Dr. Héctor Gabriel Acosta Mesa
Colposcopic Sequences Data Set
Cervical cancer is the first cause of death in Mexican women. After Pap smear test, colposcopy is the most used technique to diagnose this disease. Although some approaches have been proposed to analyze colposcopic images using digital image processing, as far as we known, none of them has established a complete methodology to acquire and analyze colposcopic sequences in order to automatically segment the image.
In this small repository, we make available data from ten women with abnormal Papanicolaou, ages ranging from 22 to 35 years are included. All of them gave informed written consent. Before colposcopy, the cervical mucus was cleaned using a cotton-wool swabs. The colposcopic tests were made spreading three milliliters of acetic acid (3%) over the cervix using a needle for fast application. A cotton-wool was put in the low part of the cervix to absorb the remaining acetic acid that drops after the application.
Images were acquired using a colposcope dfv Vasconsellos model CP-M7 with magnification 16 X without any optical filter. The viewing distance was 20 cm. and the field of view covers approximately a circle of 13 mm ratio. Images were acquired using a color camera Sony SSC-DC50A and a frame grabber Matrox Meteor-II/Standard. During the first ten seconds of the image acquisition 10 images (352x240) were taken as base line reference (1 frame/second), then after acetic acid application, three hundred images were taken in 5 minutes using the same sampling frequency. Each image was saved independently as a BMP file.
We hope this data could be used to develop and test algorithms to process colposcopic sequences
|
 |
 |
 |
 |
Subject 1 |
Subject 2 |
Subject 3 |
Subject 5 |
|
 |
 |
 |
 |
 |
Subject 6 |
Subject 7 |
Subject 8 |
Subject 9 |
Subject 10 |
Acknowledgement
This data resource was funded by the Mexican National Council for Science and Technology for the economic support of this project under the research grant: Fondo Sectorial de Investigación en Salud y Seguridad Social SSA/IMSS/ISSSTE-CONACYT (Salud-2003-C01-06).
Note: If you use the data in any publications please cite the following reference:
Acosta-Mesa Hector-Gabriel, Cruz-ramírez Nicandro, Hernandez-Jimenez Rodolfo, Aceto-White Temporal Pattern Classification using k-NN to Identify Precancerous Cervical Lesion in Colposcopic Images. Computers in Biology and Medicine. Elsevier, 2009. 39: p. 778-784.