Click here to

Session: Quantitative Imaging [Return to Session]

Using CycleGAN Machine Learning to Increase Accuracy of Relative Electron Density and Proton Stopping Power Ratio

J Scholey1*, L Vinas2, V Kearney3, S Yom4, P Larson5, M Descovich6, A Sudhyadhom7, (1) University of California San Francisco, San Francisco, CA, (2) University of California Berkeley, Berkeley, CA, (3) University of California San Francisco, San Francisco, CA, (4) University of California San Francisco, San Francisco, CA, (5)(6) University of California San Francisco, San Francisco, CA, (7) Brigham and Women's Hospital | Dana-Farber Cancer Institute | Harvard Medical School, Boston, MA


WE-C1000-IePD-F1-1 (Wednesday, 7/13/2022) 10:00 AM - 10:30 AM [Eastern Time (GMT-4)]

Exhibit Hall | Forum 1

Purpose: Kilovoltage computed tomography (kVCT) is the cornerstone of radiotherapy treatment planning for delineating tissues and towards dose calculation. For the former, kVCT provides excellent contrast and signal-to-noise ratio. For the latter, kVCT may have greater uncertainty in determining relative electron density (ρe) and proton stopping power ratio (SPR). Conversely, megavoltage CT (MVCT) may result in superior dose calculation accuracy. The purpose of this work was to convert kVCT HU to MVCT HU using deep learning to obtain higher accuracy ρe and SPR.

Methods: Tissue-mimicking phantoms were created to compare kVCT- and MVCT-determined ρe and SPR to physical measurements. Using 100 head-and-neck datasets, an unpaired deep learning model was trained to learn the relationship between kVCTs and MVCTs, creating synthetic MVCTs (sMVCTs). Similarity metrics were calculated between kVCTs, sMVCTs, and MVCTs in 20 test datasets. An anthropomorphic head phantom containing bone-mimicking material with known composition was scanned to provide an independent determination of ρe and SPR accuracy by sMVCT.

Results: In tissue-mimicking bone, ρe errors were 2.20% versus 0.19% and SPR errors were 4.38% versus 0.22%, for kVCT versus MVCT, respectively. Compared to MVCT, in vivo mean difference (MD) values were 11 and 327 HU for kVCT and 2 and 3 HU for sMVCT in soft tissue and bone, respectively. ρe MD decreased from 1.3% to 0.35% in soft tissue and 2.9% to 0.13% in bone, for kVCT and sMVCT, respectively. SPR MD decreased from 1.8% to 0.24% in soft tissue and 6.8% to 0.16% in bone, for kVCT and sMVCT, respectively. Relative to physical measurements, ρe and SPR error in anthropomorphic bone decreased from 7.50% and 7.48% for kVCT to <1% for both MVCT and sMVCT.

Conclusion: Deep learning can be used to map kVCT to sMVCT, suggesting higher accuracy ρe and SPR is achievable with sMVCT versus kVCT.


Protons, Stopping Power, Image Analysis


TH- External Beam- Particle/high LET therapy: Other particle therapy

Contact Email