| 1. |
|
|
| 2. |
|
|
| 3. |
- Christiansen, F., et al.
(författare)
-
Ultrasound image analysis using deep neural networks for discriminating between benign and malignant ovarian tumors : comparison with expert subjective assessment
- 2021
-
Ingår i: Ultrasound in Obstetrics and Gynecology. - : Wiley. - 0960-7692 .- 1469-0705. ; 57:1, s. 155-163
-
Tidskriftsartikel (refereegranskat)abstract
- Objectives: To develop and test the performance of computerized ultrasound image analysis using deep neural networks (DNNs) in discriminating between benign and malignant ovarian tumors and to compare its diagnostic accuracy with that of subjective assessment (SA) by an ultrasound expert. Methods: We included 3077 (grayscale, n = 1927; power Doppler, n = 1150) ultrasound images from 758 women with ovarian tumors, who were classified prospectively by expert ultrasound examiners according to IOTA (International Ovarian Tumor Analysis) terms and definitions. Histological outcome from surgery (n = 634) or long-term (>= 3 years) follow-up (n = 124) served as the gold standard. The dataset was split into a training set (n = 508; 314 benign and 194 malignant), a validation set (n = 100; 60 benign and 40 malignant) and a test set (n = 150; 75 benign and 75 malignant). We used transfer learning on three pre-trained DNNs: VGG16, ResNet50 and MobileNet. Each model was trained, and the outputs calibrated, using temperature scaling. An ensemble of the three models was then used to estimate the probability of malignancy based on all images from a given case. The DNN ensemble classified the tumors as benign or malignant (Ovry-Dx1 model); or as benign, inconclusive or malignant (Ovry-Dx2 model). The diagnostic performance of the DNN models, in terms of sensitivity and specificity, was compared to that of SA for classifying ovarian tumors in the test set. Results: At a sensitivity of 96.0%, Ovry-Dx1 had a specificity similar to that of SA (86.7% vs 88.0%; P = 1.0). Ovry-Dx2 had a sensitivity of 97.1% and a specificity of 93.7%, when designating 12.7% of the lesions as inconclusive. By complimenting Ovry-Dx2 with SA in inconclusive cases, the overall sensitivity (96.0%) and specificity (89.3%) were not significantly different from using SA in all cases (P = 1.0). Conclusion: Ultrasound image analysis using DNNs can predict ovarian malignancy with a diagnostic accuracy comparable to that of human expert examiners, indicating that these models may have a role in the triage of women with an ovarian tumor.
|
|
| 4. |
|
|
| 5. |
|
|
| 6. |
|
|
| 7. |
- Gliga, AR, et al.
(författare)
-
Transcriptome Profiling and Toxicity Following Long-Term, Low Dose Exposure of Human Lung Cells to Ni and NiO Nanoparticles-Comparison with NiCl2
- 2020
-
Ingår i: Nanomaterials (Basel, Switzerland). - : MDPI AG. - 2079-4991. ; 10:4
-
Tidskriftsartikel (refereegranskat)abstract
- Production of nickel (Ni) and nickel oxide (NiO) nanoparticles (NPs) leads to a risk of exposure and subsequent health effects. Understanding the toxicological effects and underlying mechanisms using relevant in vitro methods is, therefore, needed. The aim of this study is to explore changes in gene expression using RNA sequencing following long term (six weeks) low dose (0.5 µg Ni/mL) exposure of human lung cells (BEAS-2B) to Ni and NiO NPs as well as soluble NiCl2. Genotoxicity and cell transformation as well as cellular dose of Ni are also analyzed. Exposure to NiCl2 resulted in the largest number of differentially expressed genes (197), despite limited uptake, suggesting a major role of extracellular receptors and downstream signaling. Gene expression changes for all Ni exposures included genes coding for calcium-binding proteins (S100A14 and S100A2) as well as TIMP3, CCND2, EPCAM, IL4R and DDIT4. Several top enriched pathways for NiCl2 were defined by upregulation of, e.g., interleukin-1A and -1B, as well as Vascular Endothelial Growth Factor A (VEGFA). All Ni exposures caused DNA strand breaks (comet assay), whereas no induction of micronuclei was observed. Taken together, this study provides an insight into Ni-induced toxicity and mechanisms occurring at lower and more realistic exposure levels.
|
|
| 8. |
- Ninou, AH, et al.
(författare)
-
PFKFB3 Inhibition Sensitizes DNA Crosslinking Chemotherapies by Suppressing Fanconi Anemia Repair
- 2021
-
Ingår i: Cancers. - : MDPI AG. - 2072-6694. ; 13:14
-
Tidskriftsartikel (refereegranskat)abstract
- Replicative repair of interstrand crosslinks (ICL) generated by platinum chemotherapeutics is orchestrated by the Fanconi anemia (FA) repair pathway to ensure resolution of stalled replication forks and the maintenance of genomic integrity. Here, we identify novel regulation of FA repair by the cancer-associated glycolytic enzyme PFKFB3 that has functional consequences for replication-associated ICL repair and cancer cell survival. Inhibition of PFKFB3 displays a cancer-specific synergy with platinum compounds in blocking cell viability and restores sensitivity in treatment-resistant models. Notably, the synergies are associated with DNA-damage-induced chromatin association of PFKFB3 upon cancer transformation, which further increases upon platinum resistance. FA pathway activation triggers the PFKFB3 assembly into nuclear foci in an ATR- and FANCM-dependent manner. Blocking PFKFB3 activity disrupts the assembly of key FA repair factors and consequently prevents fork restart. This results in an incapacity to replicate cells to progress through S-phase, an accumulation of DNA damage in replicating cells, and fork collapse. We further validate PFKFB3-dependent regulation of FA repair in ex vivo cultures from cancer patients. Collectively, targeting PFKFB3 opens up therapeutic possibilities to improve the efficacy of ICL-inducing cancer treatments.
|
|
| 9. |
|
|
| 10. |
|
|
