Prediction of In Vivo Laser-Induced Thermal Damage with Hyperspectral Imaging Using Deep Learning.

Thermal ablation is an acceptable alternative treatment for primary liver cancer, of which laser ablation (LA) is one of the least invasive approaches, especially for tumors in high-risk locations. Precise control of the LA effect is required to safely destroy the tumor. Although temperature imaging techniques provide an indirect measurement of the thermal damage, a degree of uncertainty remains about the treatment effect. Optical techniques are currently emerging as tools to directly assess tissue thermal damage. Among them, hyperspectral imaging (HSI) has shown promising results in image-guided surgery and in the thermal ablation field. The highly informative data provided by HSI, associated with deep learning, enable the implementation of non-invasive prediction models to be used intraoperatively. Here we show a novel paradigm "peak temperature prediction model" (PTPM), convolutional neural network (CNN)-based, trained with HSI and infrared imaging to predict LA-induced damage in the liver. The PTPM demonstrated an optimal agreement with tissue damage classification providing a consistent threshold (50.6 ± 1.5 °C) for the damage margins with high accuracy (~0.90). The high correlation with the histology score (r = 0.9085) and the comparison with the measured peak temperature confirmed that PTPM preserves temperature information accordingly with the histopathological assessment.

Closed-Loop Temperature Control Based on Fiber Bragg Grating Sensors for Laser Ablation of Hepatic Tissue.

Laser ablation (LA) of cancer is a minimally invasive technique based on targeted heat release. Controlling tissue temperature during LA is crucial to achieve the desired therapeutic effect in the organs while preserving the healthy tissue around. Here, we report the design and implementation of a real-time monitoring system performing closed-loop temperature control, based on fiber Bragg grating (FBG) spatial measurements. Highly dense FBG arrays (1.19 mm length, 0.01 mm edge-to-edge distance) were inscribed in polyimide-coated fibers using the femtosecond point-by-point writing technology to obtain the spatial resolution needed for accurate reconstruction of high-gradient temperature profiles during LA. The zone control strategy was implemented such that the temperature in the laser-irradiated area was maintained at specific set values (43 and 55 °C), in correspondence to specific radii (2 and 6 mm) of the targeted zone. The developed control system was assessed in terms of measured temperature maps during an ex vivo liver LA. Results suggest that the temperature-feedback system provides several advantages, including controlling the margins of the ablated zone and keeping the maximum temperature below the critical values. Our strategy and resulting analysis go beyond the state-of-the-art LA regulation techniques, encouraging further investigation in the identification of the optimal control-loop.