Skip to main content
Top

Open Access 08-06-2024 | Original Article

Self-supervised learning for classifying paranasal anomalies in the maxillary sinus

Authors: Debayan Bhattacharya, Finn Behrendt, Benjamin Tobias Becker, Lennart Maack, Dirk Beyersdorff, Elina Petersen, Marvin Petersen, Bastian Cheng, Dennis Eggert, Christian Betz, Anna Sophie Hoffmann, Alexander Schlaefer

Published in: International Journal of Computer Assisted Radiology and Surgery

Login to get access

Abstract

Purpose

Paranasal anomalies, frequently identified in routine radiological screenings, exhibit diverse morphological characteristics. Due to the diversity of anomalies, supervised learning methods require large labelled dataset exhibiting diverse anomaly morphology. Self-supervised learning (SSL) can be used to learn representations from unlabelled data. However, there are no SSL methods designed for the downstream task of classifying paranasal anomalies in the maxillary sinus (MS).

Methods

Our approach uses a 3D convolutional autoencoder (CAE) trained in an unsupervised anomaly detection (UAD) framework. Initially, we train the 3D CAE to reduce reconstruction errors when reconstructing normal maxillary sinus (MS) image. Then, this CAE is applied to an unlabelled dataset to generate coarse anomaly locations by creating residual MS images. Following this, a 3D convolutional neural network (CNN) reconstructs these residual images, which forms our SSL task. Lastly, we fine-tune the encoder part of the 3D CNN on a labelled dataset of normal and anomalous MS images.

Results

The proposed SSL technique exhibits superior performance compared to existing generic self-supervised methods, especially in scenarios with limited annotated data. When trained on just 10% of the annotated dataset, our method achieves an area under the precision-recall curve (AUPRC) of 0.79 for the downstream classification task. This performance surpasses other methods, with BYOL attaining an AUPRC of 0.75, SimSiam at 0.74, SimCLR at 0.73 and masked autoencoding using SparK at 0.75.

Conclusion

A self-supervised learning approach that inherently focuses on localizing paranasal anomalies proves to be advantageous, particularly when the subsequent task involves differentiating normal from anomalous maxillary sinuses. Access our code at https://​github.​com/​mtec-tuhh/​self-supervised-paranasal-anomaly.
Appendix
Available only for authorised users
Literature
3.
go back to reference Varshney H, Varshney J, Biswas S, Ghosh SK (2015) Importance of CT scan of paranasal sinuses in the evaluation of the anatomical findings in patients suffering from sinonasal polyposis. Indian J Otolaryngol Head Neck Surg 68(2):167–172CrossRefPubMedPubMedCentral Varshney H, Varshney J, Biswas S, Ghosh SK (2015) Importance of CT scan of paranasal sinuses in the evaluation of the anatomical findings in patients suffering from sinonasal polyposis. Indian J Otolaryngol Head Neck Surg 68(2):167–172CrossRefPubMedPubMedCentral
4.
6.
go back to reference Tarp B, Fiirgaard B, Christensen T, Jensen JJ, Black FT (2000) The prevalence and significance of incidental paranasal sinus abnormalities on MRI. Rhinology 38(1):33–38PubMed Tarp B, Fiirgaard B, Christensen T, Jensen JJ, Black FT (2000) The prevalence and significance of incidental paranasal sinus abnormalities on MRI. Rhinology 38(1):33–38PubMed
7.
go back to reference Brierley J, Gospodarowicz MK, Wittekind C (eds) (2017) TNM classification of malignant tumours. Eighth edn. John Wiley & Sons Inc, Chichester West Sussex UK and Hoboken NJ Brierley J, Gospodarowicz MK, Wittekind C (eds) (2017) TNM classification of malignant tumours. Eighth edn. John Wiley & Sons Inc, Chichester West Sussex UK and Hoboken NJ
9.
go back to reference Papadopoulou A-M, Chrysikos D, Samolis A, Tsakotos G, Troupis T (2021) Anatomical variations of the nasal cavities and paranasal sinuses: a systematic review. Cureus 13(1):12727 Papadopoulou A-M, Chrysikos D, Samolis A, Tsakotos G, Troupis T (2021) Anatomical variations of the nasal cavities and paranasal sinuses: a systematic review. Cureus 13(1):12727
12.
14.
go back to reference Bhattacharya D, Becker BT, Behrendt F, Bengs M, Beyersdorff D, Eggert D, Petersen E, Jansen F, Petersen M, Cheng B, Betz C, Schlaefer A, Hoffmann AS (2022) Supervised contrastive learning to classify paranasal anomalies in the maxillary sinus. In: Wang L, Dou Q, Fletcher PT, Speidel S, Li S (eds) Medical image computing and computer assisted intervention-MICCAI 2022. Springer, Cham, pp 429–438 Bhattacharya D, Becker BT, Behrendt F, Bengs M, Beyersdorff D, Eggert D, Petersen E, Jansen F, Petersen M, Cheng B, Betz C, Schlaefer A, Hoffmann AS (2022) Supervised contrastive learning to classify paranasal anomalies in the maxillary sinus. In: Wang L, Dou Q, Fletcher PT, Speidel S, Li S (eds) Medical image computing and computer assisted intervention-MICCAI 2022. Springer, Cham, pp 429–438
15.
go back to reference Bhattacharya D, Behrendt F, Becker BT, Beyersdorff D, Petersen E, Petersen M, Cheng B, Eggert D, Betz C, Hoffmann AS, Schlaefer A (2023) Multiple instance ensembling for paranasal anomaly classification in the maxillary sinus. Int J Comput Assist Radiol Surg 19(2):223–231CrossRefPubMedPubMedCentral Bhattacharya D, Behrendt F, Becker BT, Beyersdorff D, Petersen E, Petersen M, Cheng B, Eggert D, Betz C, Hoffmann AS, Schlaefer A (2023) Multiple instance ensembling for paranasal anomaly classification in the maxillary sinus. Int J Comput Assist Radiol Surg 19(2):223–231CrossRefPubMedPubMedCentral
19.
go back to reference Vincent P, Larochelle H, Lajoie I, Bengio Y, Manzagol P-A (2010) Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion. J Mach Learn Res 11:3371–3408 Vincent P, Larochelle H, Lajoie I, Bengio Y, Manzagol P-A (2010) Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion. J Mach Learn Res 11:3371–3408
24.
go back to reference Baur C, Denner S, Wiestler B, Navab N, Albarqouni S (2021) Autoencoders for unsupervised anomaly segmentation in brain MR images: a comparative study. Med Image Anal 69:101952CrossRefPubMed Baur C, Denner S, Wiestler B, Navab N, Albarqouni S (2021) Autoencoders for unsupervised anomaly segmentation in brain MR images: a comparative study. Med Image Anal 69:101952CrossRefPubMed
28.
go back to reference Tran D, Wang H, Torresani L, Ray J, LeCun Y, Paluri M (2018) A closer look at spatiotemporal convolutions for action recognition. In: 2018 IEEE/CVF conference on computer vision and pattern recognition (CVPR), pp 6450–6459. IEEE Computer Society, Los Alamitos, CA, USA. https://doi.org/10.1109/CVPR.2018.00675 Tran D, Wang H, Torresani L, Ray J, LeCun Y, Paluri M (2018) A closer look at spatiotemporal convolutions for action recognition. In: 2018 IEEE/CVF conference on computer vision and pattern recognition (CVPR), pp 6450–6459. IEEE Computer Society, Los Alamitos, CA, USA. https://​doi.​org/​10.​1109/​CVPR.​2018.​00675
32.
go back to reference Ozbulak U, Lee HJ, Boga B, Anzaku ET, Park H-M, Messem AV, Neve WD, Vankerschaver J (2023) Know your self-supervised learning: a survey on image-based generative and discriminative training. Transactions on Machine Learning Research. Survey Certification Ozbulak U, Lee HJ, Boga B, Anzaku ET, Park H-M, Messem AV, Neve WD, Vankerschaver J (2023) Know your self-supervised learning: a survey on image-based generative and discriminative training. Transactions on Machine Learning Research. Survey Certification
33.
go back to reference Chen T, Kornblith S, Norouzi M, Hinton G (2020) A simple framework for contrastive learning of visual representations. In: Proceedings of the 37th international conference on machine learning. ICML. JMLR.org Chen T, Kornblith S, Norouzi M, Hinton G (2020) A simple framework for contrastive learning of visual representations. In: Proceedings of the 37th international conference on machine learning. ICML. JMLR.org
34.
go back to reference Raina R, Battle A, Lee H, Packer B, Ng AY (2007) Self-taught learning: transfer learning from unlabeled data. In: Proceedings of the 24th international conference on machine learning. ICML ’07, pp. 759–766. Association for Computing Machinery, New York, NY, USA. https://doi.org/10.1145/1273496.1273592 Raina R, Battle A, Lee H, Packer B, Ng AY (2007) Self-taught learning: transfer learning from unlabeled data. In: Proceedings of the 24th international conference on machine learning. ICML ’07, pp. 759–766. Association for Computing Machinery, New York, NY, USA. https://​doi.​org/​10.​1145/​1273496.​1273592
Metadata
Title
Self-supervised learning for classifying paranasal anomalies in the maxillary sinus
Authors
Debayan Bhattacharya
Finn Behrendt
Benjamin Tobias Becker
Lennart Maack
Dirk Beyersdorff
Elina Petersen
Marvin Petersen
Bastian Cheng
Dennis Eggert
Christian Betz
Anna Sophie Hoffmann
Alexander Schlaefer
Publication date
08-06-2024
Publisher
Springer International Publishing
Published in
International Journal of Computer Assisted Radiology and Surgery
Print ISSN: 1861-6410
Electronic ISSN: 1861-6429
DOI
https://doi.org/10.1007/s11548-024-03172-5