Systems and methods for automated cancer staging and risk prediction
Automated systems employing machine learning algorithms analyze 3D PSMA-PET images to determine prostate cancer staging scores, addressing the limitations of current methods by enhancing accuracy, reproducibility, and standardization.
WO2025072177A1 Publication Date: 2025-04-03PROGENICS PHARMACEUTICALS INC +1
12 Cites 10 Cited by
Patent Information
- Application Number
- PCT/US2024/048177
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2024-05-31
- Filing Date
- 2024-09-24
- Publication Date
- 2025-04-03
AI Technical Summary
Technical Problem
Current methods for staging prostate cancer using PSMA-PET images are time-consuming, prone to errors, and lack reproducibility, leading to subjective judgments and inter-operator variability.
Method used
The development of automated systems and methods that utilize machine learning techniques, specifically convolutional neural networks (CNNs), to analyze 3D PSMA-PET images and determine prostate cancer staging scores, such as the PRIMARY score, by identifying uptake regions and associating them with specific prostate zones.
Benefits of technology
These automated systems provide accurate, reproducible, and standardized reporting of prostate cancer staging, reducing human error and improving consistency across different assessments.
✦ Generated by Eureka AI based on patent content.
Abstract
Presented herein are systems and methods for accurate and automated cancer staging and / or risk prediction. In certain embodiments, cancer staging and / or risk prediction technologies of the present disclosure utilize machine learning techniques to, for example, accurately identify image features indicative of cancerous lesions, such as hotspots resulting from high levels of radiopharmaceutical uptake in tumors. Additionally or alternatively, in certain embodiments, systems and methods of the present disclosure include machine learning techniques that generate predictions of how a disease will evolve, such as whether cancer that appears localized has already, or will eventually, metastasize.
Need to check novelty before this filing date? Find Prior Art