Interpretation of patterns of enhancement on contrast-enhanced spectral mammography: An approach to a standardized scheme
This study included 104 malignant lesions versus 74 benign. Diagnostic accuracy parameters for CESM were sensitivity 98% (102/104) and specificity 76% (56/74). Irregular margin intense enhancement focus (1/8) was diagnosed malignant, (7/8) while regular margin faint enhancing foci were benign.Irregular shape, spiculated margin and heterogeneous internal enhancement descriptors of mass lesion descriptors conformed to malignancy (PPV 92.5% of the former and 88.7% of the latter, p value ≤ 0.001).Asymmetry with segmental distribution, (17/27) (70.8%) heterogeneous and clumped internal enhancement patterns were indicative for malignancy in non mass enhancement (PPV
ConclusionTuberculous mastitis is extremely rare variant of extrapulmonary tuberculosis. However, it should be kept in the mind of physicians and pathologists while approaching a breast mass, especially in endemic area.
ConclusionOur results demonstrate performance inconsistency across the data sets and models, indicating that the high performance of deep learning models on one data set cannot be readily transferred to unseen external data sets, and these models need further assessment and validation before being applied in clinical practice.
Publication date: Available online 14 February 2020Source: Journal of the American College of RadiologyAuthor(s): Laila R. Cochon, Catherine S. Giess, Ramin KhorasaniAbstractObjectiveCompare diagnostic performance of screening full-field digital mammography (FFDM), a hybrid FFDM and digital breast tomosynthesis (DBT) environment, and DBT only.Materials and MethodsThis institutional review board–approved, retrospective study consisted of all patients undergoing screening mammography at an urban academic medical center and outpatient imaging facility between January 1, 2011, and December 31, 2017. We used the electroni...
Performance of recently developed deep learning models for image classification surpasses that of radiologists. However, there are questions about model performance consistency and generalization in unseen external data. The purpose of this study is to determine if the high performance of deep learning on mammograms can be transferred to external data with a different data distribution.
This study aimed to evaluate the added value of digital breast tomosynthesis (DBT) to BI-RADS classification in categorization of indeterminate breast lesions after digital mammography (DM) as an initial approach.Methods and resultsWe prospectively evaluated 296 women with BI-RADS indeterminate breast lesions (BI-RADS 0, 3, and 4) by DM between January 2018 and October 2019. All patients underwent DBT. Two radiologists evaluated lesions and assigned a BI-RADS category to each lesion according to BI-RADS lexicon 2013 classification using DM, DBT, and combined DM and DBT. The results were compared in terms of main radiologic...
In many European countries, radiologists double read mammograms, followed by...Read more on AuntMinnie.comRelated Reading: New European guidelines advise biennial screening at 45 AI can reduce mammography screening's workload What's the sweet spot for batch reading mammograms? Double-read DBT + digital mammo drops recall rates Breast surgeons could be option for reading mammograms
Publication date: Available online 11 February 2020Source: Preventive MedicineAuthor(s): Brian T. Cheng
The U.S. Food and Drug Administration (FDA) on February 11 announced that it...Read more on AuntMinnie.comRelated Reading: Raleigh Radiology faces lawsuit over mammo services Mammo services halted at NC facility FDA posts warning for Texas mammography center FDA reinstates NC mammography facility's accreditation FDA posts alert for NC mammography facility
Breast MRI scans found six cases of breast cancer in high-risk women that had...Read more on AuntMinnie.comRelated Reading: AI boosts radiologists' mammography performance CEDM excels as presurgical diagnosis tool in large study Study supports interval MRI for likely benign findings PET/MRI tops MRI in breast lesion comparisons MRI finds breast cancer early in women with family history
This study shows that the panel of immunostains is useful in confirming the site of origin of a metastatic Krukenberg tumor when one is known and has limited diagnostic value for diagnosing metastases of unknown origin.