| 1. |
- Buddenkotte, Thomas, et al.
(author)
-
Deep learning-based segmentation of multisite disease in ovarian cancer
- 2023
-
In: EUROPEAN RADIOLOGY EXPERIMENTAL. - : Springer Nature. - 2509-9280. ; 7:1
-
Journal article (peer-reviewed)abstract
- Purpose: To determine if pelvic/ovarian and omental lesions of ovarian cancer can be reliably segmented on computed tomography (CT) using fully automated deep learning-based methods.Methods: A deep learning model for the two most common disease sites of high-grade serous ovarian cancer lesions (pelvis/ovaries and omentum) was developed and compared against the well-established “no-new-Net” framework and unrevised trainee radiologist segmentations. A total of 451 CT scans collected from four different institutions were used for training (n = 276), evaluation (n = 104) and testing (n = 71) of the methods. The performance was evaluated using the Dice similarity coefficient (DSC) and compared using a Wilcoxon test.Results: Our model outperformed no-new-Net for the pelvic/ovarian lesions in cross-validation, on the evaluation and test set by a significant margin (p values being 4 × 10–7, 3 × 10–4, 4 × 10–2, respectively), and for the omental lesions on the evaluation set (p = 1 × 10–3). Our model did not perform significantly differently in segmenting pelvic/ovarian lesions (p = 0.371) compared to a trainee radiologist. On an independent test set, the model achieved a DSC performance of 71 ± 20 (mean ± standard deviation) for pelvic/ovarian and 61 ± 24 for omental lesions.Conclusion: Automated ovarian cancer segmentation on CT scans using deep neural networks is feasible and achieves performance close to a trainee-level radiologist for pelvic/ovarian lesions.Relevance statement: Automated segmentation of ovarian cancer may be used by clinicians for CT-based volumetric assessments and researchers for building complex analysis pipelines.Key points:The first automated approach for pelvic/ovarian and omental ovarian cancer lesion segmentation on CT images has been presented.Automated segmentation of ovarian cancer lesions can be comparable with manual segmentation of trainee radiologists.Careful hyperparameter tuning can provide models significantly outperforming strong state-of-the-art baselines. Graphical Abstract: [Figure not available: see fulltext.]
|
|
| 2. |
- Burnum-Johnson, Kristin E., et al.
(author)
-
New Views of Old Proteins : Clarifying the Enigmatic Proteome
- 2022
-
In: Molecular & Cellular Proteomics. - : Elsevier BV. - 1535-9476 .- 1535-9484. ; 21:7
-
Journal article (peer-reviewed)abstract
- All human diseases involve proteins, yet our current tools to characterize and quantify them are limited. To better elucidate proteins across space, time, and molecular composition, we provide a >10 years of projection for technologies to meet the challenges that protein biology presents. With a broad perspective, we discuss grand opportunities to transition the science of proteomics into a more propulsive enterprise. Extrapolating recent trends, we describe a next generation of approaches to define, quantify, and visualize the multiple dimensions of the proteome, thereby transforming our understanding and interactions with human disease in the coming decade.
|
|
| 3. |
- Go, Eden P, et al.
(author)
-
Mass spectrometry reveals specific and global molecular transformations during viral infection.
- 2006
-
In: Journal of Proteome Research. - : American Chemical Society (ACS). - 1535-3893 .- 1535-3907. ; 5:9, s. 2405-16
-
Journal article (peer-reviewed)abstract
- Mass spectrometry analysis was used to target three different aspects of the viral infection process: the expression kinetics of viral proteins, changes in the expression levels of cellular proteins, and the changes in cellular metabolites in response to viral infection. The combination of these methods represents a new, more comprehensive approach to the study of viral infection revealing the complexity of these events within the infected cell. The proteins associated with measles virus (MV) infection of human HeLa cells were measured using a label-free approach. On the other hand, the regulation of cellular and Flock House Virus (FHV) proteins in response to FHV infection of Drosophila cells was monitored using stable isotope labeling. Three complementary techniques were used to monitor changes in viral protein expression in the cell and host protein expression. A total of 1500 host proteins was identified and quantified, of which over 200 proteins were either up- or down-regulated in response to viral infection, such as the up-regulation of the Drosophila apoptotic croquemort protein, and the down-regulation of proteins that inhibited cell death. These analyses also demonstrated the up-regulation of viral proteins functioning in replication, inhibition of RNA interference, viral assembly, and RNA encapsidation. Over 1000 unique metabolites were also observed with significant changes in over 30, such as the down-regulated cellular phospholipids possibly reflecting the initial events in cell death and viral release. Overall, the cellular transformation that occurs upon viral infection is a process involving hundreds of proteins and metabolites, many of which are structurally and functionally uncharacterized.
|
|
