| 1. |
- Bulten, W, et al.
(författare)
-
Artificial intelligence for diagnosis and Gleason grading of prostate cancer: the PANDA challenge
- 2022
-
Ingår i: Nature medicine. - : Springer Science and Business Media LLC. - 1546-170X .- 1078-8956. ; 28:21, s. 154-
-
Tidskriftsartikel (refereegranskat)abstract
- Artificial intelligence (AI) has shown promise for diagnosing prostate cancer in biopsies. However, results have been limited to individual studies, lacking validation in multinational settings. Competitions have been shown to be accelerators for medical imaging innovations, but their impact is hindered by lack of reproducibility and independent validation. With this in mind, we organized the PANDA challenge—the largest histopathology competition to date, joined by 1,290 developers—to catalyze development of reproducible AI algorithms for Gleason grading using 10,616 digitized prostate biopsies. We validated that a diverse set of submitted algorithms reached pathologist-level performance on independent cross-continental cohorts, fully blinded to the algorithm developers. On United States and European external validation sets, the algorithms achieved agreements of 0.862 (quadratically weighted κ, 95% confidence interval (CI), 0.840–0.884) and 0.868 (95% CI, 0.835–0.900) with expert uropathologists. Successful generalization across different patient populations, laboratories and reference standards, achieved by a variety of algorithmic approaches, warrants evaluating AI-based Gleason grading in prospective clinical trials.
|
|
| 2. |
- Rådestad, E., et al.
(författare)
-
Characterization of infiltrating lymphocytes in human benign and malignant prostate tissue
- 2017
-
Ingår i: Oncotarget. - : Impact Journals LLC. - 1949-2553. ; 8:36, s. 60257-60269
-
Tidskriftsartikel (refereegranskat)abstract
- Immune checkpoint blockade has shown promising results in numerous cancer types. However, in prostate cancer (PC), absent or limited responses have been reported. To investigate further, we compared the phenotype of infiltrating T-cells isolated from prostate tissue from patients with PC (n = 5), benign prostatic hyperplasia (BPH) (n = 27), BPH with concurrent PC (n = 4) and controls (n = 7). The majority of T-cells were CD8+ and had a CCR7-CD45RO+ effector memory phenotype. However, the yield of T-cells isolated from PC lesions was on average 20-fold higher than that obtained from control prostates. Furthermore, there were differences between the prostate conditions regarding the percentage of T-cells expressing several activation markers and co-inhibitory receptors. In conclusion, many prostateinfiltrating T-cells express co-inhibitory receptors PD-1 and LAG-3, regardless of prostate condition. Despite the observed increase in counts and percentages of PD- 1+ T-cells in PC, the concomitant demonstration of high percentage of PD-1+ T-cells in control prostates suggests that PD-1 may play a role in controlling the homeostasis of the prostate rather than in contributing to PC-associated immune-suppression. Thus, PD-1 may not be a good candidate for checkpoint blockade in PC and these data are relevant for evaluation of clinical trials and in designing future immunotherapeutic approaches of PC.
|
|
