Robotic-assisted resection of proximal jejunal ischemic stricture and intracorporeal robot-sewn anastomosis

Vishu Jain,Peeyush Varshney,Subhash Chandra Soni,Vaibhav Kumar Varshney,B Selvakumar 대한내시경로봇외과학회 2022 Journal of Minimally Invasive Surgery Vol.25 No.4

With the advent of robotic surgery as an effective means of minimally invasive surgery in the last decade, more and more surgeries are being performed robotically in today’s world. Robotic surgery has several advantages over conventional laparoscopic surgery, such as three-dimensional vision with depth perception, magnified view, tremor filtration, and, more importantly, degrees of freedom of the articulating instruments. While the literature is abundant on robotic cholecystectomy and highly complex hepatobiliary surgeries, there is hardly any literature on robotic small bowel resection with intracorporeal anastomosis. We present a case of a 50-year-old male patient with a symptomatic proximal jejunal ischemic stricture who underwent robotic-assisted resection and robot-sewn intracorporeal anastomosis in two layers. He did well in the postoperative period and was discharged on postoperative day 4 with uneventful recovery. We hereby discuss the advantages and disadvantages of robotic surgery in such a scenario with a review of the literature.

Open injury, robotic repair—moving ahead! Total robotic Roux-en-Y hepaticojejunostomy for post-open cholecystectomy Bismuth type 2 biliary stricture using indocyanine green dye

Kaushal Singh Rathore,Peeyush Varshney,Subhash Chandra Soni,Vaibhav Kumar Varshney,Selvakumar B,Lokesh Agarwal,Chhagan Lal Birda 대한내시경로봇외과학회 2023 Journal of Minimally Invasive Surgery Vol.26 No.3

Hepaticojejunostomy is currently the best treatment for post-cholecystectomy biliary strictures. Laparoscopic repair has not gained popularity due to difficult reconstruction. We present case of 43-year-old-female with Bismuth type 2 stricture following laparoscopic converted open cholecystectomy with bile duct injury done elsewhere. Position was modified Llyod-Davis position and four 8-mm robotic ports (including camera) and 12-mm assistant port were placed. The procedure included noticeable steps such as adhesiolysis, identification of gallbladder fossa, identification of common hepatic duct, lowering of hilar plate etc. Operating and console time were 420 and 350 minutes and blood loss was 100 mL. Patient was discharged on postoperative day 4. Robotic repair (hepaticojejunostomy) of biliary tract stricture after cholecystectomy is safe and feasible with good outcomes.

Identification of Green Gram (Vigna radiata) Grains Infested by Callosobruchus maculatus Through X-ray Imaging and GAN-Based Image Augmentation

Divyanth L. G.,Chelladurai V.,Loganathan M.,Jayas Digvir S.,Soni Peeyush 한국농업기계학회 2022 바이오시스템공학 Vol.47 No.3

Purpose Green gram (Vigna radiata) is an important food legume of the world. However, post-harvest losses due to pulse beetle, Callosobruchus maculatus (F.), are significant due to improper storage management practices and undetected internal infestations. The detection of early stages of infestation could help in implementing suitable control practices for insect disinfestation. This study determined the potential of detecting internal infestations caused by C. maculatus using the soft X-ray method and deep learning. Furthermore, this study aims to reduce the time and effort needed to prepare a huge amount of image data for this highly data-driven process by using generative adversarial networks (GANs). Methods A three-class classification method was implemented to identify the infestation stages, namely, uninfested kernel, larva stage, and pupa stage. The approach was based on features extraction from the deepest pooling layer of a state-of-the-art Convolutional Neural Network architecture—the Xception, and using support vector machine as the classifier. Moreover, a GAN model was proposed to synthesize artificial X-ray images. Results The overall F1-score produced by the model was improved from 0.86 to 0.91 when the GAN-synthesized dataset additionally supported the training data. Also, the classification accuracy for detecting the stage of internal infestation improved by 5.5%. Conclusion The experiment showed that X-ray imaging and deep learning–based automatic features extraction could identify internal infestation in green gram grains. The results determine that augmentation using GANs can enhance the status of learningbased grain quality assessment models with reduced manual effort.

Impact of nasogastric tube exclusion after minimally invasive esophagectomy for esophageal cancer: a single-center retrospective study in India

Vignesh N,Vaibhav Kumar Varshney,Selvakumar B,Subhash Soni,Peeyush Varshney,Lokesh Agarwal 대한내시경로봇외과학회 2024 Journal of Minimally Invasive Surgery Vol.27 No.1

Purpose: This study examines the impacts of omitting nasogastric tube (NGT) placement following cervical esophagogastric anastomosis (CEGA) in Enhanced Recovery After Surgery (ERAS) protocols, comparing outcomes to those from early NGT removal. Methods: In a retrospective cohort of esophagectomy patients treated for esophageal cancer, participants were divided into two groups: group 1 had the NGT inserted post-CEGA and removed by postoperative day 3, while group 2 underwent the procedure without NGT placement. We primarily investigated anastomotic leak rates, also analyzing hospital stay duration, pulmonary complications, and NGT reinsertion. Results: Among 50 esophageal squamous cell carcinoma patients, 30 in group I were compared with 20 in group II. The baseline demographic and tumor characteristics were similar between both groups. The overall incidence of anastomotic leak was 14.0%, comparable in both groups (16.7% vs. 10.0%, p = 0.63). The postoperative hospital stay was significantly shorter in the no NGT group (median of 7 days vs. 6 days, p = 0.03) with similar major morbidity (Clavien-Dindo grade ≥IIIa; 13.3% vs. 5.0%, p = 0.63). There was no 30-day mortality, and one patient in each group had reinsertion of NGT for conduit dilatation. Conclusion: The exclusion of an NGT across CEGA after esophagectomy did not influence the anastomotic leak rate with comparable complications and a shorter hospital stay.

A Two-Stage Deep-Learning Model for Detection and Occlusion-Based Classification of Kashmiri Orchard Apples for Robotic Harvesting

Rathore Divya,Divyanth L. G.,Reddy Kaamala Lalith Sai,Chawla Yogesh,Buragohain Mridula,Soni Peeyush,Machavaram Rajendra,Hussain Syed Zameer,Ray Hena,Ghosh Alokesh 한국농업기계학회 2023 바이오시스템공학 Vol.48 No.2

Purpose The process of robotic harvesting has revolutionized the agricultural industry, allowing for more effi cient and costeff ective fruit picking. Developing algorithms for accurate fruit detection is essential for vision-based robotic harvesting of apples. Although deep-learning techniques are popularly used for apple detection, the development of robust models that can accord information about the fruit’s occlusion condition is important to plan a suitable strategy for end-eff ector manipulation. Apples on the tree experience occlusions due to leaves, stems (branches), trellis wire, or other fruits during robotic harvesting. Methods A novel two-stage deep-learning-based approach is proposed and successfully demonstrated for detecting ontree apples and identifying their occlusion condition. In the fi rst stage, the system employs a cutting-edge YOLOv7 model, meticulously trained on a custom Kashmiri apple orchard image dataset. The second stage of the approach utilize the powerful Effi cientNet-B0 model; the system is able to classify the apples into four distinct categories based on their occlusion condition, namely, non-occluded, leaf-occluded, stem/wire-occluded, and apple-occluded apples. Results The YOLOv7 model achieved an average precision of 0.902 and an F1-score of 0.905 on a test set for detecting apples. The size of the trained weights and detection speed were observed to be 284 MB and 0.128 s per image. The classifi cation model produced an overall accuracy of 92.22% with F1-scores of 94.64%, 90.91%, 86.87%, and 90.25% for nonoccluded, leaf-occluded, stem/wire-occluded, and apple-occluded apple classes, respectively. Conclusion This study proposes a novel two-stage model for the simultaneous detection of on-tree apples and classify them based on occlusion conditions, which could improve the eff ectiveness of autonomous apple harvesting and avoid potential damage to the end-eff ector due to the objects causing the occlusion.