Efficient prediction of attosecond two-colour pulses from an X-ray free-electron laser with machine learning.

X-ray free-electron lasers are sources of coherent, high-intensity X-rays with numerous applications in ultra-fast measurements and dynamic structural imaging. Due to the stochastic nature of the self-amplified spontaneous emission process and the difficulty in controlling injection of electrons, output pulses exhibit significant noise and limited temporal coherence. Standard measurement techniques used for characterizing two-coloured X-ray pulses are challenging, as they are either invasive or diagnostically expensive. In this work, we employ machine learning methods such as neural networks and decision trees to predict the central photon energies of pairs of attosecond fundamental and second harmonic pulses using parameters that are easily recorded at the high-repetition rate of a single shot. Using real experimental data, we apply a detailed feature analysis on the input parameters while optimizing the training time of the machine learning methods. Our predictive models are able to make predictions of central photon energy for one of the pulses without measuring the other pulse, thereby leveraging the use of the spectrometer without having to extend its detection window. We anticipate applications in X-ray spectroscopy using XFELs, such as in time-resolved X-ray absorption and photoemission spectroscopy, where improved measurement of input spectra will lead to better experimental outcomes.

Detection of blackbody radiation during fiber guided laser-tissue vaporization.

Laser-tissue vaporization through a fiber catheter is evolving into a major category of surgical operations to remove diseased tissue. Currently, during a surgery, the surgeon still relies on personal experience to optimize surgical techniques. Monitoring tissue temperature during laser-tissue vaporization would provide important feedback to the surgeon; however, simple and low-cost temperature sensing technology, which can be seamlessly integrated with a fiber catheter, is not available. We propose to monitor tissue temperature during laser-tissue vaporization by detecting blackbody radiation (BBR) between 1.6 µm-1.8 µm, a relatively transparent window for both water and silica fiber. We could detect BBR after passing through a 2-meter silica fiber down to ∼70°C using lock-in detection. We further proved the feasibility of the technology through ex vivo tissue studies. We found that the BBR can be correlated to different tissue vaporization levels. The results suggest that this simple and low-cost technology could be used to provide objective feedback for surgeons to maximize laser-tissue vaporization efficiency and ensure the best clinical outcomes.

Development of hypothermia measurable fiber radiometric thermometer for thermotherapy.

Temperature monitoring is extremely important during thermotherapy. Fiber-optic temperature sensors are preferred because of their flexibility and immunity to electromagnetic interference. Although many types of fiber-optic sensors have been developed, clinically adopting them remains challenging. Here, we report a silica fiber-based radiometric thermometer using a low-cost extended InGaAs detector to detect black body radiation between 1.7 and 2.4 µm. For the first time, this silica fiber-based thermometer is capable of measuring temperatures down to 35°C, making it suitable for monitoring hyperthermia during surgery. In particular, the thermometer has potential for seamless integration with current silica fiber catheters, which are widely used in laser interstitial thermotherapy. The feasibility, capability and sensitivity of tracking tissue temperature variation were proved through ex vivo tissue studies. After further improvement, the technology has the potential to be translated into clinics for monitoring tissue temperature.