1. Feature Of The Week 2/27/11: Case Western Reserve University, Cleveland Clinic, and Imlaux Corporation Investigate Computer-Aided Diagnosis of Precancerous Cervix Tissue using OCT.

    Feature Of The Week 2/27/11: Case Western Reserve University, Cleveland Clinic, and Imlaux Corporation Investigate Computer-Aided Diagnosis of Precancerous Cervix Tissue using OCT.

    Feature Of The Week 2/27/11: Researchers at Case Western Reserve University have a long history of innovation in technology and medical applications of optical coherence tomography.  Below is a summary of some of their recent work on computer-aided diagnosis of the precancerous cervix using OCT.

     

    OCT has been investigated as a screening/diagnostic tool in the management of pre-invasive and early invasive cancers. The Biophotonics Imaging Lab at Case Western Reserve University has several on-going studies on OCT cancer imaging in cervical intraepithelial neoplasia, Barrett’s esophagus, ureter, etc. The work presented sought to determine the diagnostic efficacy of optical coherence tomography (OCT) to identify cervical intraepithelial neoplasia (CIN) grade 2 or higher by computer-aided diagnosis (CADx). An automated algorithm was developed to extract OCT image features and identify CIN 2 or higher. First, the cervical epithelium was detected by a combined watershed and active contour method. Second, four features were calculated: the thickness of epithelium and its standard deviation, and the contrast between epithelium and stroma and its standard deviation. Finally, linear discriminant analysis was applied to classify images into two categories: normal/inflammation/CIN 1 and CIN 2/CIN 3. The algorithm was applied to 152 images (74 patients) obtained from an international study. The numbers of normal/inflammatory/CIN 1/CIN 2/CIN 3 images are 74,29,14,24 and 11, respectively. Ten-fold cross-validation predicted the algorithm achieved a sensitivity of 51% (95% CI: 36%~67%) and a specificity of 92% (95% CI: 86% ~96%) with an empirical two-category prior probability estimated from the data set.  Receiver operating characteristic analysis yielded an area under the curve of 0.86. The diagnostic efficacy of CADx in OCT imaging to differentiate high grade CIN from normal/low grade CIN is demonstrated. The high specificity of OCT with CADx suggests further investigation as an effective secondary screening tool when combined with a highly sensitive primary screening tool.

     

    For more information see recent Article. Courtesy Wei Kang.

    Login to comment.

  1. Categories

    1. Applications:

      Art, Cardiology, Dentistry, Dermatology, Developmental Biology, Gastroenterology, Gynecology, Microscopy, NDE/NDT, Neurology, Oncology, Ophthalmology, Other Non-Medical, Otolaryngology, Pulmonology, Urology
    2. Business News:

      Acquisition, Clinical Trials, Funding, Other Business News, Partnership, Patents
    3. Technology:

      Broadband Sources, Probes, Tunable Sources
    4. Miscellaneous:

      Jobs & Studentships, Student Theses, Textbooks
  2. Topics Mentioned

  3. Authors