# On undesired emergent behaviors in compound prostate cancer detection systems

arXiv: https://arxiv.org/abs/2309.08381 · HTML: https://mlsanity.com/paper/2309.08381/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 25 references that are in the map.
- First posted on arXiv 15 Sep 2023.

## Builds on (most cited first, 5 of 5)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [End-to-end Prostate Cancer Detection in bpMRI via 3D CNNs: Effects of Attention Mechanisms, Clinical Priori and Decoupled False Positive Reduction](https://mlsanity.com/paper/2101.03244/) (2021)
- [Improving prostate whole gland segmentation in t2-weighted MRI with synthetically generated data](https://mlsanity.com/paper/2103.14955/) (2021)
- [Assessing gender fairness in EEG-based machine learning detection of Parkinson's disease: A multi-center study](https://mlsanity.com/paper/2303.06376/) (2023)
- [Leveraging multi-view data without annotations for prostate MRI segmentation: A contrastive approach](https://mlsanity.com/paper/2308.06477/) (2023)

## Built on by (most cited first, 1 of 1)

- [Neuropsychiatric Deviations From Normative Profiles: An MRI-Derived Marker for Early Alzheimer's Disease Detection](https://mlsanity.com/paper/2604.00545/) (2026)

## Abstract (arXiv)

Artificial intelligence systems show promise to aid in the di- agnostic 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 le- sions, 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 assum- ing 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 de- tection 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 com- pare them with an idealized setting, where prostate segmentations are assumed to have no faults. We observe significant differences in the de- tection 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: 77.93 +- 3.06 and 84.30+- 4.07, P<.001). Our results depict the relevance of holistic evalu- ations for PC detection compound systems, where interactions between system components can lead to decreased performance and degradation at deployment time.