Advances in computer-aided diagnosis for breast cancer

Current Opinion in Obstetrics and Gynecology

Volumn 18, Issue 1, 2006, Pages 64-70

  Hadjiiski, Lubomir ^a   Sahiner, Berkman ^a   Chan, Heang Ping ^a  

^a UNIVERSITY OF MICHIGAN MEDICAL SCHOOL   (United States)

Author keywords

Breast cancer; Characterization; Computer aided diagnosis; Detection; Mammography

Indexed keywords

BREAST CANCER; CANCER DIAGNOSIS; CLINICAL PRACTICE; COMPUTER ASSISTED DIAGNOSIS; DIAGNOSTIC ACCURACY; DIGITAL BREAST TOMOSYNTHESIS; ECHOMAMMOGRAPHY; HUMAN; MAMMOGRAPHY; NUCLEAR MAGNETIC RESONANCE IMAGING; PRIORITY JOURNAL; RADIOLOGIST; REVIEW; THREE DIMENSIONAL IMAGING;

BREAST NEOPLASMS; DIAGNOSIS, COMPUTER-ASSISTED; FEMALE; HUMANS; MAGNETIC RESONANCE IMAGING; MAMMOGRAPHY; ULTRASONOGRAPHY;

EID: 33646484506     PISSN: 1040872X     EISSN: None     Source Type: Journal    
DOI: 10.1097/01.gco.0000192965.29449.da     Document Type: Review

References (56)

1. Feig SA, D'Orsi CJ, Hendrick RE, et al. American College of Radiology guidelines for breast cancer screening. AJR Am J Roentgenol 1998; 171:29-33.
2. Cady B, Michaelson JS. The life-sparing potential of mammographic screening. Cancer 2001; 91:1699-1703.
3. American Cancer Society. www.cancer.org 2005. Cancer Facts & Figures 2005. 2005.
4. Sickles EA. Periodic mammographic follow-up of probably benign lesions: results in 3184 consecutive cases. Radiology 1991; 179:463-468.
5. Kopans DB. The positive predictive value of mammography. AJR Am J Roentgenol 1992; 158:521-526.
6. Adler DD, Helvie MA. Mammographic biopsy recommendations. Curr Opin Radiol 1992; 4:123-129.
7. Helvie MA, Hadjiiski LM, Makariou E, et al. Sensitivity of noncommercial computer-aided detection system for mammographic breast cancer detection - a pilot clinical trial. Radiology 2004; 231:208-214. A prospective clinical pilot trial of a CAD system with 2389 screening cases and 13 radiologists showed a 10% increase in detection rate and a 10% increase in call-back rate.
8. Birdwell RL, Bandodkar P, Ikeda DM. Computer-aided detection with screening mammography in a university hospital setting. Radiology 2005; 236:451-457. A clinical study based on 8682 cases showed a 7.4% increase in cancer detection rate and a 7.6% increase in recall rate when radiologists were using CAD.
9. Gur D, Sumkin JH, Rockette HE, et al. Changes in breast cancer detection and mammography recall rates after the introduction of a computer-aided detection system. J Natl Cancer Inst 2004; 96:185-190. No statistically significant changes in the recall and breast-cancer-detection rates between the 56 432 cases read by 24 radiologists before the introduction of the CAD system and the 59 139 cases read after its introduction were reported in this study.
10. Hadjiiski LM, Chan HP, Sahiner B, et al. Improvement of radiologists' characterization of malignant and benign breast masses in serial mammograms by computer-aided diagnosis: An ROC study. Radiology 2004; 233:255-265. The effects of CAD on radiologists' characterization of masses on serial mammograms using 253 temporal image pairs were evaluated. With CAD, the radiologists improved both their estimates of likelihood of malignancy and biopsy recommendations.
11. Destounis SV, DiNitto P, Logan-Young W, et al. Can computer-aided detection with double reading of screening mammograms help decrease the false-negative rate? Initial experience. Radiology 2004; 232:578-584. This study showed the potential of CAD to reduce the rate of false-negative findings on screening mammograms considered normal at initial double-reading.
12. Butler SA, Gabbay RJ, Kass DA, et al. Computer-aided detection in diagnostic mammography: Detection of clinically unsuspected cancers. AJR Am J Roentgenol 2004; 183:1511-1515. The effect of CAD on the detection of clinically unsuspected breast cancers was studied. CAD identified 87% of the incidentally detected cancers, other than the site of the presenting clinical finding, and may have been useful as an aid to the radiologists.
13. Marx C, Malich A, Facius M, et al. Are unnecessary follow-up procedures induced by computer-aided diagnosis (CAD) in mammography? Comparison of mammographic diagnosis with and without use of CAD. Eur J Radiol 2004; 51:66-72. In an observer experiment with five radiologists and 185 patients, an increased short-term call-back rate and also a reduced number of unnecessary recommendations for biopsies were reported when the cases were evaluated with CAD.
14. Baker JA, Lo JY, Delong DM, et al. Computer-aided detection in screening mammography: Variability in cues. Radiology 2004; 233:411-417. The consistency of a commercial CAD system was studied by scanning the same mammograms 10 times.
15. Gur D, Stalder JS, Hardesty LA, et al. Computer-aided detection performance in mammographic examination of masses: Assessment. Radiology 2004; 233:418-423. Two commercial and an in-house CAD scheme were compared on 219 patients.
16. Wei J, Sahiner B, Hadjiiski LM, et al. Computer aided detection of breast masses on full field digital mammograms. Med Phys 2005; 32:2827-2838. A multistage CAD system for the detection of masses on FFDM was proposed in this study.
17. McLoughlin KJ, Bones PJ, Karssemeijer N. Noise equalization for detection of microcalcification clusters in direct digital mammogram images. IEEE Trans Med Imaging 2004; 23:313-320. A method for noise equalization in FFDM images was developed and evaluated with CAD.
18. Sahiner B, Chan HP, Roubidoux MA, et al. Computerized characterization of breast masses on 3-D ultrasound volumes. Med Phys 2004; 31:744-754. A CAD system for characterizing breast masses as malignant or benign on three-dimensional ultrasound scans was designed and evaluated using 102 cases. The accuracy of the CAD system was similar to that of four experienced breast radiologists.
19. z was 0.87 and 0.81 for the training and testing datasets, respectively.
20. Sahiner B, Chan HP, Hadjiiski LM, et al. The effect of a multi-modality computer classifier on radiologists' accuracy in characterizing breast masses using mammograms and volumetric ultrasound images: An ROC study. In: Radiological Society of North America. RSNA Program Book; 2004. pp. 447. A combined three-dimensional ultrasound and mammographic CAD system was designed by using data from 67 patients and an observer study with five radiologists performed. The radiologists significantly improved their average performance when using combined CAD.
21. Drukker K, Horsch K, Giger ML. Multimodality computerized diagnosis of breast lesions using mammography and sonography. Acad Radiol 2005; 12:970-979. A CAD system combining an ultrasound and mammographic information was designed and evaluated on 100 lesions. The accuracy of the combined system was statistically significantly improved compared with the mammography and ultrasound systems alone.
22. Joo S, Yang YS, Moon WK, et al. Computer-aided diagnosis of solid breast nodules: Use of an artificial neural network based on multiple sonographic features. IEEE Trans Med Imaging 2004; 23:1292-1300. Design of a CAD system for classifying breast masses as malignant or benign on ultrasound images was reported.
23. Chang RF, Wu WJ, Moon WK, et al. Automatic ultrasound segmentation and morphology based diagnosis of solid breast tumors. Breast Cancer Res Treat 2005; 89:179-185.
24. Moon WK, Chang RF, Chen CJ, et al. Solid breast masses: Classification with computer-aided analysis of continuous US images obtained with probe compression. Radiology 2005; 236:458-464. Evaluation of the accuracy of continuous ultrasound images obtained during probe compression and CAD for the classification of biopsy-proved benign and malignant breast tumors was introduced.
25. Song JH, Venkatesh SS, Conant EA, et al. Comparative analysis of logistic regression and artificial neural network for computer-aided diagnosis of breast masses. Acad Radiol 2005; 12:487-495.
26. Deurloo EE, Muller SH, Peterse JL, et al. Clinically and mammographically occult breast lesions on MR images: Potential effect of computerized assessment on clinical reading. Radiology 2005; 234:693-701. The study demonstrated that the complementary information from a radiologist and a computer system on contrast-enhanced MRI images had the potential to increase the overall performance for clinically and mammographically occult lesions.
27. z using a linear classifier was 0.80 and 0.86 for hand-segmented and computer-segmented contours, respectively.
28. Nattkemper TW, Arnrich B, Lichte O, et al. Evaluation of radiological features for breast tumour classification in clinical screening with machine learning methods. Art Intell Med 2005; 34:129-139. A report on the malignant and benign classification of breast masses based on support vector machines using MRI data.
29. DeMartini WB, Lehman CD, Peacock S, et al. Computer-aided detection applied to breast MRI: Assessment of CAD-generated enhancement and tumor sizes in breast cancers before and after neoadjuvant chemotherapy. Acad Radiol 2005; 12:806-814. CAD for newly diagnosed locally advanced breast cancers with MRI before and after neoadjuvant chemotherapy.
30. Chan HP, Wei J, Sahiner B, et al. Computerized detection of masses on digital tomosynthesis mammograms - a preliminary study. In: 7th International Workshop on Digital Mammography, Durham, NC. (in press). A study proposing a CAD system for breast masses on DBT mammograms.
31. Chan HP, Wei J, Sahiner B, et al. Computer-aided detection system for breast masses on digital tomosynthesis mammograms - preliminary experience. Radiology 2005; 237:107-1080. Development of a CAD system for detecting breast masses on DBT mammograms using 26 cases and three-dimensional features. The CAD system achieved a sensitivity of 85% with 2.2 false-positives per case. The results demonstrate the feasibility of this approach for the development of a CAD system for DBT mammograms.
32. Reiser I, Nishikawa RM, Giger ML, et al. Computerized detection of mass lesions in digital breast tomosynthesis images using two- and three dimensional radial gradient index segmentation. Technol Cancer Res Treat 2004; 3:437-441. Presentation of initial results for a computerized mass-lesion-detection scheme for DBT images. The algorithm uses a radial gradient-index feature for the initial detection of lesions and for the segmentation of lesion candidates. For shape features, classification using three-dimensional features was improved compared with the equivalent features.
33. Filev P, Hadjiiski LM, Sahiner B, et al. Comparison of similarity measures for the task of template matching of masses on serial mammograms. Med Phys 2005; 32:515-529. Similarity measures applied to the automatic registration of corresponding masses on temporal pairs of mammograms were introduced.
34. Marias K, Behrenbruch C, Parbhoo S, et al. A registration framework for the comparison of mammogram sequences. IEEE Trans Med Imaging 2005; 24: 782-790. An automatic methods for the registration of corresponding masses on temporal pairs of mammograms.
35. Timp S, Van Engeland S, Karssemeijer N. A regional registration method to find corresponding mass lesions in temporal mammogram pairs. Med Phys 2005; 32:2629-2638. CAD for the automatic registration of corresponding masses on temporal pairs of mammograms based on the combined method.
36. Wei J, Chan HP, Helvie MA, et al. Correlation between mammographic density and volumetric fibroglandular tissue estimated on breast MR images. Med Phys 2004; 31:933-942. Evaluation of the correlation between the percentage dense area on the mammogram and the percentage glandular tissue volume as estimated from MRI images. A high correlation was obtained.
37. Zhou C, Chan HP, Petrick N, et al. Computerized image analysis: Estimation of breast density on mammograms. Med Phys 2001; 28:1056-1069.
38. Li H, Giger ML, Olopade OI, et al. Computerized texture analysis of mammographic parenchymal patterns of digitized mammograms. Acad Radiol 2005; 12:863-873. Computerized texture analysis of mammograms that provided radiographic descriptors of mammographic parenchymal patterns, which might be useful for identifying women at high risk of breast cancer and for monitoring the treatment of breast-cancer patients.
39. Brem RE, Hoffmeister JW, Rapelyea JA, et al. Impact of breast density on computer-aided detection for breast cancer. AJR Am J Roentgenol 2005; 184:439-444. The article investigates the effect of breast density on CAD performance. The authors suggested that CAD might be particularly advantageous in patients with dense breasts, in whom mammography is most challenging.
40. Brem RF, Hoffmeister JW, Zisman G, et al. A computer-aided detection system for the evaluation of breast cancer by mammographic appearance and lesion size. AJR Am J Roentgenol 2005; 184:893-896. The article investigates the effect of lesion appearance and cancer size on CAD-detection performance.
41. Brem RF, Rapelyea JA, Zisman G, et al. Evaluation of breast cancer with a computer-aided detection system by mammographic appearance and histopathology. Cancer 2005; 104:931-935. The effect of lesion appearance and tumor histopathology on CAD-detection performance was studied in this article.
42. Catarious DM, Baydush AH, Floyd CE. Incorporation of an iterative, linear segmentation routine into a mammographic mass CAD system. Med Phys 2004; 31:1512-1520. Development of a method that improves the segmentation of the breast masses using iterative linear segmentation.
43. Timp S, Karssemeijer N. A new 2D segmentation method based on dynamic programming applied to computer aided detection in mammography. Med Phys 2004; 31:958-971. Introduction of method that improves segmentation based on dynamic programming.
44. Wei J, Sahiner B, Hadjiiski LM, et al. A dual computer-aided detection (CAD) system for improvement of mass detection on mammograms. RSNA Program Book; 2004 (2004; 491). In this study, a dual CAD-system approach to the detection of subtle masses was proposed.
45. Soo MS, Rosen EL, Xia JQ, et al. Computer-aided detection of amorphous calcifications. AJR Am J Roentgenol 2005; 184:887-892. A commercial system was used to detect amorphous calcifications, which usually are difficult for radiologists to detect.
46. Bilska-Wolak AO, Floyd CE, Lo JY, et al. Computer aid for decision to biopsy breast masses on mammography: Validation on new cases. Acad Radiol 2005; 12:671-680. In this study, a likelihood-ratio classifier was designed for the classification of masses as malignant or benign, and its performance was tested on an independent data set.
47. Lim WK, Er MJ. Classification of mammographic masses using generalized dynamic fuzzy neural networks. Med Phys 2004; 31:1288-1295.
48. Paquerault S, Yarusso LM, Papaioannou J, et al. Radial gradient-based segmentation of mammographic microcalcifications: Observer evaluation and effect on CAD performance. Med Phys 2004; 31:2648-2657. In this study, a classification of microcalcifications as malignant and benign based on radial gradient-based segmentation was performed.
49. Kallergi M. Computer-aided diagnosis of mammographic microcalcification clusters. Med Phys 2004; 31:314-326. A classification of microcalcifications as malignant and benign based on artificial neural networks is included in this article.
50. Leichter I, Lederman R, Buchbinder SS, et al. Computerized evaluation of mammographic lesions: What diagnostic role does the shape of the individual microcalcifications play compared with the geometry of the cluster? AJR Am J Roentgenol 2004; 182:705-712. The shape of individual microcalcification and the geometry of clusters of microcalcifications were used for classifying malignant and benign lesions.
51. Wei L, Yang Y, Nishikawa RM, et al. A study on several machine-learning methods for classification of malignant and benign clustered microcalcifications. IEEE Trans Med Imaging 2005; 24:371-380. Classification of microcalcifications as malignant and benign using methods based on support vector machines were covered in this article.
52. Papadopoulos A, Fotiadis DI, Likas A. Characterization of clustered microcalcifications in digitized mammograms using neural networks and support vector machines. Art Intell Med 2005; 34:141-150.
53. Nakayama R, Uchiyama Y, Watanabe R, et al. Computer-aided diagnosis scheme for histological classification of clustered microcalcifications on magnification mammograms. Med Phys 2004; 31:789-799. A computer classification of microcalcification clusters on five different histological types was performed.
54. Zhou C, Chan HP, Paramagul C, et al. Computerized nipple identification for multiple image analysis in computer-aided diagnosis. Med Phys 2004; 31: 2871-2882. A new automated method for breast-nipple detection was reported in this study.
55. Ferrari RJ, Rangayyan RM, Desautels JEL, et al. Automatic identification of the pectoral muscle in mammograms. IEEE Trans Med Imaging 2004; 23: 232-245. A computerized method for pectoral muscle segmentation was reported.
56. Kwok SM, Chandrasekhar R, Attikiouzel Y, et al. Automatic pectoral muscle segmentation on mediolateral oblique view mammograms. IEEE Trans Med Imaging 2004; 23:1129-1140. An additional study reporting automatic methods for pectoral muscle segmentation.