Search

Background: Recent artificial intelligence has exhibited great potential in breast imaging, but its value in precise risk stratification of mammography still needs further investigation. This study is to develop an artificial intelligence system (AIS) for accurate malignancy diagnosis and supportive decision-making on mammographic risk stratification. Methods: In this retrospective study, 49732 mammograms of 24866 breasts from 12815 women from two Asian clinics between August 2012 and December 2018 were included. We developed an AIS using multi-view mammograms and multi-level convolutional neural network features to diagnosis malignancy and further assess the relative strengths of AIS versus current BI-RADS categorization. We further evaluate AIS by conducting a counterbalance-designed AI-assisted study, where ten radiologists read 1302 cases with/without AIS assistance. The area under the receiver operating characteristic curve (AUC), sensitivity, specificity, accuracy, F1 score were measured. Results: The AIS yielded AUC of 0.910 to 0.995 for malignancy diagnosis in the validation and testing sets. Within BI-RADS 3–4 subgroups with pathological results, AIS can downgrade 83.1% of false-positives into benign groups, and upgrade 54.1% of false-negatives into malignant groups. Compared with BI-RADS, AIS performed better sensitivity and specificity in dense and no-calcification subgroups. AIS also can successfully assist radiologists identify 7 out of 43 malignancies initially diagnosed with BI-RADS 0 with specificity of 96.7%. In the counterbalance-designed AI-assisted study, the average AUC across 10 readers was significantly improved with AIS assistance (P = 0.001). Conclusion: AIS can identify malignancy on mammography and further serve as a supportive tool for stratifying BI-RADS categorization.

Automatic medical image segmentation plays a critical role in scientific research and medical care. Existing high-performance deep learning methods typically rely on large training datasets with high-quality manual annotations, which are difficult to obtain in many clinical applications. Here, we introduce Annotation-effIcient Deep lEarning (AIDE), an open-source framework to handle imperfect training datasets. Methodological analyses and empirical evaluations are conducted, and we demonstrate that AIDE surpasses conventional fully-supervised models by presenting better performance on open datasets possessing scarce or noisy annotations. We further test AIDE in a real-life case study for breast tumor segmentation. Three datasets containing 11,852 breast images from three medical centers are employed, and AIDE, utilizing 10% training annotations, consistently produces segmentation maps comparable to those generated by fully-supervised counterparts or provided by independent radiologists. The 10-fold enhanced efficiency in utilizing expert labels has the potential to promote a wide range of biomedical applications., Existing high-performance deep learning methods typically rely on large training datasets with high-quality manual annotations, which are difficult to obtain in many clinical applications. Here, the authors introduce an open-source framework to handle imperfect training datasets.

Objectives The aim of our study was to preoperatively predict the human epidermal growth factor receptor 2 (HER2) status of patients with breast cancer using radiomics signatures based on single-parametric and multiparametric magnetic resonance imaging (MRI). Methods Three hundred six patients with invasive ductal carcinoma of no special type (IDC-NST) were retrospectively enrolled. Quantitative imaging features were extracted from fat-suppressed T2-weighted and dynamic contrast-enhanced T1 weighted (DCE-T1) preoperative MRI. Then, three radiomics signatures based on fat-suppressed T2-weighted images, DCE-T1 images and their combination were developed using a support vector machine (SVM) to predict the HER2-positive vs HER2-negative status of patients with breast cancer. The area under the curve (AUC), accuracy, sensitivity, and specificity were calculated to assess the predictive performances of the signatures. Results Twenty-eight quantitative radiomics features, namely, 14 texture features, 4 first-order features, 9 wavelet features, and 1 shape feature, were used to construct radiomics signatures. The performance of the radiomics signatures for distinguishing HER2-positive from HER2-negative breast cancer based on fat-suppressed T2-weighted images, DCE-T1 images, and their combination had an AUC of 0.74 (95% confidence interval [CI], 0.700 to 0.770), 0.71 (0.673 to 0.738), and 0.86 (0.832 to 0.882) in the primary cohort and 0.70 (0.666 to 0.744), 0.68 (0.650 to 0.726), and 0.81 (0.776 to 0.837) in the validation cohort, respectively. Conclusion Radiomics signatures based on multiparametric MRI represent a potential and efficient alternative tool to evaluate the HER2 status in patients with breast cancer.

Breast tumor segmentation plays a crucial role in subsequent disease diagnosis, and most algorithms need interactive prior to firstly locate tumors and perform segmentation based on tumor-centric candidates. In this paper, we propose a fully convolutional network to achieve automatic segmentation of breast tumor in an end-to-end manner. Considering the diversity of shape and size for malignant tumors in the digital mammograms, we introduce multiscale image information into the fully convolutional dense network architecture to improve the segmentation precision. Multiple sampling rates of atrous convolution are concatenated to acquire different field-of-views of image features without adding additional number of parameters to avoid over fitting. Weighted loss function is also employed during training according to the proportion of the tumor pixels in the entire image, in order to weaken unbalanced classes problem. Qualitative and quantitative comparisons demonstrate that the proposed algorithm can achieve automatic tumor segmentation and has high segmentation precision for various size and shapes of tumor images without preprocessing and postprocessing.

Acute myeloid leukemia (AML) is as a highly aggressive and heterogeneous hematological malignancy. MiR-20a-5p has been reported to function as an oncogene or tumor suppressor in several tumors, but the clinical significance and regulatory mechanisms of miR-20a-5p in AML cells have not been fully understood. In this study, we found miR-20a-5p was significantly decreased in bone marrow from AML patients, compared with that in healthy controls. Moreover, decreased miR-20a-5p expression was correlated with risk status and poor survival prognosis in AML patients. Overexpression of miR-20a-5p suppressed cell proliferation, induced cell cycle G0/G1 phase arrest and apoptosis in two AML cell lines (THP-1 and U937) using CCK-8 assay and flow cytometry analysis. Moreover, miR-20a-5p overexpression attenuated tumor growth in vivo by performing tumor xenograft experiments. Luciferase reporter assay and western blot demonstrated that protein phosphatase 6 catalytic subunit (PPP6C) as a target gene of miR-20a-5p was negatively regulated by miR-20a-5p in AML cells. Furthermore, PPP6C knockdown imitated, while overexpression reversed the effects of miR-20a-5p overexpression on AML cell proliferation, cell cycle G1/S transition and apoptosis. Taken together, our findings demonstrate that miR-20a-5p/PPP6C represent a new therapeutic target for AML and a potential diagnostic marker for AML therapy.

Background The acquisition of drug resistance has been considered as a main obstacle for cancer chemotherapy. Tumor protein 53 target gene 1 (TP53TG1), a p53-induced lncRNA, plays a vital role in the progression of human cancers. However, little is known about the detailed function and molecular mechanism of TP53TG1 in cisplatin resistance of NSCLC. Methods qRT-PCR analysis was used to detect the expression of TP53TG1, miR-18a and PTEN mRNA in NSCLC tissues and cells. Western blot analysis was performed to determine the protein level of PTEN and cleaved caspase-3. Cell viability and IC50 value were measured by MTT assay. Cell apoptosis was confirmed by flow cytometry assay. Subcellular fractionation assay was used to identify the subcellular location of TP53TG1. Dual-luciferase reporter assay, RNA pull down assay and RNA immunoprecipitation assay were carried out to verify the interaction between TP53TG1 and miR-18a. Xenografts in nude mice were established to verify the effect of TP53TG1 on cisplatin sensitivity of NSCLC cells in vivo. Results TP53TG1 level was downregulated in NSCLC tissues and cell lines. Upregulated TP53TG1 enhanced cisplatin sensitivity and apoptosis of A549/DDP cells, while TP53TG1 depletion inhibited cisplatin sensitivity and apoptosis of A549 cells. TP53TG1 suppressed miR-18a expression in A549 cells. Moreover, TP53TG1-mediated enhancement effect on cisplatin sensitivity was abated following the restoration of miR-18a expression in A549/DDP cells, while si-TP53TG1-induced decrease of cisplatin sensitivity and apoptosis was counteracted by miR-18a inhibitor in A549 cells. Furthermore, TP53TG1 promoted PTEN expression via inhibiting miR-18a. Finally, TP53TG1 sensitized NSCLC cells to cisplatin in vivo. Conclusion TP53TG1 increased the sensitivity of NSCLC cells to cisplatin by modulating miR-18a/PTEN axis, elucidating a novel approach to boost the effectiveness of chemotherapy for NSCLC. Electronic supplementary material The online version of this article (10.1186/s13578-018-0221-7) contains supplementary material, which is available to authorized users.

The aim of the study was to describe the clinical, radiographic, and pathologic features of inflammatory myofibroblastic tumor (IMT) to enhance the recognition of this rare disease.The clinical, imaging, and pathologic findings were retrospectively reviewed in 54 patients with IMT lesions, which were conformed by biopsy or surgical pathology. Of 54 patients, 51 had preoperative computed tomography (CT) examination and 13 had preoperative magnetic resonance imaging records.The clinical appearances of these 54 patients had some relationship with the locations of lesions. Of 54 IMT patients, 87.0% cases (47/54) had solitary lesion. The mean long diameter of the lesions located at the sites of chest, abdomen, and pelvic regions was bigger than that of other locations (F = 3.025, P = 0.038). On plain CT images, soft tissue mass was found in all IMT lesions, except for 3 lesions that arose in the intestine tract, appearing as focal or diffuse thickening in the bowel wall. After contrast administration, all lesions were persistently enhanced; 72.7% cases (24/33) demonstrated heterogeneous enhancement with various cystic regions. Comparing the CT features with different anatomic lesions, ill-defined margin on the plain CT images and calcification were seen more frequently in the lesions of the head and neck (P = 0.010 and 0.035); however, the other radiological findings had no significant differences (all P0.05). Twelve of 51 IMT patients showed invasion into adjacent structures. On magnetic resonance imaging, 92.3% lesions (12/13) showed soft tissue masses demonstrating isointense to hypointense contrast compared with skeletal muscle on T1-weighted images and heterogeneously high signals on T2-weighted images; 85.7%(6/7) of lesions were heterogeneously enhanced with cystic changes. Immunohistochemistry showed that the percentage of positive staining for SMA, vimentin, anaplastic lymphoma kinase, CD68, CD34, CD99, B-cell lymphoma/leukemia-2, cytokeratin, Desmin, and S-100 protein were 88.9%, 87.0%, 44.4%, 59.3%, 53.7%, 29.6%, 42.6%, 28.5%, 13.0%, and 24.1%, respectively.Inflammatory myofibroblastic tumor can involve any part of the body, and the clinical and radiological appearances are various owing to different anatomic sites. An ill-defined soft tissue mass heterogeneous enhancement with or without invasion into adjacent structures on computed tomographic or magnetic resonance images and positive staining for SMA and vimentin on immunohistochemical examination could suggest the diagnosis.

In order to solve the pathological grading of hepatocellular carcinomas (HCC) which depends on biopsy or surgical pathology invasively, a quantitative analysis method based on radiomics signature was proposed for pathological grading of HCC in non-contrast magnetic resonance imaging (MRI) images. The MRI images were integrated to predict clinical outcomes using 328 radiomics features, quantifying tumour image intensity, shape and text, which are extracted from lesion by manual segmentation. Least absolute shrinkage and selection operator (LASSO) were used to select the most-predictive radiomics features for the pathological grading. A radiomics signature, a clinical model, and a combined model were built. The association between the radiomics signature and HCC grading was explored. This quantitative analysis method was validated in 170 consecutive patients (training dataset:为了解决目前肝脏肿瘤病理分级主要依靠穿刺活检、手术病理取材等侵入式方法的问题，提出了一种在非增强核磁共振图像（MRI）上进行肝脏肿瘤病理分级的定量分析方法。首先对采集到的 MRI 图像，由医生在专业软件中人工分割出病灶部位，对这些病灶部位提取高通量的 328 维图像特征，包括灰度、形状、纹理、小波等特征，利用最小绝对收缩和选择运算符（LASSO）和交叉验证方法从中挑选出对病理分级最有价值的特征，组成影像组学模型并融合临床信息实现对肿瘤高、低分化分类的定量分析。在 170 位肝脏肿瘤患者的 MRI 图像（T1 加权图像和 T2 加权图像）上进行实验，通过计算接收者操作特征（ROC）曲线下面积（AUC）来衡量模型的预测性能。结果表明，基于高通量图像特征的 LASSO 回归定量分析方法，在训练集上获得 AUC 为 0.909，在测试集上 AUC 为 0.800。挑选出来的图像特征组成的影像学标签可以对高、低分化进行自动分类，从而为医生提供了一种非侵入的辅助诊断方法，有助于预后判断和治疗方案的制定。.

Purpose The aim of our study was to evaluate the HER-2 status in breast cancer patients using mammography (MG) radiomics features. Methods A total of 306 Chinese female patients with invasive ductal carcinoma of no special type (IDC-NST) enrolled from January 2013 to July 2018 were divided into a training set (n = 244) and a testing set (n = 62). One hundred and eighty-six radiomics features were extracted from digital MG images based on the training set. The least absolute shrinkage and selection operator (LASSO) method was used to select the optimal predictive features for HER-2 status from the training set. Both support vector machine (SVM) and logistic regression models were employed based on the selected features. The area under the receiver operating characteristic (ROC) curves (AUCs) of the training set and testing set were used to evaluate the predictive performance of the models. Results Compared with the SVM model, the performance of the logistic regression model using a combination of cranial caudal (CC) and mediolateral oblique (MLO) MG views was optimal. In the training set, the sensitivity, specificity, accuracy and area under the curve (AUC) values of the logistic regression model for evaluating HER-2 status based on quantitative radiomics features were 87.29%, 58.73%, 80.00% and 0.846 (95% confidence interval (CI), 0.800-0.887), respectively, and in the testing set, the values were 73.91%, 68.75%, 77.00% and 0.787 (95% CI, 0.673-0.885), respectively. Conclusions Radiomics features could be an efficient tool for the preoperative evaluation of HER-2 status in patients with breast cancer.

The aim of the study was to investigate the value of sequential application of molybdenum target X-ray, multi-slice spiral computed tomography (MSCT) and magnetic resonance imaging (MRI) in the preoperative evaluation of breast-conserving surgeries. In total, 76 patients with indications for breast-conserving surgery due to complicated breast cancer participated in the study and were assigned to either control or observation group (n=38 per group). The patients in the control group were evaluated with two sets of random combinations of molybdenum target X-ray, MSCT or MRI with ultrasound inspection, whereas the patients in the observation group were evaluated by sequential inspection methods of molybdenum target X-ray, MSCT and MRI. A comparison of surgery outcomes, incidence of complications, rate of positive surgical margins, and recurrence and survival rates in the groups during a follow-up period of 24 months was made. Comparisons of the preoperative evaluation results for tumor number, average maximum diameter, number of lymphatic metastatic groups and number of metastatic lymph nodes in the observation group showed the numbers to be significantly higher than those in the control group (P

Objective: To establish a radiomics nomogram by integrating clinical risk factors and radiomics features extracted from digital mammography (MG) images for pre-operative prediction of axillary lymph node (ALN) metastasis in breast cancer. Methods: 216 patients with breast cancer lesions confirmed by surgical excision pathology were divided into the primary cohort (n = 144) and validation cohort (n = 72). Radiomics features were extracted from craniocaudal (CC) view of mammograms, and radiomics features selection were performed using the methods of ANOVA F-value and least absolute shrinkage and selection operator; then a radiomics signature was constructed with the method of support vector machine. Multivariate logistic regression analysis was used to establish a radiomics nomogram based on the combination of radiomics signature and clinical factors. The C-index and calibration curves were derived based on the regression analysis both in the primary and validation cohorts. Results: 95 of 216 patients were confirmed with ALN metastasis by pathology, and 52 cases were diagnosed as ALN metastasis based on MG-reported criteria. The sensitivity, specificity, accuracy and AUC (area under the receiver operating characteristic curve of MG-reported criteria were 42.7%, 90.8%, 24.1% and 0.666 (95% confidence interval: 0.591–0.741]. The radiomics nomogram, comprising progesterone receptor status, molecular subtype and radiomics signature, showed good calibration and better favorite performance for the metastatic ALN detection (AUC 0.883 and 0.863 in the primary and validation cohorts) than each independent clinical features (AUC 0.707 and 0.657 in the primary and validation cohorts) and radiomics signature (AUC 0.876 and 0.862 in the primary and validation cohorts). Conclusion: The MG-based radiomics nomogram could be used as a non-invasive and reliable tool in predicting ALN metastasis and may facilitate to assist clinicians for pre-operative decision-making. Advances in knowledge: ALN status remains among the most important breast cancer prognostic factors and is essential for making treatment decisions. However, the value of detecting metastatic ALN by MG is very limited. The studies on pre-operative ALN metastasis prediction using the method of MG-based radiomics in breast cancer are very few. Therefore, we studied whether MG-based radiomics nomogram could be used as a predictive biomarker for the detection of metastatic ALN.

Histopathological grading of breast cancer is an important tumor-related prognostic factor and plays an important role in breast cancer prognosis analysis. Nowadays, histopathological grading of breast cancer is mainly identified by pathological images and radiologists cannot differentiate the histopathological grade directly from digital mammograms. In this paper, we propose to discriminate the histopathological grades directly based on digital mammograms, which is noninvasive and convenient. End-to-end training Convolutional Neural Network (CNN) is firstly designed to extract semantic features directly from raw image data. Considering the scarce annotated mammograms data and large size of tumor region, a light and deep network with less training parameters is modified to prevent overfitting. Results demonstrate that our proposed network is superior to other CNN models and traditional classifier based on hand-crafted features.

This study was conducted in order to investigate the value of magnetic resonance imaging (MRI)-based radiomics signatures for the preoperative prediction of hepatocellular carcinoma (HCC) grade. Data from 170 patients confirmed to have HCC by surgical pathology were divided into a training group (n = 125) and a test group (n = 45). The radiomics features of tumours based on both T1-weighted imaging (WI) and T2WI were extracted by using Matrix Laboratory (MATLAB), and radiomics signatures were generated using the least absolute shrinkage and selection operator (LASSO) logistic regression model. The predicted values of pathological HCC grades using radiomics signatures, clinical factors (including age, sex, tumour size, alpha fetoprotein (AFP) level, history of hepatitis B, hepatocirrhosis, portal vein tumour thrombosis, portal hypertension and pseudocapsule) and the combined models were assessed. Radiomics signatures could successfully categorise high-grade and low-grade HCC cases (p

Additional file 1: Figure S1. PTEN expression in NSCLC was analyzed using the TCGA dataset. Red represents NSCLC tumor tissue (n = 483), and black represents normal tissues (n = 347).

Background Primitive neuroectodermal tumors (PNETs) constitute a rare type of malignant neuroectodermal tumors that have chromosomal translocations identical to Ewing’s sarcoma (ES), and the characteristics of this disease remain unclear. Purpose To describe the clinical, radiological, and pathological features of peripheral PNETs (pPNETs) to enhance their recognition. Material and Methods The clinical, imaging, and pathologic findings of 35 patients with pPNETs were retrospectively reviewed, all being confirmed by biopsy or surgical pathology. All 35 patients had preoperative computed tomography (CT) examinations; 10 patients had preoperative magnetic resonance imaging (MRI) studies. Results Of 35 pPNET patients, 54.3% had a primary tumor in soft tissue, the others in bone. On plain CT images, 33 lesions demonstrated heterogeneous hypodense masses with multiple lamellar lower density, and with osteolytic destruction if the tumor originated in bone. Calcification was only found in five lesions arising in soft tissue. All lesions enhanced heterogeneously with varying areas of cystic changes, and all lesions in bone and 52.6% of lesions in soft tissue showed ill-defined margins after contrast administration. On MRI, these tumors appeared in conjunction with osteolytic bone destruction and irregular soft tissue masses iso- to hypointense to skeletal muscle on T1-weighted images and showed heterogeneously high intensity on T2-weighted images. All lesions enhanced heterogeneously with cystic changes. Homer–Wright rosettes were observed in 15 lesions, and 97.1% lesions were positive for CD99 in histopathological results. Conclusion pPNETs can involve any part of the body, and a large, ill-defined, aggressive soft tissue mass and heterogeneous enhancement with or without osteolytic bone destruction on CT or MR images could suggest the diagnosis.

To study the imaging and clinical features of breast sclerosing adenosis (SA), and to enhance the recognition of this disease, as well as to help the clinic to give a correct diagnosis. Imaging findings were retrospectively reviewed in 47 women with SA lesions confirmed by pathology (including 39 cases of mammography, 40 cases of ultrasound [US], and 34 cases magnetic resonance imaging [MRI]). Of 47 patients confirmed with SA, 18 cases were pure SA, and 29 cases coexist with other proliferative lesions and malignancies; the maximum diameter of SA lesions was 0.5 to 3.5 cm with an average of 1.6 cm. On the mammogram of 39 SA cases, the percentage of architectural distortion, calcifications, mass/nodular, asymmetric density, and mass combining with calcifications were 30.8%, 23.1%, 17.9%, 12.8%, and 7.7%, respectively; and 3 cases had no abnormal findings. On the sonogram (excluding 5 normal finding cases), the majority of lesions showed regular shaped (57.1%), well defined margined (60.0%), heterogenous low echoed (71.4%) nodulus. 85.3% lesions showed high signal on T2-weighted images, and all lesions were enhanced markedly, including 82.4% lesions appearing mass-like enhancement (17 star-shaped enhanced masses included); and the percentage of the time-signal intensity curve in type 1, type 2, and type 3 were 52.9%, 41.2%, and 5.9%, respectively. If the category breast imaging-reporting and data system ≥4b was considered to be a suspicious malignant lesion, the misdiagnostic rates of mammography, US, and MRI would be 17.9%, 17.5%, and 35.3%, respectively. The SA lesions are small and can occur with other diseases histologically. The majority of SA lesions showed distortion or calcifications on mammograms, low echo-level nodules with heterogenous echo on US and mass-like lesion with or without star shape on enhanced MRI.

To describe the clinical, CT and pathological findings of paediatric peripheral primitive neuroectodermal tumours (pPNETs) to enhance the recognition of these rare tumours.The clinical, CT and pathological findings of 18 paediatric patients with pPNETs confirmed by biopsy or surgical pathology were retrospectively reviewed.The age of these 18 paediatric patients with pPNETs ranged from 4 months to 15 years, with a mean age of 7.7 years. The lesions of these 18 paediatric patients with pPNETs were located in the head and neck (n = 4), chest (n = 2), abdomen and pelvic cavity (n = 6), spine (n = 3), ilium (n = 2) and femur (n = 1). Immunohistochemical examination revealed Homer-Wright rosettes in seven lesions, and 94.4% of lesions showed consistent positive staining for CD99. On plain CT images, the majority of pPNETs showed lesions that were ill-defined (72.2%), irregularly shaped (83.3%), heterogeneous (66.7%) or hypodense masses (94.4%), and together with osteolytic bone destruction when the lesion originated in the bone. Calcifications were found in three lesions. After contrast administration, all soft-tissue masses were persistently enhanced heterogeneously with various cystic or necrotic regions, and 71.4% of them had linear enhancement. 94.4% of soft-tissue masses showed a moderate degree of enhancement. Seven cases had lymph node metastasis at diagnosis.Paediatric pPNET can involve any part of the body, and a large, ill-defined, aggressive soft-tissue mass and moderate heterogeneous enhancement with varying cystic regions and linear enhancement, with or without osteolytic bone destruction, on CT images could suggest the diagnosis.Primitive neuroectodermal tumours constitute a rare type of malignant neuroectodermal tumours that have chromosomal translocations identical to Ewing's sarcoma, and reports about radiological characteristics of this disease in children are insufficient. This study has described the clinical features and CT and pathological findings in 18 paediatric patients diagnosed with pPNETs in different locations, as a way to enhance the recognition of these tumours and help to differentiate from other types of paediatric malignant bone and soft-tissue tumours.

To discuss the best noise index combined with ASIR weighting selection in low-dose chest scanning based on BMI.200 patients collected from May to December 2014 underwent non-contrast chest CT examinations, they were randomly assigned into standard dose group (Group A, NI15 combined with 30% ASIR) and low-dose groups (Group B, NI25 combined with 40% ASIR, Group C, NI30 combined with 50% ASIR, Group D, NI35 combined with 60% ASIR), 50 cases in each group; the patients were assigned into three groups based on BMI (kg/m2): BMI18.5; 18.5≤BMI≤25; BMI25. Signal-to-nosie ratio (SNR), contrast-to noise ratio (CNR), CT dose index volume (CTDIvol), dose-length product (DLP), effective dose (ED) and subjective scoring between the standard and low-dose groups were compared and analyzed statistically. Differences of SNR, CNR, CTDIvol, DLP and ED among groups were determined with ANOVA analysis and the consistency of diagnosis with Kappa test.SNR, CTDIvol, DLP and ED reduced with the increase of nosie index, the differences among the groups were statistically significant (P0.05). Kappa value of the two reviewers were 0.888. Subjective scoring of four groups were all above 3 points in BMI18.5 kg/m2 group; subjective scoring of ABC groups were all above 3 points in 18.5 kg/m2≤BMI≤25 kg/m2 group and subjective scoring of AB groups were all above 3 points in BMI25 kg/m2 group.NI35 combined with 60% ASIR in BMI18.5 kg/m2 group; NI30 combined with 50% ASIR in 18.5 kg/m2≤BMI≤25 kg/m2 group; NI25 combined with 40% ASIR in 18.5 kg/m2≤BMI≤25 kg/m2 group were the best parameters combination which both can significantly reduce the radiation dose and ensure the image quality.

Purpose To study the radiological appearance and pathological features of breast phyllodes tumors (PTs), and to enhance the recognition of the tumor. Materials and methods Clinical and imaging findings were retrospectively reviewed in 24 women with PTs confirmed by surgical pathology. All of the 24 patients had preoperative MRI and sonography, and 10 had preoperative mammography. Results The histologic findings were benign, borderline and malignant PTs in 16.7% (4/24), 45.8% (11/24) and 37.5% (9/24) of cases, respectively. The tumor size ( p = 0.001), irregular shape on sonographic imaging ( p = 0.039), internal non-enhanced septations ( p = 0.009), silt-like changes in enhanced images ( p = 0.006) and signal changes from T2-weighted to enhanced images on MRI ( p = 0.001) correlated significantly with the histologic grade; the BI-RADS category of the MRI could reflect the PT's histologic grade with a correlation coefficient of 0.440 ( p = 0.031). If the category BI-RADS ≥4a was considered to be a suspicious malignant lesion, the diagnostic accuracy of mammography, US and MRI would be 70% (7/10), 62.5% (15/24) and 95.8% (23/24), respectively. Conclusion The tumor size and several US and MRI findings can be used to help preoperatively determine the histologic grade of breast PTs. When a patient presents with a progressively enlarging, painless breast mass, MRI should be recommended first.

Objective The aim of our study was to assess the value of dynamic contrast-enhanced magnetic resonance imaging (DMRI) in predicting early response to neoadjuvant chemotherapy (NAC) in patients with locally advanced breast cancer (LABC) and to assess the accuracy of DMRI in evaluating residual disease after NAC.