Revisiting prostate segmentation in magnetic resonance imaging (MRI): On model transferability, degradation and PI-RADS adherence
Fernandez-Quilez, A.; Nordstom, T.; Eftestol, T.; Alvestad, A. B.; Jaderling, F.; Kjosavik, S. R.; Eklund, M.
Show abstract
PurposeTo investigate the effect of scanner and prostate MRI acquisition characteristics when compared to PI-RADSv2.1 technical standards in the performance of a deep learning prostate segmentation model trained with data from one center (INST1), longitudinally evaluated at the same institution and when transferred to other institutions. Materials and MethodsIn this retrospective study, a nn-UNet for prostate MRI segmentation was trained with data from 204 patients from one institution (INST1) (0.50mm2 in-plane, 3.6mm thickness and 16cm field of view [FOV]). Post-deployment performance at INST1 was tested with 30 patients acquired with a different protocol and in a different period of time (0.60mm2 in-plane, 4.0mm thickness and 19cm FOV). Transferability was tested on 248 patient sequences from five institutions (INST2, INST3, INST4, INST5 and INST6) acquired with different scanners and with heterogeneous degrees of PI-RADS v2.1 technical adherence. Performance was assessed using Dice Score Coefficient, Hausdorff Distance, Absolute Boundary Distance and Relative Volume Difference. ResultsThe model presented a significant degradation for the whole gland (WG) in the presence of a change of acquisition protocol at INST1 (DSC:99.46{+/-}0.12% and 91.24{+/-}3.32%,P<.001; RVD:-0.006{+/-}0.127% and 8.10{+/-}8.16%, P<.001). The model had a significantly higher performance in centers adhering to PI-RADS v2.1 when compared to those that did not (DSC: 86.24{+/-}9.67% and 74.83{+/-}15.45%, P <.001; RVD: -6.50{+/-}18.46% and 1.64{+/-}29.12%, P=.003). ConclusionsAdherence to PI-RADSv2.1 technical standards benefits inter-institutional transferability of a deep learning prostate segmentation model. Post-deployment evaluations are critical to ensure model performance is maintained over time in the presence of protocol acquisition modifications.
Matching journals
The top 9 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Enhancing Semantic Segmentation in Chest X-Ray Images through Image Preprocessing: ps-KDE for Pixel-wise Substitution by Kernel Density Estimation 92%
- Improved accuracy of breast volume calculation from 3D surface imaging data using statistical shape models 91%
- Internal calibration for opportunistic computed tomography muscle density analysis 91%
Similar papers in this journal
- Necessity and Impact of Specialization of Large Foundation Model for Medical Segmentation Tasks 94%
- Fully Automated Explainable Abdominal CT Contrast Media Phase Classification Using Organ Segmentation and Machine Learning 93%
- PSMA-Hornet: fully-automated, multi-target segmentation of healthy organs in PSMA PET/CT images 92%
Similar papers in this journal
- Improving Rectal Tumor Segmentation with Anomaly Fusion Derived from Anatomical Inpainting: A Multicenter Study 93%
- PathProfiler: Automated Quality Assessment of Retrospective Histopathology Whole-Slide Image Cohorts by Artificial Intelligence, A Case Study for Prostate Cancer Research 92%
- Automated cervix biometry, volumetry and normative models for 3D motion-corrected T2-weighted 0.55-3T fetal MRI during 2nd and 3rd trimesters 92%
Similar papers in this journal
- Breast density prediction from low and standard dose mammograms using deep learning: effect of image resolution and model training approach on prediction quality 91%
- Model uncertainty estimates for deep learning mammographic density prediction using ordinal and classification approaches 89%
- Recent advances in the clinical applications of machine learning in proton therapy 89%
Similar papers in this journal
- Segmentation stability of human head and neck medical images for radiotherapy applications under de-identification conditions: benchmarking for data sharing and artificial intelligence use-cases 93%
- Deep-Learning-Based Generation of Synthetic High-Resolution MRI from Low-Resolution MRI for Use in Head and Neck Cancer Adaptive Radiotherapy 92%
- Leveraging intelligent optimization for automated, cardiac-sparing accelerated partial breast treatment planning 89%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.