PREDICTING THE LOCATION OF THE UTERINE CERVICAL OS FROM 2D IMAGES WITH CNN
Year 2020,
Volume: 8 Issue: 5, 52 - 57, 29.12.2020
Taner Danışman
,
Yiğit Ali Üncü
,
Deniz Karaçaylı
Uğur Bilge
Özer Birge
,
Mehmet Bakır
,
Mehmet Göksu
,
Tayup Şimşek
Murat Canpolat
Abstract
In an automated cervical cancer test, the prediction of the location of the cervical os from 2D images is required. Cervical os is the reference point to determine the lesion's location by either using cervical four-quadrant location or by 12 o’clock locations. Precise detection of the cervical os point ensures correct addressing of the lesions. This study used a 6-layer convolutional neural network to predict the center of the cervical os’ coordinates (x,y) on 2D grayscale images. We used a holistic approach without masking any visual element to predict the location of the cervical os. The 2D images were obtained using a telecentric lens and a CCD camera with light wavelengths of 500 550 nanometers. Because of the limited number of image samples (145 images), we used augmentation techniques to increase the training set size by rotating each original image in 1-degree increments from -30 degrees to +30 degrees relative to the center of the image. The 6-layer convolutional neural network was tested on 21 unseen cervix images using augmentation data. The outcomes showed that the image center-based augmentation technique improves the prediction performance. We obtained 2.4 RMSE in predicting the location of the cervical os.
Supporting Institution
Scientific and Technological Research Council of Turkey
Thanks
This study was supported by the Scientific and Technological Research Council of Turkey (TÜBİTAK) with Grant No: 116S349.
References
- Das, A., Kar, A., Bhattacharyya, D., 2011. Elimination of specular reflection and identification of ROI: The first step in automated detection of Cervical Cancer using Digital Colposcopy. In: 2011 IEEE International Conference on Imaging Systems and Techniques. pp. 237–241.
- Greenspan, H., Gordon, S., Zimmerman, G., Lotenberg, S., Jeronimo, J., Antani, S., Long, R., 2009. Automatic Detection of Anatomical Landmarks in Uterine Cervix Images. IEEE Transactions on Medical Imaging. 28, 454–468.
- Guo, P., Xue, Z., Long, L.R., Antani, S.K., 2020. Anatomical landmark segmentation in uterine cervix images using deep learning. In: Chen, P.-H., Deserno, T.M. (Eds.), Medical Imaging 2020: Imaging Informatics for Healthcare, Research, and Applications. SPIE, pp. 258–267.
- Kudva, V., Prasad, K., Guruvare, S., 2017. Detection of Specular Reflection and Segmentation of Cervix Region in Uterine Cervix Images for Cervical Cancer Screening. IRBM. 38, 281–291.
- Lange, H., 2005. Automatic glare removal in reflectance imagery of the uterine cervix. In: Fitzpatrick, J.M., Reinhardt, J.M. (Eds.), Medical Imaging 2005: Image Processing, Society of Photo-Optical Instrumentation Engineers (SPIE) Conference Series. pp. 2183–2192.
- Liu, J., Li, L., Wang, L., 2018. Acetowhite region segmentation in uterine cervix images using a registered ratio image. Computers in Biology and Medicine. 93, 47–55.
- Patil, D.B., Gaikwad, M.S., Singh, D.K., Vishwanath, T.S., 2016. Semi-automated lession grading in cervix images with Specular Reflection removal. In: 2016 International Conference on Inventive Computation Technologies (ICICT). pp. 1–5.
- Xue, Z., Antani, S., Long, L.R., M.D., J.J., Thoma, G.R., 2007. Comparative performance analysis of cervix ROI extraction and specular reflection removal algorithms for uterine cervix image analysis. In: Pluim, J.P.W., Reinhardt, J.M. (Eds.), Medical Imaging 2007: Image Processing. SPIE, pp. 1507–1515.
CNN İLE 2B GÖRÜNTÜLERDEN SERVİKAL OS KONUMUNU TAHMİN ETME
Year 2020,
Volume: 8 Issue: 5, 52 - 57, 29.12.2020
Taner Danışman
,
Yiğit Ali Üncü
,
Deniz Karaçaylı
Uğur Bilge
Özer Birge
,
Mehmet Bakır
,
Mehmet Göksu
,
Tayup Şimşek
Murat Canpolat
Abstract
Otomatik bir rahim ağzı kanseri testinde, 2 boyutlu görüntülerden rahim ağzının yerinin tahmin edilmesi gerekir. Servikal os, dört kadran konumu gösteriminde veya 12 saatlik dilimler halindeki gösterimde her bir konumun yerini belirlemek için referans noktası olarak kullanılmaktadır. Servikal os noktasının hassas tespiti lezyonların doğru adreslenmesini sağlar. Bu çalışmada, 2 boyutlu gri tonlamalı görüntülerde servikal os koordinatının (x, y) merkezini tahmin etmek için 6 katmanlı bir evrişimli sinir ağı kullanılmıştır. Servikal os'un yerini tahmin etmek için herhangi bir görsel unsuru maskelemeden bütünsel bir yaklaşım kullandık. Çalışmada kullanılan iki boyutlu görüntüler, bir telesentrik lens ve 500-550 nanometre ışık dalga boylarına sahip bir CCD kamera kullanılarak elde edildi. Sınırlı sayıda örnek görüntü (145 görüntü) nedeniyle veri, büyütme tekniklerinden faydalanılarak her bir orijinal görüntü, görüntünün merkez noktasına göre -30 dereceden +30 dereceye kadar 1 derecelik artan açılar ile döndürüldü. Bu veriler üzerinden öğrenme yapan 6 katmanlı evrişimli sinir ağı, daha önce görülmeyen 21 serviks görüntüsü üzerinde test edildi. Sonuçlar, kullanılan görüntü merkezi tabanlı büyütme tekniğinin tahmin performansını iyileştirdiğini gösterdi. Servikal os lokasyonunun tahmininde 2.4 RMSE değeri elde edildi.
References
- Das, A., Kar, A., Bhattacharyya, D., 2011. Elimination of specular reflection and identification of ROI: The first step in automated detection of Cervical Cancer using Digital Colposcopy. In: 2011 IEEE International Conference on Imaging Systems and Techniques. pp. 237–241.
- Greenspan, H., Gordon, S., Zimmerman, G., Lotenberg, S., Jeronimo, J., Antani, S., Long, R., 2009. Automatic Detection of Anatomical Landmarks in Uterine Cervix Images. IEEE Transactions on Medical Imaging. 28, 454–468.
- Guo, P., Xue, Z., Long, L.R., Antani, S.K., 2020. Anatomical landmark segmentation in uterine cervix images using deep learning. In: Chen, P.-H., Deserno, T.M. (Eds.), Medical Imaging 2020: Imaging Informatics for Healthcare, Research, and Applications. SPIE, pp. 258–267.
- Kudva, V., Prasad, K., Guruvare, S., 2017. Detection of Specular Reflection and Segmentation of Cervix Region in Uterine Cervix Images for Cervical Cancer Screening. IRBM. 38, 281–291.
- Lange, H., 2005. Automatic glare removal in reflectance imagery of the uterine cervix. In: Fitzpatrick, J.M., Reinhardt, J.M. (Eds.), Medical Imaging 2005: Image Processing, Society of Photo-Optical Instrumentation Engineers (SPIE) Conference Series. pp. 2183–2192.
- Liu, J., Li, L., Wang, L., 2018. Acetowhite region segmentation in uterine cervix images using a registered ratio image. Computers in Biology and Medicine. 93, 47–55.
- Patil, D.B., Gaikwad, M.S., Singh, D.K., Vishwanath, T.S., 2016. Semi-automated lession grading in cervix images with Specular Reflection removal. In: 2016 International Conference on Inventive Computation Technologies (ICICT). pp. 1–5.
- Xue, Z., Antani, S., Long, L.R., M.D., J.J., Thoma, G.R., 2007. Comparative performance analysis of cervix ROI extraction and specular reflection removal algorithms for uterine cervix image analysis. In: Pluim, J.P.W., Reinhardt, J.M. (Eds.), Medical Imaging 2007: Image Processing. SPIE, pp. 1507–1515.