nach oben

International Journal of Computer Assisted Radiology and Surgery

Erschienen in:

04.06.2019 | Original Article

EasyLabels: weak labels for scene segmentation in laparoscopic videos

verfasst von: Félix Fuentes-Hurtado, Abdolrahim Kadkhodamohammadi, Evangello Flouty, Santiago Barbarisi, Imanol Luengo, Danail Stoyanov

Erschienen in: International Journal of Computer Assisted Radiology and Surgery | Ausgabe 7/2019

Einloggen, um Zugang zu erhalten

Abstract

Purpose

We present a different approach for annotating laparoscopic images for segmentation in a weak fashion and experimentally prove that its accuracy when trained with partial cross-entropy is close to that obtained with fully supervised approaches.

Methods

We propose an approach that relies on weak annotations provided as stripes over the different objects in the image and partial cross-entropy as the loss function of a fully convolutional neural network to obtain a dense pixel-level prediction map.

Results

We validate our method on three different datasets, providing qualitative results for all of them and quantitative results for two of them. The experiments show that our approach is able to obtain at least \(90\%\) of the accuracy obtained with fully supervised methods for all the tested datasets, while requiring \(\sim 13\)\(\times \) less time to create the annotations compared to full supervision.

Conclusions

With this work, we demonstrate that laparoscopic data can be segmented using very few annotated data while maintaining levels of accuracy comparable to those obtained with full supervision.

Nur mit Berechtigung zugänglich

For simplicity, even if there are approaches either using points, bounding boxes or scribbles, we will refer to this approach as just “scribbles.”

Please note that the skeleton is computed as the ridge of the distance transform.

Bearman A, Russakovsky O, Ferrari V, Fei-Fei L (2016) What’s the point: semantic segmentation with point supervision. In: European conference on computer vision. Springer, pp 549–565

Bodenstedt S, Allan M, Agustinos A, Du X, Garcia-Peraza-Herrera L, Kenngott H, Kurmann T, Müller-Stich B, Ourselin S, Pakhomov D, Sznitman R, Teichmann M, Thoma M, Vercauteren T, Voros S, Wagner M, Wochner P, Maier-Hein L, Stoyanov D, Speidel S. (2018) Comparative evaluation of instrument segmentation and tracking methods in minimally invasive surgery. arXiv preprint arXiv:1805.02475

Bodenstedt S, Ohnemus A, Katic D, Wekerle AL, Wagner M, Kenngott H, Müller-Stich B, Dillmann R, Speidel S. (2018) Real-time image-based instrument classification for laparoscopic surgery. arXiv preprint arXiv:1808.00178

Bouget D, Allan M, Stoyanov D, Jannin P (2017) Vision-based and marker-less surgical tool detection and tracking: a review of the literature. Med Image Anal 35:633–654CrossRefPubMed

Chen LC, Zhu Y, Papandreou G, Schroff F, Adam H (2018) Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Proceedings of the European conference on computer vision (ECCV), pp 801–818

Chollet F (2017) Xception: Deep learning with depthwise separable convolutions. In: The IEEE conference on computer vision and pattern recognition (CVPR)

Gao M, Xu Z, Lu L, Wu A, Nogues I, Summers RM, Mollura DJ (2016) Segmentation label propagation using deep convolutional neural networks and dense conditional random field. In: 2016 IEEE 13th international symposium on biomedical imaging (ISBI). IEEE, pp 1265–1268

García-Peraza-Herrera LC, Li W, Fidon L, Gruijthuijsen C, Devreker A, Attilakos G, Deprest J, Vander Poorten E, Stoyanov D, Vercauteren T, Ourselin S (2017) Toolnet: holistically-nested real-time segmentation of robotic surgical tools. In: 2017 IEEE/RSJ international conference on intelligent robots and systems (IROS). IEEE, pp 5717–5722

García-Peraza-Herrera LC, Li W, Gruijthuijsen C, Devreker A, Attilakos G, Deprest J, Vander Poorten E, Stoyanov D, Vercauteren T, Ourselin S (2016) Real-time segmentation of non-rigid surgical tools based on deep learning and tracking. In: International workshop on computer-assisted and robotic endoscopy. Springer, pp 84–95

10.

Laina I, Rieke N, Rupprecht C, Vizcaíno JP, Eslami A, Tombari F, Navab N (2017) Concurrent segmentation and localization for tracking of surgical instruments. In: International conference on medical image computing and computer-assisted intervention. Springer, pp 664–672

11.

Lejeune L, Grossrieder J, Sznitman R (2018) Iterative multi-path tracking for video and volume segmentation with sparse point supervision. Med Image Anal 50:65–81CrossRefPubMed

12.

Lin D, Dai J, Jia J, He K, Sun J (2016) Scribblesup: scribble-supervised convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3159–3167

13.

Maier-Hein L, Ross T, Gröhl J, Glocker B, Bodenstedt S, Stock C, Heim E, Götz M, Wirkert S, Kenngott H, Speidel S, Maier-Hein K (2016) Crowd-algorithm collaboration for large-scale endoscopic image annotation with confidence. In: International conference on medical image computing and computer-assisted intervention. Springer, pp 616–623

14.

MICCAI 2015: Endovis 2015 instrument segmentation and tracking. https://endovissub-instrument.grand-challenge.org (2015). [Online; Accessed 6-Nov-2018]

15.

Pakhomov D, Premachandran V, Allan M, Azizian M, Navab N (2017) Deep residual learning for instrument segmentation in robotic surgery. arXiv preprint arXiv:1703.08580

16.

Ross T, Zimmerer D, Vemuri A, Isensee F, Wiesenfarth M, Bodenstedt S, Both F, Kessler P, Wagner M, Müller B, Kengott H, Speidel S, Kop-Schneider A, Maier-Hein K, Maier-Hein L (2018) Exploiting the potential of unlabeled endoscopic video data with self-supervised learning. Int J Comput Assist Radiol Surg 13:1–9CrossRef

17.

Schoeffmann K, Husslein H, Kletz S, Petscharnig S, Muenzer B, Beecks C (2017) Video retrieval in laparoscopic video recordings with dynamic content descriptors. Multimed Tools Appl 77:16813–16832. https://doi.org/10.1007/s11042-017-5252-2 CrossRef

18.

Shvets A, Rakhlin A, Kalinin AA, Iglovikov V (2018) Automatic instrument segmentation in robot-assisted surgery using deep learning. arXiv preprint arXiv:1803.01207

19.

Stoyanov D (2012) Surgical vision. Ann Biomed Eng 40(2):332–345CrossRefPubMed

20.

Tang M, Djelouah A, Perazzi F, Boykov Y, Schroers C (2018) Normalized cut loss for weakly-supervised cnn segmentation. In: IEEE conference on computer vision and pattern recognition (CVPR), Salt Lake City

21.

Tang P, Wang X, Wang A, Yan Y, Liu W, Huang J, Yuille A (2018) Weakly supervised region proposal network and object detection. In: Proceedings of the European conference on computer vision (ECCV), pp 352–368

22.

Vardazaryan A, Mutter D, Marescaux J, Padoy N (2018) Weakly-supervised learning for tool localization in laparoscopic videos. In: Stoyanov D et al (eds) Intravascular imaging and computer assisted stenting and large-scale annotation of biomedical data and expert label synthesis. LABELS 2018, CVII 2018, STENT 2018. Lecture Notes in Computer Science, vol 11043. Springer, Cham, pp 169–179

23.

Wang X, You S, Li X, Ma H (2018) Weakly-supervised semantic segmentation by iteratively mining common object features. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1354–1362

24.

Zhao X, Liang S, Wei Y (2018) Pseudo mask augmented object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4061–4070

Titel: EasyLabels: weak labels for scene segmentation in laparoscopic videos
verfasst von: Félix Fuentes-Hurtado
Abdolrahim Kadkhodamohammadi
Evangello Flouty
Santiago Barbarisi
Imanol Luengo
Danail Stoyanov
Publikationsdatum: 04.06.2019
Verlag: Springer International Publishing
Erschienen in: International Journal of Computer Assisted Radiology and Surgery / Ausgabe 7/2019
Print ISSN: 1861-6410
Elektronische ISSN: 1861-6429
DOI: https://doi.org/10.1007/s11548-019-02003-2

Neu im Fachgebiet Radiologie

18.04.2024 | Pädiatrische Notfallmedizin | Nachrichten

Update Radiologie

Bestellen Sie unseren Fach-Newsletter und bleiben Sie gut informiert.

Newsletter bestellen

Springer Medizin

EasyLabels: weak labels for scene segmentation in laparoscopic videos

Abstract

Purpose

Methods

Results

Conclusions

Neu im Fachgebiet Radiologie

Fünf Dinge, die im Kindernotfall besser zu unterlassen sind

„Nur wer sich gut aufgehoben fühlt, kann auch für Patientensicherheit sorgen“

Wie toxische Männlichkeit der Gesundheit von Männern schadet

Studie bestätigt Potenzial von KI in der Radiologie

Update Radiologie

Springer Medizin

Abstract

Purpose

Methods

Results

Conclusions

Bitte loggen Sie sich ein, um Zugang zu diesem Inhalt zu erhalten

Weitere Artikel der Ausgabe 7/2019

A “pickup” stereoscopic camera with visual-motor aligned control for the da Vinci surgical system: a preliminary study

Flexible and comprehensive patient-specific mitral valve silicone models with chordae tendineae made from 3D-printable molds

Extending pretrained segmentation networks with additional anatomical structures

An in vivo porcine dataset and evaluation methodology to measure soft-body laparoscopic liver registration accuracy with an extended algorithm that handles collisions

Learning soft tissue behavior of organs for surgical navigation with convolutional neural networks

Implicit domain adaptation with conditional generative adversarial networks for depth prediction in endoscopy

Neu im Fachgebiet Radiologie

Fünf Dinge, die im Kindernotfall besser zu unterlassen sind

„Nur wer sich gut aufgehoben fühlt, kann auch für Patientensicherheit sorgen“

Wie toxische Männlichkeit der Gesundheit von Männern schadet

Studie bestätigt Potenzial von KI in der Radiologie

Update Radiologie