Gamma Source Location Learning from Synthetic Multi-pinhole Collimator Data
Sentinel lymph node biopsy (SNB) is a surgical method to stage certain cancer types in a minimally invasive manner. However, the current sensing methods for SNB are limited in accuracy, as they are based on acoustic feedback radiation probes to detect tracer enriched sentinel lymph nodes. We present a deep neural network approach to learn the latent spatial activity distributions from a simulated gamma source on 2D activity images. Data processing can then be applied for multi-pinhole collimator optimization, lymph node visualization or surgical navigation to further support SNB. Using simulations of photon multi-pinhole collimator interaction, we generate labeled synthetic 2D activity images to train convolutional neural networks (CNN). These CNNs are then evaluated on synthetic as well as on real experimental data from a radioactive point-like source, collected by our own stationary small form factor multi-pinhole collimator. We achieve good results on synthetic data for the xy-component ensemble learners with a localization class accuracy of 0.97, while depth estimation achieves a localization class accuracy of 0.55. Accuracy on real experimental data is limited due to the small sample set and its variability, compared to the simulation.
KeywordsSentinel lymph node biopsy Radioguided surgery Inverse problem Machine learning Convolutional neural network
- 3.Seppi, C., et al.: Compressed sensing on multi-pinhole collimator SPECT camera for sentinel lymph node biopsy. In: Descoteaux, M., Maier-Hein, L., Franz, A., Jannin, P., Collins, D.L., Duchesne, S. (eds.) MICCAI 2017. LNCS, vol. 10434, pp. 415–423. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-66185-8_47CrossRefGoogle Scholar
- 5.Mansour, H.: Beyond l1-norm minimization for sparse signal recovery. In: IEEE Statistical Signal Processing Workshop, SSP 2012, pp. 337–340 (2012)Google Scholar