Skip to main content
Top
Published in: International Journal of Computer Assisted Radiology and Surgery 6/2017

01-06-2017 | Original Article

SLIM (slit lamp image mosaicing): handling reflection artifacts

Authors: Kristina Prokopetc, Adrien Bartoli

Published in: International Journal of Computer Assisted Radiology and Surgery | Issue 6/2017

Login to get access

Abstract

Purpose

The slit lamp is an essential instrument for eye care. It is used in navigated laser treatment with retina mosaicing to assist diagnosis. Specifics of the imaging setup introduce bothersome illumination artifacts. They not only degrade the quality of the mosaic but may also affect the diagnosis. Existing solutions in SLIM manage to deal with strong glares which corrupt the retinal content entirely while leaving aside the correction of semitransparent specular highlights and lens flare. This introduces ghosting and information loss.

Methods

We propose an effective technique to detect and correct light reflections of different degrees in SLIM. We rely on the specular-free image concept to obtain glare-free image and use it coupled with a contextually driven probability map to segment the visible part of the retina in every frame before image mosaicing. We then perform the image blending on a subset of all spatially aligned frames. We detect the lens flare and label each pixel as ‘flare’ or ‘non flare’ using a probability map. We then invoke an adequate blending method. We also introduce a new quantitative measure for global photometric quality.

Results

We tested on a set of video sequences obtained from slit lamp examination sessions of 11 different patients presenting healthy and unhealthy retinas. The segmentation of glare and visible retina was evaluated and compared to state-of-the-art methods. The correction of lens flare and semitransparent highlight with content-aware blending was applied and its performance was evaluated qualitatively and quantitatively.

Conclusion

The experiments demonstrated that integrating the proposed method to the mosaicing framework significantly improves the global photometric quality of the mosaics and outperforms existing works in SLIM.
Literature
1.
go back to reference Allan M, Ourselin S, Thompson S, Hawkes DJ, Kelly J, Stoyanov D (2013) Toward detection and localization of instruments in minimally invasive surgery. IEEE Trans Biomed Eng 60(4):1050–1058CrossRefPubMed Allan M, Ourselin S, Thompson S, Hawkes DJ, Kelly J, Stoyanov D (2013) Toward detection and localization of instruments in minimally invasive surgery. IEEE Trans Biomed Eng 60(4):1050–1058CrossRefPubMed
2.
3.
go back to reference Boykov Y, Jolly MP (2000) Interactive organ segmentation using graph cuts. In: International conference on medical image computing and computer-assisted intervention, pp 276–286. Springer Boykov Y, Jolly MP (2000) Interactive organ segmentation using graph cuts. In: International conference on medical image computing and computer-assisted intervention, pp 276–286. Springer
4.
go back to reference Chhatkuli A, Bartoli A, Malti A, Collins T. (2014) Live image parsing in uterine laparoscopy. In: 2014 IEEE 11th international symposium on biomedical imaging (ISBI), pp 1263–1266. IEEE Chhatkuli A, Bartoli A, Malti A, Collins T. (2014) Live image parsing in uterine laparoscopy. In: 2014 IEEE 11th international symposium on biomedical imaging (ISBI), pp 1263–1266. IEEE
5.
go back to reference Kim H, Jin H, Hadap S, Kweon I. (2013) Specular reflection separation using dark channel prior. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1460–1467 Kim H, Jin H, Hadap S, Kweon I. (2013) Specular reflection separation using dark channel prior. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1460–1467
6.
go back to reference Lange H (2005) Automatic glare removal in reflectance imagery of the uterine cervix. In: Medical Imaging, pp 2183–2192. International Society for Optics and Photonics Lange H (2005) Automatic glare removal in reflectance imagery of the uterine cervix. In: Medical Imaging, pp 2183–2192. International Society for Optics and Photonics
7.
go back to reference Nussberger A, Grabner H, Van Gool L (2015) Robust aerial object tracking in images with lens flare. In: 2015 IEEE international conference on robotics and automation, pp 6380–6387. IEEE Nussberger A, Grabner H, Van Gool L (2015) Robust aerial object tracking in images with lens flare. In: 2015 IEEE international conference on robotics and automation, pp 6380–6387. IEEE
8.
go back to reference Prokopetc K, Bartoli A (2016) A comparative study of transformation models for the sequential mosaicing of long retinal sequences of slit-lamp images obtained in a closed-loop motion. Int J Comput Assis Radiol Surg 1–10 Prokopetc K, Bartoli A (2016) A comparative study of transformation models for the sequential mosaicing of long retinal sequences of slit-lamp images obtained in a closed-loop motion. Int J Comput Assis Radiol Surg 1–10
9.
go back to reference Prokopetc K, Bartoli A (2016) Reducing drift in mosaicing slit-lamp retinal images. In: The IEEE conference on computer vision and pattern recognition (CVPR) workshops, pp 93–100. IEEE Prokopetc K, Bartoli A (2016) Reducing drift in mosaicing slit-lamp retinal images. In: The IEEE conference on computer vision and pattern recognition (CVPR) workshops, pp 93–100. IEEE
10.
go back to reference Prokopetc K, Collins T, Bartoli A (2015) Automatic detection of the uterus and fallopian tube junctions in laparoscopic images. In: International conference on information processing in medical imaging, pp 552–563. Springer Prokopetc K, Collins T, Bartoli A (2015) Automatic detection of the uterus and fallopian tube junctions in laparoscopic images. In: International conference on information processing in medical imaging, pp 552–563. Springer
11.
go back to reference Reinhard E, Stark M, Shirley P, Ferwerda J (2002) Photographic tone reproduction for digital images. ACM Trans Gr 21(3):267–276CrossRef Reinhard E, Stark M, Shirley P, Ferwerda J (2002) Photographic tone reproduction for digital images. ACM Trans Gr 21(3):267–276CrossRef
12.
go back to reference Richa R, Linhares R, Comunello E, von Wangenheim A, Schnitzler JY, Wassmer B, Guillemot C, Thuret G, Gain P, Hager G et al (2014) Fundus image mosaicking for information augmentation in computer-assisted slit-lamp imaging. IEEE Trans Med Imaging 33(6):1304–1312CrossRefPubMed Richa R, Linhares R, Comunello E, von Wangenheim A, Schnitzler JY, Wassmer B, Guillemot C, Thuret G, Gain P, Hager G et al (2014) Fundus image mosaicking for information augmentation in computer-assisted slit-lamp imaging. IEEE Trans Med Imaging 33(6):1304–1312CrossRefPubMed
13.
go back to reference Saint-Pierre CA, Boisvert J, Grimard G, Cheriet F (2011) Detection and correction of specular reflections for automatic surgical tool segmentation in thoracoscopic images. Mach Vision Appl 22(1):171–180CrossRef Saint-Pierre CA, Boisvert J, Grimard G, Cheriet F (2011) Detection and correction of specular reflections for automatic surgical tool segmentation in thoracoscopic images. Mach Vision Appl 22(1):171–180CrossRef
14.
go back to reference Shen HL, Zhang HG, Shao SJ, Xin JH (2008) Chromaticity-based separation of reflection components in a single image. Pattern Recognit 41(8):2461–2469CrossRef Shen HL, Zhang HG, Shao SJ, Xin JH (2008) Chromaticity-based separation of reflection components in a single image. Pattern Recognit 41(8):2461–2469CrossRef
15.
go back to reference Sun C, Liu S, Yang T, Zeng B, Wang Z, Liu G (2016) Automatic reflection removal using gradient intensity and motion cues. In: Proceedings of the ACM on multimedia conference, pp 466–470. ACM Sun C, Liu S, Yang T, Zeng B, Wang Z, Liu G (2016) Automatic reflection removal using gradient intensity and motion cues. In: Proceedings of the ACM on multimedia conference, pp 466–470. ACM
16.
go back to reference Tan RT, Ikeuchi K (2005) Separating reflection components of textured surfaces using a single image. IEEE Trans Pattern Anal Mach Intell 27(2):178–193CrossRefPubMed Tan RT, Ikeuchi K (2005) Separating reflection components of textured surfaces using a single image. IEEE Trans Pattern Anal Mach Intell 27(2):178–193CrossRefPubMed
17.
go back to reference Xu C, Wang X, Wang H, Zhang Y (2015) Accurate image specular highlight removal based on light field imaging. In: Visual Communications and Image Processing, pp. 1–4. IEEE Xu C, Wang X, Wang H, Zhang Y (2015) Accurate image specular highlight removal based on light field imaging. In: Visual Communications and Image Processing, pp. 1–4. IEEE
18.
go back to reference Yang Q, Wang S, Ahuja N (2010) Real-time specular highlight removal using bilateral filtering. In: European conference on computer vision, pp 87–100. Springer Yang Q, Wang S, Ahuja N (2010) Real-time specular highlight removal using bilateral filtering. In: European conference on computer vision, pp 87–100. Springer
19.
go back to reference Yang Q, Wang S, Ahuja N, Yang R (2011) A uniform framework for estimating illumination chromaticity, correspondence, and specular reflection. IEEE Trans Image Process 20(1):53–63CrossRefPubMed Yang Q, Wang S, Ahuja N, Yang R (2011) A uniform framework for estimating illumination chromaticity, correspondence, and specular reflection. IEEE Trans Image Process 20(1):53–63CrossRefPubMed
20.
go back to reference Zanet S, Rudolph T, Richa R, Tappeiner C, Sznitman R (2016) Retinal slit lamp video mosaicking. Int J Comput Assist Radiol Surg 1–7 Zanet S, Rudolph T, Richa R, Tappeiner C, Sznitman R (2016) Retinal slit lamp video mosaicking. Int J Comput Assist Radiol Surg 1–7
Metadata
Title
SLIM (slit lamp image mosaicing): handling reflection artifacts
Authors
Kristina Prokopetc
Adrien Bartoli
Publication date
01-06-2017
Publisher
Springer International Publishing
Published in
International Journal of Computer Assisted Radiology and Surgery / Issue 6/2017
Print ISSN: 1861-6410
Electronic ISSN: 1861-6429
DOI
https://doi.org/10.1007/s11548-017-1555-z

Other articles of this Issue 6/2017

International Journal of Computer Assisted Radiology and Surgery 6/2017 Go to the issue