Skip to main content
Springer Nature Link
Log in

A Self-supervised Deep Learning Model for Diagonal Sulcus Detection with Limited Labeled Data

  • Research
  • Published:
Neuroinformatics Aims and scope Submit manuscript

Abstract

Sulci are a fundamental part of brain morphology, closely linked to brain function, cognition, and behavior. Tertiary sulci, characterized as the shallowest and smallest subtype, pose a challenging task for detection. The diagonal sulcus (ds), located in a crucial area in language processing, has a prevalence between 50% and 60%. Automatic detection of the ds is an unexplored field: while some sulci segmenters include the ds, their accuracy is usually low. In this work, we present a deep learning based model for ds detection using a fine-tuning approach with limited training labeled data. A convolutional autoencoder was employed to learn specific features related to brain morphology with unlabeled data through self-supervised learning. Subsequently, the pre-trained network was fine-tuned to detect the ds using a less extensive labeled dataset. We achieved a mean F1-score of 0.7176 (SD=0.0736) for the test set and a F1-score of 0.72 for a second held-out set, surpassing the results of a standard software and other alternative deep learning models. We conducted an interpretability analysis of the results using occlusion maps and observed that the models focused on adjacent sulci to the ds for prediction, consistent with the approach taken by experts in manual annotation. We also analyzed the challenges of manual labeling by conducting a thorough examination of interrater agreement on a small dataset and its relationship with our model’s performance. Finally, we applied our method on a population analysis and reported the prevalence of ds in a case study.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11

Data Availability

Data used in this article comprises MRI images taken from various public datasets and an in-house dataset. The IXI dataset is available at http://braindevelopment.org/ixi-dataset, the ADNI dataset is available at http://adni.loni.usc.edu/, and the OASIS dataset is available at https://www.oasisbrains.org/. The private data (HEC-HR dataset) used in this study is not publicly available to protect patient privacy.

Code Availability

Code is available on GitHub at https://github.com/hkulsgaard/sulcus.

Notes

  1. https://adni.loni.usc.edu

  2. https://www.oasis-brains.org/

  3. https://brain-development.org/ixi-dataset/

References

  • Akula, S. K., Exposito-Alonso, D., & Walsh, C. A. (2023). Shaping the brain: The emergence of cortical structure andfolding. Developmental Cell, 58(24), 2836–2849.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  • Amiez, C., & Petrides, M. (2018). Functional rostro-caudal gradient in the human posterior lateral frontal cortex. Brain Structure and Function, 223(3), 1487–1499.

    PubMed  Google Scholar 

  • Borne, L., Rivière, D., Mancip, M., & Mangin, J.-F. (2020). Automatic labeling of cortical sulci using patch-or cnn-based segmentation techniques combined with bottom-up geometric constraints. Medical Image Analysis, 62, 101651.

    Article  PubMed  Google Scholar 

  • Chen, S., Ma, K., & Zheng, Y. (2019). Med3d: Transfer learning for 3d medical image analysis. arXiv preprint arXiv:1904.00625

  • Cointepas, Y., Mangin, J.-F., Garnero, L., Poline, J.-B., & Benali, H. (2001). Brainvisa: Software platform for visualization and analysis of multi-modality brain data. Neuroimage, 13(6), 98.

    Article  Google Scholar 

  • Desikan, R. S., Ségonne, F., Fischl, B., Quinn, B. T., Dickerson, B. C., Blacker, D., Buckner, R. L., Dale, A. M., Maguire, R. P., Hyman, B. T., Albert, M. S., & Killiany, R. J. (2006). An automated labeling system for subdividing the human cerebral cortex on mri scans into gyral based regions of interest. Neuroimage, 31(3), 968–980.

    Article  PubMed  Google Scholar 

  • Destrieux, C., Fischl, B., Dale, A., & Halgren, E. (2010). Automatic parcellation of human cortical gyri and sulci using standard anatomical nomenclature. Neuroimage, 53(1), 1–15.

    Article  PubMed  Google Scholar 

  • Fedorenko, E., & Blank, I. A. (2020). Broca’s area is not a natural kind. Trends in Cognitive Sciences, 24(4), 270–284.

    Article  PubMed  PubMed Central  Google Scholar 

  • Fernández, V., & Borrell, V. (2023). Developmental mechanisms of gyrification. Current Opinion in Neurobiology, 80, 102711.

    Article  PubMed  Google Scholar 

  • Garrison, J. R., Fernyhough, C., McCarthy-Jones, S., Haggard, M., 7, A. S. R. B. C. V...S. U.. S. R.. J. A.. M. B.. M. P.. C. S.. H. F.. P. C...L. C., & Simons, J. S. (2015). Paracingulate sulcus morphology is associated with hallucinations in the human brain. Nature communications, 6(1), 8956.

  • Gaser, C., Dahnke, R., Thompson, P. M., Kurth, F., Luders, E., & Initiative, A. D. N. (2022). Cat–a computational anatomy toolbox for the analysis of structural mri data. biorxiv, 2022–06.

  • He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 770–778).

  • IXI Dataset (2012). https://brain-development.org/ixi-dataset/

  • Keller, S. S., Crow, T., Foundas, A., Amunts, K., & Roberts, N. (2009). Broca’s area: Nomenclature, anatomy, typology and asymmetry. Brain and Language, 109(1), 29–48.

    Article  PubMed  Google Scholar 

  • Keller, S. S., Highley, J. R., Garcia-Finana, M., Sluming, V., Rezaie, R., & Roberts, N. (2007). Sulcal variability, stereological measurement and asymmetry of broca’s area on mr images. Journal of Anatomy, 211(4), 534–555.

    Article  PubMed  PubMed Central  Google Scholar 

  • Knaus, T. A., Corey, D. M., Bollich, A. M., Lemen, L. C., & Foundas, A. L. (2007). Anatomical asymmetries of anterior perisylvian speech-language regions. Cortex, 43(4), 499–510.

    Article  PubMed  Google Scholar 

  • LaMontagne, P. J., Benzinger, T. L., Morris, J. C., Keefe, S., Hornbeck, R., Xiong, C., Grant, E., Hassenstab, J., Moulder, K., Vlassenko, A. G., Raichle, M. E., Cruchaga, C., & Marcus, D. (2019). Oasis-3: Longitudinal neuroimaging, clinical, and cognitive dataset for normal aging and alzheimer disease. MedRxiv, 2019–12.

  • Lee, P., Kim, H.-R., Jeong, Y., & Initiative, A. D. N. (2020). Detection of gray matter microstructural changes in alzheimer’s disease continuum using fiber orientation. BMC Neurology, 20, 1–10.

    Article  CAS  Google Scholar 

  • Li, X., Morgan, P. S., Ashburner, J., Smith, J., & Rorden, C. (2016). The first step for neuroimaging data analysis: Dicom to nifti conversion. Journal of neuroscience methods, 264, 47–56.

    Article  PubMed  Google Scholar 

  • McCarthy, J., Collins, D. L., & Ducharme, S. (2018). Morphometric mri as a diagnostic biomarker of frontotemporal dementia: A systematic review to determine clinical applicability. NeuroImage: Clinical, 20, 685–696.

    Article  PubMed  Google Scholar 

  • Miller, J. A., Voorhies, W. I., Lurie, D. J., D’Esposito, M., & Weiner, K. S. (2021). Overlooked tertiary sulci serve as a meso-scale link between microstructural and functional properties of human lateral prefrontal cortex. Journal of Neuroscience, 41(10), 2229–2244.

    Article  CAS  PubMed  Google Scholar 

  • Miller, J. A., & Weiner, K. S. (2022). Unfolding the evolution of human cognition. Trends in Cognitive Sciences, 26(9), 735–737.

    Article  PubMed  Google Scholar 

  • Mueller, S. G., Weiner, M. W., Thal, L. J., Petersen, R. C., Jack, C., Jagust, W., Trojanowski, J. Q., Toga, A. W., & Beckett, L. (2005). The alzheimer’s disease neuroimaging initiative. Neuroimaging Clinics, 15(4), 869–877.

    Article  PubMed  Google Scholar 

  • Ono, M., Kubik, S., & Abernathey, C. D. (1990). Atlas of the Cerebral Sulci. New York: Thieme.

    Google Scholar 

  • Penny, W. D., Friston, K. J., Ashburner, J. T., Kiebel, S. J., & Nichols, T. E. (2011). Statistical Parametric Mapping: The Analysis of Functional Brain Images. London: Elsevier.

    Google Scholar 

  • Pérez-García, F., Sparks, R., & Ourselin, S. (2021). Torchio: A python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learning. Computer Methods and Programs in Biomedicine, 208, 106236.

    Article  PubMed  PubMed Central  Google Scholar 

  • Perrot, M., Rivière, D., & Mangin, J.-F. (2011). Cortical sulci recognition and spatial normalization. Medical image analysis, 15(4), 529–550.

    Article  PubMed  Google Scholar 

  • Sprung-Much, T., Eichert, N., Nolan, E., & Petrides, M. (2022). Broca’s area and the search for anatomical asymmetry: Commentary and perspectives. Brain Structure and Function, 227(2), 441–449.

    Article  PubMed  Google Scholar 

  • Sprung-Much, T., & Petrides, M. (2018). Morphological patterns and spatial probability maps of two defining sulci of the posterior ventrolateral frontal cortex of the human brain: The sulcus diagonalis and the anterior ascending ramus of the lateral fissure. Brain Structure and Function, 223, 4125–4152.

    Article  PubMed  Google Scholar 

  • Troiani, V., Patti, M. A., & Adamson, K. (2020). The use of the orbitofrontal h-sulcus as a reference frame for value signals. European Journal of Neuroscience, 51(9), 1928–1943.

    Article  PubMed  Google Scholar 

  • Vallejo-Azar, M. N., Alba-Ferrara, L., Bouzigues, A., Princich, J. P., Markov, M., Bendersky, M., & Gonzalez, P. N. (2023). Influence of accessory sulci of the frontoparietal operculum on gray matter quantification. Frontiers in Neuroanatomy, 16, 134.

    Article  Google Scholar 

  • Vijayakumari, A. A., Fernandez, H. H., & Walter, B. L. (2023). Mri-based multivariate gray matter volumetric distance for predicting motor symptom progression in parkinson’s disease. Scientific Reports, 13(1), 17704.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  • Voorhies, W. I., Miller, J. A., Yao, J. K., Bunge, S. A., & Weiner, K. S. (2021). Cognitive insights from tertiary sulci in prefrontal cortex. Nature Communications, 12(1), 5122.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  • Weiner, K. S., Golarai, G., Caspers, J., Chuapoco, M. R., Mohlberg, H., Zilles, K., Amunts, K., & Grill-Spector, K. (2014). The mid-fusiform sulcus: A landmark identifying both cytoarchitectonic and functional divisions of human ventral temporal cortex. Neuroimage, 84, 453–465.

    Article  PubMed  Google Scholar 

  • Welker, W. (1990). Why does cerebral cortex fissure and fold? a review of determinants of gyri and sulci. Cerebral Cortex: comparative structure and evolution of Cerebral Cortex, Part, II, 3–136.

  • Willbrand, E., Parker, B., Voorhies, W., Miller, J., Lyu, I., Hallock, T., Aponik-Gremillion, L., Koslov, S., Null, N., Bunge, S., Foster, B. L., & Weiner, K. S. (2022). Uncovering a tripartite landmark in posterior cingulate cortex. Science Adventure, 8, eabn9516.

    Article  Google Scholar 

  • Williams, L. Z., Fitzgibbon, S. P., Bozek, J., Winkler, A. M., Dimitrova, R., Poppe, T., Schuh, A., Makropoulos, A., Cupitt, J., O’Muircheartaigh, J., Duffc, E. P., Cordero-Grande, L., Price, A. N., Hajnal, J. V., Rueckert, D., Smith, S. M., Edwards, A. D., & Robinson, E. C. (2023). Structural and functional asymmetry of the neonatal cerebral cortex. Nature Human Behaviour, 1–14.

  • Yang, F., & Kruggel, F. (2009). A graph matching approach for labeling brain sulci using location, orientation, and shape. Neurocomputing, 73(1–3), 179–190.

    Article  Google Scholar 

  • Yang, S., Zhao, Z., Cui, H., Zhang, T., Zhao, L., He, Z., Liu, H., Guo, L., Liu, T., Becker, B., Kendrick, K. M., & Jiang, X. (2019). Temporal variability of cortical gyral-sulcal resting state functional activity correlates with fluid intelligence. Frontiers in Neural Circuits, 13, 36.

    Article  PubMed  PubMed Central  Google Scholar 

  • Yao, J. K., Voorhies, W. I., Miller, J. A., Bunge, S. A., & Weiner, K. S. (2023). Sulcal depth in prefrontal cortex: A novel predictor of working memory performance. Cerebral Cortex, 33(5), 1799–1813.

    Article  PubMed  Google Scholar 

  • Zeiler, M. D., & Fergus, R. (2014). Visualizing and understanding convolutional networks. In Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part I 13 (pp. 818–833). Springer.

Download references

Acknowledgements

We thank the technician Sergio Morganti, who acquired the images; the volunteers at III Normal Anatomy Department, Facultad de Medicina, Universidad de Buenos Aires (Argentina): Santiago Lasalle, César Gómez, Melanie Catena Baudo, Martina Arfili Perez y Lucía Canestrari who participated in our study in the process of image labeling; and the volunteers of Hospital El Cruce and Hospital Angel Roffo for their participation in this study.

Funding

This work was partially funded by PIP GI 2021-2023 - 11220200102472CO (CONICET) and PICT 2016-0116 (ANPCyT).

Author information

Author notes

  1. Delfina Braggio and Hernán C. Külsgaard contributed equally to this work.

Authors and Affiliations

  1. Consejo Nacional de Investigaciones Científicas y Técnicas, CONICET, Buenos Aires, Argentina

    Delfina Braggio, Hernán C. Külsgaard, Mariana Vallejo-Azar, Paula González, José Ignacio Orlando & Ignacio Larrabide

  2. Yatiris, PLADEMA, Facultad de Ciencias Exactas, UNICEN, Tandil, Buenos Aires, Argentina

    Delfina Braggio, Hernán C. Külsgaard, José Ignacio Orlando & Ignacio Larrabide

  3. Unidad Ejecutora de Estudios en Neurociencias y Sistemas Complejos, CONICET, UNAJ, Hospital El Cruce, Florencio Varela, Argentina

    Mariana Vallejo-Azar, Paula González & Lucía Alba-Ferrara

  4. Laboratorio de Anatomía Viviente, Facultad de Medicina, Universidad de Buenos Aires, Ciudad Autónoma de Buenos Aires, Buenos Aires, Argentina

    Mariana Bendersky

  5. Facultad de Ciencias Biomédicas, Universidad Austral, Ciudad Autónoma de Buenos Aires, Buenos Aires, Argentina

    Lucía Alba-Ferrara

Authors
  1. Delfina Braggio
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Hernán C. Külsgaard
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Mariana Vallejo-Azar
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Mariana Bendersky
    View author publications

    You can also search for this author inPubMed Google Scholar

  5. Paula González
    View author publications

    You can also search for this author inPubMed Google Scholar

  6. Lucía Alba-Ferrara
    View author publications

    You can also search for this author inPubMed Google Scholar

  7. José Ignacio Orlando
    View author publications

    You can also search for this author inPubMed Google Scholar

  8. Ignacio Larrabide
    View author publications

    You can also search for this author inPubMed Google Scholar

Contributions

Conception and study design: D.B., H.C.K., J.I.O., I.L. Data processing and analysis: D.B., H.C.K. Data Acquisition: M.V., M.B., P.G., L.A. Software development: D.B, H.C.K. Interpretation of results: D.B., H.C.K., J.I.O., I.L. Drafting the manuscript work and revising it: All authors Approval of final version to be published: All authors

Corresponding author

Correspondence to Delfina Braggio.

Ethics declarations

Conflicts of Interest

The authors declare that there are no conflicts of interest in this work.

Consent

Written informed consent was obtained from all patients/parti-cipants prior to their involvement in the study.

Ethics Approval

The ethical committees of Hospital El Cruce and Hospital Angel Roffo in Buenos Aires, Argentina, reviewed and approved the studies involving human participants.

Competing Interests

The authors declare no competing interests.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file 1 (pdf 1544 KB)

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Braggio, D., Külsgaard, H.C., Vallejo-Azar, M. et al. A Self-supervised Deep Learning Model for Diagonal Sulcus Detection with Limited Labeled Data. Neuroinform 23, 13 (2025). https://doi.org/10.1007/s12021-024-09700-7

Download citation

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s12021-024-09700-7

Keywords