RATIONALE AND OBJECTIVES: To investigate the effect of a computer-aided diagnosis (CADx) system on radiologists' performance in discriminating malignant and benign masses on mammograms and three-dimensional (3D) ultrasound (US) images. MATERIALS AND METHODS: Our dataset contained mammograms and 3D US volumes from 67 women (median age, 51; range: 27-86) with 67 biopsy-proven breast masses (32 benign and 35 malignant). A CADx system was designed to automatically delineate the mass boundaries on mammograms and the US volumes, extract features, and merge the extracted features into a multi-modality malignancy score. Ten experienced readers (subspecialty academic breast imaging radiologists) first viewed the mammograms alone, and provided likelihood of malignancy (LM) ratings and Breast Imaging and Reporting System assessments. Subsequently, the reader viewed the US images with the mammograms, and provided LM and action category ratings. Finally, the CADx score was shown and the reader had the opportunity to revise the ratings. The LM ratings were analyzed using receiver-operating characteristic (ROC) methodology, and the action category ratings were used to determine the sensitivity and specificity of cancer diagnosis. RESULTS: Without CADx, readers' average area under the ROC curve, A(z), was 0.93 (range, 0.86-0.96) for combined assessment of the mass on both the US volume and mammograms. With CADx, their average A(z) increased to 0.95 (range, 0.91-0.98), which was borderline significant (P = .05). The average sensitivity of the readers increased from 98% to 99% with CADx, while the average specificity increased from 27% to 29%. The change in sensitivity with CADx did not achieve statistical significance for the individual radiologists, and the change in specificity was statistically significant for one of the radiologists. CONCLUSIONS: A well-trained CADx system that combines features extracted from mammograms and US images may have the potential to improve radiologists' performance in distinguishing malignant from benign breast masses and making decisions about biopsies.
RATIONALE AND OBJECTIVES: To investigate the effect of a computer-aided diagnosis (CADx) system on radiologists' performance in discriminating malignant and benign masses on mammograms and three-dimensional (3D) ultrasound (US) images. MATERIALS AND METHODS: Our dataset contained mammograms and 3D US volumes from 67 women (median age, 51; range: 27-86) with 67 biopsy-proven breast masses (32 benign and 35 malignant). A CADx system was designed to automatically delineate the mass boundaries on mammograms and the US volumes, extract features, and merge the extracted features into a multi-modality malignancy score. Ten experienced readers (subspecialty academic breast imaging radiologists) first viewed the mammograms alone, and provided likelihood of malignancy (LM) ratings and Breast Imaging and Reporting System assessments. Subsequently, the reader viewed the US images with the mammograms, and provided LM and action category ratings. Finally, the CADx score was shown and the reader had the opportunity to revise the ratings. The LM ratings were analyzed using receiver-operating characteristic (ROC) methodology, and the action category ratings were used to determine the sensitivity and specificity of cancer diagnosis. RESULTS: Without CADx, readers' average area under the ROC curve, A(z), was 0.93 (range, 0.86-0.96) for combined assessment of the mass on both the US volume and mammograms. With CADx, their average A(z) increased to 0.95 (range, 0.91-0.98), which was borderline significant (P = .05). The average sensitivity of the readers increased from 98% to 99% with CADx, while the average specificity increased from 27% to 29%. The change in sensitivity with CADx did not achieve statistical significance for the individual radiologists, and the change in specificity was statistically significant for one of the radiologists. CONCLUSIONS: A well-trained CADx system that combines features extracted from mammograms and US images may have the potential to improve radiologists' performance in distinguishing malignant from benign breast masses and making decisions about biopsies.
Authors: H P Chan; B Sahiner; M A Helvie; N Petrick; M A Roubidoux; T E Wilson; D D Adler; C Paramagul; J S Newman; S Sanjay-Gopal Journal: Radiology Date: 1999-09 Impact factor: 11.105
Authors: Karla Horsch; Maryellen L Giger; Carl J Vyborny; Li Lan; Ellen B Mendelson; R Edward Hendrick Journal: Radiology Date: 2006-08 Impact factor: 11.105
Authors: David Gur; Andriy I Bandos; Carl R Fuhrman; Amy H Klym; Jill L King; Howard E Rockette Journal: Acad Radiol Date: 2007-01 Impact factor: 3.173
Authors: Berkman Sahiner; Heang-Ping Chan; Marilyn A Roubidoux; Lubomir M Hadjiiski; Mark A Helvie; Chintana Paramagul; Janet Bailey; Alexis V Nees; Caroline Blane Journal: Radiology Date: 2007-01-23 Impact factor: 11.105
Authors: David Gur; Luisa P Wallace; Amy H Klym; Lara A Hardesty; Gordon S Abrams; Ratan Shah; Jules H Sumkin Journal: Radiology Date: 2005-03-15 Impact factor: 11.105
Authors: Ahmedin Jemal; Rebecca Siegel; Elizabeth Ward; Taylor Murray; Jiaquan Xu; Michael J Thun Journal: CA Cancer J Clin Date: 2007 Jan-Feb Impact factor: 508.702
Authors: Hui Li; Heather M Whitney; Yu Ji; Alexandra Edwards; John Papaioannou; Peifang Liu; Maryellen L Giger Journal: J Med Imaging (Bellingham) Date: 2022-06-06
Authors: Konstantinos P Sidiropoulos; Spiros A Kostopoulos; Dimitris T Glotsos; Emmanouil I Athanasiadis; Nikos D Dimitropoulos; John T Stonham; Dionisis A Cavouras Journal: Int J Comput Assist Radiol Surg Date: 2013-01-25 Impact factor: 2.924
Authors: Frederic Padilla; Marilyn A Roubidoux; Chintana Paramagul; Sumedha P Sinha; Mitchell M Goodsitt; Gerald L Le Carpentier; Heang-Ping Chan; Lubomir M Hadjiiski; J Brian Fowlkes; Annette D Joe; Katherine A Klein; Alexis V Nees; Mitra Noroozian; Stephanie K Patterson; Renee W Pinsky; Fong Ming Hooi; Paul L Carson Journal: J Ultrasound Med Date: 2013-01 Impact factor: 2.153