Breast Cytology Diagnosis via Digital Image Analysis 1 2 3

An interactive computer system has been developed for evaluating cytologic features derived directly from a digital scan of breast ne needle aspirate (FNA) slides. The system uses computer vision techniques to analyze cell nuclei and classi es them using an inductive method based on linear programming. A digital scan of selected areas of the aspirate slide is done by a trained observer, while the analysis of the digitized image is done by an untrained observer. When trained and tested on 119 breast FNAs (68 benign and 51 malignant) using leave-one-out testing, 90% correctness was achieved. These results indicate that the method is accurate (good intraand interobserver reproducibility) and that an untrained operator can obtain diagnostic results comparable to those achieved visually by experienced observers. Abbreviated title: Computerized Breast Cancer Diagnosis

[1]  Kristin P. Bennett,et al.  Decision Tree Construction Via Linear Programming , 1992 .

[2]  J. Baak,et al.  The value of morphometry to classic prognosticators in breast cancer , 1985, Cancer.

[3]  V. Wadehra,et al.  Use of fine needle aspiration cytology with immediate reporting in the diagnosis of breast disease , 1988, The British journal of surgery.

[4]  M. R. Mickey,et al.  Estimation of Error Rates in Discriminant Analysis , 1968 .

[5]  A. Halevy,et al.  Diagnosis of carcinoma of the breast by fine needle aspiration cytology , 1987, Surgery, gynecology & obstetrics.

[6]  Mubarak Shah,et al.  A fast algorithm for active contours , 1990, [1990] Proceedings Third International Conference on Computer Vision.

[7]  M. Kaplan,et al.  Fine-needle aspiration biopsy in the management of solid breast tumors. , 1985, Archives of surgery.

[8]  D J Zahniser,et al.  High-resolution and contextual analysis for the diagnosis of fine needle aspirates of breast. , 1991, Analytical and quantitative cytology and histology.

[9]  D. Waldron,et al.  The role of aspiration cytologic examination in the diagnosis of carcinoma of the breast. , 1991, Surgery, gynecology & obstetrics.

[10]  A. P. Kiovuniemi Fine-needle aspiration biopsy of the breast. , 1976, Annals of clinical research.

[11]  T. Delozier,et al.  Fiabilité de la ponction cytologique. Qui doit ponctionner les tumeurs du sein , 1983 .

[12]  T. K. Hunt,et al.  Fine-needle aspiration of palpable breast masses. A program for staged implementation. , 1983, Archives of surgery.

[13]  F. Fulciniti,et al.  Fine‐needle aspiration biopsies of breast masses. An additional experience with 1153 cases (1985 to 1988) and a meta‐analysis , 1992, Cancer.

[14]  R. Gupta,et al.  The value of needle aspiration cytology of the breast, with an emphasis on the diagnosis of breast disease in young women below the age of 30. , 1990, Acta Cytologica.

[15]  Michael A. Saunders,et al.  MINOS 5. 0 user's guide , 1983 .

[16]  F. Rilke,et al.  Problems in Fine-Needle Aspiration Biopsy Cytology of Clinically or Mammographically Uncertain Breast Tumors , 1982, Tumori.

[17]  W. E. Clark,et al.  Negative findings on fine-needle aspiration biopsy of solid breast masses: patient management. , 1988, American journal of surgery.

[18]  C Wittekind,et al.  Computerized morphometric image analysis of cytologic nuclear parameters in breast cancer. , 1987, Analytical and quantitative cytology and histology.

[19]  N. Bjurstam,et al.  Diagnosis of breast carcinoma. An evaluation of clinical examination, mammography, thermography and aspiration biopsy in breast disease. , 1974, Progress in surgery.

[20]  D. Larsimont,et al.  Comparison of fine needle aspirates of breast cancers to imprint smears by means of digital cell image analysis. , 1991, Analytical and quantitative cytology and histology.

[21]  B Stenkvist,et al.  A morphometric expression of differentiation in fine-needle biopsies of breast cancer. , 1981, Cytometry.

[22]  H. Wanebo,et al.  Fine needle aspiration cytology in lieu of open biopsy in management of primary breast cancer. , 1984, Annals of surgery.

[23]  O. Mangasarian,et al.  Multisurface method of pattern separation for medical diagnosis applied to breast cytology. , 1990, Proceedings of the National Academy of Sciences of the United States of America.

[24]  O. Mangasarian,et al.  Robust linear programming discrimination of two linearly inseparable sets , 1992 .

[25]  Azriel Rosenfeld,et al.  Computer Vision , 1988, Adv. Comput..

[26]  A. Herbert,et al.  Accuracy of aspiration cytology in the diagnosis of breast disease , 1985, The British journal of surgery.

[27]  Nesa L'abbe Wu,et al.  Linear programming and extensions , 1981 .

[28]  O L Mangasarian,et al.  Computer-designed expert systems for breast cytology diagnosis. , 1993, Analytical and quantitative cytology and histology.

[29]  J. Canter,et al.  Fine needle aspiration in the diagnosis and management of solid breast lesions. , 1984, American journal of surgery.

[30]  H. Hughes,et al.  Virus Persistence , 1982 .

[31]  L G Koss,et al.  Thin needle aspiration biopsy. , 1980, Acta cytologica.

[32]  William H. Press,et al.  Numerical recipes , 1990 .

[33]  C. Cobb,et al.  Fine-needle aspiration cytology in the diagnosis of primary breast cancer. , 1989, Surgery.

[34]  K. Pienta,et al.  Correlation of nuclear morphometry with progression of breast cancer , 1991, Cancer.

[35]  J. Hermans,et al.  The value of aspiration cytologic examination of the breast a statistical review of the medical literature , 1992, Cancer.

[36]  M. Stone Cross‐Validatory Choice and Assessment of Statistical Predictions , 1976 .

[37]  Jancik,et al.  Multisurface Method of Pattern Separation , 1993 .

[38]  D. C. Knight,et al.  Aspiration of the breast and nipple discharge cytology. , 1986, Surgery, gynecology & obstetrics.

[39]  Sholom M. Weiss,et al.  Computer Systems That Learn , 1990 .