Detection of Local Prostate Cancer Recurrence from PET/CT Scans Using Deep Learning
Authors:
- Marko KorbMKMarko Korb
- Hülya EfetürkHEHülya Efetürk
- Tim JedamzikTJTim Jedamzik
- Philipp E. HartrampfPHPhilipp E. Hartrampf
- Aleksander KosmalaAKAleksander Kosmala
- Sebastian E. SerflingSSSebastian E. Serfling
- Robin DirkRDRobin Dirk
- Kerstin MichalskiKMKerstin Michalski
- Andreas K. BuckABAndreas K. Buck
- Rudolf A. WernerRWRudolf A. Werner
- Wiebke SchlötelburgWSWiebke Schlötelburg
- Markus J. AnkenbrandMAMarkus J. Ankenbrand
Open Access
Abstract
Background: Prostate cancer (PC) is a leading cause of cancer-related deaths in men worldwide. PSMA-directed positron emission tomography (PET) has shown promising results in detecting recurrent PC and metastasis, improving the accuracy of diagnosis and treatment planning. To evaluate an artificial intelligence (AI) model based on [18F]-prostate specific membrane antigen (PSMA)-1007 PET datasets for the detection of local recurrence in patients with prostate cancer. Methods: We retrospectively analyzed 1404 [18F]-PSMA-1007 PET/CTs from patients with histologically confirmed prostate cancer. Artificial neural networks were trained to recognize the presence of local recurrence based on the PET data. First, the hyperparameters were optimized for an initial model (model A). Subsequently, the bladder was localized using an already published model and a model (model B) was trained only on a 20 cm cube around the bladder. Finally, two separate models were trained on the same section depending on the prostatectomy status (model C (post-prostatectomy) and model D (non-operated)). Results: Model A achieved an accuracy of 56% on the validation data. By restricting the region to the area around the bladder, Model B achieved a validation accuracy of 71%. When validating the specialized models according to prostatectomy status, model C achieved an accuracy of 77% and model D an accuracy of 77%. All models achieved accuracies of almost 100% on the training data, indicating overfitting. Conclusions: For the presented task, 1404 examinations were insufficient to reach an accuracy of over 90% even when employing data augmentation, including additional metadata and performing automated hyperparameter optimization. The low F1-score and AUC values indicate that none of the presented models produce reliable results. However, we will facilitate future research and the development of better models by openly sharing our source code and all pre-trained models for transfer learning.Keywords
All Related Versions
Funding Information
- Interdisciplinary Center of Clinical Research (IZKF), University Hospital of Wuerzburg (Z-2/91, Z-3BC/08)
This publication has 28 references indexed in Scilit:
- An Automated Deep Learning-Based Framework for Uptake Segmentation and Classification on PSMA PET/CT Imaging of Patients with Prostate CancerJournal of Imaging Informatics in Medicine, 2024
- Prostate cancer grading framework based on deep transfer learning and Aquila optimizerNeural Computing and Applications, 2024
- Overview of the HECKTOR Challenge at MICCAI 2022: Automatic Head and Neck Tumor Segmentation and Outcome Prediction in PET/CT2023
- Deep learning for improving PET/CT attenuation correction by elastic registration of anatomical dataEuropean Journal of Nuclear Medicine and Molecular Imaging, 2023
- PSMA PET/CT: joint EANM procedure guideline/SNMMI procedure standard for prostate cancer imaging 2.0European Journal of Nuclear Medicine and Molecular Imaging, 2023
- Artificial Intelligence–Based Data Corrections for Attenuation and Scatter in Position Emission Tomography and Single-Photon Emission Computed TomographyPET Clinics, 2021
- An [18F]FDG-PET/CT deep learning method for fully automated detection of pathological mediastinal lymph nodes in lung cancer patientsEuropean Journal of Nuclear Medicine and Molecular Imaging, 2021
- Deep learning‐based cardiac cine segmentation: Transfer learning application to 7T ultrahigh‐field MRIMagnetic Resonance in Medicine, 2021
- Deep learning detection of prostate cancer recurrence with 18F-FACBC (fluciclovine, Axumin®) positron emission tomographyEuropean Journal of Nuclear Medicine and Molecular Imaging, 2020
- Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based LocalizationInternational Journal of Computer Vision, 2019