosis differs depending on the surgical technique, and the risk of fat necrosis increases as the NAC transfer distance increases, especially in those who have undergone superomedial pedicle breast reduction surgery.

To evaluate the influence of menstrual cycle timing on quantitative background parenchymal enhancement and to assess an optimal timing of breast MRI in premenopausal women.

A total of 197 premenopausal women were enrolled, 120 of which were in the malignant group and 77 in the benign group. Two radiologists depicted the regions of interest (ROI) of the three consecutive biggest slices of glandular tissue in the unaffected side and calculated the ratio (=[SI_post - SI_pre]/SI_pre) in ROI from the precontrast and early phase to assess BPE quantitatively. Association of BPE with menstrual cycle timing was compared in three categories. The relationships between BPE and age /body mass index (BMI) were also explored.

We found that the BPE ratio presented lower in patients with the follicular phase (day1-14) compared to the luteal phase (day15-30) in the benign group (P = .036). Also, the BPE ratio presented significantly lower in the proliferative phase (day5-14) than the menstrual phase (day1-4) and the secretory phase(day15-30) in the benign group (P = .006). While the BPE ratio was not significantly different among the respective weeks (1-4) of the menstrual cycle in the benign group (P > .05). In the malignant group, the BPE ratio did not significantly differ between/among any menstrual cycle phase or week (all P > .05).

It seems more suitable for Asian women whose lesions need to follow up or are suspected of malignant to undergo breast MRI within the 1st to 14th day of the menstrual cycle, especially on the 5th to 14th day.

Imaging of breast cancer is the backbone of breast cancer screening, diagnosis, preoperative/treatment assessment and follow-up. The main modalities are mammography, ultrasound and magnetic resonance imaging, each with its own advantages and disadvantages. New emerging technologies have also enabled each modality to improve on their weaknesses. Imaging-guided biopsies have allowed for accurate diagnosis of breast cancer, with low complication rates. The purpose of this article is to review the common modalities for breast cancer imaging in current practice with emphasis on the strengths and potential weaknesses, discuss the selection of the best imaging modality for the specific clinical question or patient population, and explore new technologies / future directions of breast cancer imaging.