Visualization of the normal pituitary gland during the endoscopic endonasal removal of pituitary adenoma by narrow band imaging

Deep learning based identification of pituitary adenoma on surgical endoscopic images: a pilot study

Accurate tumor identification during surgical excision is necessary for neurosurgeons to determine the extent of resection without damaging the surrounding tissues. No conventional technologies have achieved reliable performance for pituitary adenomas. This study proposes a deep learning approach using intraoperative endoscopic images to discriminate pituitary adenomas from non-tumorous tissue inside the sella turcica. Static images were extracted from 50 intraoperative videos of patients with pituitary adenomas. All patients underwent endoscopic transsphenoidal surgery with a 4 K ultrahigh-definition endoscope. The tumor and non-tumorous tissue within the sella turcica were delineated on static images. Using intraoperative images, we developed and validated deep learning models to identify tumorous tissue. Model performance was evaluated using a fivefold per-patient methodology. As a proof-of-concept, the model's predictions were pathologically cross-referenced with a medical professional's diagnosis using the intraoperative images of a prospectively enrolled patient. In total, 605 static images were obtained. Among the cropped 117,223 patches, 58,088 were labeled as tumors, while the remaining 59,135 were labeled as non-tumorous tissues. The evaluation of the image dataset revealed that the wide-ResNet model had the highest accuracy of 0.768, with an F1 score of 0.766. A preliminary evaluation on one patient indicated alignment between the ground truth set by neurosurgeons, the model's predictions, and histopathological findings. Our deep learning algorithm has a positive tumor discrimination performance in intraoperative 4-K endoscopic images in patients with pituitary adenomas.

Trends in endoscopic and microscopic transsphenoidal surgery: a survey of the international society of pituitary surgeons between 2010 and 2020

PURPOSE

This comparative survey of surgical practice patterns between 2010 and 2020 aims to elicit trends in practice patterns for transsphenoidal surgery and to identify areas for improvement.

METHODS

Web-based surveys were sent to the International Society of Pituitary Surgeons via a membership listserv in 2010 and 2020. These 33-item surveys collected information on demographics, surgical approach, perceived advantages and disadvantages, and recommendations for improvements. Statistical analyses were conducted using the Mann-Whitney U test for continuous variables and Fisher's exact test for categorical variables.

RESULTS

There were 51 respondents in 2010 and 82 respondents in 2020. The majority were full-time academic surgeons from the United States or Europe. Preference for a purely endoscopic technique increased from 43% in 2010 to 87% in 2020. Preference for routinely working with an otolaryngologist or second neurosurgeon increased from 35 to 51%. Most surgeons (74%) reported that they were more likely to achieve a greater extent of resection with the endoscope, though 51% noted increased operating time. The most commonly rated advantage (34%) of endoscopic TSS was fewer postoperative nasoseptal perforations; the most commonly (34%) rated disadvantage was more postoperative complications, including cerebrospinal fluid leak. Respondents were divided on whether microscopic TSS should continue to be taught in residency. Many (32%) advocated for improved endoscopic instrumentation and team training.

CONCLUSION

Endoscopic TSS is now the clearly preferred method for surgery amongst a cohort of higher-volume academic neurosurgeons. This trend is likely to continue, and this provides guidelines for future training.

Preliminary experience with 4K ultra-high definition endoscope: analysis of pros and cons in skull base surgery

During the last two decades endoscopic skull base surgery observed a continuous technical and technological development 3D endoscopy and ultra High Definition (HD) endoscopy have provided great advances in terms of visualisation and spatial resolution. Ultra-high definition (UHD) 4K systems, recently introduced in the clinical practice, will shape next steps forward especially in skull base surgery field. Patients were operated on through transnasal transsphenoidal endoscopic approaches performed using Olympus NBI 4K UHD endoscope with a 4 mm 0° Ultra Telescope, 300 W xenon lamp (CLV-S400) predisposed for narrow band imaging (NBI) technology connected through a camera head to a high-quality control unit (OTV-S400 – VISERA 4K UHD) (Olympus Corporation, Tokyo, Japan). Two screens are used, one 31" Monitor – (LMD-X310S) and one main ultra-HD 55" screen optimised for UHD image reproduction (LMD-X550S). In selected cases, we used a navigation system (Stealthstation S7, Medtronic, Minneapolis, MN, US). We evaluated 22 pituitary adenomas (86.3% macroadenomas; 13.7% microadenomas). 50% were not functional (NF), 22.8% GH, 18.2% ACTH, 9% PRL-secreting. Three of 22 were recurrences. In 91% of cases we achieved total removal, while in 9% near total resection. A mean follow-up of 187 days and average length of hospitalisation was 3.09 ± 0.61 days. Surgical duration was 128.18± 30.74 minutes. We experienced only 1 case of intraoperative low flow fistula with no further complications. None of the cases required any post- or intraoperative blood transfusion. The visualisation and high resolution of the operative field provided a very detailed view of all anatomical structures and pathologies allowing an improvement in safety and efficacy of the surgical procedure. The operative time was similar to the standard 2D HD and 3D procedures and the physical strain was also comparable to others in terms of ergonomics and weight.