Pediatric Brain Tissue Segmentation Using a Snapshot Hyperspectral Imaging (sHSI) Camera and Machine Learning Classifier.

Pediatric brain tumors are the second most common type of cancer, accounting for one in four childhood cancer types. Brain tumor resection surgery remains the most common treatment option for brain cancer. While assessing tumor margins intraoperatively, surgeons must send tissue samples for biopsy, which can be time-consuming and not always accurate or helpful. Snapshot hyperspectral imaging (sHSI) cameras can capture scenes beyond the human visual spectrum and provide real-time guidance where we aim to segment healthy brain tissues from lesions on pediatric patients undergoing brain tumor resection. With the institutional research board approval, Pro00011028, 139 red-green-blue (RGB), 279 visible, and 85 infrared sHSI data were collected from four subjects with the system integrated into an operating microscope. A random forest classifier was used for data analysis. The RGB, infrared sHSI, and visible sHSI models achieved average intersection of unions (IoUs) of 0.76, 0.59, and 0.57, respectively, while the tumor segmentation achieved a specificity of 0.996, followed by the infrared HSI and visible HSI models at 0.93 and 0.91, respectively. Despite the small dataset considering pediatric cases, our research leveraged sHSI technology and successfully segmented healthy brain tissues from lesions with a high specificity during pediatric brain tumor resection procedures.

TOETVA parathyroid autofluorescence detection: hANDY-i endoscopy attachment.

Background: Treatment options for thyroid pathologies have expanded to include scarless and remote access methods such as the transoral endoscopic thyroidectomy vestibular approach (TOETVA). Currently, no standardized methods exist for locating parathyroid glands (PGs) in patients undergoing TOETVA, which can lead to parathyroid injury and subsequent hypocalcemia. This early feasibility study describes and evaluates the hANDY-i endoscopic attachment for detecting PGs in transoral thyroidectomy. Methods: We used a prototype parathyroid autofluorescence imager (hANDY-i) that was mounted to a 10-mm 0-degree endoscope. The device delivers a split screen view of Red-green-blue (RGB) and near-infrared autofluorescence (NIRAF) which allows for simultaneous anatomical localization and fluorescence visualization of PGs during endoscopic thyroid dissection. Results: One cadaveric case and two patient cases were included in this study. The endoscopic hANDY-i imaging system successfully visualized PGs during all procedures. Conclusion: The ability to leverage parathyroid autofluorescence during TOETVA may lead to improved PG localization and preservation. Further human studies are needed to assess its effect on postoperative hypocalcemia and hypoparathyroidism.

Parathyroid gland detection using an intraoperative autofluorescence handheld imager - early feasibility study.

Introduction: Parathyroid glands may be compromised during thyroid surgery which can lead to hypoparathyroidism and hypocalcemia. Identifying the parathyroid glands relies on the surgeon's experience and the only way to confirm their presence was through tissue biopsy. Near infrared autofluorescence technology offers an opportunity for real-time, non-invasive identification of the parathyroid glands. Methods: We used a new research prototype (hANDY-I) developed by Optosurgical, LLC. It offers coaxial excitation light and a dual-Red Green Blue/Near Infrared sensor that guides anatomical landmarks and can aid in identification of parathyroid glands by showing a combined autofluorescence and colored image simultaneously. Results: We tested the imager during 23 thyroid surgery cases, where initial clinical feasibility data showed that out of 75 parathyroid glands inspected, 71 showed strong autofluorescence signal and were correctly identified (95% accuracy) by the imager. Conclusions: The hANDY-I prototype demonstrated promising results in this feasibility study by aiding in real-time visualization of the parathyroid glands. However, further testing by conducting randomized clinical trials with a bigger sample size is required to study the effect on levels of hypoparathyroidism and hypocalcemia.