Search

Abstract This study aimed to assess the diagnostic performance of deep convolutional neural networks (DCNNs) in classifying breast microcalcification in screening mammograms. To this end, 1579 mammographic images were collected retrospectively from patients exhibiting suspicious microcalcification in screening mammograms between July 2007 and December 2019. Five pre-trained DCNN models and an ensemble model were used to classify the microcalcifications as either malignant or benign. Approximately one million images from the ImageNet database had been used to train the five DCNN models. Herein, 1121 mammographic images were used for individual model fine-tuning, 198 for validation, and 260 for testing. Gradient-weighted class activation mapping (Grad-CAM) was used to confirm the validity of the DCNN models in highlighting the microcalcification regions most critical for determining the final class. The ensemble model yielded the best AUC (0.856). The DenseNet-201 model achieved the best sensitivity (82.47%) and negative predictive value (NPV; 86.92%). The ResNet-101 model yielded the best accuracy (81.54%), specificity (91.41%), and positive predictive value (PPV; 81.82%). The high PPV and specificity achieved by the ResNet-101 model, in particular, demonstrated the model effectiveness in microcalcification diagnosis, which, in turn, may considerably help reduce unnecessary biopsies.

Purpose To evaluate the CT features of incidental breast lesions on chest CT and to suggest useful criteria for referral to a specialized breast unit. Materials and Methods Between May 2009 and April 2014, enhanced chest CT examination reports containing the key word ‘breast’ were reviewed retrospectively. Patients who had incidental breast lesion and were referred to a specialized breast unit and then underwent pathological confirmation or follow-up over a 1-year period were included. Finally, 86 patients (all female, mean age, 48.9 ± 12.6 years) were enrolled. Two radiologists evaluated lesion characteristics, including size, shape, margins, and enhancement. The correlations between the CT features and pathologies were evaluated, and the diagnostic accuracy of CT features in various combinations was assessed. Results Among the CT features, irregular shape, non-circumscribed margin, and high contrast enhancement were different between malignant and benign lesions (p < 0.05). The combination of non-circumscribed margin and high contrast enhancement had the highest accuracy (97.7%). Conclusion Reliable CT features for incidental malignant breast masses are irregular shape, non-circumscribed margin, and high contrast enhancement. The combination of non-circumscribed margin and high contrast enhancement could help distinguish incidental malignant breast lesions and indicate referral to a specialized breast unit.

Shear-wave elastography (SWE) is a recently developed ultrasound technique that can visualize and measure tissue elasticity. In breast ultrasonography, SWE has been shown to be useful for differentiating benign breast lesions from malignant breast lesions, and it has been suggested that SWE enhances the diagnostic performance of ultrasonography, potentially improving the specificity of conventional ultrasonography using the Breast Imaging Reporting and Data System criteria. More recently, not only has SWE been proven useful for the diagnosis of breast cancer, but has also been shown to provide valuable information that can be used as a preoperative predictor of the prognosis or response to chemotherapy.

Purpose: The goal of this study was to assess the clinicopathologic and ultrasonographic features of thyroid nodules with nondiagnostic results on repeat ultrasonography (US)-guided fineneedle aspiration biopsy (FNAB) according to size and the number of suspicious findings and to determine the proper management of nodules with consecutive nondiagnostic results. Methods: This retrospective study included 297 nodules with nondiagnostic results on repeat FNAB that were evaluated by US over the course of at least 12 months of follow-up, a follow-up biopsy, or an operation. We compared clinical and US variables between benign and malignant nodules in thyroid nodules with repeat nondiagnostic results. Results: The comparison of benign and malignant nodules with repeat nondiagnostic results revealed that age, marked hypoechogenicity, irregular or microlobulated margins, microcalcifications, and nonparallel shape were significantly associated with malignancy. Multivariate logistic regression analysis in malignant nodules revealed that microcalcifications and irregular or microlobulated margins were independently associated with malignancy. Among them, only irregular or microlobulated margins were independently significant as a predictor of malignancy in repeatedly nondiagnostic nodules measuring >10 mm. Using receiver operating characteristic analysis, the best cutoff value for the “number of suspicious findings” between benign and malignant nodules was three in nodules of all sizes, three in nodules measuring ≤10 mm, and two in nodules measuring >10 mm. Conclusion: Irregular or microlobulated margins may be the most frequent US features in repeatedly nondiagnostic nodules >10 mm. The presence of “two or more suspicious findings” can be used as the cutoff for distinguishing benign and malignant nodules.

Purpose: To evaluate the concordance of estrogen receptor, progesterone receptor, and human epidermal growth factor receptor 2 (HER2) statuses between ultrasound (US)-guided 14-gauge core needle biopsy (CNB) and surgery and to analyze whether the clinicopathological and imaging features including those from mammography and ultrasonography can predict the concordance in breast cancer patients. Methods: The concordance of receptor status between CNB and surgery was assessed for 55 breast cancers in 55 women who underwent CNB before treatment. The clinicopathological and imaging features and the concordance rates were compared between the non-neoadjuvant chemotherapy (non-NAC) group and the NAC group according to the initial treatment. The concordance rates were analyzed according to the clinicopathological and imaging features, by using the chi-square or Fisher exact test and McNemar test for the categorical and the independent t-test for continuous variables. Results: Among 55 women, 22 women (40%) were part of the non-NAC group and 33 women (60%) were part of the NAC group. The concordance rates were 0.86-1.00 in the non-NAC group and 0.76-0.88 in the NAC group. In all three receptors, the difference in the concordance rate between the two groups was not significant. In the NAC group, the absence of axillary lymph node metastasis (1.00, P=0.02) and visibility of cancer on mammography (0.93, P=0.04) showed the higher concordance of the HER2 status. Conclusion: Concordance of the receptor status between surgery and US-guided 14-gauge CNB was feasible in breast cancer patients. The absence of axillary lymph node metastasis after NAC and the visibility of cancer on mammography prior to NAC may be helpful for predicting the concordance of HER2 in breast cancer patients.

To investigate the significance of accompanying NME in invasive ductal carcinoma (IDC) on preoperative MR imaging and assess the factors affecting the significance.Between January 2015 and February 2016, 163 consecutive patients with IDC who underwent preoperative MR imaging and subsequent surgery were enrolled and reviewed. Index cancer mass size and total extent with accompanying NME on MR images was measured and compared with pathologic size. Positive NME was defined as pathological result of IDC or DCIS. To identify affecting factors associated with frequency of accompanying NME on MR and positive pathologic result, clinicopathologic features were compared between breast cancers with NME and without NME, and between breast cancers with positive NME and negative NME using the Student t-test or Chi-square test.Of the 163 invasive breast cancers, 123(75.5%) cancers presented as only mass feature and 40(24.5%) cancers had accompanying NME around the index mass. Of the 40 accompanying NME, 22 (55%) had positive pathologic results and 18 (45%) had negative results. The HER2 positive status was significantly associated with positive pathologic results of accompanying NME (P = .016).Accompanying NME on preoperative MR imaging showed malignant pathologic results in 55%. The HER2 positive IDC was more frequently accompanied by malignant NME.

To investigate whether the diagnostic performance of lesion-to-fat elasticity ratio (Eratio) was affected by the location of the reference fat.For 257 breast masses in 250 women who underwent shear-wave elastography before biopsy or surgery, multiple Eratios were measured with a fixed region-of-interest (ROI) in the mass along with multiple ROIs over the surrounding fat in different locations. Logistic regression analysis was used to determine that Eratio was independently associated with malignancy adjusted for the location of fat ROI (depth, laterality, and distance from lesion or skin). Mean (Emean) and maximum (Emax) elasticity values of fat were divided into four groups according to their interquartile ranges. Diagnostic performance of each group was evaluated using the area under the ROC curve (AUC). False diagnoses of Eratio were reviewed for ROIs on areas showing artifactual high or low stiffness and analyzed by logistic regression analysis to determine variables (associated palpable abnormality, lesion size, the vertical distance from fat ROI to skin, and elasticity values of lesion or fat) independently associated with false results.Eratio was independently associated with malignancy adjusted for the location of fat ROI (P

To assess the malignancy rates of thyroid nodules repeatedly classified as Bethesda category III on fine needle aspiration (FNA), and to suggest management guidelines for these lesions.This is a retrospective study that included 395 thyroid nodules categorized as Bethesda III undergone either surgery or ultrasound (US) follow-up. There were 67 nodules classified a second time as Bethesda category III on repeat FNA. We compared malignancy rates, clinicopathologic and ultrasonographic characteristics between direct surgery and repeat FNA groups and between the initial and repeat Bethesda category III groups, each. And in the repeat Bethesda III group, clinicopathologic and US variables were compared between benign and malignant nodules.Incidence of concurrent cancer, underlying thyroiditis and positive BRAF mutation were significantly higher in 142 nodules with direct surgery than 243 nodules with repeat FNA (p < 0.05). Of the 395 nodules with Bethesda category III cytology on initial FNA, the malignancy rate was 59.5%. In 67 nodules with repeat Bethesda III classification, however, the malignancy rate was 73.1% (p < 0.05). However, none of the variables were significantly different between the initial Bethesda category III group and the repeat Bethesda category III group (p > 0.05). In the repeat Bethesda category III group, solid consistency, irregular/microlobulated margins, nonparallel shape, and number of suspicious findings or "suspicious malignant" US assessments were associated with a high malignancy rate (p < 0.05). On multivariate logistic regression analysis, the factor associated with malignancy in the repeat Bethesda category III group was irregular/microlobulated margin (odds ratio = 15.576; 95% CI, 2.097-115.6804, p = 0.007) with a sensitivity, specificity, positive and negative predictive values, and accuracy of 81.6%, 83.3%, 93.0%, 62.5% and 82.1%, respectively.Thyroid nodules with repeated Bethesda category III classification and irregular/microlobulated margins on US are at increased risk of malignancy, and operative management should be considered as opposed to repeat FNA.

Purpose: To evaluate the potential of prospective electrocardiography (ECG)- gated 64-slice multidetector computed tomography (MDCT) for evaluation of myocardial enhancement, infarct size, and stent patency after percutaneous coronary intervention (PCI) with stenting in patients with myocardial infarction. Materials and Methods: Seventeen patients who were admitted with acute myocardial infarction were examined with prospective ECG-gated 64-slice cardiac MDCT and magnetic resonance (MR) imaging after reperfusion using PCI with stenting. Cardiac MDCT was performed with two different phases: arterial and delayed phases. We evaluated the stent patency on the arterial phase, and nonviable myocardium on the delayed phase of computed tomography (CT) image, and they were compared with the results from the delayed MR images. Results: Total mean radiation dose was 7.7 ± 0.5 mSv on the two phases of CT images. All patients except one showed good patency of the stent at the culprit lesion on the arterial phase CT images. All patients had hyperenhanced area on the delayed phase CT images, which correlated well with those on the delayed phase MR images, with a mean difference of 1.6% (20 ± 10% vs. 22 ± 10%, r = 0.935, p = 0.10). Delayed MR images had a better contrast-to-noise ratio (CNR) than delayed CT images (27.1 ± 17.8% vs. 4.3 ± 2.1%, p < 0.001). Conclusion: Prospective ECG-gated 64-slice MDCT provides the potential to evaluate myocardial viability on delayed phase as well as for stent patency on arterial phase with an acceptable radiation dose after PCI with stenting in patients with myocardial infarction. [ABSTRACT FROM AUTHOR]