Optoelectronic region of interest detection: an application in automated cytology.

Diagnostic cytology, which is used to screen for cervical cancer, involves characterizing cellular features such as shape, size, and texture. Automated screening of cervical smear slides is desirable but computationally challenging since each slide requires processing 2 x 10(9) pixels at a resolution of 0.8 mum per pixel. We demonstrate that the throughput of optical processors can be exploited in automated cervical smear-screening systems. In particular, we identify a morphological shape detector to perform the initial region of interest (ROI) detection and to demonstrate experimentally its optoelectronic implementation. The ROI detector is tested on 200 images, and its performance is characterized as a receiver operating characteristic (ROC). The area under the ROC curve is as high as 96.4% of the total area. The simulation and the experimental results are found comparable, and the discrepancy between the two results is determined to be a function of the number of bits represented in the filter plane device.

[1]  Richard A. Domanik,et al.  AccuMed International, Inc. , 1996 .

[2]  T. Crimmins,et al.  Image Algebra and Automatic Shape Recognition , 1985, IEEE Transactions on Aerospace and Electronic Systems.

[3]  D H Grohs.  Challenges in cervical cancer screening: what clinicians, patients and the general public need to know. , 1996, Acta cytologica.

[4]  C Garbay,et al.  A double scanning microphotometer for image analysis: hardware, software and biomedical applications. , 1979, The journal of histochemistry and cytochemistry : official journal of the Histochemistry Society.

[5]  D P Casasent,et al.  Optical laboratory morphological inspection processor. , 1989, Applied optics.

[6]  D J McKnight,et al.  256 × 256 liquid-crystal-on-silicon spatial light modulator. , 1994, Applied optics.

[7]  C Ferreira,et al.  Optoelectronic morphological image processor. , 1993, Optics letters.

[8]  W. Lehmacher,et al.  The validation of cervical cytology. Sensitivity, specificity and predictive values. , 1991, Acta cytologica.

[9]  Y Li,et al.  Compact parallel real-time programmable optical morphological image processor. , 1989, Optics letters.

[10]  W Abmayr,et al.  Progress report of the TUDAB project for automated cancer cell detection. , 1979, The journal of histochemistry and cytochemistry : official journal of the Histochemistry Society.

[11]  Kenneth R. Castleman,et al.  Estimating cell populations , 1981, Pattern Recognit..

[12]  P. Bartels,et al.  The numerical composition of cellular samples from the female reproductive tract. II. Cases with invasive squamous carcinoma of uterine cervix. , 1976, Acta cytologica.

[13]  William T. Rhodes,et al.  Nonlinear Optical Image Filtering By Time-Sequential Threshold Decomposition , 1988 .

[14]  D J McKnight,et al.  Analog distorted helix ferroelectric liquid-crystal-on-silicon spatial light modulator. , 1995, Optics letters.

[15]  P. Wingo,et al.  Cancer statistics, 1995 , 1995, CA: a cancer journal for clinicians.

[16]  P H Bartels,et al.  The TICAS-RTCIP real time cell identification processor. , 1975, Acta cytologica.

[17]  P. Bartels,et al.  The numerical composition of cellular samples from the female reproductive tract. I. Carcinoma in situ. , 1975, Acta cytologica.

[18]  G. P. Vooys,et al.  BioPEPR: a system for the automatic prescreening of cervical smears. , 1979, The journal of histochemistry and cytochemistry : official journal of the Histochemistry Society.

[19]  J H Tucker.  CERVISCAN: an image analysis system for experiments in automatic cervical smear prescreening. , 1976, Computers and biomedical research, an international journal.

[20]  K Okamoto,et al.  Automated cytologic screening system (CYBEST model 4): an integrated image cytometry system. , 1987, Applied optics.

[21]  R A Athale,et al.  Acousto-optic processing with electronic image feedback for morphological filtering. , 1992, Applied optics.

[22]  S. H. Lee,et al.  Two-dimensional spatial light modulators: a tutorial , 1990, Proc. IEEE.

[23]  Husain Oa,et al.  Automation in cervical cancer screening. Part 1: fixed cell scanning systems. , 1976 .

[24]  Demetri Psaltis,et al.  Optical-Image Correlation With A Binary Spatial Light-Modulator , 1984 .

[25]  J. Serra.  Introduction to mathematical morphology , 1986 .

[26]  Effect of random abnormal cell proportion on specimen classifier performance. , 1993, Cytometry.