The Experts below are selected from a list of 1056384 Experts worldwide ranked by ideXlab platform

Andreas Boss - One of the best experts on this subject based on the ideXlab platform.

  • Classification of Mammographic Breast Microcalcifications Using a Deep Convolutional Neural Network: A BI-RADS-Based Approach.
    Investigative radiology, 2020
    Co-Authors: Claudio Schönenberger, Alexander Ciritsis, Magda Marcon, Cristina Rossi, Patryk Hejduk, Andreas Boss
    Abstract:

    The goal of this retrospective cohort study was to investigate the potential of a deep convolutional neural network (dCNN) to accurately classify microcalcifications in mammograms with the aim of obtaining a standardized observer-independent microcalcification classification system based on the Breast Imaging Reporting and Data System (BI-RADS) catalog. MATERIALS AND METHODS: Over 56,000 images of 268 mammograms from 94 patients were labeled to 3 classes according to the BI-RADS standard: "no microcalcifications" (BI-RADS 1), "probably benign microcalcifications" (BI-RADS 2/3), and "suspicious microcalcifications" (BI-RADS 4/5). Using the preprocessed images, a dCNN was trained and validated, generating 3 types of models: BI-RADS 4 cohort, BI-RADS 5 cohort, and BI-RADS 4 + 5 cohort. For the final validation of the trained dCNN models, a test data set consisting of 141 images of 51 mammograms from 26 patients labeled according to the corresponding BI-RADS classification from the radiological reports was applied. The performances of the dCNN models were evaluated, classifying each of the mammograms and computing the accuracy in comparison to the classification from the radiological reports. For visualization, probability maps of the classification were generated. RESULTS: The accuracy on the validation set after 130 epochs was 99.5% for the BI-RADS 4 cohort, 99.6% for the BI-RADS 5 cohort, and 98.1% for the BI-RADS 4 + 5 cohort. Confusion matrices of the "real-world" test data set for the 3 cohorts were generated where the radiological reports served as ground truth. The resulting accuracy was 39.0% for the BI-RADS 4 cohort, 80.9% for BI-RADS 5 cohort, and 76.6% for BI-RADS 4 + 5 cohort. The probability maps exhibited excellent image quality with correct classification of microcalcification distribution. CONCLUSIONS: The dCNNs can be trained to successfully classify microcalcifications on mammograms according to the BI-RADS classification system in order to act as a standardized quality control tool providing the expertise of a team of radiologists.

  • Automatic classification of ultrasound breast lesions using a deep convolutional neural network mimicking human decision-making
    European Radiology, 2019
    Co-Authors: Alexander Ciritsis, Magda Marcon, Matthias Eberhard, Anton S. Becker, Cristina Rossi, Andreas Boss
    Abstract:

    ObjectivesTo evaluate a deep convolutional neural network (dCNN) for detection, highlighting, and classification of ultrasound (US) breast lesions mimicking human decision-making according to the Breast Imaging Reporting and Data System (BI-RADS).Methods and materialsOne thousand nineteen breast ultrasound images from 582 patients (age 56.3 ± 11.5 years) were linked to the corresponding radiological report. Lesions were categorized into the following classes: no tissue, normal breast tissue, BI-RADS 2 (cysts, lymph nodes), BI-RADS 3 (non-cystic mass), and BI-RADS 4–5 (suspicious). To test the accuracy of the dCNN, one internal dataset (101 images) and one external test dataset (43 images) were evaluated by the dCNN and two independent readers. Radiological reports, histopathological results, and follow-up examinations served as reference. The performances of the dCNN and the humans were quantified in terms of classification accuracies and receiver operating characteristic (ROC) curves.ResultsIn the internal test dataset, the classification accuracy of the dCNN differentiating BI-RADS 2 from BI-RADS 3–5 lesions was 87.1% (external 93.0%) compared with that of human readers with 79.2 ± 1.9% (external 95.3 ± 2.3%). For the classification of BI-RADS 2–3 versus BI-RADS 4–5, the dCNN reached a classification accuracy of 93.1% (external 95.3%), whereas the classification accuracy of humans yielded 91.6 ± 5.4% (external 94.1 ± 1.2%). The AUC on the internal dataset was 83.8 (external 96.7) for the dCNN and 84.6 ± 2.3 (external 90.9 ± 2.9) for the humans.ConclusiondCNNs may be used to mimic human decision-making in the evaluation of single US images of breast lesion according to the BI-RADS catalog. The technique reaches high accuracies and may serve for standardization of highly observer-dependent US assessment.Key Points• Deep convolutional neural networks could be used to classify US breast lesions.• The implemented dCNN with its sliding window approach reaches high accuracies in the classification of US breast lesions.• Deep convolutional neural networks may serve for standardization in US BI-RADS classification.

Jay A. Baker - One of the best experts on this subject based on the ideXlab platform.

  • Interobserver Variability Between Breast Imagers Using the Fifth Edition of the BI-RADS MRI Lexicon.
    AJR. American journal of roentgenology, 2015
    Co-Authors: Lars J. Grimm, Andy L. Anderson, Jay A. Baker, Karen S. Johnson, Ruth Walsh, Sora C. Yoon, Sujata V. Ghate
    Abstract:

    OBJECTIVE. The purpose of this study was to assess the interobserver variability of users of the MRI lexicon in the fifth edition of the BI-RADS atlas. MATERIALS AND METHODS. Three breast imaging specialists reviewed 280 routine clinical breast MRI findings reported as BI-RADS category 3. Lesions reported as BI-RADS 3 were chosen because variability in the use of BI-RADS descriptors may influence which lesions are classified as probably benign. Each blinded reader reviewed every study and recorded breast features (background parenchymal enhancement) and lesion features (lesion morphology, mass shape, mass margin, mass internal enhancement, nonmass enhancement distribution, nonmass enhancement internal enhancement, enhancement kinetics) according to the fifth edition of the BI-RADS lexicon and provided a final BI-RADS assessment. Interobserver variability was calculated for each breast and lesion feature and for the final BI-RADS assessment. RESULTS. Interobserver variability for background parenchymal enh...

  • using the bi rads lexicon in a restrictive form of double reading as a strategy for minimizing screening mammography recall rates
    American Journal of Roentgenology, 2012
    Co-Authors: Sujata V. Ghate, Jay A. Baker, Karen S. Johnson, Ruth Walsh, Connie Kim, Mary Scott Soo
    Abstract:

    OBJECTIVE. The purpose of this article is to determine the potential reduction in screening recall rates by strictly following standardized BI-RADS lexicon for lesions seen on screening mammography. MATERIALS AND METHODS. Of 3084 consecutive mammograms performed at our screening facilities, 345 women with 437 lesions were recalled for additional imaging and constituted our study population. Three radiologists retrospectively classified lesions using the standard BI-RADS lexicon and assigned each to one of four groups: group A, the finding met criteria for recall by the BI-RADS lexicon; group B, the finding did not meet strict BI-RADS criteria for recall but was sufficiently indeterminate to warrant recall by the majority of the study panel; group C, the finding was classifiable by the BI-RADS lexicon but was not recalled because it was benign or stable; and group D, the questioned finding was not considered an abnormality by our study panel. Recall rates and the cancer detection rate were determined. The ...

  • BI-RADS for sonography: positive and negative predictive values of sonographic features.
    AJR. American journal of roentgenology, 2005
    Co-Authors: Andrea S. Hong, Eric L. Rosen, Mary Scott Soo, Jay A. Baker
    Abstract:

    OBJECTIVE. The purpose of this study was to assess the positive predictive value (PPV) and negative predictive value (NPV) of features described in the new sonographic BI-RADS lexicon for evaluating solid masses with known histologic diagnoses.MATERIALS AND METHODS. Sonograms of 403 solid lesions were analyzed by one of three dedicated breast radiologists. Each lesion was described using features from the sonographic BI-RADS lexicon. Lesion description and biopsy results were correlated. PPV and NPV were calculated.RESULTS. Histologic results showed that 141 (35%) of 403 masses were malignant. Sonographic BI-RADS descriptors showing high predictive value for malignancy include spiculated margin (86%, 19/22), irregular shape (62%, 102/164), and nonparallel orientation (69%, 75/109). Sonographic BI-RADS descriptors highly predictive of benign lesions include circumscribed margin (90%, 160/178), parallel orientation (78%, 228/294), and oval shape (84%, 200/237). For the sonographic BI-RADS features of mass m...

  • breast imaging reporting and data system standardized mammography lexicon observer variability in lesion description
    American Journal of Roentgenology, 1996
    Co-Authors: Jay A. Baker, P J Kornguth, Carey E Floyd
    Abstract:

    The American College of Radiology has recommended the Breast Imaging Reporting and Data System (BI-RADS) as a standardized scheme for describing mammographic lesions. The objective of this study was to measure inter- and intraobserver variabilities of radiologists' descriptions of mammographic lesions with the BI-RADS standardized lexicon.Sixty mammographic studies with abnormal findings were independently evaluated by five radiologists. Readers described each lesion by selecting a single term from the BI-RADS lexicon for each of eight morphologic categories: calcification distribution, number, and description; mass margin, shape, and density; associated findings; and special cases. Additionally, each reader assessed the significance of each lesion on a five-point scale. One observer read each case twice. Inter- and intraobserver variabilities for each description and interpretation category of the BI-RADS lexicon were determined with Cohen's kappa statistic. Radiologists' specific use of calcification de...

Tsai Wang Chang - One of the best experts on this subject based on the ideXlab platform.

  • Prognostic and Predictive Values of BI-RADS Classification in Breast Cancer Patients
    Annals of Oncology, 2012
    Co-Authors: Yueh-hsiung Kuo, Lili Cheng, Tsai Wang Chang
    Abstract:

    ABSTRACT Objective The goal of this study is to determine the prognostic and predictive values of the Breast Imaging Reporting and Data System (BI-RADS) classification in breast cancer patients. Patients and methods 1045 patients with breast cancer were disgnosed between January 1, 1999, and December 31, 2007, and 512 (48.9%) of them were classified as BI-RADS 5. Overall survival and disease-free survival were estimated with the Kaplan-Meier method and compared across the two groups (BI-RADS 5 versus BI-RADS 0-4) using the log-rank test. Univariate and multivariate analyses were used to identify the prognostic factors. Results The median follow-up time was 87.8 months. Laplan-Meier analysis showed a significant difference between the two subgroups in five-year overall survival (p  Conclusion The BI-RADS classification is a reliable prognostic and predictive factor. Taiwanese breast cancer patients with BI-RADS 5 mammographic finding showed a higher relapse rate than patients with BI-RADS 0-4 mammographic finding. Disclosure All authors have declared no conflicts of interest.

  • Clinical impact of BI-RADS classification in Taiwanese breast cancer patients: BI-RADS 5 versus BI-RADS 0-4.
    European journal of radiology, 2011
    Co-Authors: Yao Lung Kuo, Lili Cheng, Tsai Wang Chang
    Abstract:

    Abstract Objective The aim of this study was to analyze and determine the prognostic value of the Breast Imaging Reporting and Data System (BI-RADS) classification in Taiwanese patients with breast cancer. Patients and methods Nine hundred ninety-eight patients with breast cancer were diagnosed between January 1, 1999, and August 31, 2005, and 491 (49%) of them were classified as BI-RADS 5. Overall survival and disease-free survival were estimated with the Kaplan–Meier method and compared across the two groups (BI-RADS 5 versus BI-RADS 0–4) using the log-rank test. Univariate and multivariate analyses were used to identify the prognostic factors. Results The median follow-up time was 81.8 months. Kaplan–Meier analysis showed a significant difference between the two subgroups in five-year overall survival ( P =0.001) and five-year disease-free survival ( P Conclusion The BI-RADS classification is a reliable prognostic and predictive factor. Patients with BI-RADS 5 breast cancer showed a worse pattern of relapse than that of BI-RADS 0–4 breast cancer patients.

Andrew Evans - One of the best experts on this subject based on the ideXlab platform.

Alexander Ciritsis - One of the best experts on this subject based on the ideXlab platform.

  • Classification of Mammographic Breast Microcalcifications Using a Deep Convolutional Neural Network: A BI-RADS-Based Approach.
    Investigative radiology, 2020
    Co-Authors: Claudio Schönenberger, Alexander Ciritsis, Magda Marcon, Cristina Rossi, Patryk Hejduk, Andreas Boss
    Abstract:

    The goal of this retrospective cohort study was to investigate the potential of a deep convolutional neural network (dCNN) to accurately classify microcalcifications in mammograms with the aim of obtaining a standardized observer-independent microcalcification classification system based on the Breast Imaging Reporting and Data System (BI-RADS) catalog. MATERIALS AND METHODS: Over 56,000 images of 268 mammograms from 94 patients were labeled to 3 classes according to the BI-RADS standard: "no microcalcifications" (BI-RADS 1), "probably benign microcalcifications" (BI-RADS 2/3), and "suspicious microcalcifications" (BI-RADS 4/5). Using the preprocessed images, a dCNN was trained and validated, generating 3 types of models: BI-RADS 4 cohort, BI-RADS 5 cohort, and BI-RADS 4 + 5 cohort. For the final validation of the trained dCNN models, a test data set consisting of 141 images of 51 mammograms from 26 patients labeled according to the corresponding BI-RADS classification from the radiological reports was applied. The performances of the dCNN models were evaluated, classifying each of the mammograms and computing the accuracy in comparison to the classification from the radiological reports. For visualization, probability maps of the classification were generated. RESULTS: The accuracy on the validation set after 130 epochs was 99.5% for the BI-RADS 4 cohort, 99.6% for the BI-RADS 5 cohort, and 98.1% for the BI-RADS 4 + 5 cohort. Confusion matrices of the "real-world" test data set for the 3 cohorts were generated where the radiological reports served as ground truth. The resulting accuracy was 39.0% for the BI-RADS 4 cohort, 80.9% for BI-RADS 5 cohort, and 76.6% for BI-RADS 4 + 5 cohort. The probability maps exhibited excellent image quality with correct classification of microcalcification distribution. CONCLUSIONS: The dCNNs can be trained to successfully classify microcalcifications on mammograms according to the BI-RADS classification system in order to act as a standardized quality control tool providing the expertise of a team of radiologists.

  • Automatic classification of ultrasound breast lesions using a deep convolutional neural network mimicking human decision-making
    European Radiology, 2019
    Co-Authors: Alexander Ciritsis, Magda Marcon, Matthias Eberhard, Anton S. Becker, Cristina Rossi, Andreas Boss
    Abstract:

    ObjectivesTo evaluate a deep convolutional neural network (dCNN) for detection, highlighting, and classification of ultrasound (US) breast lesions mimicking human decision-making according to the Breast Imaging Reporting and Data System (BI-RADS).Methods and materialsOne thousand nineteen breast ultrasound images from 582 patients (age 56.3 ± 11.5 years) were linked to the corresponding radiological report. Lesions were categorized into the following classes: no tissue, normal breast tissue, BI-RADS 2 (cysts, lymph nodes), BI-RADS 3 (non-cystic mass), and BI-RADS 4–5 (suspicious). To test the accuracy of the dCNN, one internal dataset (101 images) and one external test dataset (43 images) were evaluated by the dCNN and two independent readers. Radiological reports, histopathological results, and follow-up examinations served as reference. The performances of the dCNN and the humans were quantified in terms of classification accuracies and receiver operating characteristic (ROC) curves.ResultsIn the internal test dataset, the classification accuracy of the dCNN differentiating BI-RADS 2 from BI-RADS 3–5 lesions was 87.1% (external 93.0%) compared with that of human readers with 79.2 ± 1.9% (external 95.3 ± 2.3%). For the classification of BI-RADS 2–3 versus BI-RADS 4–5, the dCNN reached a classification accuracy of 93.1% (external 95.3%), whereas the classification accuracy of humans yielded 91.6 ± 5.4% (external 94.1 ± 1.2%). The AUC on the internal dataset was 83.8 (external 96.7) for the dCNN and 84.6 ± 2.3 (external 90.9 ± 2.9) for the humans.ConclusiondCNNs may be used to mimic human decision-making in the evaluation of single US images of breast lesion according to the BI-RADS catalog. The technique reaches high accuracies and may serve for standardization of highly observer-dependent US assessment.Key Points• Deep convolutional neural networks could be used to classify US breast lesions.• The implemented dCNN with its sliding window approach reaches high accuracies in the classification of US breast lesions.• Deep convolutional neural networks may serve for standardization in US BI-RADS classification.