| 11. |
|
|
| 12. |
- Helland, Ragnhild Holden, et al.
(författare)
-
Segmentation of glioblastomas in early post-operative multi-modal MRI with deep neural networks.
- 2023
-
Ingår i: Scientific reports. - 2045-2322. ; 13:1
-
Tidskriftsartikel (refereegranskat)abstract
- Extent of resection after surgery is one of the main prognostic factors for patients diagnosed with glioblastoma. To achieve this, accurate segmentation and classification of residual tumor from post-operative MR images is essential. The current standard method for estimating it is subject to high inter- and intra-rater variability, and an automated method for segmentation of residual tumor in early post-operative MRI could lead to a more accurate estimation of extent of resection. In this study, two state-of-the-art neural network architectures for pre-operative segmentation were trained for the task. The models were extensively validated on a multicenter dataset with nearly 1000 patients, from 12 hospitals in Europe and the United States. The best performance achieved was a 61% Dice score, and the best classification performance was about 80% balanced accuracy, with a demonstrated ability to generalize across hospitals. In addition, the segmentation performance of the best models was on par with human expert raters. The predicted segmentations can be used to accurately classify the patients into those with residual tumor, and those with gross total resection.
|
|
| 13. |
|
|
| 14. |
- Taskén, Kjetil, et al.
(författare)
-
Single point of entry to the European precision cancer medicine trial network PRIME-ROSE
- 2024
-
Ingår i: Journal of Clinical Oncology. - : American Society of Clinical Oncology. - 1527-7755 .- 0732-183X. ; 42:16
-
Konferensbidrag (refereegranskat)abstract
- Background: Over the last decades, there has been a surge in the development and approval of targeted drugs and immunotherapies for treating cancer patients, as seen by the 757 % increase in approvals by the FDA for new cancer treatments since 2000 (1). This has significantly impacted cancer care and contributed to improving overall survival in various cancer subgroups. However, access to these new treatments is constrained by the market access strategy of the patent-owning company and available knowledge of treatment effects. Only a few treatments have received pan-cancer approval from EMA or FDA, and most drugs receive market authorization per indication. As a result, there is a widening access gap between patients with different cancer types (2). Methods: Exploring the effect of biomarker-driven treatments in new cancer subtypes requires the ability to find patients with rare biomarkers. PRIME-ROSE is a European precision medicine network comprising 11 ongoing or soon-to-start national DRUP-like clinical trials testing registered drugs outside their current label (www.prime-rose.eu). Patients with relevant tumor biomarkers are identified and treated with matched drugs available in each trial’s drug portfolio. The ambition is to swiftly and systematically evaluate the effectiveness of approved precision cancer medicines in new indications through pragmatic trial designs and with RWE control cohorts, ensuring expansion into all relevant patient groups to maximize societal benefit. This is particularly relevant for rare cancers, which are enriched in precision medicine trials (3). Results: In PRIME-ROSE, the trials now share and aggregate data to build evidence faster and more effectively impact patient care by addressing key challenges in precision cancer medicine implementation (increasing the recruitment area to 71 million inhabitants). This will significantly reduce the time for filling treatment cohorts and contribute to closing the indication/drug-specific knowledge gap. In fact, several pharmaceutical companies have already shown their interest in and commitment to participating in PRIME-ROSE, as it offers the unique advantage of entering the trials in the network simultaneously (single point of entry) and with a floating allocation of treatment slots between trials, increasing efficiency in finding patients with specific biomarkers to fill treatment cohorts. Conclusions: A unified entry point to the PRIME-ROSE network is feasible and can facilitate building the knowledge base faster for label expansion and/or country-specific approvals/ reimbursement. National multi-stakeholder ecosystems that include pragmatic, RWE-controlled DRUP-like clinical trials may advance precision medicine implementation.
|
|
