Granulomatous lobular mastitis (GLM) is a rare and chronic benign inflammatory disease of the breast. Difficulties exist in the management of GLM for many front-line surgeons and medical specialists who care for patients with inflammatory disorders of the breast. This consensus is summarized to establish evidence-based recommendations for the management of GLM. Literature was reviewed using PubMed from January 1, 1971 to July 31, 2020. Sixty-six international experienced multidisciplinary experts from 11 countries or regions were invited to review the evidence. Levels of evidence were determined using the American College of Physicians grading system, and recommendations were discussed until consensus. Experts discussed and concluded 30 recommendations on historical definitions, etiology and predisposing factors, diagnosis criteria, treatment, clinical stages, relapse and recurrence of GLM. GLM was recommended as a widely accepted definition. In addition, this consensus introduced a new clinical stages and management algorithm for GLM to provide individual treatment strategies. In conclusion, diagnosis of GLM depends on a combination of history, clinical manifestations, imaging examinations, laboratory examinations and pathology. The approach to treatment of GLM should be applied according to the different clinical stage of GLM. This evidence-based consensus would be valuable to assist front-line surgeons and medical specialists in the optimal management of GLM.

Background: Granulomatous mastitis (GM) is a rare inflammatory breast disease that may mimic the clinical characteristics and radiologic imaging findings of breast carcinoma. Considering the importance of making a correct diagnosis, careful radiologic evaluations and recognition of imaging features are necessary. Objectives: The aim of this study was to review the radiological findings and diagnostic value of the imaging in GM. Patients and Methods: This retrospective study involved a total of 29 patients who were diagnosed with GM between 2009 and 2013 and who underwent mammography (MG) and/or ultrasound (US) examination in addition to magnetic resonance imaging (MRI) before diagnosis. Results: Among 14 patients over 35 years of age who underwent MG imaging, focal asymmetric, ill-defined nodular, or diffusely increased densities were detected in nine (64.3%), two (14.3%), and one (7.1%) subjects, respectively, while there were no pathological findings in two (14.3%) patients. In the overall group of 29 patients, US showed heterogeneous hypoechoic lesions with tubular extensions in 16 (55.2%), well-demarcated heterogeneous hypoechoic lesions in eight (27.6%), parenchymal heterogeneous appearance in three (10.3%), and a heterogeneous hypoechoic lesion with irregular margins in one (3.4%), with another (3.4%) patient having normal US findings. MRI findings included lesions consistent with solitary or multiple separate or confluent abscesses with marked peripheral ring enhancement in 25 (86.2%) patients, accompanied by intensity changes suggesting edematous inflammation in the peripheral parenchyma, as well as non-mass-like heterogeneous segmental and regional contrast enhancement. Four (13.8%) patients had non-mass-like segmental and regional contrast enhancement only. A histopathological diagnosis of GM was established in all patients with biopsy. Conclusion: GM presents with a wide range of conventional radiological findings, hampering the diagnosis. In patients with inconclusive conventional findings, MRI may assist in the differential diagnosis and assessment of the extent of disease. However, a definitive diagnosis and relevant treatment require histopathological confirmation. Keywords: Granulomatous Mastitis; Breast; Mammography; Ultrasonography

The use of dynamic magnetic resonance imaging (MRI) of the breast as a complementary problem-solving tool was explored in a heterogeneous population sample. A total of 3,076 patients that underwent breast MRI examination between January 2008 and June 2012 in our center were screened retrospectively. Of these, 868 met the following inclusion criteria and were considered eligible for the study: available data on clinical signs, symptoms and on the results of mammography and ultrasound examinations in medical records; at least 1 year of follow-up; and documented pathology findings. Lesions with a stable course over a follow-up period of at least 12 months were considered benign. MRI was suggestive of a suspicious abnormality (BI-RADS 4) or highly suggestive of malignancy (BI-RADS 5) in 129 (15%) of 868 patients, leading to a biopsy examination in these cases. On the other hand, MRI findings were considered normal in 739 (85%) subjects based on normal (BI-RADS 1), benign (BI-RADS 2) or probably benign (BI-RADS 3) findings. Of the 129 patients undergoing a histopathologic examination based on MRI findings, 63 were diagnosed with cancer, and in 66, the biopsy proved to be benign. Forty of the 63 patients (40/63) with a diagnosis of malignancy and 34 of the 66 patients (34/66) with a benign diagnosis had been categorized as BI-RADS 4 with conventional methods. A total of 23 patients with BI-RADS category of 0 to 3 according to conventional methods were diagnosed as having cancer with MRI. In six of these, the family history was positive. The sensitivity, specificity, positive predictive value, and negative predictive value (NPV) of MRI for the detection of cancer were 100%, 92%, 52%, and 100%, respectively. In cases with inconclusive findings on conventional imaging studies or in patients with clinical/radiological suspicion of malignancy, MRI should be more effectively used as a problem-solving approach owing to its high sensitivity and NPV in this condition. Use of MRI as a problem-solving method in such cases may decrease rather than increase unnecessary biopsy procedures and patient anxiety.

Objectives: Breast cancer is a type of cancer caused by the uncontrolled growth of cells in the breast tissue. In a few cases, erroneous diagnosis of breast cancer by specialists and unnecessary biopsies can lead to various negative consequences. In some cases, radiologic examinations or clinical findings may raise the suspicion of breast cancer, but subsequent detailed evaluations may not confirm cancer. In addition to causing unnecessary anxiety and stress to patients, such diagnosis can also lead to unnecessary biopsy procedures, which are painful, expensive, and prone to misdiagnosis. Therefore, there is a need for the development of more accurate and reliable methods for breast cancer diagnosis.Methods: In this study, we proposed an artificial intelligence (AI)‐based method for automatically classifying breast solid mass lesions as benign vs malignant. In this study, a new breast cancer dataset (Breast‐XD) was created with 791 solid mass lesions belonging to 752 different patients aged 18 to 85 years, which were examined by experienced radiologists between 2017 and 2022.Results: Six classifiers, support vector machine (SVM), K‐nearest neighbor (K‐NN), random forest (RF), decision tree (DT), logistic regression (LR), and XGBoost, were trained on the training samples of the Breast‐XD dataset. Then, each classifier made predictions on 159 test data that it had not seen before. The highest classification result was obtained using the explainable XGBoost model (X²GAI) with an accuracy of 94.34%. An explainable structure is also implemented to build the reliability of the developed model.Conclusions: The results obtained by radiologists and the X²GAI model were compared according to the diagnosis obtained from the biopsy. It was observed that our developed model performed well in cases where experienced radiologists gave false positive results.