Merge CAD Benefits

Supporting Research

Improving Confidence in MRI

CADstream continues to be validated by a growing body of research. The following are selected peer-reviewed publications and abstracts using CADstream. Peer-reviewed papers on breast MRI can be found in Confirma's bibliography.

Click on a title below to view the full text:

	Computer-Aided Detection (CAD) for Breast MRI: Evaluation of Efficacy at 3.0 Carla Meeuwis, MD et al

	MRI Detected Suspicious Breast Findings: Comparison of Kinetic Features Measured by Computer Aided Evaluation in Benign and Malignant Lesions (Lilian Wang, MD, et al., Presented at RSNA 2007) The purpose of this study was to compare three distinct computer aided evaluation kinetic features of suspicious breast MRI lesions to determine which could best predict benign or malignant outcomes.

	Automated Breast MR Tumor Volume Measurements for Prediction of Outcome in Breast Cancer Patients on Neoadjuvant Chemotherapy (Nola Hylton, PhD, et al., Presented at RSNA 2006) The purpose of this study was to determine if automated measurements of breast MRI tumor volumes using the CADstream package are predictive of length of recurrence free survival (LRFS).

	Analysis of a Computer Aided Evaluation Program for Breast MRI in Discriminating Benign from Malignant Lesions (W. DeMartini MD, et al., Presented at RSNA 2005) The purpose of this study was to compare the accuracy of breast magnetic resonance imaging interpretation without and with computer aided evaluation in discriminating benign from malignant lesions.

	Do Automated Methods of Contrast Kinetic Analysis (CADstream) Improve Interobserver Variability in Breast MRI Contrast Kinetic Analysis: A Comparison Study between Automated and Manual ROI Determination (H. Gabriel MD, et al., Presented at RSNA 2005) The purpose of this study was to determine if automated ROI methods decrease interobserver variability in breast MRI contrast kinetic interpretation and improve overall accuracy in lesion interpretation compared to manual methods.

	Effectiveness of CAD (Computer-Aided-Detection) in the Evaluation of Breast Cancer by Breast MRI and Pathology (J. Vilanova MD, et al., Presented at RSNA 2005) The purpose of this study was to evaluate the effectiveness of an automatic CAD system to detect breast cancer based on MR mammography features and the pathology results.

	An Advanced Method of Computer Aided Evaluation Applied to Breast MRI: A Useful Tool Both for the Radiologist Analysis and for the Diagnostic Accuracy (J. Vilanova MD, J. Barceló MD, Presented at ARRS 2005) The purpose of this study was to analyze and compare between a new commercially available method of computer aided evaluation for breast MRI and standard MRI software analysis. This research focused on diagnostic accuracy, registration of data to correct patient movement-related artifact, and the usefulness for the radiologist who interprets MR breast examinations.

	Quality Control Study of Image Registration in 40 Breast Cancer MR Imaging Patients Using Confirma CADstream Software (M. Middleton MD, et al., Presented at ARRS 2004) The purpose of this study was to evaluate registration of breast cancer MR images using Confirma CADstream software.

	Comparison of Automatic Time Curve Selection Methods for Breast MR CAD (T. Niemeyer, et al.) The purpose of this study examines a single temporal feature, a time versus percent enhancement curve. The automatic extraction of this feature could lead to better CAD algorithms for breast cancer detection in MR.

	Classification of Cardiac Related Artifacts in Dynamic Contrast Breast MRI (K. Stegbauer, et al.) This study was designed to build and evaluate the performance of a novel spatial classifier for detecting enhancing clusters within the chest wall. The use of such a classifier improves the appearance and utility of automatically generated MIP images in dynamic contrast breast MRI.

	A New Method of Computer Aided Evaluation Applied to Breast MRI: Improved Specificity Without Decreased Sensitivity (C. Lehman MD, PhD, et al.) The purpose of this study was to compare the accuracy of breast MRI interpretations with and without CADstream at three distinct thresholds of enhancement.

	Increasing the Utility of Breast MRI for Pre-Surgical Planning by Reporting Information Useful to Surgeons (J. Smith MD, et al.) The purpose of this work is to describe a method for tailoring the results of the breast MRI examination to efficiently answer the breast surgeon's clinical questions regarding the extent of disease and a patient's response to therapy.

	A CAD System for Breast MR Image Interpretation (J. Smith MD, C. Wood) Recent advances in breast MR image acquisition techniques have increased the amount of data acquired in a typical exam, further increasing the time required for radiologists to read and interpret the studies. In this analysis, a pre-released version of a commercial image processing system (CADstream®) was utilized in the interpretation of 10 breast MRI studies.

	Patient Motion Correction in Breast MRI (J. Smith MD, et al.) Breast MRI studies rely on both the acquisition and analysis of pre- and post-contrast images. While quantitative analysis of these studies has the potential to decrease interpretation time and increase accuracy, patient movement between scans can introduce artifact. In this study, a pre-released version of a commercial image processing system (CADstream) was used to evaluate the effect of a non-rigid registration tool on quantitative analysis.

	Bilateral and Multicentric Breast Carcinoma: Findings on Dynamic and High Spatial Resolution Breast MRI (J. Smith MD, B. Porter MD) The extent of tumor within the breast is the major determinant of whether breast conserving therapy or simple mastectomy will be the preferred treatment. Owing to its high sensitivity, breast MRI is becoming an established means for detecting breast carcinoma. The appearance of multicentric and bilateral tumor by bilateral dynamic breast MRI at a community-based practice is reviewed.