Diagnostic Values of Breast Imaging Reporting and Data System and ultrasound Elastography in Benign and Malignant Breast Tumor

2016 ◽  
Vol 13 (10) ◽  
pp. 6509-6513
Author(s):  
Xin-Hua Lu
Keyword(s):  
Breast Cancer ◽  
Roc Curve ◽  
Predictive Value ◽  
Breast Tumor ◽  
Breast Imaging ◽  
Data System ◽  
Ultrasound Elastography ◽  
Malignant Breast Tumor ◽  
Diagnostic Values ◽  
Malignant Breast

Objective: To evaluate the diagnostic values of Breast Imaging Reporting and Data System (BI-RADS), ultrasound elastography (UE) and the combination in differentiating benign and malignant breast tumor. Methods: The BI-RADS and UE image features of 248 breast cancer patients (a total of 260 lesions) proved by surgery and pathology from February 2013 to March 2015 were retrospectively analyzed. With the pathologic results as the gold standard, the sensitivity, specificity, positive and negative predictive values, and accuracy were calculated for BI-RADS, UE and the combination. On the basis of the sensitivity and specificity, they were analyzed by receiver operating characteristic (ROC) curve. Results: In all 260 lesions, 71 lesions were benign and 189 were malignant according to UE diagnosis; 50 lesions were benign and 210 were malignant proved by BI-RADS; 55 lesions were benign and 205 were malignant diagnosed by the combination. The sensitivity (86.09%), specificity (61.64%), positive predictive value (85.19%), negative predictive value (63.38%), and accuracy (79.23%) of ultrasound elastography were all less than that of BI-RADS (98.39%, 64.38%, 88.85%, 87.62%, 94.00%) and the combination (99.47%, 73.97%, 92.31%, 90.73%, 98.18%). The areas under the ROC curve for UE, BI-RADS and the combination were respectively 0.746[95%CI(0.673–0.818)], 0.814[95%CI(0.744–0.884)] and 0.867[95%CI(0.805–0.929)]. Conclusion: Ultrasonic BI-RADS can be the first choice for diagnosing breast cancer, with UE as the auxiliary method. The combined application can further improve the diagnosis rate of benign and malignant breast tumor.

Logistic Regression and Artificial Neural Network: A Comparative Study in Diagnosing Breast Cancer

2021 ◽  
pp. 6330-6334
Author(s):  
W. Abdul Hameed ◽  
Anuradha D. ◽  
Kaspar S.
Keyword(s):  
Breast Cancer ◽  
Neural Network ◽  
Artificial Neural Network ◽  
Logistic Regression ◽  
Breast Tumor ◽  
Diagnostic Performance ◽  
Malignant Breast Tumor ◽  
Malignant Breast ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

Breast tumor is a common problem in gynecology. A reliable test for preoperative discrimination between benign and malignant breast tumor is highly helpful for clinicians in culling the malignant cells through felicitous treatment for patients. This paper is carried out to generate and estimate both logistic regression technique and Artificial Neural Network (ANN) technique to predict the malignancy of breast tumor, utilizing Wisconsin Diagnosis Breast Cancer Database (WDBC). Our aim in this Paper is: (i) to compare the diagnostic performance of both methods in distinguishing between malignant and benign patterns, (ii) to truncate the number of benign cases sent for biopsy utilizing the best model as an auxiliary implement, and (iii) to authenticate the capability of each model to recognize incipient cases as an expert system.

scholarly journals Sex Steroid Hormones in Serum and Tissue of Benign and Malignant Breast Tumor Patients

2000 ◽  
Vol 16 (3-4) ◽  
pp. 151-157 ◽  
Author(s):  
Essam A. Mady ◽  
Ezz El-Din H. Ramadan ◽  
Alaa A. Ossman
Keyword(s):  
Breast Cancer ◽  
Postmenopausal Women ◽  
Steroid Hormones ◽  
Breast Tumor ◽  
Tumor Tissue ◽  
Breast Tumors ◽  
Sex Steroid ◽  
Malignant Breast Tumor ◽  
Malignant Breast ◽  
Benign Breast Tumors

The ability of breast tumors to synthesize sex steroid hormones is well recognized and their local production is thought to play a role in breast cancer development and growth. The aim of this study was to estimate local intra-tumoral and circulating levels of Estrone (E1), Estrone Sulfate (E1S), Estradiol (E2), Estriol (E3), and Testosterone (T) in 33 pre- and postmenopausal women with primary breast cancer in comparison to 12 pre- and postmenopausal women with benign breast tumors. The mean levels of the studied sex hormones were higher in serum and tumor tissue of breast cancer women than those with benign breast tumors apart from Testosterone which showed a significant decrease in pre- and postmenopausal women with breast cancer (P< 0.001 for follicular phase,P< 0.001 for luteal phase, andP< 0.001 for postmenopausal). The levels of the five hormones were significantly higher intra-tumoral than in serum of both benign and malignant breast tumor women with E1S as the predominant estrogen. There was only a positive significant correlation between serum and tumor tissue levels of E1(rs= 0.52,P< 0.05 for follicular;rs= 0.63,P< 0.05 for luteal andrs= 0.58,P< 0.05 for postmenopausal) and a significant correlation between serum and tumor tissue of T (rs= 0.64,P< 0.05 for follicular;rs= -0.51,P< 0.05 for luteal andrs= -0.81,P< 0.04 for postmenopausal).

scholarly journals The Usefulness of Spectral Mammography in Surgical Planning of Breast Cancer Treatment—Analysis of 999 Patients with Primary Operable Breast Cancer

2021 ◽  
Vol 28 (4) ◽  
pp. 2548-2559
Author(s):  
Andrzej Lorek ◽  
Katarzyna Steinhof-Radwańska ◽  
Anna Barczyk-Gutkowska ◽  
Wojciech Zarębski ◽  
Piotr Paleń ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Predictive Value ◽  
Breast Imaging ◽  
Incidence Rates ◽  
Diagnostic Sensitivity ◽  
Breast Cancer Surgery ◽  
Imaging Method ◽  
Treatment Change ◽  
Contrast Enhanced ◽  
General Number

Contrast-enhanced spectral mammography (CESM) is a promising, digital breast imaging method for planning surgeries. The study aimed at comparing digital mammography (MG) with CESM as predictive factors in visualizing multifocal-multicentric cancers (MFMCC) before determining the surgery extent. We analyzed 999 patients after breast cancer surgery to compare MG and CESM in terms of detecting MFMCC. Moreover, these procedures were assessed for their conformity with postoperative histopathology (HP), calculating their sensitivity and specificity. The question was which histopathological types of breast cancer were more frequently characterized by multifocality–multicentrality in comparable techniques as regards the general number of HP-identified cancers. The analysis involved the frequency of post-CESM changes in the extent of planned surgeries. In the present study, MG revealed 48 (4.80%) while CESM 170 (17.02%) MFMCC lesions, subsequently confirmed in HP. MG had MFMCC detecting sensitivity of 38.51%, specificity 99.01%, PPV (positive predictive value) 85.71%, and NPV (negative predictive value) 84.52%. The respective values for CESM were 87.63%, 94.90%, 80.57% and 96.95%. Moreover, no statistically significant differences were found between lobular and NST cancers (27.78% vs. 21.24%) regarding MFMCC. A treatment change was required by 20.00% of the patients from breast-conserving to mastectomy, upon visualizing MFMCC in CESM. In conclusion, mammography offers insufficient diagnostic sensitivity for detecting additional cancer foci. The high diagnostic sensitivity of CESM effectively assesses breast cancer multifocality/multicentrality and significantly changes the extent of planned surgeries. The multifocality/multicentrality concerned carcinoma, lobular and invasive carcinoma of no special type (NST) cancers with similar incidence rates, which requires further confirmation.

Developing and validating deep learning-based heterogeneous model to improve diagnostic performance of ultrasound elastography for axillary lymph node metastasis of early breast cancer.

2021 ◽  
Vol 39 (15_suppl) ◽  
pp. e12583-e12583
Author(s):  
Jian Li ◽  
Cai Nian ◽  
Xie Ze-Ming ◽  
Zhou Jingwen ◽  
Huang Kemin
Keyword(s):  
Breast Cancer ◽  
Deep Learning ◽  
Lymph Node ◽  
Early Breast Cancer ◽  
Predictive Value ◽  
Axillary Lymph Node ◽  
Diagnostic Performance ◽  
Ultrasound Elastography ◽  
Axillary Lymph ◽  
Heterogeneous Model

e12583 Background: To improve the performance of ultrasound (US) for diagnosing metastatic axillary lymph node (ALN), machine learning was used to reveal the inherently medical hints from ultrasonic images and assist pre-treatment evaluation of ALN for patients with early breast cancer. Methods: A total of 214 eligible patients with 220 breast lesions, from whom 220 target ALNs of ipsilateral axillae underwent ultrasound elastography (UE), were prospectively recruited. Based on feature extraction and fusion of B-mode and shear wave elastography (SWE) images of 140 target ALNs using radiomics and deep learning, with reference to the axillary pathological evaluation from training cohort, a proposed deep learning-based heterogeneous model (DLHM) was established and then validated by a collection of B-mode and SWE images of 80 target ALNs from testing cohort. Performance was compared between UE based on radiological criteria and DLHM in terms of areas under the receiver operating characteristics curve (AUC), sensitivity, specificity, accuracy, negative predictive value, and positive predictive value for diagnosing ALN metastasis. Results: DLHM achieved an excellent performance for both training and validation cohorts. In the prospectively testing cohort, DLHM demonstrated the best diagnostic performance with AUC of 0.911(95% confidence interval [CI]: 0.826, 0.963) in identifying metastatic ALN, which significantly outperformed UE in terms of AUC (0.707, 95% CI: 0.595, 0.804, P<0.001). Conclusions: DLHM provides an effective, accurate and non-invasive preoperative method for assisting the diagnosis of ALN metastasis in patients with early breast cancer.[Table: see text]

scholarly journals A case of giant cell tumor of the breast, clinically suspected as malignant breast tumor

2019 ◽  
Vol 5 (1) ◽  
Author(s):  
Mitsuo Terada ◽  
Naomi Gondo ◽  
Masataka Sawaki ◽  
Masaya Hattori ◽  
Akiyo Yoshimura ◽  
...  
Keyword(s):  
Giant Cell Tumor ◽  
Giant Cell ◽  
Breast Tumor ◽  
Cell Tumor ◽  
Malignant Breast Tumor ◽  
Malignant Breast

scholarly journals A Benign and Malignant Breast Tumor Classification Method via Efficiently Combining Texture and Morphological Features on Ultrasound Images

2020 ◽  
Vol 2020 ◽  
pp. 1-12
Author(s):  
Mengwan Wei ◽  
Yongzhao Du ◽  
Xiuming Wu ◽  
Qichen Su ◽  
Jianqing Zhu ◽  
...  
Keyword(s):  
Breast Tumor ◽  
Texture Features ◽  
Morphological Features ◽  
High Dimensional ◽  
Svm Classifier ◽  
Ultrasound Images ◽  
Malignant Breast Tumor ◽  
Malignant Breast ◽  
Low Dimensional

The classification of benign and malignant based on ultrasound images is of great value because breast cancer is an enormous threat to women’s health worldwide. Although both texture and morphological features are crucial representations of ultrasound breast tumor images, their straightforward combination brings little effect for improving the classification of benign and malignant since high-dimensional texture features are too aggressive so that drown out the effect of low-dimensional morphological features. For that, an efficient texture and morphological feature combing method is proposed to improve the classification of benign and malignant. Firstly, both texture (i.e., local binary patterns (LBP), histogram of oriented gradients (HOG), and gray-level co-occurrence matrixes (GLCM)) and morphological (i.e., shape complexities) features of breast ultrasound images are extracted. Secondly, a support vector machine (SVM) classifier working on texture features is trained, and a naive Bayes (NB) classifier acting on morphological features is designed, in order to exert the discriminative power of texture features and morphological features, respectively. Thirdly, the classification scores of the two classifiers (i.e., SVM and NB) are weighted fused to obtain the final classification result. The low-dimensional nonparameterized NB classifier is effectively control the parameter complexity of the entire classification system combine with the high-dimensional parametric SVM classifier. Consequently, texture and morphological features are efficiently combined. Comprehensive experimental analyses are presented, and the proposed method obtains a 91.11% accuracy, a 94.34% sensitivity, and an 86.49% specificity, which outperforms many related benign and malignant breast tumor classification methods.

scholarly journals Cytokeratin on Frozen Sections of Sentinel Node May Spare Breast Cancer Patients Secondary Axillary Surgery

2012 ◽  
Vol 2012 ◽  
pp. 1-5 ◽  
Author(s):  
Elisabeth Specht Stovgaard ◽  
Tove Filtenborg Tvedskov ◽  
Anne Vibeke Lænkholm ◽  
Eva Balslev
Keyword(s):  
Breast Cancer ◽  
Sentinel Node ◽  
Predictive Value ◽  
Frozen Section ◽  
Axillary Lymph ◽  
Breast Cancer Patients ◽  
Frozen Sections ◽  
Paraffin Sections ◽  
Significant Difference ◽  
Diagnostic Values

Background. The feasibility and accuracy of immunohistochemistry (IHC) on frozen sections, when assessing sentinel node (SN) status intraoperatively in breast cancer, is a matter of continuing discussion. In this study, we compared a center using IHC on frozen section with a center not using this method with focus on intraoperative diagnostic values. Material and Methods. Results from 336 patients from the centre using IHC intraoperatively were compared with 343 patients from the center not using IHC on frozen section. Final evaluation on paraffin sections with haematoxylin-eosin (HE) staining supplemented with cytokeratin staining was used as gold standard. Results. Significantly more SN with isolated tumor cells (ITCs) and micrometastases (MICs) were found intraoperatively when using IHC on frozen sections. There was no significant difference in the number of macrometastases (MACs) found intraoperatively. IHC increased the sensitivity, the negative predictive value, and the accuracy of the intraoperative evaluation of SN without decreasing the specificity and positive predictive value of SN evaluation. Conclusions. IHC on frozen section leads to the detection of more ITC and MIC intraoperatively. As axillary lymph node dissection (ALND) is performed routinely in some countries when ITC and MIC are found in the SN, IHC on frozen section provides valuable information that can lead to fewer secondary ALNDs.

Sign in / Sign up

Export Citation Format

Share Document