A unified set of analysis tools for uterine cervix image segmentation.

Segmentation is a fundamental component of many medical image-processing applications, and it has long been recognized as a challenging problem. In this paper, we report our research and development efforts on analyzing and extracting clinically meaningful regions from uterine cervix images in a large database created for the study of cervical cancer. In addition to proposing new algorithms, we also focus on developing open source tools which are in synchrony with the research objectives. These efforts have resulted in three Web-accessible tools which address three important and interrelated sub-topics in medical image segmentation, respectively: the Boundary Marking Tool (BMT), Cervigram Segmentation Tool (CST), and Multi-Observer Segmentation Evaluation System (MOSES). The BMT is for manual segmentation, typically to collect "ground truth" image regions from medical experts. The CST is for automatic segmentation, and MOSES is for segmentation evaluation. These tools are designed to be a unified set in which data can be conveniently exchanged. They have value not only for improving the reliability and accuracy of algorithms of uterine cervix image segmentation, but also promoting collaboration between biomedical experts and engineers which are crucial to medical image-processing applications. Although the CST is designed for the unique characteristics of cervigrams, the BMT and MOSES are very general and extensible, and can be easily adapted to other biomedical image collections.

SPIRS: a Web-based image retrieval system for large biomedical databases.

PURPOSE: With the increasing use of images in disease research, education, and clinical medicine, the need for methods that effectively archive, query, and retrieve these images by their content is underscored. This paper describes the implementation of a Web-based retrieval system called SPIRS (Spine Pathology & Image Retrieval System), which permits exploration of a large biomedical database of digitized spine X-ray images and data from a national health survey using a combination of visual and textual queries. METHODS: SPIRS is a generalizable framework that consists of four components: a client applet, a gateway, an indexing and retrieval system, and a database of images and associated text data. The prototype system is demonstrated using text and imaging data collected as part of the second U.S. National Health and Nutrition Examination Survey (NHANES II). Users search the image data by providing a sketch of the vertebral outline or selecting an example vertebral image and some relevant text parameters. Pertinent pathology on the image/sketch can be annotated and weighted to indicate importance. RESULTS: During the course of development, we explored different algorithms to perform functions such as segmentation, indexing, and retrieval. Each algorithm was tested individually and then implemented as part of SPIRS. To evaluate the overall system, we first tested the system's ability to return similar vertebral shapes from the database given a query shape. Initial evaluations using visual queries only (no text) have shown that the system achieves up to 68% accuracy in finding images in the database that exhibit similar abnormality type and severity. Relevance feedback mechanisms have been shown to increase accuracy by an additional 22% after three iterations. While we primarily demonstrate this system in the context of retrieving vertebral shape, our framework has also been adapted to search a collection of 100,000 uterine cervix images to study the progression of cervical cancer. CONCLUSIONS: SPIRS is automated, easily accessible, and integratable with other complementary information retrieval systems. The system supports the ability for users to intuitively query large amounts of imaging data by providing visual examples and text keywords and has beneficial implications in the areas of research, education, and patient care.

Age-related changes of the cervix influence human papillomavirus type distribution.

Approximately 15 human papillomavirus (HPV) types cause virtually all cervical cancer whereas other HPV types are unrelated to cancer. We were interested in whether some noncarcinogenic types differ from carcinogenic in their affinity for the cervical transformation zone, where nearly all HPV-induced cancers occur. To examine this possibility, we tested cervical specimens from 8,374 women without cervical precancer and cancer participating in a population-based study in Guanacaste for >40 HPV types using PCR. We compared age-group specific prevalences of HPV types of the alpha9 species, which are mainly carcinogenic and include HPV16, to the genetically distinct types of the alpha3/alpha15 species (e.g., HPV71), which are noncarcinogenic and common in vaginal specimens from hysterectomized women. We related HPV detection of each group to the location of the junction between the squamous epithelium of the ectocervix and vagina and the columnar epithelium of the endocervical canal. Models evaluated the independent effects of amount of exposed columnar epithelium (ectopy) and age on the presence of alpha9 or alpha3/alpha15 types. Prevalence of alpha9 types (7.6%) peaked in the youngest women, declined in middle-aged women, and then increased slightly in older women. By contrast, prevalence of alpha3/alpha15 types (7.6%) tended to remain invariant or to increase with increasing age. Detection of alpha9 infections increased (P(trend) < 0.0005) but alpha3/alpha15 infections decreased (P(trend) < 0.0005) with increasing exposure of the columnar epithelia. Older age and decreasing cervical ectopy were independently positively associated with having an alpha3/alpha15 infection compared with having an alpha9 infection. These patterns need to be confirmed in other studies and populations. We suggest that these genetically distinct groups of HPV types may differ in tissue preferences, which may contribute to their differences in carcinogenic potential.

Digital tools for collecting data from cervigrams for research and training in colposcopy.

Colposcopy is a critical part of gynecologic practice but has documented deficiencies, including lack of correlation between the colposcopic appearance and the severity of underlying neoplasia, limited reproducibility, and difficulty in the optimal placement of colposcopically directed biopsies. In a collaborative effort to improve colposcopy, we are analyzing digitized cervigram images from National Cancer Institute-funded studies. Specifically, the National Cancer Institute has collected close to 100,000 cervigrams, digitized to create a database of images of the uterine cervix for research, training, and education. In addition to the cervigram images, this database contains clinical, cytologic, and molecular information at multiple examinations of 15,000 women, with password and ID labeling strategies to protect patient privacy. The National Library of Medicine has designed two web-accessible software tools. The Boundary Marking Tool allows experts on colposcopy to perform an evaluation of the pictures and to mark boundary regions of normal and abnormal regions of the uterine cervix; these evaluations are collected and saved in the database. The Multimedia Database Tool enables retrieval of test and image biomedical data according to specific queries, for example, all women with cervical intraepithelial neoplasia 3 whose cytologic results are atypical squamous cells of undetermined significance. The resource soon will be available as an open resource, via a teaching tool coordinated by a database manager, which will permit a variety of applications for teaching and research. In this article, we describe the perceived need for the resource and its components.

Preparing digitized cervigrams for colposcopy research and education: determination of optimal resolution and compression parameters.

OBJECTIVE: Visual assessment of digitized cervigrams through the Internet needs to be optimized. The National Cancer Institute and National Library of Medicine are involved in a large effort to improve colposcopic assessment and, in preparation, are conducting methodologic research. MATERIALS AND METHODS: We selected 50 cervigrams with diagnoses ranging from normal to cervical intraepithelial neoplasia 3 or invasive cancer. Those pictures were scanned at 5 resolution levels from 1,550 to 4,000 dots per inch (dpi) and were presented to 4 expert colposcopists to assess image quality. After the ideal resolution level was determined, pictures were compressed at 7 compression ratios from 20:1 to 80:1 to determine the optimal level of compression that permitted full assessment of key visual details. RESULTS: There were no statistically significant differences between the 3,000 and 4,000 dpi pictures. At 2,000 dpi resolution, only one colposcopist found a slightly statistically significant difference (p = 0.02) compared with the gold standard. There was a clear loss of quality of the pictures at 1,660 dpi. At compression ratio 60:1, 3 of 4 evaluators found statistically significant differences when comparing against the gold standard. CONCLUSIONS: Our results suggest that 2,000 dpi is the optimal level for digitizing cervigrams, and the optimal compression ratio is 50:1 using a novel wavelet-based technology. At these parameters, pictures have no significant differences with the gold standard.