Breast MR imaging in women at high-risk of breast cancer. Is something changing in early breast cancer detection?

Sardanelli, Francesco; Podo, Franca

doi:10.1007/s00330-006-0389-9

Cited by 114 publications

(82 citation statements)

References 114 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The pooled sensitivity for mammography was 40%, in comparison to 81% for MRI [20]. The detected cancers in 168 patients were small: 49% B10 mm diameter, and only 19% of invasive cancers were associated with lymph node involvement [20]. Similar figures were found in the review of Warner et al [21] who evaluated 11 prospective non-randomized studies in which MRI and mammography were used to screen women at very high risk for breast cancer (not only women with high familial risk).…”

Section: Introductionmentioning

confidence: 91%

“…In five prospective studies [15][16][17][18][19], 3,571 women were screened with contrast-enhanced MR imaging and mammography, and with ultrasound in three of five studies. The pooled sensitivity for mammography was 40%, in comparison to 81% for MRI [20]. The detected cancers in 168 patients were small: 49% B10 mm diameter, and only 19% of invasive cancers were associated with lymph node involvement [20].…”

Section: Introductionmentioning

confidence: 95%

See 1 more Smart Citation

Assessment of false-negative cases of breast MR imaging in women with a familial or genetic predisposition

Obdeijn

Loo

Rijnsburger

et al. 2009

Breast Cancer Res Treat

View full text Add to dashboard Cite

In order to assess the characteristics of malignant breast lesions those were not detected during screening by MR imaging. In the Dutch MRI screening study (MRISC), a non-randomized prospective multicenter study, women with high familial risk or a genetic predisposition for breast cancer were screened once a year by mammography and MRI and every 6 months with a clinical breast examination (CBE). The false-negative MR examinations were subject of this study and were retrospectively reviewed by two experienced radiologists. From November 1999 until March 2006, 2,157 women were eligible for study analyses. Ninety-seven malignant breast tumors were detected, including 19 DCIS (20%). In 22 patients with a malignant lesion, the MRI was assessed as BI-RADS 1 or 2. One patient was excluded because the examinations were not available for review. Forty-three percent (9/21) of the false-negative MR cases concerned pure ductal carcinoma in situ (DCIS) or DCIS with invasive foci, in eight of them no enhancement was seen at the review. In six patients the features of malignancy were missed or misinterpreted. Small lesion size (n = 3), extensive diffuse contrast enhancement of the breast parenchyma (n = 2), and a technically inadequate examination (n = 1) were other causes of the missed diagnosis. A major part of the false-negative MR diagnoses concerned non-enhancing DCIS, underlining the necessity of screening not only with MRI but also with mammography. Improvement of MRI scanning protocols may increase the detection rate of DCIS. The missed and misinterpreted cases are reflecting the learning curve of a multicenter study.

show abstract

Section: Introductionmentioning

confidence: 91%

Section: Introductionmentioning

confidence: 95%

Assessment of false-negative cases of breast MR imaging in women with a familial or genetic predisposition

Obdeijn

Loo

Rijnsburger

et al. 2009

Breast Cancer Res Treat

View full text Add to dashboard Cite

show abstract

“…Moreover, most biopsies might be avoidable because the current PPV for cases that undergo biopsy is about 20%-40%. [5][6][7][8][9][10][11] The PPV value is low because as stated above many benign solid masses are recommended for biopsy.…”

Section: Introductionmentioning

confidence: 99%

Similarity evaluation in a content‐based image retrieval (CBIR) CADx system for characterization of breast masses on ultrasound images

et al. 2011

View full text Add to dashboard Cite

Purpose:The authors are developing a content-based image retrieval ͑CBIR͒ CADx system to assist radiologists in characterization of breast masses on ultrasound images. In this study, the authors compared seven similarity measures to be considered for the CBIR system. The similarity between the query and the retrieved masses was evaluated based on radiologists' visual similarity assessments. Methods: The CADx system retrieves masses that are similar to a query mass from a reference library based on computer-extracted features using a k-nearest neighbor ͑k-NN͒ approach. Among seven similarity measures evaluated for the CBIR system, four similarity measures including linear discriminant analysis ͑LDA͒, Bayesian neural network ͑BNN͒, cosine similarity measure ͑Cos͒, and Euclidean distance ͑ED͒ similarity measure were compared by radiologists' visual assessment. For LDA and BNN, the features of a query mass were combined first into a malignancy score and then masses with similar scores were retrieved. For Cos and ED, similar masses were retrieved based on the normalized dot product and the Euclidean distance, respectively, between two feature vectors. For the observer study, three most similar masses were retrieved for a given query mass with each method. All query-retrieved mass pairs were mixed and presented to the radiologists in random order. Three Mammography Quality Standards Act ͑MQSA͒ radiologists rated the similarity between each pair using a nine-point similarity scale ͑1 = very dissimilar, 9 = very similar͒. The accuracy of the CBIR CADx system using the different similarity measures to characterize malignant and benign masses was evaluated by ROC analysis. Results: The BNN measure used with the k-NN classifier provided slightly higher performance for classification of malignant and benign masses ͑A z values of 0.87͒ than those with the LDA, Cos, and ED measures ͑A z of 0.86, 0.84, and 0.81, respectively͒. The average similarity ratings of all radiologists for LDA, BNN, Cos, and ED were 4.71, 4.95, 5.18, and 5.32, respectively. The k-NN with the ED measures retrieved masses of significantly higher similarity ͑p Ͻ 0.008͒ than LDA and BNN. Conclusions: Similarity measures using the resemblance of individual features in the multidimensional feature space can retrieve visually more similar masses than similarity measures using the resemblance of the classifier scores. A CBIR system that can most effectively retrieve similar masses to the query may not have the best A z .

show abstract

“…Currently, the positive predictive value for biopsy ranges only from 20% to 40%. [7][8][9][10][11][12][13] Therefore, it is very important to improve the accuracy of noninvasive methods of distinguishing malignant from benign masses and reduce the number of unnecessary biopsies.…”

Section: Introductionmentioning

confidence: 99%

A similarity study of content‐based image retrieval system for breast cancer using decision tree

et al. 2012

View full text Add to dashboard Cite

Purpose:We are developing a decision tree content-based image retrieval (DTCBIR) CADx system to assist radiologists in characterization of breast masses on ultrasound images. Methods: Three DTCBIR configurations, including decision tree with boosting (DTb), decision tree with full leaf features (DTL), and decision tree with selected leaf features (DTLs) were compared. For DTb, features of a query mass were combined first into a merged feature score and then masses with similar scores were retrieved. For DTL and DTLs, similar masses were retrieved based on the Euclidean distance between feature vectors of the query and those of selected references. For each DTCBIR configuration, we investigated the use of full feature set and subset of features selected by the stepwise linear discriminant analysis (LDA) and simplex optimization method, resulting in six retrieval methods and selected five, DTb-lda, DTL-lda, DTb-full, DTL-full, and DTLs-full, for the observer study. Three MQSA radiologists rated similarities between the query mass and computerretrieved three most similar masses using nine-point similarity scale (9 = very similar). Results: For DTb-lda, DTL-lda, DTb-full, DTL-full, and DTLs-full, average A z values were 0.90 ± 0.03, 0.85 ± 0.04, 0.87 ± 0.04, 0.79 ± 0.05, and 0.71 ± 0.06, respectively, and average similarity ratings were 5.00, 5.41, 4.96, 5.33, and 5.13, respectively. Conclusions: The DTL-lda is a promising DTCBIR CADx configuration which had simple tree structure, good classification performance, and highest similarity rating.

show abstract

Breast MR imaging in women at high-risk of breast cancer. Is something changing in early breast cancer detection?

Cited by 114 publications

References 114 publications

Assessment of false-negative cases of breast MR imaging in women with a familial or genetic predisposition

Assessment of false-negative cases of breast MR imaging in women with a familial or genetic predisposition

Similarity evaluation in a content‐based image retrieval (CBIR) CADx system for characterization of breast masses on ultrasound images

A similarity study of content‐based image retrieval system for breast cancer using decision tree

Contact Info

Product

Resources

About