Related Experiment Video
Updated: Aug 11, 2025
Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence
Published on: June 10, 2025
Time series radiomics for the prediction of prostate cancer progression in patients on active surveillance
Nikita Sushentsev1, Leonardo Rundo2,3, Luis Abrego4
1Department of Radiology, School of Clinical Medicine, Addenbrooke's Hospital, University of Cambridge, Cambridge Biomedical Campus, Box 218, Cambridge, CB2 0QQ, UK. ns784@medschl.cam.ac.uk.
Abstract:
Serial MRI is an essential assessment tool in prostate cancer (PCa) patients enrolled on active surveillance (AS). However, it has only moderate sensitivity for predicting histopathological tumour progression at follow-up, which is in part due to the subjective nature of its clinical reporting and variation among centres and readers. In this study, we used a long short-term memory (LSTM) recurrent neural network (RNN) to develop a time series radiomics (TSR) predictive model that analysed longitudinal changes in tumour-derived radiomic features across 297 scans from 76 AS patients, 28 with histopathological PCa progression and 48 with stable disease. Using leave-one-out cross-validation (LOOCV), we found that an LSTM-based model combining TSR and serial PSA density (AUC 0.86 [95% CI: 0.78-0.94]) significantly outperformed a model combining conventional delta-radiomics and delta-PSA density (0.75 [0.64-0.87]; p = 0.048) and achieved comparable performance to expert-performed serial MRI analysis using the Prostate Cancer Radiologic Estimation of Change in Sequential Evaluation (PRECISE) scoring system (0.84 [0.76-0.93]; p = 0.710). The proposed TSR framework, therefore, offers a feasible quantitative tool for standardising serial MRI assessment in PCa AS. It also presents a novel methodological approach to serial image analysis that can be used to support clinical decision-making in multiple scenarios, from continuous disease monitoring to treatment response evaluation. KEY POINTS: •LSTM RNN can be used to predict the outcome of PCa AS using time series changes in tumour-derived radiomic features and PSA density. •Using all available TSR features and serial PSA density yields a significantly better predictive performance compared to using just two time points within the delta-radiomics framework. •The concept of TSR can be applied to other clinical scenarios involving serial imaging, setting out a new field in AI-driven radiology research.
Insights
A new AI model using time series radiomics (TSR) and PSA density can predict prostate cancer (PCa) progression in patients on active surveillance (AS). This AI approach offers a quantitative, standardized method for serial MRI assessment, improving clinical decision-making.
Area of Science:
- Artificial Intelligence in Radiology
- Medical Imaging Analysis
- Prostate Cancer Diagnostics
Background:
- Serial MRI is crucial for monitoring prostate cancer (PCa) patients on active surveillance (AS).
- Current MRI interpretation for PCa progression has moderate sensitivity due to subjectivity and inter-observer variability.
- Objective tools are needed to standardize and improve the accuracy of serial MRI assessments in PCa AS.
Purpose of the Study:
- To develop and evaluate a time series radiomics (TSR) predictive model using a long short-term memory (LSTM) recurrent neural network (RNN).
- To assess the model's ability to predict histopathological tumor progression in PCa patients undergoing active surveillance.
- To compare the performance of the TSR model against conventional radiomics and expert assessment.
Main Methods:
- A LSTM-based recurrent neural network (RNN) was employed to analyze longitudinal changes in radiomic features from serial MRI scans.
- The model integrated time series radiomics (TSR) with serial PSA density from 297 scans of 76 AS patients.
- Leave-one-out cross-validation (LOOCV) was used to evaluate the model's predictive performance.
Main Results:
- The LSTM-based TSR model combining TSR and serial PSA density achieved an AUC of 0.86 (95% CI: 0.78-0.94).
- This model significantly outperformed a delta-radiomics and delta-PSA density model (AUC 0.75; p=0.048).
- The TSR model's performance was comparable to expert serial MRI analysis using the PRECISE scoring system (AUC 0.84).
Conclusions:
- LSTM RNN-based TSR offers a feasible and quantitative tool for standardizing serial MRI assessment in prostate cancer active surveillance.
- This novel framework provides a significant improvement over conventional delta-radiomics approaches for predicting PCa progression.
- The TSR methodology can be extended to other clinical scenarios involving serial imaging, advancing AI-driven radiology research.
