A Multi-Modal Deep Learning Framework for Predicting PSA Progression-Free Survival in Metastatic Prostate Cancer Using PSMA PET/CT Imaging
Ghaderi, H.; Shen, C.; Issa, W.; Pomper, M. G.; Oz, O. K.; Zhang, T.; Wang, J.; Yang, D. X.
Show abstract
PSMA PET/CT imaging has been increasingly utilized in the management of patients with metastatic prostate cancer (mPCa). Imaging biomarkers derived from PSMA PET may provide improved prognostication and prediction of treatment response for mPCa patients. This study investigates a novel deep learning-derived imaging biomarker framework for outcome prediction using multi-modal PSMA PET/CT and clinical features. A single institution cohort of 99 mPCa patients with 396 lesions was evaluated. Imaging features were extracted from cropped lesion areas and combined with clinical variables including body mass index, ECOG performance status, prostate specific antigen (PSA) level, Gleason score, and treatments received. The PSA progression-free survival (PFS) model was trained using a ResNet architecture with a Cox proportional hazards loss function using five-fold cross-validation. Performance was assessed using concordance index (C-index) and Kaplan-Meier survival analysis. Among evaluated model architectures, the ResNet-18 backbone offered the best performance. The multi-modal deep learning framework achieved a 5-fold cross-validation C-index ranging from 0.75 to 0.94, outperforming models incorporating imaging only (0.70-0.89) and clinical features only (0.53-0.65). Kaplan-Meir survival analysis performed on the deep learning-derived predictions demonstrated clear risk stratification, with a median PSA progression free survival (PFS) of 19.7 months in the high-risk group and 26 months in the low-risk group (P < 0.001). Deep learning-derived imaging biomarker based on PSMA PET/CT can effectively predict PSA PFS for mPCa patients. Further clinical validation in prospective cohorts is warranted.
Matching journals
The top 4 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Association Between Artificial Intelligence-Derived Tumor Volume and Oncologic Outcomes for Localized Prostate Cancer Treated with Radiation Therapy 93%
- Circulating Tumor-Derived Extracellular Vesicles Predict Clinical Outcomes in 11C Choline-identified Oligometastatic Castration-Refractory Prostate Cancer Treated with Stereotactic Ablative Radiotherapy 92%
- Bayesian Learning to Reduce Cardiac Risk for Locally Advanced NSCLC Patients Based on Personalized Radiotherapy Prescription 91%
Similar papers in this journal
- PSMA+ Extracellular Vesicles are a Biomarker for SABR in Oligorecurrent Prostate Cancer Analysis from the STOMP-like and ORIOLE trial cohorts 92%
- Human Papilloma Virus Circulating Cell-Free DNA Kinetics in Cervical Cancer Patients Undergoing Definitive Chemoradiation 90%
- Leveraging Longitudinal Patient-Reported Outcomes Trajectories to Predict Survival in Non-Small-Cell Lung Cancer 89%
Similar papers in this journal
- Diagnostic accuracy and safety of coaxial core-needle biopsy (CNB) system in Oncology patients treated in a specialist cancer centre with prospective validation within clinical trial data 91%
- Digital Spatial Profiling identifies phospho-JNK as a biomarker for early risk stratification of aggressive prostate cancer 91%
- Predicting Axillary Lymph Node Metastasis in Early Breast Cancer Using Deep Learning on Primary Tumor Biopsy Slides 91%
Similar papers in this journal
- Accurate prognosis for localized prostate cancer through coherent voting networks and multi-omic data 92%
- Comparison of Radiomic Feature Aggregation Methods for Patients with Multiple Tumors 92%
- Towards integration of 64Cu-DOTA-Trasztusumab PET-CT and MRI with mathematical modeling to predict response to neoadjuvant therapy in HER2+ breast cancer 91%
Similar papers in this journal
- Prediction of radiation-induced hypothyroidism using radiomic data analysis does not show superiority over standard normal tissue complication models 92%
- Use of high-plex data reveals novel insights into the tumour microenvironment of clear cell renal cell carcinoma 90%
- Breast invasive ductal carcinoma classification on whole slide images with weakly-supervised and transfer learning 90%
"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.