51
|
Van Herk M, Burnet N, Dinapoli N, Meijer G, Nestlé U, Van den Bongard D, Stock M. EP-1854 Application of a tool for bulk treatment plan evaluation in advanced treatment planning training. Radiother Oncol 2019. [DOI: 10.1016/s0167-8140(19)32274-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/26/2022]
|
52
|
Kostiukhina N, Palmans H, Waid S, Stock M, Georg D, Knäusl B. PO-0977 Improved 4D proton dosimetry via correlation with beam delivery details using log-files. Radiother Oncol 2019. [DOI: 10.1016/s0167-8140(19)31397-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/30/2022]
|
53
|
Stock M, Gora J, Perpar A, Georg P, Kragl G, Hug E, Vondracek V, Kubes J, Algranati C, Cianchetti M, Amichetti M, Kajdrowicz T, Kopec R, Olko P, Skowronska K, Sowa U, Gora E, Kisielewicz K, Sas-Korczynska B, Skora T, Bäck A, Gustafsson M, Sooaru M, Nyström PW, Eriksson TB. PO-0943 Harmonization of proton planning for head and neck cancer using PBS: First report of the IPACS collaboration. Radiother Oncol 2019. [DOI: 10.1016/s0167-8140(19)31363-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/01/2022]
|
54
|
De Baerdemaeker NJF, Stock M, Van den Bulcke J, De Baets B, Van Hoorebeke L, Steppe K. X-ray microtomography and linear discriminant analysis enable detection of embolism-related acoustic emissions. PLANT METHODS 2019; 15:153. [PMID: 31889977 PMCID: PMC6916244 DOI: 10.1186/s13007-019-0543-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/18/2019] [Accepted: 12/05/2019] [Indexed: 05/08/2023]
Abstract
BACKGROUND Acoustic emission (AE) sensing is in use since the late 1960s in drought-induced embolism research as a non-invasive and continuous method. It is very well suited to assess a plant's vulnerability to dehydration. Over the last couple of years, AE sensing has further improved due to progress in AE sensors, data acquisition methods and analysis systems. Despite these recent advances, it is still challenging to detect drought-induced embolism events in the AE sources registered by the sensors during dehydration, which sometimes questions the quantitative potential of AE sensing. RESULTS In quest of a method to separate embolism-related AE signals from other dehydration-related signals, a 2-year-old potted Fraxinus excelsior L. tree was subjected to a drought experiment. Embolism formation was acoustically measured with two broadband point-contact AE sensors while simultaneously being visualized by X-ray computed microtomography (µCT). A machine learning method was used to link visually detected embolism formation by µCT with corresponding AE signals. Specifically, applying linear discriminant analysis (LDA) on the six AE waveform parameters amplitude, counts, duration, signal strength, absolute energy and partial power in the range 100-200 kHz resulted in an embolism-related acoustic vulnerability curve (VCAE-E) better resembling the standard µCT VC (VCCT), both in time and in absolute number of embolized vessels. Interestingly, the unfiltered acoustic vulnerability curve (VCAE) also closely resembled VCCT, indicating that VCs constructed from all registered AE signals did not compromise the quantitative interpretation of the species' vulnerability to drought-induced embolism formation. CONCLUSION Although machine learning could detect similar numbers of embolism-related AE as µCT, there still is insufficient model-based evidence to conclusively attribute these signals to embolism events. Future research should therefore focus on similar experiments with more in-depth analysis of acoustic waveforms, as well as explore the possibility of Fast Fourier transformation (FFT) to remove non-embolism-related AE signals.
Collapse
|
55
|
Stock M, Pahikkala T, Airola A, Waegeman W, De Baets B. Algebraic shortcuts for leave-one-out cross-validation in supervised network inference. Brief Bioinform 2018; 21:262-271. [PMID: 30329015 DOI: 10.1093/bib/bby095] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/27/2018] [Revised: 08/21/2018] [Accepted: 09/06/2018] [Indexed: 12/20/2022] Open
Abstract
Supervised machine learning techniques have traditionally been very successful at reconstructing biological networks, such as protein-ligand interaction, protein-protein interaction and gene regulatory networks. Many supervised techniques for network prediction use linear models on a possibly nonlinear pairwise feature representation of edges. Recently, much emphasis has been placed on the correct evaluation of such supervised models. It is vital to distinguish between using a model to either predict new interactions in a given network or to predict interactions for a new vertex not present in the original network. This distinction matters because (i) the performance might dramatically differ between the prediction settings and (ii) tuning the model hyperparameters to obtain the best possible model depends on the setting of interest. Specific cross-validation schemes need to be used to assess the performance in such different prediction settings.In this work we discuss a state-of-the-art kernel-based network inference technique called two-step kernel ridge regression. We show that this regression model can be trained efficiently, with a time complexity scaling with the number of vertices rather than the number of edges. Furthermore, this framework leads to a series of cross-validation shortcuts that allow one to rapidly estimate the model performance for any relevant network prediction setting. This allows computational biologists to fully assess the capabilities of their models. The machine learning techniques with the algebraic shortcuts are implemented in the RLScore software package: https://github.com/aatapa/RLScore.
Collapse
|
56
|
Carlino A, Stock M, Zagler N, Marrale M, Osorio J, Vatnitsky S, Palmans H. Characterization of PTW-31015 PinPoint ionization chambers in photon and proton beams. ACTA ACUST UNITED AC 2018; 63:185020. [DOI: 10.1088/1361-6560/aadd39] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/12/2022]
|
57
|
Stock M, Pahikkala T, Airola A, De Baets B, Waegeman W. A Comparative Study of Pairwise Learning Methods Based on Kernel Ridge Regression. Neural Comput 2018; 30:2245-2283. [PMID: 29894652 DOI: 10.1162/neco_a_01096] [Citation(s) in RCA: 12] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/27/2023]
Abstract
Many machine learning problems can be formulated as predicting labels for a pair of objects. Problems of that kind are often referred to as pairwise learning, dyadic prediction, or network inference problems. During the past decade, kernel methods have played a dominant role in pairwise learning. They still obtain a state-of-the-art predictive performance, but a theoretical analysis of their behavior has been underexplored in the machine learning literature. In this work we review and unify kernel-based algorithms that are commonly used in different pairwise learning settings, ranging from matrix filtering to zero-shot learning. To this end, we focus on closed-form efficient instantiations of Kronecker kernel ridge regression. We show that independent task kernel ridge regression, two-step kernel ridge regression, and a linear matrix filter arise naturally as a special case of Kronecker kernel ridge regression, implying that all these methods implicitly minimize a squared loss. In addition, we analyze universality, consistency, and spectral filtering properties. Our theoretical results provide valuable insights into assessing the advantages and limitations of existing pairwise learning methods.
Collapse
|
58
|
Reisz N, Kuess P, Fuchs H, Steininger P, Messner I, Law A, Deutschmann H, Stock M, Ableitinger A, Georg D. PO-1007: Monte Carlo modelling of the ImagingRing System – a new method for realistic X-ray distribution. Radiother Oncol 2018. [DOI: 10.1016/s0167-8140(18)31317-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
|
59
|
Resch A, Carlino A, Fuchs H, Elia A, Stock M, Georg D, Grevillot L. EP-1805: Dose calculation accuracy of Gate/Geant4 on transverse dose profiles of proton pencil beams in water. Radiother Oncol 2018. [DOI: 10.1016/s0167-8140(18)32114-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/14/2022]
|
60
|
Haymerle G, Enzenhofer E, Lechner W, Stock M, Schratter-Sehn A, Vyskocil E, Bachtiary B, Selzer E, Erovic B. Cover Image. Clin Otolaryngol 2018. [DOI: 10.1111/coa.13083] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/27/2022]
|
61
|
Kostiukhina N, Clausen M, Stock M, Georg D, Knäusl B. OC-0602: Characterization of a novel breathing phantom for 4D applications in ion beam therapy. Radiother Oncol 2018. [DOI: 10.1016/s0167-8140(18)30912-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/14/2022]
|
62
|
Nicolaï N, De Leersnyder F, Copot D, Stock M, Ionescu CM, Gernaey KV, Nopens I, De Beer T. Liquid‐to‐solid ratio control as an advanced process control solution for continuous twin‐screw wet granulation. AIChE J 2018. [DOI: 10.1002/aic.16161] [Citation(s) in RCA: 15] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/16/2023]
|
63
|
Lehmann R, Müller M, Klassert TE, Driesch D, Stock M, Heinrich A, Conrad T, Moore C, Schier U, Guthke R, Slevogt H. Differential regulation of the transcriptomic and secretomic landscape of sensor and effector funtions of human airway epithelial cells. Pneumologie 2018. [DOI: 10.1055/s-0037-1619390] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/28/2022]
|
64
|
Verona C, Magrin G, Solevi P, Bandorf M, Marinelli M, Stock M, Verona Rinati G. Toward the use of single crystal diamond based detector for ion-beam therapy microdosimetry. RADIAT MEAS 2018. [DOI: 10.1016/j.radmeas.2018.02.001] [Citation(s) in RCA: 24] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/27/2022]
|
65
|
Carlino A, Gouldstone C, Kragl G, Traneus E, Marrale M, Vatnitsky S, Stock M, Palmans H. End-to-end tests using alanine dosimetry in scanned proton beams. ACTA ACUST UNITED AC 2018; 63:055001. [DOI: 10.1088/1361-6560/aaac23] [Citation(s) in RCA: 10] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/11/2022]
|
66
|
Haymerle G, Enzenhofer E, Lechner W, Stock M, Schratter-Sehn A, Vyskocil E, Bachtiary B, Selzer E, Erovic BM. The effect of adjuvant radiotherapy on radial forearm free flap volume after soft palate reconstruction in 13 patients. Clin Otolaryngol 2017; 43:742-745. [PMID: 29194976 DOI: 10.1111/coa.13042] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 11/26/2017] [Indexed: 12/01/2022]
|
67
|
Stock M, Grevillot L, Kragl G, Ableitinger A, Palmans H, Osorio J, Böhlen T, Gora J, Hopfgartner J, Letellier V, Dreindl R, Fuchs H, Knäusl B, Carlino A, Utz A, Mumot M, Zechner A, Elia A, Vatnitsky S. 46. Medical commissioning of a Light Ion Beam Therapy facility: The MedAustron experience of starting up using innovative technology. Phys Med 2017. [DOI: 10.1016/j.ejmp.2017.10.071] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 11/30/2022] Open
|
68
|
Van Peer G, De Paepe A, Stock M, Anckaert J, Volders PJ, Vandesompele J, De Baets B, Waegeman W. miSTAR: miRNA target prediction through modeling quantitative and qualitative miRNA binding site information in a stacked model structure. Nucleic Acids Res 2017; 45:e51. [PMID: 27986855 PMCID: PMC5397177 DOI: 10.1093/nar/gkw1260] [Citation(s) in RCA: 11] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/14/2014] [Accepted: 12/09/2016] [Indexed: 11/14/2022] Open
Abstract
In microRNA (miRNA) target prediction, typically two levels of information need to be modeled: the number of potential miRNA binding sites present in a target mRNA and the genomic context of each individual site. Single model structures insufficiently cope with this complex training data structure, consisting of feature vectors of unequal length as a consequence of the varying number of miRNA binding sites in different mRNAs. To circumvent this problem, we developed a two-layered, stacked model, in which the influence of binding site context is separately modeled. Using logistic regression and random forests, we applied the stacked model approach to a unique data set of 7990 probed miRNA-mRNA interactions, hereby including the largest number of miRNAs in model training to date. Compared to lower-complexity models, a particular stacked model, named miSTAR (miRNA stacked model target prediction; www.mi-star.org), displays a higher general performance and precision on top scoring predictions. More importantly, our model outperforms published and widely used miRNA target prediction algorithms. Finally, we highlight flaws in cross-validation schemes for evaluation of miRNA target prediction models and adopt a more fair and stringent approach.
Collapse
|
69
|
Stock M, Distler A, Distler J, Beyer C, Ruiz-Heiland G, Ipseiz N, Seeling M, Krönke G, Nimmerjahn F, Schett G. Corrigendum to "Fc-gamma receptors are not involved in cartilage damage during experimental osteoarthritis" [Osteoarthritis Cartilage 23 (2015) 1221-1225]. Osteoarthritis Cartilage 2017; 25:995. [PMID: 27865755 DOI: 10.1016/j.joca.2016.11.003] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 02/02/2023]
|
70
|
Fernandez J, Rouzard K, Webb C, Voronkov M, Healy J, Huber K, Stock J, Stock M, Gordon J, Perez E. 641 SIG-1459 and SIG-1460: Novel anti-acne phytyl-cysteine compounds. J Invest Dermatol 2017. [DOI: 10.1016/j.jid.2017.02.663] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/19/2022]
|
71
|
Häussler R, Gritsai Y, Zschau E, Missbach R, Sahm H, Stock M, Stolle H. Large real-time holographic 3D displays: enabling components and results. APPLIED OPTICS 2017; 56:F45-F52. [PMID: 28463298 DOI: 10.1364/ao.56.000f45] [Citation(s) in RCA: 8] [Impact Index Per Article: 1.1] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/07/2023]
Abstract
A holographic 3D display with 300 mm×200 mm active area was built. The display includes a spatial light modulator that modulates amplitude and phase of light and thus enables holographic reconstruction with high efficiency. Furthermore, holographic optical elements in photopolymer films and laser light sources are used. The requirements on these optical components are discussed. Photographs taken at the display demonstrate that a 3D scene is reconstructed in depth, thus enabling selective accommodation of the observer's eye lenses and natural depth perception. The results demonstrate the advantages of SeeReal's holographic 3D display solution.
Collapse
|
72
|
Böhlen T, Dreindl R, Osorio J, Kragl G, Stock M. PO-0800: Log file based performance characterization of a PBS dose delivery system with dose re-computation. Radiother Oncol 2017. [DOI: 10.1016/s0167-8140(17)31237-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/19/2022]
|
73
|
Carlino A, Palmans H, Kragl G, Traneus E, Gouldstone C, Vatnitsky S, Stock M. PO-0806: Dosimetric end-to-end test procedures using alanine dosimetry in scanned proton beam therapy. Radiother Oncol 2017. [DOI: 10.1016/s0167-8140(17)31243-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/19/2022]
|
74
|
Grevillot L, Osorio J, Letellier V, Dreindl R, Elia A, Fuchs H, Carlino A, Vatnitsky S, Palmans H, Stock M. EP-1450: Implementation of dosimetry equipment and phantoms in clinical practice of light ion beam therapy. Radiother Oncol 2017. [DOI: 10.1016/s0167-8140(17)31885-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/19/2022]
|
75
|
Kragl G, Böhlen T, Carlino A, Grevillot L, Palmans H, Elia A, Knäusl B, Osorio J, Dreindl R, Hopfgartner J, Vatnitsky S, Stock M. EP-1556: Dosimetric commissioning of a TPS for a synchrotron-based proton PBS delivery system. Radiother Oncol 2017. [DOI: 10.1016/s0167-8140(17)31991-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
|