Comparison of Technical Details and Short-term Outcomes of Single-incision Versus Multiport Laparoscopic Adrenalectomy

Utilization of artificial intelligence in minimally invasive right adrenalectomy: recognition of anatomical landmarks with deep learning

BACKGROUND

The primary surgical approach for removing adrenal masses is minimally invasive adrenalectomy. Recognition of anatomical landmarks during surgery is critical for minimizing complications. Artificial intelligence-based tools can be utilized to create real-time navigation systems during laparoscopic and robotic right adrenalectomy. In this study, we aimed to develop deep learning models that can identify critical anatomical structures during minimally invasive right adrenalectomy.

METHODS

In this experimental feasibility study, intraoperative videos of 20 patients who underwent minimally invasive right adrenalectomy in a tertiary care center between 2011 and 2023 were analyzed and used to develop an artificial intelligence-based anatomical landmark recognition system. Semantic segmentation of the liver, the inferior vena cava (IVC), and the right adrenal gland were performed. Fifty random images per patient during the dissection phase were extracted from videos. The experiments on the annotated images were performed on two state-of-the-art segmentation models named SwinUNETR and MedNeXt, which are transformer and convolutional neural network (CNN)-based segmentation architectures, respectively. Two loss function combinations, Dice-Cross Entropy and Dice-Focal Loss were experimented with for both of the models. The dataset was split into training and validation subsets with an 80:20 distribution on a patient basis in a 5-fold cross-validation approach. To introduce a sample variability to the dataset, strong-augmentation techniques were performed using intensity modifications and perspective transformations to represent different surgery environment scenarios. The models were evaluated by Dice Similarity Coefficient (DSC) and Intersection over Union (IoU) which are widely used segmentation metrics. For pixelwise classification performance, accuracy, sensitivity and specificity metrics were calculated on the validation subset.

RESULTS

Out of 20 videos, 1000 images were extracted, and the anatomical landmarks (liver, IVC, and right adrenal gland) were annotated. Randomly distributed 800 images and 200 images were selected for the training and validation subsets, respectively. Our benchmark results show that the utilization of Dice-Cross Entropy Loss with the transformer-based SwinUNETR model achieved 78.37%, whereas the CNN-based MedNeXt model reached a 77.09% mDSC score. Conversely, MedNeXt reaches a higher mIoU score of 63.71% than SwinUNETR by 62.10% on a three-region prediction task.

CONCLUSION

Artificial intelligence-based systems can predict anatomical landmarks with high performance in minimally invasive right adrenalectomy. Such tools can later be used to create real-time navigation systems during surgery in the near future.

[Surgical treatment of pheochromocytoma]

This review article contains a summary of modern aspects of preoperative preparation, surgical treatment, and follow-up of patients with adrenal pheochromocytomas. The main component of preoperative preparation is the use of alpha-blockers. The need to prescribe them to all patients is increasingly disputed, especially for patients without severe hypertension. An increasing number of publications demonstrate positive results of treatment without the use of alpha-blockers, advocating an individual approach and the use of the drug according to certain indications. Minimally invasive endoscopic techniques of adrenalectomy have become widespread in surgical treatment. They are represented by laparoscopic and retroperitonescopic technic, including using their single-port modifications. The earliest possible intersection of the central vein in the past was considered the most important aspect of adrenalectomy for pheochromocytoma, currently, due to the development of surgical techniques and anesthesiological manuals, this has ceased to be a mandatory rule of successful surgery. Despite the significant influence of the intersection of this vessel on intraoperative hemodynamics, surgical tactics with its later intersection have their own justifications and do not lead to a deterioration in treatment results. The standard volume of surgical intervention for pheochromocytomas is total adrenalectomy, however, in the presence of hereditary syndromes, such as multiple endocrine neoplasia type 2 syndrome, neurofibomatosis type 1, von Hippel-Lindau syndrome, it is possible to perform cortical-sparing adrenalectomy.

Laparoendoscopic single-site adrenalectomy versus multi-port laparoendoscopic adrenalectomy: A systemic review and meta-analysis

Background

To investigate the outcomes of laparoendoscopic single-site adrenalectomy (LESS-A) compared to multi-port laparoendoscopic adrenalectomy (m-LA).

Methods

Studies comparing LESS-A with m-LA were identified from PubMed, Embase, and Cochrane Library before June 2020. Post-operative pain, resumption outcomes, and perioperative outcomes were analyzed. We conducted meta-analyses using the Mantel-Haenszel method with random-effects model. Subset analyses were conducted according to peritoneal and retroperitoneal approaches. A small study effect was illustrated using funnel plots and Egger's test.

Results

One randomized controlled trial (RCT) and nineteen retrospective cohort studies involving 1554 patients were included for analyzed. Pooled analysis showed that LESS-A had significantly lower postoperative pain scores (MD −0.77, 95%CI −1.45 to −0.10) and less pain medication used (RR 0.74, 95%CI 0.60 to 0.91) compared to m-LA. Besides, LESS-A had significantly shorter hospital stays (MD −0.75, 95%CI −1.18 to −0.33), shorter duration of oral intake resumption (MD −0.33, 95%CI −0.60 to −0.06), and better cosmetic satisfaction (SMD 1.15, 95%CI 0.21 to −2.09). As for perioperative outcomes, LESS-A led to significant longer operative time (MD 13.43, 95%CI 4.08 to 22.77). No significant differences were observed in terms of the remaining perioperative outcomes.

Conclusions

LESS-A is associated with less post-operative pain and quicker recovery duration. However, the longer operative time of LESS-A compared with m-LA is a drawback.

•

Multi-port laparoscopic adrenalectomy (m-LA) is widely used for treatment of benign adrenal tumor.

•

Laparoscopic single-site adrenalectomy (LESS-A) had significant less post-operative pain and less pain medication consumption comparing with m-LA.

•

LESS-A had better resumption outcomes, including shorter hospital stay and quicker post-operative oral intake.

•

LESS-A offer better cosmetic satisfaction.

•

Longer operative time is a drawback of LESS-A.

Single-incision robotic adrenalectomy (SIRA): the future of adrenal surgery?

In compliance with the trend toward less invasive techniques, single incision robotic surgeries have become more common and they have been increasingly used for several surgeries including adrenalectomy. Single incision robotic adrenalectomy (SIRA) aims to combine the merits of robotic surgery with previously defined single incision laparoscopic techniques. It has been shown to be safe and feasible, however, there are only few studies on this new technique. Due to scant data on SIRA in the current literature, it remains to be a current challenge in adrenal surgery. In this review, our goal is to present current literature on SIRA and discuss the data regarding perioperative outcomes, patient selection, learning curve, and its limitations.

Experience in the application of laparoscopic anatomical adrenalectomy via the renal cortex surface monolayer

Objective:

To discuss the clinical application of laparoscopic anatomical adrenalectomy via the renal cortex surface in the operation of adrenal masses.

Methods:

A retrospective analysis was performed on 231 patients with adrenal masses who were received and cured in the urology department of the Affiliated Hospital of Hebei University from July 2016 to January 2019. All patients received retroperitoneal adrenalectomy by means of laparoscopic anatomical adrenalectomy via the renal cortex surface. Operation duration, bleeding volume, postoperative complications, retention time of the drainage tube were measured and analyzed, and postoperative follow-up surveys were administered.

Results:

All cases were successfully operated. Two cases were converted to open surgery due to the presence of large adrenal tumors, and the patients suffered no significant complications. The mean operation duration, bleeding volume and retention time of the drainage tube were 31 minutes, 20 mL and 1.2±0.6 d, respectively. In terms of the postoperative pathology of adrenal tumors, 183 cases were shown to have adenomas, 34 had pheochromocytomas, nine had schwannomas, 3 had metastases from lung cancer, and two had sarcomas. A total of 174 patients were followed up for three to 18 months. Only one case with sarcoma that relapsed within half a year of the operation.

Conclusion:

In the treatment of adrenal masses, laparoscopic anatomical adrenalectomy via the renal cortex surface has many advantages including the large operation space, clear view of anatomical markers, little bleeding, small trauma, few postoperative complications, simple operational procedures and short learning curves. This technique needs clinical promotion.