Abstract
Early diagnosis of prostate cancer is crucial for efficient treatment. Multi-parametric Magnetic Resonance Images (mp-MRI) are widely used for lesion detection. The Prostate Imaging Reporting and Data System (PI-RADS) has standardized interpretation of prostate MRI by defining a score for lesion malignancy. PI-RADS data is readily available from radiology reports but is subject to high inter-reports variability. We propose a new contrastive loss function that leverages weak metadata with multiple annotators per sample and takes advantage of inter-reports variability by defining metadata confidence. By combining metadata of varying confidence with unannotated data into a single conditional contrastive loss function, we report a 3% AUC increase on lesion detection on the public PI-CAI challenge dataset.
Code is available at: https://github.com/camilleruppli/decoupled_ccl.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
The maximum number of metadata available for an exam is \(n=7\), the minimal achievable confidence value is thus \(c = 2(4/7 -1/2) > 0.14\). We fix \(\epsilon \) so that the confidence for \(n=1\) is higher than 0 but less that the minimal confidence when n is odd.
- 2.
The 100 validation cases on the PI-CAI challenge website being hidden we could not compare our methods to the leaderboard performances.
References
Alonso, I., Sabater, A., Ferstl, D., Montesano, L., Murillo, A.C.: Semi-supervised semantic segmentation with pixel-level contrastive learning from a class-wise memory bank. In: ICCV, pp. 8199–8208 (2021)
Basak, H., Yin, Z.: Pseudo-label guided contrastive learning for semi-supervised medical image segmentation. In: CVPR (2023)
Bhattacharya, I., Seetharaman, A., et al.: Selective identification and localization of indolent and aggressive prostate cancers via CorrSigNIA: an MRI-pathology correlation and deep learning framework. Med. Image Anal. 75, 102288 (2021)
Bosma, J.S., Saha, A., et al.: Annotation-efficient cancer detection with report-guided lesion annotation for deep learning-based prostate cancer detection in bpMRI. arxiv:2112.05151 (2021)
Bovsnjak, M., Richemond, P.H., et al.: SemPPL: predicting pseudo-labels for better contrastive representations. In: ICLR (2023)
Chaitanya, K., Erdil, E., Karani, N., Konukoglu, E.: Local contrastive loss with pseudo-label based self-training for semi-supervised medical image segmentation. Med. Image Anal. 87, 102792 (2021)
Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: ICML, vol. 119, pp. 1597–1607 (2020)
Dufumier, B., Barbano, C.A., Louiset, R., Duchesnay, E., Gori, P.: Integrating prior knowledge in contrastive learning with kernel. In: International Conference on Machine Learning (ICML) (2023)
Dufumier, B., Gori, P., et al.: Conditional alignment and uniformity for contrastive learning with continuous proxy labels. In: MedNeurIPS (2021)
Dufumier, B., et al.: Contrastive learning with continuous proxy meta-data for 3D MRI classification. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12902, pp. 58–68. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-87196-3_6
Dwibedi, D., Aytar, Y., et al.: With a little help from my friends: nearest-neighbor contrastive learning of visual representations. In: ICCV, pp. 9568–9577 (2021)
Epstein, J.I., Egevad, L., Amin, M.B., Delahunt, B., Srigley, J.R., Humphrey, P.A.: The 2014 international society of urological pathology (ISUP) consensus conference on gleason grading of prostatic carcinoma: definition of grading patterns and proposal for a new grading system. Am. J. Surg. Pathol. 40, 244–252 (2015)
Fernandez-Quilez, A., Eftestøl, T., Kjosavik, S.R., Olsen, M.G., Oppedal, K.: Contrasting axial T2W MRI for prostate cancer triage: a self-supervised learning approach. In: ISBI, pp. 1–5 (2022)
Greer, M.D., et al.: Interreader variability of prostate imaging reporting and data system version 2 in detecting and assessing prostate cancer lesions at prostate MRI. In: AJR, pp. 1–8 (2019)
Grill, J.B., Strub, F., et al.: Bootstrap your own latent: a new approach to self-supervised learning. In: NeurIPS (2020)
He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.B.: Momentum contrast for unsupervised visual representation learning. In: CVPR, pp. 9726–9735 (2019)
Isensee, F., Jaeger, P.F., Kohl, S.A.A., Petersen, J., Maier-Hein, K.: nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat. Methods 18, 203–211 (2020)
Khosla, P., Teterwak, P., et al.: Supervised contrastive learning. In: NeurIPS (2020)
Li, S., Xia, X., Ge, S., Liu, T.: Selective-supervised contrastive learning with noisy labels. In: CVPR, pp. 316–325 (2022)
Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
Rouvière, O., et al.: Use of prostate systematic and targeted biopsy on the basis of multiparametric MRI in biopsy-naive patients (MRI-FIRST): a prospective, multicentre, paired diagnostic study. Lancet Oncol. 20(1), 100–109 (2019)
Saha, A., Hosseinzadeh, M., Huisman, H.J.: End-to-end prostate cancer detection in bpMRI via 3D CNNs: effect of attention mechanisms, clinical priori and decoupled false positive reduction. Med. Image Anal. 73, 102155 (2021)
Saha, A., Twilt, J.J., et al.: Artificial intelligence and radiologists at prostate cancer detection in MRI: the PI-CAI challenge (2022)
Saha, A., Twilt, J.J., et al.: The PI-CAI challenge: public training and development dataset (2022)
Smith, C.P., et al.: Intra- and interreader reproducibility of PI-RADSv2: a multireader study. J. Magn. Reson. Imaging 49, 1694–1703 (2019)
Tsai, Y.H.H., Li, T., et al.: Conditional contrastive learning with kernel. In: ICLR (2022)
Turkbey, B.I., et al.: Prostate imaging reporting and data system version 2.1: 2019 update of prostate imaging reporting and data system version 2. Eur. Urol. 76, 340–351 (2019)
Wang, T., Isola, P.: Understanding contrastive representation learning through alignment and uniformity on the hypersphere. In: ICML, vol. 119, pp. 9929–9939 (2020)
Westphalen, A.C., et al.: Variability of the positive predictive value of PI-RADS for prostate MRI across 26 centers: experience of the society of abdominal radiology prostate cancer disease-focused panel. Radiology, 190646 (2020)
Xue, Y., Whitecross, K., Mirzasoleiman, B.: Investigating why contrastive learning benefits robustness against label noise. In: ICML, pp. 24851–24871 (2022)
Yeh, C., Hong, C., et al.: Decoupled contrastive learning. In: Avidan, S., Brostow, G., Cisse, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13686, pp. 668–684. Springer, Heidelberg (2022). https://doi.org/10.1007/978-3-031-19809-0_38
Yi, L., Liu, S., She, Q., McLeod, A., Wang, B.: On learning contrastive representations for learning with noisy labels. In: CVPR, pp. 16661–16670 (2022)
Yu, X., et al.: Deep attentive panoptic model for prostate cancer detection using biparametric MRI scans. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12264, pp. 594–604. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-59719-1_58
Yu, X., Lou, B., et al.: False positive reduction using multiscale contextual features for prostate cancer detection in multi-parametric MRI scans. In: IEEE 17th International Symposium on Biomedical Imaging (ISBI), pp. 1355–1359 (2020)
Zhao, X., et al.: Contrastive learning for label efficient semantic segmentation. In: ICCV, pp. 10603–10613 (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Ruppli, C., Gori, P., Ardon, R., Bloch, I. (2023). Decoupled Conditional Contrastive Learning with Variable Metadata for Prostate Lesion Detection. In: Xue, Z., et al. Medical Image Learning with Limited and Noisy Data. MILLanD 2023. Lecture Notes in Computer Science, vol 14307. Springer, Cham. https://doi.org/10.1007/978-3-031-44917-8_9
Download citation
DOI: https://doi.org/10.1007/978-3-031-44917-8_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-47196-4
Online ISBN: 978-3-031-44917-8
eBook Packages: Computer ScienceComputer Science (R0)