• No results found

University of Groningen Methodological aspects and standardization of PET radiomics studies Pfaehler, Elisabeth

N/A
N/A
Protected

Academic year: 2021

Share "University of Groningen Methodological aspects and standardization of PET radiomics studies Pfaehler, Elisabeth"

Copied!
6
0
0

Bezig met laden.... (Bekijk nu de volledige tekst)

Hele tekst

(1)

University of Groningen

Methodological aspects and standardization of PET radiomics studies

Pfaehler, Elisabeth

DOI:

10.33612/diss.149306583

IMPORTANT NOTE: You are advised to consult the publisher's version (publisher's PDF) if you wish to cite from it. Please check the document version below.

Document Version

Publisher's PDF, also known as Version of record

Publication date: 2021

Link to publication in University of Groningen/UMCG research database

Citation for published version (APA):

Pfaehler, E. (2021). Methodological aspects and standardization of PET radiomics studies. University of Groningen. https://doi.org/10.33612/diss.149306583

Copyright

Other than for strictly personal use, it is not permitted to download or to forward/distribute the text or part of it without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license (like Creative Commons).

Take-down policy

If you believe that this document breaches copyright please contact us providing details, and we will remove access to the work immediately and investigate your claim.

Downloaded from the University of Groningen/UMCG research database (Pure): http://www.rug.nl/research/portal. For technical reasons the number of authors shown on this cover page is limited to 10 maximum.

(2)

205

Chapter 11

(3)

206

Without the help of many people I would not be where I am today. In the next lines, I would like to thank everyone who supported me in the last years.

First of all, I would like to thank my supervisors Ronald and Johan for giving me the opportunity to make a PhD in the exciting field of medical image processing and for all the help and guidance in the last years. Ronald, I was very lucky to have such a reliable, experienced, and professional supervisor during my PhD. Thanks a lot for teaching me so many things about medical image processing and PET imaging. I appreciate a lot that I could always rely on you. Was it that you were reading the manuscripts on time, you were re-scheduling a meeting for me, or answering fast to emails. I learned a lot in our discussions and appreciate always your input and thoughts about the different projects. Thank you for letting me explore my own ideas and supporting me. Johan, thank you for the help in programming and phantom scanning. Thank you for your friendly and helpful advices and your moral support.

Moreover, I want to thank all other people who helped me with my projects: First, thanks a lot to Alex Zwanenburg for the always friendly and nice answers and for helping me to improve the speed of my code. I learned a lot about efficient programming from you. Thanks a lot to Bram for the effort you made to make the 3D printed tumour inserts and for always being friendly and helpful. For me, this project was a lot of fun and it would for sure not have been possible without you. Also thanks a lot to Hinke for the help with the phantom scanning. Thanks to Paul, Bram, and Rolf for helping me with organizing the phantom scans. Thanks a lot to every co-author who helped me to improve the quality of the manuscript, giving me new ideas or constructive comments. Thank you Alberto, Ivan, and Len for the chance to write the review together, the lessons about GANs and for opening the way to future collaborations.

Thanks a lot to all the people organizing and maintaining the Peregrine cluster. Without your work, at least three chapters of this thesis would not have been possible. Thanks a lot for your always fast, nice, and helpful answers to my questions. Moreover, I want to thank the people maintaining the ITK mailing list for the always helpful answers!

Besides the people who helped me in the last four years, I would also like to thank my supervisor during my diploma thesis Hans Meine for teaching me how to program. I have to admit that I appreciate the effort you made for me much more now than I did during my time in Bremen. Thank you for being sometimes very strict with me.

Thanks a lot to Gerda and Sarita for helping with everything! I would also like to thank Klaas Willem for the help whenever there was a problem with the computer.

I would like to thank each PhD student in the department who supported me in the last years. Anna, thanks a lot for the many coffees, soups, salads, walks, and conversations.

(4)

207

Groningen would have been very grey without you. Joyce, thanks a lot for the time we spent together in the last years. Thanks for sharing the love to do sports and everything else. It was very nice to meet you in Groningen and I hope, we will see us again on conferences or when we come over for a visit. Thanks also for being my paranymph and for all the help. Lara and Miguel, thanks a lot for all the support in the last years. It was a pleasure to meet you in Groningen and I hope we will meet once again in Galicia, any other place in Spain or in Germany. Thanks a lot for making Groningen more live-able, for the nice cooking, and for being so nice with Maya. Rodrigo, Groningen was more sunny because you were there. I appreciated a lot to have you around and was always happy when we had some time to talk. Thank you for the time we spent together, for your friendship and everything else. Thanks a lot to Ananthi, Andrea, Emile, Ming, and all other office mates for the nice company in the office and at conferences.

Thanks a lot to the group of ‘Duitse Mamas’ for the nice time spent together, for understanding me, for all conversations, and all advices! I do not know how the last years would have been without you.

Thanks to Saskia and Philippe. Thanks a lot for sharing our experiences, all our conversations and dinners. Thank you for providing Maya always a nice place to play and sharing your garden with us. Saskia, thanks a lot for your friendship and for agreeing to be my paranymph.

Thanks to all my wonderful friends back in Germany (and Spain) I see and speak too seldom. Thank you for all the letters, postcards, and parcels, for all the provided help, and for providing me/us a place to stay whenever we are around.

Papa, thank you for rising me the way you did, for supporting me with my plans, and for always being proud of me. Mama, this thesis is for you. I would not have made it so far without the things you taught me, thank you.

Oscar. One thing is for sure, I would not be here today without you. This is not only true because I came to Groningen with you. Thank you for staying with me in all these years, for all your patience, all your understanding, and for always believing in me. Thank you for being always open to new compromises and supporting me. I know that I am a very lucky person that I met someone like you. Meine kleine Maya. Von allen Projekten der letzten Jahre bist du ohne jeden Zweifel das Wichtigste und das, was uns am besten gelungen ist. Dich aufwachsen zu sehen und dir dabei zuzusehen, wie du die Welt entdeckst, macht mein Leben reicher und lässt mich das Leben aus einer anderen Perspektive sehen. Danke.

(5)

208

Publications

Pfaehler, E.

, Mesotten, L., … & Boellaard, R.(2020): Repeatability of two artificial

intelligence approaches for tumour segmentation in PET. Pre-print

Pfaehler, E.

, Mesotten, L., … & Boellaard, R. (2020). Textural Feature Based

Segmentation: A Repeatable and Accurate Segmentation Approach for Tumours in

PET Images. Conference proceedings Medical Image Analysis and Understanding

Pfaehler, E.,

Burggraaf, C., … & Boellaard, R. (2020). PET segmentation of bulky

tumours: Strategies and workflows to improve inter-observer variability, PloS ONE

Pfaehler, E., van Sluis, J. , ... & Boellaard, R. (2019). Experimental multicenter and

multivendor evaluation of PET radiomic features performance using 3D printed

phantom inserts, Journal of Nuclear Medicine

Pfaehler, E.*

, Beukinga, R. J.*

, … & Boellaard, R.

(2019).

Repeatability of 18 F-FDG

PET radiomic features: A phantom study to explore sensitivity to image

reconstruction settings, noise, and delineation method

.

Medical Physics

(*equal

contribution)

Pfaehler, E.

, Zwanenburg, A.

, de Jong, J. R., Boellaard, R.

(2019).

RaCaT: An open

source and easy to use radiomics calculator tool

.

PloS ONE

Pfaehler, E., De Jong, J. R.

, … & Boellaard, R.

(2018).

SMART (SiMulAtion and

ReconsTruction) PET: an efficient PET simulation-reconstruction tool

.

EJNMMI

physics

Mansor, S.*

, Pfaehler, E.*

, ..., & Yaqub, M. (2017).

Impact of PET/CT system,

reconstruction protocol, data analysis method, and repositioning on PET/CT

precision: An experimental evaluation using an oncology and brain phantom

.

Medical Physics

, (*equal contribution)

Martens, R., …, Pfaehler, E., .. & Boellaard, R.(2020): Predictive value of

quantitative 18F-FDG-PET radiomics analysis in patients with head and neck

squamous cell carcinoma

Cysouw, M., … Pfaehler, E., … & Boellaard, R. (2020) Machine Learning-based

Analysis of [18F]DCFPyL PET Radiomics for Risk Stratification in Primary Prostate

Cancer, EJNMMI

(6)

209

Zwanenburg, A., …, Pfaehler E., …& Löck, S. (2020). The Image Biomarker

Standardization Initiative: standardized quantitative radiomics for

high-throughput image-based phenotyping. Radiology

Dal Toso, L., Pfaehler, E.

, …& Marsden, P. (2019). Deep Learning Based Approach

to Quantification of PET Tracer Uptake in Small Tumours. International Workshop

on Machine Learning for Medical Image Reconstruction

Traverso, A., …, Pfaehler, E., .. & Wee, L. (2019): PO-0953 Are quality assurance

phantoms useful to assess radiomics reproducibility? A multi-center study.

Radiotherapy and Oncology

Kalendralis, P., ..., Pfaehler, E., .. & Wee, L. (2018): Multicenter CT phantoms

public dataset for radiomics reproducibility tests. Medical Physics

Referenties

GERELATEERDE DOCUMENTEN

I would like to thank the team of the Falls and Balance Outpatient Clinic at the Royal Melbourne Hospital, Melbourne, Australia, including Aileen, Anne, Cassie, Cathy, Daya,

Based on the assessment criteria, a good service scan should not only gives a general framework but also provide a framework for analyzing specific processes.. The

How do process, product and market characteristics affect the MTO-MTS decision in the food processing industry and how do market requirements affect the production and

Together with a majority vote approach (combining the results of four conventional segmentation approaches) the proposed segmentation methods were superior to the

Figure 7: Jaccard Coefficient (JC) values dependent on lesion size: JC values for bigger (left figure) and smaller (right figure) lesions for all segmentation approaches

Therefore, the aim of this thesis was to identify the image reconstruction and discretization setting that lead to the highest number of comparable PET radiomic

A standardization of each step in the radiomics pipeline is essential for the clinical implementation of PET radiomic features. Radiomic studies should be described in a way that

I would also like to thank Huub Röttgering for giving me the opportunity to embark a PhD, for welcoming in the LOFAR group, and for giving me his trust to choose my own research