Variational based smoke removal in laparoscopic images

Identifying Responsible Factors for Poor Surgical Visibility in Pediatric Laparoscopic Fundoplication: A Retrospective Single-Center Study

Background: Laparoscopic fundoplication is commonly performed in patients with neurological impairment. However, these patients often have spinal deformities that can complicate achieving a clear surgical view. This study aimed to identify factors associated with poor visibility in pediatric laparoscopic fundoplication. Methods: Operative videos, medical records, and radiographs of patients who underwent laparoscopic fundoplication between 2015 and 2023 were retrospectively reviewed. The videos were reviewed by two pediatric surgeons and classified into good or poor visibility groups. Age, sex, height, weight, history of abdominal surgery, lordosis, operative time, blood loss, and intraoperative complications were compared between the two groups. Lordosis was evaluated using the sagittal view of computed tomography images, and the anterior vertebral depth and abdominal thickness were measured to calculate the ratio. Results: Forty-one patients were included in this study. Based on the video review, the patients were classified into good (20 patients) and poor (21 patients) visibility groups. The median age, height, and weight were 6 years, 110 cm, and 16.1 kg, respectively. In the poor visibility group, 23.8% of patients had a history of abdominal surgery (P = .048). Additionally, the anterior vertebral depth to abdominal thickness ratios at the first and third lumbar vertebrae were significantly lower in the poor visibility group (P = .016 and P = .0018, respectively). There were no significant differences in the operative time, blood loss, or intraoperative complications between the two groups. Conclusions: Lordosis and a history of abdominal surgery may be risk factors for poor visibility in pediatric laparoscopic fundoplication.

Evaluation of mediastinoscopy for cranial mediastinal and tracheobronchial lymphadenectomy in canine cadavers

OBJECTIVE

To report technical feasibility and describe procedural details of a novel single incision minimally invasive approach to the mediastinum in cadaver dogs.

STUDY DESIGN

Cadaveric study.

ANIMALS

Large breed (25-40 kg) cadaver dogs (n = 10).

METHODS

Three of 10 cadavers were used for preliminary technique development without data recording. Cadaver specimens underwent pre- and postoperative thoracic computed tomographic scans. Seven dogs were placed in dorsal recumbency and mediastinoscopy was performed via a SILS port placed cranial to the thoracic inlet with CO2 insufflation of the mediastinum at 2-4 mmHg. Retrieval of all CT and visually identified mediastinal lymph nodes (LN) was attempted; endoscopic compartmental and individual LN dissection times and subjective operative challenges were recorded. Procedural success scores for visualization and dissection as well as NASA-task force index scores were recorded per lymph node, per cadaver.

RESULTS

Median time required for initial approach including SILS placement was 5 min (range 5-10 min). Individual LN retrieval times ranged from 2 to 32 min. Mediastinoscopic retrieval of LNs was most commonly successful for the left tracheobronchial LN (7/7), followed by the right tracheobronchial LN (4/7), the left and right sternal LNs (3/7 each), and the cranial mediastinal LNs (1/7). Post-procedure pleural gas was identified on CT in 4/7 cadavers.

CONCLUSIONS

Mediastinoscopy as reported was feasible in large breed canine cadavers and retrieval or cup biopsy of a variety of lymph nodes is possible from the described approach. Application in living animals and its associated challenges should be further investigated.

CLINICAL SIGNIFICANCE

Mediastinoscopy may provide a novel minimally invasive approach to the evaluation and oncologic staging of the cranial mediastinum in dogs.

Knowledge mapping of surgical smoke from 2003 to 2022: a bibliometric analysis

PURPOSE

The purpose of this study is to identify and characterize the literature on surgical smoke, visualize the data and sketch a certain trending outline.

METHODS

In the Web of Science Core Collection (WoSCC), all the data were acquired from January 1st 2003 to December 31st 2022. VOSviewer and CiteSpace were employed to visualize data, based on publications, bibliographic coupling, co-citation, or co-authorship relations. Microsoft Excel 2019 was used to comb and categorize all the statistics.

RESULT

A total 363 of journal papers were retrieved. The publication number was in a slow but steady growth between 2003 and 2019, followed by a sharp surge in 2020, and then the publication kept in a productive way. Surgical endoscopy and other interventional techniques was the most active journal on surgical smoke. USA played an important role among all the countries/regions. There were 1847 authors for these 363 papers, among whom 44 authors published more than three articles on surgical smoke. "Surgical smoke", "covid-19" and "surgery" were the top 3 appeared keywords, while the latest hot-spot keywords were "COVID-19", "virus", "transmission", "exposure" and "risk". There were 1105 co-cited references and 3786 links appeared in all 363 articles. Among them, 38 references are cited more than 10 times. The most co-cited article was "Detecting hepatitis B virus in surgical smoke emitted during laparoscopic surgery." Based on the titles of references and calculated by CiteSpace, the top 3 cluster trend network are "laparoscopic surgery", "COVID-19 pandemic" and "surgical smoke".

CONCLUSION

According to bibliometric analysis, the research on surgical smoke has been drawing attention of more scholars in the world. Increasing number of countries or regions added in this field, and among them, USA, Italy, and China has been playing important roles, however, more wide and intense cooperation is still in expectation.

Smoke veil prior regularized surgical field desmoking without paired in-vivo data

Though deep learning-based surgical smoke removal methods have shown significant improvements in effectiveness and efficiency, the lack of paired smoke and smoke-free images in real surgical scenarios limits the performance of these methods. Therefore, methods that can achieve good generalization performance without paired in-vivo data are in high demand. In this work, we propose a smoke veil prior regularized two-stage smoke removal framework based on the physical model of smoke image formation. More precisely, in the first stage, we leverage a reconstruction loss, a consistency loss and a smoke veil prior-based regularization term to perform fully supervised training on a synthetic paired image dataset. Then a self-supervised training stage is deployed on the real smoke images, where only the consistency loss and the smoke veil prior-based loss are minimized. Experiments show that the proposed method outperforms the state-of-the-art ones on synthetic dataset. The average PSNR, SSIM and RMSE values are 21.99±2.34, 0.9001±0.0252 and 0.2151±0.0643, respectively. The qualitative visual inspection on real dataset further demonstrates the effectiveness of the proposed method.

MARS-GAN: Multilevel-Feature-Learning Attention-Aware Based Generative Adversarial Network for Removing Surgical Smoke

Surgical smoke caused poor visibility during laparoscopic surgery, the smoke removal is important to improve the safety and efficiency of the surgery. We propose the Multilevel-feature-learning Attention-aware based Generative Adversarial Network for Removing Surgical Smoke (MARS-GAN) in this work. MARS-GAN incorporates multilevel smoke feature learning, smoke attention learning, and multi-task learning together. Specifically, the multilevel smoke feature learning adopts the multilevel strategy to adaptively learn non-homogeneity smoke intensity and area features with specific branches and integrates comprehensive features to preserve both semantic and textural information with pyramidal connections. The smoke attention learning extends the smoke segmentation module with the dark channel prior module to provide the pixel-wise measurement for focusing on the smoke features while preserving the smokeless details. And the multi-task learning strategy fuses the adversarial loss, cyclic consistency loss, smoke perception loss, dark channel prior loss, and contrast enhancement loss to help the model optimization. Furthermore, a paired smokeless/smoky dataset is synthesized for elevating smoke recognition ability. The experimental results show that MARS-GAN outperforms the comparative methods for removing surgical smoke on both synthetic/real laparoscopic surgical images, with the potential to be embedded in laparoscopic devices for smoke removal.

Development and validation of a deep learning-based laparoscopic system for improving video quality

PURPOSE

A clear surgical field of view is a prerequisite for successful laparoscopic surgery. Surgical smoke, image blur, and lens fogging can affect the clarity of laparoscopic imaging. We aimed to develop a real-time assistance system (namely LVQIS) for removing these interfering factors during laparoscopic surgery, thereby improving laparoscopic video quality.

METHODS

LVQIS was developed with generative adversarial networks (GAN) and transfer learning, which included two classification models (ResNet-50), a motion blur removal model (MPRNet), and a smoke/fog removal model (GAN). 136 laparoscopic surgery videos were retrospectively collected in a tripartite dataset for training and validation. A synthetic dataset was simulated using the image enhancement library Albumentations and the 3D rendering software Blender. The objective evaluation results were through PSNR, SSIM and FID, and the subjective evaluation includes the operation pause time and the degree of anxiety of surgeons.

RESULTS

The synthesized dataset contained 19,245 clear images, 19,245 motion blur images, and 19,245 smoke/fog images. The ResNet-50 CNN model identified whether a single laparoscopic image had motion blur and smoke/fog with an accuracy of over 0.99. The PSNR, SSIM and FID of the de-smoke model were 29.67, 0.9551 and 74.72, respectively, and the PSNR, SSIM and FID of the de-blurring model were 26.78, 0.9020 and 80.10, respectively, which were better than other advanced de-blurring and de-smoke/fog models. In a comparative study of 100 laparoscopic surgeries, the use of LVQIS significantly reduced the operation pause time (P < 0.001) and the anxiety of surgeons (P = 0.004).

CONCLUSIONS

In this study, LVQIS is an efficient and robust system that can improve the quality of laparoscopic video, reduce surgical pause time and the anxiety of surgeons, and has the potential for real-time application in real clinical settings.

A 3D reconstruction based on an unsupervised domain adaptive for binocular endoscopy

In minimally invasive surgery, endoscopic image quality plays a crucial role in surgery. Aiming at the lack of a real parallax in binocular endoscopic images, this article proposes an unsupervised adaptive neural network. The network combines adaptive smoke removal, depth estimation of binocular endoscopic images, and the 3D display of high-quality endoscopic images. We simulated the smoke generated during surgery by artificially adding fog. The training images of U-Net fused by Laplacian pyramid are introduced to improve the network’s ability to extract intermediate features. We introduce Convolutional Block Attention Module to obtain the optimal parameters of each layer of the network. We utilized the disparity transformation relationship between left- and right-eye images to combine the left-eye images with disparity in HS-Resnet to obtain virtual right-eye images as labels for self-supervised training. This method extracts and fuses the parallax images at different scale levels of the decoder, making the generated parallax images more complete and smoother. A large number of experimental research results show that the scheme can remove the smoke generated during the operation, effectively reconstruct the 3D image of the tissue structure of the binocular endoscope, and at the same time, preserve the contour, edge, detail, and texture of the blood vessels in the medical image. Compared with the existing similar schemes, various indicators have been greatly improved. It has good clinical application prospects.

Evaluation of the safety and efficacy of suction-tip forceps, a new tool for laparoscopic surgery, for gastric cancer

INTRODUCTION

Laparoscopic surgery is a minimally invasive surgery; however, obstacles to its functional optimization remain. Surgical ports can accommodate only one instrument at a time so complex exchange manipulations are necessary during surgery which increases operation times and patient risk. We developed a new laparoscopic instrument that functions as both forceps and a suction tube, which renders intraoperative tool exchange unnecessary. This pilot study was undertaken to evaluate the safety and efficacy of this novel dual-function device in laparoscopic surgery for gastric cancer.

METHODS

This single-center pilot study assessed patient safety during and after laparoscopic distal gastrectomy for gastric cancer with the suction-forceps using intraoperative video and clinical follow-up, respectively. To evaluate instrument efficacy, we measured the time interval between the start of any bleeding and the start of aspiration ("suction access time") and compared this time with that of a conventional surgical setup.

RESULTS

In total 15 patients participated, with all procedures being successful. No excess tissue damage occurred during surgery. Suction access time was significantly shorter in cases of bleeding when the suction-tip forceps were used for aspiration (2.01 seconds) compared to an ordinary suction tube (12.5 seconds; P < .01).

CONCLUSION

These findings suggest that our new suction-tip forceps are a useful, safe, and efficacious operative tool. This surgical innovation may considerably simplify gastric laparoscopic surgery. This pilot study was registered with Japan Clinical Trial Registration on 22 June 2017 (registration number: UMIN000027879).

Unsupervised smoke to desmoked laparoscopic surgery images using contrast driven Cyclic-DesmokeGAN

In laparoscopic surgery, energized dissecting devices and laser ablation causes smoke, which degrades the visual quality of the operative field. This paper proposes an unsupervised approach to desmoke laparoscopic images called Cyclic-DesmokeGAN. In the generator, multi-scale residual blocks help to alleviate the smoke component at multiple scales, while refinement module helps to obtain desmoked images with sharper boundaries. As the presence of smoke degrades contrast and fine structure, the proposed method utilizes high boost filtered image at each encoder layer. The contrast loss improves overall contrast, thereby reducing the smoke, while Unsharp Regularization loss helps to stabilize the network. The proposed Cyclic-DesmokeGAN is tested on 200 smoke images obtained from Cholec80 dataset consisting of videos of cholecystectomy surgeries. The results depict effectiveness, as proposed approach achieved 3.47±0.09 Contrast-Distorted Images Quality, 4.15±0.74 Naturalness Image Quality Evaluator, and 0.23±0.00 Fog Aware Density Evaluator, these indexes are best in comparison to other state-of-the-art methods.