OBJECTIVES: In the face of multiple available diagnostic criteria in MR-mammography (MRM), a practical algorithm for lesion classification is needed. Such an algorithm should be as simple as possible and include only important independent lesion features to differentiate benign from malignant lesions. This investigation aimed to develop a simple classification tree for differential diagnosis in MRM. METHODS: A total of 1,084 lesions in standardised MRM with subsequent histological verification (648 malignant, 436 benign) were investigated. Seventeen lesion criteria were assessed by 2 readers in consensus. Classification analysis was performed using the chi-squared automatic interaction detection (CHAID) method. Results include the probability for malignancy for every descriptor combination in the classification tree. RESULTS: A classification tree incorporating 5 lesion descriptors with a depth of 3 ramifications (1, root sign; 2, delayed enhancement pattern; 3, border, internal enhancement and oedema) was calculated. Of all 1,084 lesions, 262 (40.4 %) and 106 (24.3 %) could be classified as malignant and benign with an accuracy above 95 %, respectively. Overall diagnostic accuracy was 88.4 %. CONCLUSIONS: The classification algorithm reduced the number of categorical descriptors from 17 to 5 (29.4 %), resulting in a high classification accuracy. More than one third of all lesions could be classified with accuracy above 95 %. KEY POINTS: • A practical algorithm has been developed to classify lesions found in MR-mammography. • A simple decision tree consisting of five criteria reaches high accuracy of 88.4 %. • Unique to this approach, each classification is associated with a diagnostic certainty. • Diagnostic certainty of greater than 95 % is achieved in 34 % of all cases.
OBJECTIVES: In the face of multiple available diagnostic criteria in MR-mammography (MRM), a practical algorithm for lesion classification is needed. Such an algorithm should be as simple as possible and include only important independent lesion features to differentiate benign from malignant lesions. This investigation aimed to develop a simple classification tree for differential diagnosis in MRM. METHODS: A total of 1,084 lesions in standardised MRM with subsequent histological verification (648 malignant, 436 benign) were investigated. Seventeen lesion criteria were assessed by 2 readers in consensus. Classification analysis was performed using the chi-squared automatic interaction detection (CHAID) method. Results include the probability for malignancy for every descriptor combination in the classification tree. RESULTS: A classification tree incorporating 5 lesion descriptors with a depth of 3 ramifications (1, root sign; 2, delayed enhancement pattern; 3, border, internal enhancement and oedema) was calculated. Of all 1,084 lesions, 262 (40.4 %) and 106 (24.3 %) could be classified as malignant and benign with an accuracy above 95 %, respectively. Overall diagnostic accuracy was 88.4 %. CONCLUSIONS: The classification algorithm reduced the number of categorical descriptors from 17 to 5 (29.4 %), resulting in a high classification accuracy. More than one third of all lesions could be classified with accuracy above 95 %. KEY POINTS: • A practical algorithm has been developed to classify lesions found in MR-mammography. • A simple decision tree consisting of five criteria reaches high accuracy of 88.4 %. • Unique to this approach, each classification is associated with a diagnostic certainty. • Diagnostic certainty of greater than 95 % is achieved in 34 % of all cases.
Authors: Pascal A T Baltzer; Matthias Benndorf; Matthias Dietzel; Mieczyslaw Gajda; Ingo B Runnebaum; Werner A Kaiser Journal: AJR Am J Roentgenol Date: 2010-06 Impact factor: 3.959
Authors: Matthias Dietzel; Pascal A T Baltzer; Tibor Vag; Aimee Herzog; Mieczyslaw Gajda; Oumar Camara; Werner A Kaiser Journal: Breast J Date: 2010 Nov-Dec Impact factor: 2.431
Authors: Wendy B Demartini; Brenda F Kurland; Robert L Gutierrez; C Craig Blackmore; Sue Peacock; Constance D Lehman Journal: Eur Radiol Date: 2011-02-27 Impact factor: 5.315
Authors: Ruth M L Warren; Deborah Thompson; Linda J Pointon; Rebecca Hoff; Fiona J Gilbert; Anwar R Padhani; Douglas F Easton; Sunil R Lakhani; Martin O Leach Journal: Radiology Date: 2006-06 Impact factor: 11.105
Authors: Ellen Warner; Hans Messersmith; Petrina Causer; Andrea Eisen; Rene Shumak; Donald Plewes Journal: Ann Intern Med Date: 2008-05-06 Impact factor: 25.391
Authors: Matthias Dietzel; Pascal A T Baltzer; Tibor Vag; Aimee Herzog; Mieczyslaw Gajda; Oumar Camara; Werner A Kaiser Journal: Korean J Radiol Date: 2010-02-22 Impact factor: 3.500
Authors: Maria Adele Marino; Paola Clauser; Ramona Woitek; Georg J Wengert; Panagiotis Kapetas; Maria Bernathova; Katja Pinker-Domenig; Thomas H Helbich; Klaus Preidler; Pascal A T Baltzer Journal: Eur Radiol Date: 2015-10-29 Impact factor: 5.315
Authors: Clemens G Kaiser; C Reich; M Dietzel; P A T Baltzer; J Krammer; K Wasser; S O Schoenberg; W A Kaiser Journal: Eur Radiol Date: 2015-01-11 Impact factor: 5.315