Intraobserver interpretation of breast ultrasonography following the BI-RADS classification

Calas, Maria Júlia Gregório; Almeida, R. M. V. R.; Gutfilen, Bianca; Pereira, Wagner Coelho de Albuquerque

doi:10.1016/j.ejrad.2009.04.015

Cited by 46 publications

(45 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Nevertheless, we can envisage the potential benefits to an automated classification scheme. The first one is that radiologists evaluation always present interobserver and intraobserver variations that could result in misdiagnosis [39], while an automated algorithm produces the same result for the same images and, therefore, it could be a useful tool to reduce observers disagreement. Another point is that, once an automated algorithm of an adequate performance is built, improvements can be added for analyzing different views of the same lesion, including 3D aspects, or even combination of different image techniques and/or clinical information.…”

Section: Discussionmentioning

confidence: 99%

Assessing the performance of morphological parameters in distinguishing breast tumors on ultrasound images

Alvarenga

Infantosi

Pereira

et al. 2010

Medical Engineering & Physics

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 99%

Assessing the performance of morphological parameters in distinguishing breast tumors on ultrasound images

Alvarenga

Infantosi

Pereira

et al. 2010

Medical Engineering & Physics

View full text Add to dashboard Cite

“…In BI-RADS categorization, a score of 3 is defined as probably benign and of 4 as probably malignant (11)(12)(13). The fact that both the malignancy rate and positive predictive value of BI-RADS 4 lesions were significantly higher as compared to BI-RADS 3 lesions is a manifestation of the expected situation.…”

Section: Discussionmentioning

confidence: 92%

“…By this means, attempts on identification of suspicious lesions at higher rates and minimizing false positive or false negative rates are being made. The radiologic classification Breast Imaging Reporting and Data System (BI-RADS) is the most commonly used classification in that regard (11)(12)(13).…”

Section: Introductionmentioning

confidence: 99%

A Retrospective Comparative Study of Image-Guided Excisional Biopsy in High-Risk Non-Palpable Breast Lesions: Predictive Factors for Malignancy

et al. 2015

View full text Add to dashboard Cite

Objective: The use of mammography (MM) in breast cancer screening programs has been increasing in recent years. Thus, increasing the number of detected nonpalpable breast cancer patients, through early diagnosis and treatment also increased survival rates. In our study, we wanted to share the factors about imagingguided exicional biopsies for non-palpable breast lesions in postoperative proven breast carcinoma patients. Materials and Methods:The surgical data were reviewed for 83 patients with non-palpabl high-risk breast lesions undergoing imaging-guided surgery in our department between January, 2006 and May, 2011. Histopathologic results and age, ultrasound(US) results, MM image results, BI-RADS categorization, localization of lesion(quadrant) were assessed and factors for predicting malignity were detected.Results: Median age was 52 (age range 32-80 years). 29 (34,9%) of patients were malign in histopathologic results. In four patient, re-excision performed because of positive surgical margins. Axillary examination results were normal in 24 (82,7%) of malignant patients. In MM examination; microcalcifications and nodular opasity were diagnosed in 74,6% of patients before surgery. There were no differance about malignity in these groups after surgery (p:0,428). 59% and 32,7% of patients were BI-RADS 4 and 3, respectively. Postoperative diagnosed malignancies in BI-RADS 4 group were significantly higher than BI-RADS 3 group (p:<0,001). Conclusion:In our study; we concluded that, preoperative BI-RADS categorization (US and MM) is correlated with histopathologic findings after surgery and imaging-guided breast surgery is effective for diagnosis of early-stage breast carcinoma.

show abstract

“…Hence, the diagnosis depends on their expertise and training. This subjectivity can lead to large variations of inter-/intraobservers image interpretation, and, consequently, to distinct clinical conduct recommendations [2], [3].…”

Section: Introductionmentioning

confidence: 99%

Feature selection and classifier performance in computer-aided diagnosis for breast ultrasound

Gómez

Rodríguez

Pereira

et al. 2013

2013 10th International Conference and Expo on Emerging Technologies for a Smarter World (CEWIT)

View full text Add to dashboard Cite

We propose a feature selection method for classifying breast ultrasound (BUS) images based on mutual information technique and statistical tests. The BUS dataset consisted of 641 BUS images (228 carcinomas and 413 benign lesions) and every image was segmented by a technique based on Watershed transform. Thereafter, 22 morphological features were computed from segmented lesions and the resultant feature space was ranked by mutual information approach, where the first feature presents the largest discrimination power between benign and malignant classes. Next, feature subsets were built by adding iteratively the first m ranked attributes until all of the 22 features were considered. The .632+ bootstrap method estimated the discrimination performance of each feature subset in terms of the area under the ROC curve (AUC), by using the Fisher discriminant analysis (FLDA) as classifier. The results pointed out that the AUC values were 0.952 and 0.953 for the reduced (with seven features) and complete sets (with 22 features), respectively. Hence, dimensionality reduction was reached while maintaining the classification performance.

show abstract

Intraobserver interpretation of breast ultrasonography following the BI-RADS classification

Cited by 46 publications

References 17 publications

Assessing the performance of morphological parameters in distinguishing breast tumors on ultrasound images

Assessing the performance of morphological parameters in distinguishing breast tumors on ultrasound images

A Retrospective Comparative Study of Image-Guided Excisional Biopsy in High-Risk Non-Palpable Breast Lesions: Predictive Factors for Malignancy

Feature selection and classifier performance in computer-aided diagnosis for breast ultrasound

Contact Info

Product

Resources

About