Abstract
Artificial intelligence systems show promise to aid in the diagnostic pathway of prostate cancer (PC), by supporting radiologists in interpreting magnetic resonance images (MRI) of the prostate. Most MRI-based systems are designed to detect clinically significant PC lesions, with the main objective of preventing over-diagnosis. Typically, these systems involve an automatic prostate segmentation component and a clinically significant PC lesion detection component. In spite of the compound nature of the systems, evaluations are presented assuming a standalone clinically significant PC detection component. That is, they are evaluated in an idealized scenario and under the assumption that a highly accurate prostate segmentation is available at test time. In this work, we aim to evaluate a clinically significant PC lesion detection system accounting for its compound nature. For that purpose, we simulate a realistic deployment scenario and evaluate the effect of two non-ideal and previously validated prostate segmentation modules on the PC detection ability of the compound system. Following, we compare them with an idealized setting, where prostate segmentations are assumed to have no faults. We observe significant differences in the detection ability of the compound system in a realistic scenario and in the presence of the highest-performing prostate segmentation module (DSC: 90.07 ± 0.74), when compared to the idealized one (AUC: 77.97 ± 3.06 and 84.30 ± 4.07, P<.001). Our results depict the relevance of holistic evaluations for PC detection compound systems, where interactions between system components can lead to decreased performance and degradation at deployment time.
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
References
Anaya-Isaza, A., Mera-Jiménez, L., Fernandez-Quilez, A.: Crosstransunet: a new computationally inexpensive tumor segmentation model for brain mri. IEEE Access 11, 27066–27085 (2023)
Cao, R., et al.: Joint prostate cancer detection and Gleason score prediction in MP-MRI via focalnet. IEEE Trans. Med. Imaging 38(11), 2496–2506 (2019)
Cuocolo, R., et al.: Deep learning whole-gland and zonal prostate segmentation on a public MRI dataset. J. Magn. Reson. Imaging 54(2), 452–459 (2021)
Eklund, M., et al.: MRI-targeted or standard biopsy in prostate cancer screening. N. Engl. J. Med. 385(10), 908–920 (2021)
Fassia, M.K., et al.: Deep learning prostate MRI segmentation accuracy and robustness: a systematic review. Radiol. Artif. Intell. 2014, e230138 (2024)
Fernandez-Quilez, A.: Deep learning in radiology: ethics of data and on the value of algorithm transparency, interpretability and explainability. AI Ethics 3(1), 257–265 (2023)
Fernandez-Quilez, A., Larsen, S.V., Goodwin, M., Gulsrud, T.O., Kjosavik, S.R., Oppedal, K.: Improving prostate whole gland segmentation in t2-weighted MRI with synthetically generated data. In: 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI), pp. 1915–1919. IEEE (2021)
Fernandez-Quilez, A., Nordström, T., Jäderling, F., Kjosavik, S.R., Eklund, M.: Prostate age gap: an MRI surrogate marker of aging for prostate cancer detection. J. Magn. Reson. Imaging 60(2), 458–468 (2024). https://doi.org/10.1002/jmri.29090
Isensee, F., Jaeger, P.F., Kohl, S.A., Petersen, J., Maier-Hein, K.H.: NNU-net: a self-configuring method for deep learning-based biomedical image segmentation. Nat. Methods 18(2), 203–211 (2021)
Kurbatskaya, A., Jaramillo-Jimenez, A., Ochoa-Gomez, J.F., Brnnick, K., Fernandez-Quilez, A.: Assessing gender fairness in EEG-based machine learning detection of Parkinson’s disease: a multi-center study. In: 2023 31st European Signal Processing Conference (EUSIPCO), pp. 1020–1024 (2023). https://doi.org/10.23919/EUSIPCO58844.2023.10289837
Kwee, T.C., Kwee, R.M.: Workload of diagnostic radiologists in the foreseeable future based on recent scientific advances: growth expectations and role of artificial intelligence. Insights Imaging 12(1), 1–12 (2021)
van Leeuwen, K.G., Schalekamp, S., Rutten, M.J., van Ginneken, B., de Rooij, M.: Artificial intelligence in radiology: 100 commercially available products and their scientific evidence. Eur. Radiol. 31, 3797–3804 (2021)
Lindeijer, T.N., et al.: Leveraging multi-view data without annotations for prostate MRI segmentation: a contrastive approach. arXiv preprint arXiv:2308.06477 (2023)
Litjens, G., Debats, O., Barentsz, J., Karssemeijer, N., Huisman, H.: Computer-aided detection of prostate cancer in MRI. IEEE Trans. Med. Imaging 33(5), 1083–1092 (2014)
Litjens, G., et al.: Evaluation of prostate segmentation algorithms for MRI: the promise12 challenge. Med. Image Anal. 18(2), 359–373 (2014)
McKinney, S.M., et al.: International evaluation of an AI system for breast cancer screening. Nature 577(7788), 89–94 (2020)
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
Saha, A., et al.: Artificial intelligence and radiologists in prostate cancer detection on MRI (PI-CAI): an international, paired, non-inferiority, confirmatory study. Lancet Oncol. (2024)
Saha, A., Hosseinzadeh, M., Huisman, H.: End-to-end prostate cancer detection in BPMRI via 3D CNNs: effects of attention mechanisms, clinical priori and decoupled false positive reduction. Med. Image Anal. 73, 102155 (2021)
Sanford, T., et al.: Deep-learning-based artificial intelligence for PI-RADS classification to assist multiparametric prostate MRI interpretation: a development study. J. Magn. Reson. Imaging 52(5), 1499–1507 (2020)
Sanyal, J., Banerjee, I., Hahn, L., Rubin, D.: An automated two-step pipeline for aggressive prostate lesion detection from multi-parametric MR sequence. AMIA Summits Transl. Sci. Proc. 2020, 552 (2020)
Suarez-Ibarrola, R., et al.: Artificial intelligence in magnetic resonance imaging-based prostate cancer diagnosis: where do we stand in 2021? Eur. Urol. Focus 8(2), 409–417 (2022)
Wenderott, K., Krups, J., Luetkens, J.A., Gambashidze, N., Weigl, M.: Prospective effects of an artificial intelligence-based computer-aided detection system for prostate imaging on routine workflow and radiologists’ outcomes. Eur. J. Radiol. 170, 111252 (2024)
Widner, K., et al.: Lessons learned from translating AI from development to deployment in healthcare. Nat. Med. 29(6), 1304–1306 (2023)
Yushkevich, P.A., Gao, Y., Gerig, G.: ITK-SNAP: an interactive tool for semi-automatic segmentation of multi-modality biomedical images. In: 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 3342–3345. IEEE (2016)
Acknowledgements
The authors would like to show their gratitude to the organizers of the ProstateX challenge for providing access to their curated dataset.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Ethics declarations
Disclosure of Interests
The authors declare that they have no competing interests.
Rights and permissions
Copyright information
© 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Sortland Rolfsnes, E. et al. (2025). On Undesired Emergent Behaviors in Compound Prostate Cancer Detection Systems. In: Ali, S., van der Sommen, F., Papież, B.W., Ghatwary, N., Jin, Y., Kolenbrander, I. (eds) Cancer Prevention, Detection, and Intervention. CaPTion 2024. Lecture Notes in Computer Science, vol 15199. Springer, Cham. https://doi.org/10.1007/978-3-031-73376-5_7
Download citation
DOI: https://doi.org/10.1007/978-3-031-73376-5_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-73375-8
Online ISBN: 978-3-031-73376-5
eBook Packages: Computer ScienceComputer Science (R0)
