Skip to main content

2018 | OriginalPaper | Buchkapitel

Star Shape Prior in Fully Convolutional Networks for Skin Lesion Segmentation

verfasst von : Zahra Mirikharaji, Ghassan Hamarneh

Erschienen in: Medical Image Computing and Computer Assisted Intervention – MICCAI 2018

Verlag: Springer International Publishing

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

Semantic segmentation is an important preliminary step towards automatic medical image interpretation. Recently deep convolutional neural networks have become the first choice for the task of pixel-wise class prediction. While incorporating prior knowledge about the structure of target objects has proven effective in traditional energy-based segmentation approaches, there has not been a clear way for encoding prior knowledge into deep learning frameworks. In this work, we propose a new loss term that encodes the star shape prior into the loss function of an end-to-end trainable fully convolutional network (FCN) framework. We penalize non-star shape segments in FCN prediction maps to guarantee a global structure in segmentation results. Our experiments demonstrate the advantage of regularizing FCN parameters by the star shape prior and our results on the ISBI 2017 skin segmentation challenge data set achieve the first rank in the segmentation task among 21 participating teams.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literatur
4.
Zurück zum Zitat Bi, L., et al.: Automatic skin lesion analysis using large-scale dermoscopy images and deep residual networks. arXiv:1703.04197 (2017) Bi, L., et al.: Automatic skin lesion analysis using large-scale dermoscopy images and deep residual networks. arXiv:​1703.​04197 (2017)
5.
Zurück zum Zitat Chen, F., et al.: Deep learning shape priors for object segmentation. In: IEEE CVPR, pp. 1870–1877 (2013) Chen, F., et al.: Deep learning shape priors for object segmentation. In: IEEE CVPR, pp. 1870–1877 (2013)
6.
Zurück zum Zitat Chen, L.C., et al.: DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. arXiv:1606.00915 (2016) Chen, L.C., et al.: DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. arXiv:​1606.​00915 (2016)
7.
Zurück zum Zitat Chittajallu, D.R., et al.: A shape-driven MRF model for the segmentation of organs in medical images. In: IEEE CVPR, pp. 3233–3240 (2010) Chittajallu, D.R., et al.: A shape-driven MRF model for the segmentation of organs in medical images. In: IEEE CVPR, pp. 3233–3240 (2010)
8.
Zurück zum Zitat Codella, N.C.F., et al.: Skin lesion analysis toward melanoma detection: a challenge at the 2017 international symposium on biomedical imaging (ISBI), hosted by the international skin imaging collaboration (ISIC). arXiv:1710.05006 (2017) Codella, N.C.F., et al.: Skin lesion analysis toward melanoma detection: a challenge at the 2017 international symposium on biomedical imaging (ISBI), hosted by the international skin imaging collaboration (ISIC). arXiv:​1710.​05006 (2017)
9.
Zurück zum Zitat Cootes, T.F., et al.: Active appearance models. IEEE TPAMI 23(6), 681–685 (2001)CrossRef Cootes, T.F., et al.: Active appearance models. IEEE TPAMI 23(6), 681–685 (2001)CrossRef
10.
Zurück zum Zitat Cremers, D., et al.: A review of statistical approaches to level set segmentation: integrating color, texture, motion and shape. IJCV 72(2), 195–215 (2007)CrossRef Cremers, D., et al.: A review of statistical approaches to level set segmentation: integrating color, texture, motion and shape. IJCV 72(2), 195–215 (2007)CrossRef
11.
Zurück zum Zitat Freedman, D., Zhang, T.: Interactive graph cut based segmentation with shape priors. IEEE CVPR 1, 755–762 (2005) Freedman, D., Zhang, T.: Interactive graph cut based segmentation with shape priors. IEEE CVPR 1, 755–762 (2005)
12.
Zurück zum Zitat He, K., et al.: Deep residual learning for image recognition. In: IEEE CVPR, pp. 770–778 (2016) He, K., et al.: Deep residual learning for image recognition. In: IEEE CVPR, pp. 770–778 (2016)
13.
Zurück zum Zitat Kass, M., et al.: Snakes: active contour models. IJCV 1(4), 321–331 (1988)CrossRef Kass, M., et al.: Snakes: active contour models. IJCV 1(4), 321–331 (1988)CrossRef
14.
Zurück zum Zitat Long, J., et al.: Fully convolutional networks for semantic segmentation. In: IEEE CVPR, pp. 3431–3440 (2015) Long, J., et al.: Fully convolutional networks for semantic segmentation. In: IEEE CVPR, pp. 3431–3440 (2015)
15.
Zurück zum Zitat McInerney, T., Terzopoulos, D.: Deformable models in medical image analysis: a survey. MIA 1(2), 91–108 (1996) McInerney, T., Terzopoulos, D.: Deformable models in medical image analysis: a survey. MIA 1(2), 91–108 (1996)
16.
Zurück zum Zitat Nosrati, M.S., Hamarneh, G.: Segmentation of overlapping cervical cells: a variational method with star-shape prior. In: IEEE ISBI, pp. 186–189 (2015) Nosrati, M.S., Hamarneh, G.: Segmentation of overlapping cervical cells: a variational method with star-shape prior. In: IEEE ISBI, pp. 186–189 (2015)
17.
18.
Zurück zum Zitat Oktay, O., et al.: Anatomically constrained neural networks (ACNNs): application to cardiac image enhancement and segmentation. IEEE TMI 37(2), 384–395 (2018) Oktay, O., et al.: Anatomically constrained neural networks (ACNNs): application to cardiac image enhancement and segmentation. IEEE TMI 37(2), 384–395 (2018)
19.
Zurück zum Zitat Ravishankar, H., Venkataramani, R., Thiruvenkadam, S., Sudhakar, P., Vaidya, V.: Learning and incorporating shape models for semantic segmentation. In: Descoteaux, M., Maier-Hein, L., Franz, A., Jannin, P., Collins, D.L., Duchesne, S. (eds.) MICCAI 2017. LNCS, vol. 10433, pp. 203–211. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-66182-7_24CrossRef Ravishankar, H., Venkataramani, R., Thiruvenkadam, S., Sudhakar, P., Vaidya, V.: Learning and incorporating shape models for semantic segmentation. In: Descoteaux, M., Maier-Hein, L., Franz, A., Jannin, P., Collins, D.L., Duchesne, S. (eds.) MICCAI 2017. LNCS, vol. 10433, pp. 203–211. Springer, Cham (2017). https://​doi.​org/​10.​1007/​978-3-319-66182-7_​24CrossRef
22.
Zurück zum Zitat Vu, N., Manjunath, B.: Shape prior segmentation of multiple objects with graph cuts. In: IEEE CVPR, pp. 1–8 (2008) Vu, N., Manjunath, B.: Shape prior segmentation of multiple objects with graph cuts. In: IEEE CVPR, pp. 1–8 (2008)
25.
Zurück zum Zitat Yuan, J., et al.: An efficient convex optimization approach to 3D prostate MRI segmentation with generic star shape prior. In: PROMISE Challenge, MICCAI (2012) Yuan, J., et al.: An efficient convex optimization approach to 3D prostate MRI segmentation with generic star shape prior. In: PROMISE Challenge, MICCAI (2012)
26.
27.
Zurück zum Zitat Zheng, S., et al.: Conditional random fields as recurrent neural networks. In: ICCV, pp. 1529–1537 (2015) Zheng, S., et al.: Conditional random fields as recurrent neural networks. In: ICCV, pp. 1529–1537 (2015)
Metadaten
Titel
Star Shape Prior in Fully Convolutional Networks for Skin Lesion Segmentation
verfasst von
Zahra Mirikharaji
Ghassan Hamarneh
Copyright-Jahr
2018
DOI
https://doi.org/10.1007/978-3-030-00937-3_84