Chapter 10 Abstract Background In thyroid and parathyroid surgery iatrogenic parathyroid injury should be prevented. Parathyroid‐specific image enhancement might be realized with hyperspectral cameras using silicon (Si) or indium‐gallium‐arsenide (InGaAs) sensors. Feasibility of this technology for automated parathyroid detection was examined by analyzing performance of single‐spot diffuse reflectance spectroscopy (DRS). Methods DRS (350 – 1830 nm) was performed during thyroid and parathyroid resections. From the acquired spectra 36 features at predefined wavelengths were extracted. Best features for parathyroid classification versus adipose tissue or thyroid were assessed by binary logistic regression for Si‐ and InGaAs‐sensor ranges. Classification performance was evaluated by leave‐one‐out cross‐validation. Results In 19 patients 299 spectra were recorded (62 tissue sites: thyroid n=23, parathyroid n=21, adipose n=18). Classification accuracy of parathyroid–adipose was respectively 79% (Si), 82% (InGaAs) and 97% (Si/InGaAs combined). Parathyroid–thyroid classification accuracies: 80%, 75%, 82%. Conclusion Si and InGaAs sensors are fairly accurate for automated parathyroid discrimination from adipose or thyroid tissue. Combination of both sensor technologies improves accuracy. 146
proefschrift_Schols_SLV
To see the actual publication please follow the link above