Deformable MRI Sequence Registration for AI-based Prostate Cancer Diagnosis
Preprint
Abstract
The PI-CAI (Prostate Imaging: Cancer AI) challenge led to expert-level diagnostic algorithms for clinically significant prostate cancer detection. The algorithms receive biparametric MRI scans as input, which consist of T2-weighted and diffusion-weighted scans. These scans can be misaligned due to multiple factors in the scanning process. Image registration can alleviate this issue by predicting the deformation between the sequences. We investigate the effect of image registration on the diagnostic performance of AI-based prostate cancer diagnosis. First, the image registration algorithm, developed in MeVisLab, is analyzed using a dataset with paired lesion annotations. Second, the effect on diagnosis is evaluated by comparing case-level cancer diagnosis performance between using the original dataset, rigidly aligned diffusion-weighted scans, or deformably aligned diffusion-weighted scans. Rigid registration showed no improvement. Deformable registration demonstrated a substantial improvement in lesion overlap (+10% median Dice score) and a positive yet non-significant improvement in diagnostic performance (+0.3% AUROC, p=0.18). Our investigation shows that a substantial improvement in lesion alignment does not directly lead to a significant improvement in diagnostic performance. Qualitative analysis indicated that jointly developing image registration methods and diagnostic AI algorithms could enhance diagnostic accuracy and patient outcomes.Keywords
All Related Versions
This publication has 11 references indexed in Scilit:
- Addressing image misalignments in multi-parametric prostate MRI for enhanced computer-aided diagnosis of prostate cancerScientific Reports, 2023
- Deep learning for fully automatic detection, segmentation, and Gleason grade estimation of prostate cancer in multiparametric magnetic resonance imagesScientific Reports, 2022
- Medical imaging and nuclear medicine: a Lancet Oncology CommissionThe Lancet Oncology, 2021
- Population-Based Prostate Cancer Screening With Magnetic Resonance Imaging or UltrasonographyJAMA Oncology, 2021
- Deep Learning Regression for Prostate Cancer Detection and Grading in Bi-Parametric MRIIEEE Transactions on Biomedical Engineering, 2020
- MRI in active surveillance: a critical reviewProstate Cancer and Prostatic Diseases, 2018
- A Matrix-Free Approach to Parallel and Memory-Efficient Deformable Image RegistrationSIAM Journal on Scientific Computing, 2018
- A matrix-free approach to efficient affine-linear image registration on CPU and GPUJournal of Real-Time Image Processing, 2016
- Fast Implementation of DeLong’s Algorithm for Comparing the Areas Under Correlated Receiver Operating Characteristic CurvesIEEE Signal Processing Letters, 2014
- Image Similarity and Tissue Overlaps as Surrogates for Image Registration Accuracy: Widely Used but UnreliableIEEE Transactions on Medical Imaging, 2011