Challenges in automated detection of cervical intraepithelial neoplasia

Cervical Intraepithelial Neoplasia (CIN) is a precursor to invasive cervical cancer, which annually accounts for about 3700 deaths in the United States and about 274,000 worldwide. Early detection of CIN is important to reduce the fatalities due to cervical cancer. While the Pap smear is the most common screening procedure for CIN, it has been proven to have a low sensitivity, requiring multiple tests to confirm an abnormality and making its implementation impractical in resource-poor regions. Colposcopy and cervicography are two diagnostic procedures available to trained physicians for non-invasive detection of CIN. However, many regions suffer from lack of skilled personnel who can precisely diagnose the bio-markers due to CIN. Automatic detection of CIN deals with the precise, objective and non-invasive identification and isolation of these bio-markers, such as the Acetowhite (AW) region, mosaicism and punctations, due to CIN. In this paper, we study and compare three different approaches, based on Mathematical Morphology (MM), Deterministic Annealing (DA) and Gaussian Mixture Models (GMM), respectively, to segment the AW region of the cervix. The techniques are compared with respect to their complexity and execution times. The paper also presents an adaptive approach to detect and remove Specular Reflections (SR). Finally, algorithms based on MM and matched filtering are presented for the precise segmentation of mosaicism and punctations from AW regions containing the respective abnormalities.

[1]  Scott B. Cantor,et al.  COLPOSCOPY FOR THE DIAGNOSIS OF SQUAMOUS INTRAEPITHELIAL LESIONS: A META‐ANALYSIS , 1998, Obstetrics and gynecology.

[2]  Sunanda Mitra,et al.  Segmentation and Classification of Cervix Lesions by Pattern and Texture Analysis , 2005, The 14th IEEE International Conference on Fuzzy Systems, 2005. FUZZ '05..

[3]  R. Sankaranarayanan,et al.  A Practical Manual on Visual Screening for Cervical Neoplasia , 2003 .

[4]  K. Rose.  Deterministic annealing for clustering, compression, classification, regression, and related optimization problems , 1998, Proc. IEEE.

[5]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[6]  Shiri Gordon,et al.  Content analysis of uterine cervix images: initial steps toward content based indexing and retrieval of cervigrams , 2006, SPIE Medical Imaging.

[7]  Jitendra Malik,et al.  Blobworld: Image Segmentation Using Expectation-Maximization and Its Application to Image Querying , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Viara Van Raad.  Active contour models - a multiscale implementation for anatomical feature delineation in cervical images , 2004, 2004 International Conference on Image Processing, 2004. ICIP '04..

[9]  Ferris Dg,et al.  Cervicography--an adjunct to Papanicolaou screening. , 1994 .

[10]  Jitendra Malik,et al.  Scale-Space and Edge Detection Using Anisotropic Diffusion , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  T. Wright,et al.  Evaluation of alternative methods of cervical cancer screening for resource‐poor settings , 2000, Cancer.

[12]  D G Ferris,et al.  Cervicography--an adjunct to Papanicolaou screening. , 1994, American family physician.

[13]  Shiri Gordon,et al.  Image segmentation of uterine cervix images for indexing in PACS , 2004, Proceedings. 17th IEEE Symposium on Computer-Based Medical Systems.

[14]  Qiang Ji,et al.  Texture analysis for classification of cervix lesions , 2000, IEEE Transactions on Medical Imaging.

[15]  A. R. Morse,et al.  A Text and Atlas of Integrated Colposcopy , 1991 .

[16]  Jeff A. Bilmes,et al.  A gentle tutorial of the em algorithm and its application to parameter estimation for Gaussian mixture and hidden Markov models , 1998 .

[17]  Bhakti M Tulpule.  Color and texture analysis of cervix lesions , 2004 .

[18]  Sunanda Mitra,et al.  Digitized Cervical Images: Problems, Solutions, and Potential Medical Impact , 2006, Journal of lower genital tract disease.

[19]  Andrew P. Bradley,et al.  Active Contour Model Based Segmentation of Colposcopy Images of Cervix Uteri Using Gaussian Pyramids , 2002 .

[20]  S. Gordon,et al.  Content-based indexing and retrieval of uterine cervix images , 2004, 2004 23rd IEEE Convention of Electrical and Electronics Engineers in Israel.

[21]  L. Koss.  The Papanicolaou test for cervical cancer detection. A triumph and a tragedy. , 1989, JAMA.