The Role of Quantitative Imaging for Early Detection of Prostate Cancer Progression in Patients on Active Surveillance
Motivation: Patients on Active Surveillance (AS) for prostate cancer have a high risk of cancer progression to treatment. There is a need for additional tools to risk stratify AS patients. Goal(s): To evaluate the Habitat Risk Score (HRS) method for automatic identification of lesions for early detection of AS progressors in a prospective trial. Approach: HRS was assessed in patients that progressed in the 1st, 2nd or 3rd year of AS. Results: In 40% of the patients, HRS identified a dominant lesion that was not targeted during biopsy. The study illustrates the quantitative power of HRS as compared to PIRADS. Impact: Integrating Habitat Risk Score (HRS) in Active Surveillance for prostate cancer has the potential to significantly reduce the number of surveillance biopsies. HRS facilitates the detection of progression through assignment of robust biopsy targets and quantification of tumor habitat changes.
Authors
- Oleksandr N. Kryvenko (ORCID: https://orcid.org/0000-0001-5731-1748)
- Radka Stoyanova (ORCID: https://orcid.org/0000-0002-1301-3228)
- Patricia Castillo (ORCID: https://orcid.org/0000-0001-6290-4361)
- Sanoj Punnen (ORCID: https://orcid.org/0000-0002-0383-7311)
- Ahmad Algohary (ORCID: https://orcid.org/0000-0003-1286-3164)
- Sandra Gaston
- Evangelia I. Zacharaki (ORCID: https://orcid.org/0000-0001-8228-0437)
- Matthew C. Abramowitz (ORCID: https://orcid.org/0000-0002-2632-579X)
- Alan Pollack (ORCID: https://orcid.org/0000-0002-1801-2865)
- Adrian Breto (ORCID: https://orcid.org/0000-0002-4958-2991)
- Veronica Wallaengen
- Isabella Kimbel
Publication Details
- Journal
- Proceedings on CD-ROM - International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition/Proceedings of the International Society for Magnetic Resonance in Medicine, Scientific Meeting and Exhibition
- Published
- 2024-11-26
- DOI
- https://doi.org/10.58530/2024/0551
- Primary Topic
- Radiomics and Machine Learning in Medical Imaging
- Type
- article
- Field-Weighted Citation Impact
- 0.00