EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Unsupervised Deep Learning for Synthetic CT Generation from CBCT Images for Proton and Carbon Ion Therapy for Paediatric Patients

Matteo Pepa iD, Siavash Taleghani, Giulia Sellaro, Alfredo Mirandola, Francesca Colombo, Sabina Vennarini, Mario Ciocca, Chiara Paganelli iD, Ester Orlandi iD, Guido Baroni, Andrea Pella

Sensors · 2024

DOI: 10.3390/s24237460 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2024. Verfasst von Matteo Pepa und 10 weiteren Autor:innen. Beteiligte Einrichtung: Bioengineering Unit, Clinical Department, CNAO National Centre for Oncological Hadrontherapy, 27100 Pavia, Italy. Hauptthemen laut MEDLINE: Deep Learning, Cone-Beam Computed Tomography, Proton Therapy, Heavy Ion Radiotherapy. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 73 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Image-guided treatment adaptation is a game changer in oncological particle therapy (PT), especially for younger patients. The purpose of this study is to present a cycle generative adversarial network (CycleGAN)-based method for synthetic computed tomography (sCT) generation from cone beam CT (CBCT) towards adaptive PT (APT) of paediatric patients. Firstly, 44 CBCTs of 15 young pelvic patients were pre-processed to reduce ring artefacts and rigidly registered on same-day CT scans (i.e., verification CT scans, vCT scans) and then inputted to the CycleGAN network (employing either Res-Net and U-Net generators) to synthesise sCT. In particular, 36 and 8 volumes were used for training and testing, respectively. Image quality was evaluated qualitatively and quantitatively using the structural similarity index metric (SSIM) and the peak signal-to-noise ratio (PSNR) between registered CBCT (rCBCT) and vCT and between sCT and vCT to evaluate the improvements brought by CycleGAN. Despite limitations due to the sub-optimal input image quality and the small field of view (FOV), the quality of sCT was found to be overall satisfactory from a quantitative and qualitative perspective. Our findings indicate that CycleGAN is promising to produce sCT scans with acceptable CT-like image texture in paediatric settings, even when CBCT with narrow fields of view (FOV) are employed.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningCone-Beam Computed TomographyProton TherapyHeavy Ion RadiotherapyHumansChildImage Processing, Computer-AssistedSignal-To-Noise RatioTomography, X-Ray Computed

Stichwörter der Autor:innen

CBCTCycleGANadaptive particle therapyartificial intelligencecarbon ion therapydeep learningpaediatric oncologyproton therapysynthetic CT

Autor:innen und Institutionen

  • Bioengineering Unit, Clinical Department, CNAO National Centre for Oncological Hadrontherapy, 27100 Pavia, Italy.
  • Department of Electronics, Information and Bioengineering, Politecnico di Milano (POLIMI), 20133 Milan, Italy.
  • Medical Physics Unit, Clinical Department, CNAO National Centre for Oncological Hadrontherapy, 27100 Pavia, Italy.
  • Radiation Oncology Unit, Clinical Department, CNAO National Centre for Oncological Hadrontherapy, 27100 Pavia, Italy.
  • Paediatric Radiotherapy Unit, Fondazione IRCCS Istituto Nazionale dei Tumori (INT), 20133 Milan, Italy.
  • Department of Clinical, Surgical, Diagnostic and Pediatric Sciences, University of Pavia, 27100 Pavia, Italy.

ORCID-Profile: Matteo Pepa, Chiara Paganelli, Ester Orlandi

Zitieren

APA

Pepa, M., Taleghani, S., Sellaro, G., Mirandola, A., Colombo, F., Vennarini, S., Ciocca, M., Paganelli, C., Orlandi, E., Baroni, G., & Pella, A. (2024). Unsupervised Deep Learning for Synthetic CT Generation from CBCT Images for Proton and Carbon Ion Therapy for Paediatric Patients. Sensors. https://doi.org/10.3390/s24237460

Vancouver

Pepa M, Taleghani S, Sellaro G, Mirandola A, Colombo F, Vennarini S, et al. Unsupervised Deep Learning for Synthetic CT Generation from CBCT Images for Proton and Carbon Ion Therapy for Paediatric Patients. Sensors. 2024. doi:10.3390/s24237460

BibTeX
@article{Pepa2024,
  author = {Pepa, Matteo and Taleghani, Siavash and Sellaro, Giulia and Mirandola, Alfredo and Colombo, Francesca and Vennarini, Sabina and Ciocca, Mario and Paganelli, Chiara and Orlandi, Ester and Baroni, Guido and Pella, Andrea},
  title = {Unsupervised Deep Learning for Synthetic CT Generation from CBCT Images for Proton and Carbon Ion Therapy for Paediatric Patients},
  journal = {Sensors},
  year = {2024},
  doi = {10.3390/s24237460}
}
Kostenlos starten →