| 1. |
- Strom, Peter, et al.
(författare)
-
Artificial intelligence for diagnosis and grading of prostate cancer in biopsies : a population-based, diagnostic study
- 2020
-
Ingår i: The Lancet Oncology. - : Elsevier. - 1470-2045 .- 1474-5488. ; 21:2, s. 222-232
-
Tidskriftsartikel (refereegranskat)abstract
- BackgroundAn increasing volume of prostate biopsies and a worldwide shortage of urological pathologists puts a strain on pathology departments. Additionally, the high intra-observer and inter-observer variability in grading can result in overtreatment and undertreatment of prostate cancer. To alleviate these problems, we aimed to develop an artificial intelligence (AI) system with clinically acceptable accuracy for prostate cancer detection, localisation, and Gleason grading.MethodsWe digitised 6682 slides from needle core biopsies from 976 randomly selected participants aged 50–69 in the Swedish prospective and population-based STHLM3 diagnostic study done between May 28, 2012, and Dec 30, 2014 (ISRCTN84445406), and another 271 from 93 men from outside the study. The resulting images were used to train deep neural networks for assessment of prostate biopsies. The networks were evaluated by predicting the presence, extent, and Gleason grade of malignant tissue for an independent test dataset comprising 1631 biopsies from 246 men from STHLM3 and an external validation dataset of 330 biopsies from 73 men. We also evaluated grading performance on 87 biopsies individually graded by 23 experienced urological pathologists from the International Society of Urological Pathology. We assessed discriminatory performance by receiver operating characteristics and tumour extent predictions by correlating predicted cancer length against measurements by the reporting pathologist. We quantified the concordance between grades assigned by the AI system and the expert urological pathologists using Cohen's kappa.FindingsThe AI achieved an area under the receiver operating characteristics curve of 0·997 (95% CI 0·994–0·999) for distinguishing between benign (n=910) and malignant (n=721) biopsy cores on the independent test dataset and 0·986 (0·972–0·996) on the external validation dataset (benign n=108, malignant n=222). The correlation between cancer length predicted by the AI and assigned by the reporting pathologist was 0·96 (95% CI 0·95–0·97) for the independent test dataset and 0·87 (0·84–0·90) for the external validation dataset. For assigning Gleason grades, the AI achieved a mean pairwise kappa of 0·62, which was within the range of the corresponding values for the expert pathologists (0·60–0·73).InterpretationAn AI system can be trained to detect and grade cancer in prostate needle biopsy samples at a ranking comparable to that of international experts in prostate pathology. Clinical application could reduce pathology workload by reducing the assessment of benign biopsies and by automating the task of measuring cancer length in positive biopsy cores. An AI system with expert-level grading performance might contribute a second opinion, aid in standardising grading, and provide pathology expertise in parts of the world where it does not exist.
|
|
| 2. |
- Bady, Pierre, et al.
(författare)
-
DNA methylation-based age acceleration observed in IDH wild-type glioblastoma is associated with better outcome - including in elderly patients
- 2022
-
Ingår i: Acta neuropathologica communications. - : BMC. - 2051-5960. ; 10:1
-
Tidskriftsartikel (refereegranskat)abstract
- Elderly patients represent a growing proportion of individuals with glioblastoma, who however, are often excluded from clinical trials owing to poor expected prognosis. We aimed at identifying age-related molecular differences that would justify and guide distinct treatment decisions in elderly glioblastoma patients. The combined DNA methylome (450 k) of four IDH wild-type glioblastoma datasets, comprising two clinical trial cohorts, was interrogated for differences based on the patients age, DNA methylation (DNAm) age acceleration (DNAm age "Horvath-clock" minus patient age), DNA methylation-based tumor classification (Heidelberg), entropy, and functional methylation of DNA damage response (DDR) genes. Age dependent methylation included 19 CpGs (p-value <= 0.1, Bonferroni corrected), comprising a CpG located in the ELOVL2 gene that is part of a 13-gene forensic age predictor. Most of the age related CpGs (n = 16) were also associated with age acceleration that itself was associated with a large number of CpGs (n = 50,551). Over 70% age acceleration-associated CpGs (n = 36,348) overlapped with those associated with the DNA methylation based tumor classification (n = 170,759). Gene set enrichment analysis identified associated pathways, providing insights into the biology of DNAm age acceleration and respective commonalities with glioblastoma classification. Functional methylation of several DDR genes, defined as correlation of methylation with gene expression (r <= -0.3), was associated with age acceleration (n = 8), tumor classification (n = 12), or both (n = 4), the latter including MGMT. DNAm age acceleration was significantly associated with better outcome in both clinical trial cohorts, whereof one comprised only elderly patients. Multivariate analysis included treatment (RT, RT/TMZ -> TMZ; TMZ, RT), MGMT promoter methylation status, and interaction with treatment. In conclusion, DNA methylation features of age acceleration are an integrative part of the methylation-based tumor classification (RTK I, RTK II, MES), while patient age seems hardly reflected in the glioblastoma DNA methylome. We found no molecular evidence justifying other treatments in elderly patients, not owing to frailty or co-morbidities.
|
|
| 3. |
- Conti, David, V, et al.
(författare)
-
Trans-ancestry genome-wide association meta-analysis of prostate cancer identifies new susceptibility loci and informs genetic risk prediction
- 2021
-
Ingår i: Nature Genetics. - : Springer Nature. - 1061-4036 .- 1546-1718. ; 53:1, s. 65-75
-
Tidskriftsartikel (refereegranskat)abstract
- Prostate cancer is a highly heritable disease with large disparities in incidence rates across ancestry populations. We conducted a multiancestry meta-analysis of prostate cancer genome-wide association studies (107,247 cases and 127,006 controls) and identified 86 new genetic risk variants independently associated with prostate cancer risk, bringing the total to 269 known risk variants. The top genetic risk score (GRS) decile was associated with odds ratios that ranged from 5.06 (95% confidence interval (CI), 4.84-5.29) for men of European ancestry to 3.74 (95% CI, 3.36-4.17) for men of African ancestry. Men of African ancestry were estimated to have a mean GRS that was 2.18-times higher (95% CI, 2.14-2.22), and men of East Asian ancestry 0.73-times lower (95% CI, 0.71-0.76), than men of European ancestry. These findings support the role of germline variation contributing to population differences in prostate cancer risk, with the GRS offering an approach for personalized risk prediction. A meta-analysis of genome-wide association studies across different populations highlights new risk loci and provides a genetic risk score that can stratify prostate cancer risk across ancestries.
|
|
| 4. |
- Mareschal, Sylvain, et al.
(författare)
-
Challenging conventional karyotyping by next-generation karyotyping in 281 intensively treated patients with AML
- 2021
-
Ingår i: Blood Advances. - : American Society of Hematology. - 2473-9529 .- 2473-9537. ; 5:4, s. 1003-1016
-
Tidskriftsartikel (refereegranskat)abstract
- Although copy number alterations (CNAs) and translocations constitute the backbone of the diagnosis and prognostication of acute myeloid leukemia (AML), techniques used for their assessment in routine diagnostics have not been reconsidered for decades. We used a combination of 2 next-generation sequencing-based techniques to challenge the currently recommended conventional cytogenetic analysis (CCA), comparing the approaches in a series of 281 intensively treated patients with AML. Shallow whole-genome sequencing (sWGS) outperformed CCA in detecting European Leukemia Net (ELN)-defining CNAs and showed that CCA overestimated monosomies and suboptimally reported karyotype complexity. Still, the concordance between CCA and sWGS for all ELN CNA-related criteria was 94%. Moreover, using in silico dilution, we showed that 1 million reads per patient would be enough to accurately assess ELN-defining CNAs. Total genomic loss, defined as a total loss 200 Mb by sWGS, was found to be a better marker for genetic complexity and poor prognosis compared with the CCA-based definition of complex karyotype. For fusion detection, the concordance between CCA and whole-transcriptome sequencing (WTS) was 99%. WTS had better sensitivity in identifying inv(16) and KMT2A rearrangements while showing limitations in detecting lowly expressed PML-RARA fusions. Ligation-dependent reverse transcription polymerase chain reaction was used for validation and was shown to be a fast and reliable method for fusion detection. We conclude that a next-generation sequencing-based approach can replace conventional CCA for karyotyping, provided that efforts are made to cover lowly expressed fusion transcripts.
|
|
| 5. |
- Wang, Anqi, et al.
(författare)
-
Characterizing prostate cancer risk through multi-ancestry genome-wide discovery of 187 novel risk variants
- 2023
-
Ingår i: Nature Genetics. - : Springer Nature. - 1061-4036 .- 1546-1718. ; 55:12, s. 2065-2074
-
Tidskriftsartikel (refereegranskat)abstract
- The transferability and clinical value of genetic risk scores (GRSs) across populations remain limited due to an imbalance in genetic studies across ancestrally diverse populations. Here we conducted a multi-ancestry genome-wide association study of 156,319 prostate cancer cases and 788,443 controls of European, African, Asian and Hispanic men, reflecting a 57% increase in the number of non-European cases over previous prostate cancer genome-wide association studies. We identified 187 novel risk variants for prostate cancer, increasing the total number of risk variants to 451. An externally replicated multi-ancestry GRS was associated with risk that ranged from 1.8 (per standard deviation) in African ancestry men to 2.2 in European ancestry men. The GRS was associated with a greater risk of aggressive versus non-aggressive disease in men of African ancestry (P = 0.03). Our study presents novel prostate cancer susceptibility loci and a GRS with effective risk stratification across ancestry groups.
|
|
| 6. |
- Österroos, Albin, et al.
(författare)
-
Integrated transcriptomic and genomic analysis improves prediction of complete remission and survival in elderly patients with acute myeloid leukemia
- 2020
-
Ingår i: Blood Cancer Journal. - : NATURE PUBLISHING GROUP. - 2044-5385. ; 10:6
-
Tidskriftsartikel (refereegranskat)abstract
- Relevant molecular tools for treatment stratification of patients >= 65 years with acute myeloid leukemia (AML) are lacking. We combined clinical data with targeted DNA- and full RNA-sequencing of 182 intensively and palliatively treated patients to predict complete remission (CR) and survival in AML patients >= 65 years. Intensively treated patients withNPM1andIDH2(R172)mutations had longer overall survival (OS), whereas mutatedTP53conferred lower CR rates and shorter OS.FLT3-ITDandTP53mutations predicted worse OS in palliatively treated patients. Gene expression levels most predictive of CR were combined with somatic mutations for an integrated risk stratification that we externally validated using the beatAML cohort. We defined a high-risk group with a CR rate of 20% in patients with mutatedTP53, compared to 97% CR in low-risk patients defined by high expression ofZBTB7AandEEPD1withoutTP53mutations. Patients without these criteria had a CR rate of 54% (intermediate risk). The difference in CR rates translated into significant OS differences that outperformed ELN stratification for OS prediction. The results suggest that an integrated molecular risk stratification can improve prediction of CR and OS and could be used to guide treatment in elderly AML patients.
|
|
