RESUMEN
Background: Bile duct injuries during laparoscopic cholecystectomy can arise from misinterpretation of biliary anatomy, leading to dissection in improper areas. The integration of a deep learning framework into laparoscopic procedures offers the potential for real-time anatomical landmark recognition, ensuring accurate dissection. The objective of this study is to develop a deep learning framework that can precisely identify anatomical landmarks, including Rouviere's sulcus and the liver base of segment IV, and provide a guided dissection line during laparoscopic cholecystectomy. Methods: We retrospectively collected 40 laparoscopic cholecystectomy videos and extracted 80 images form each video to establish the dataset. Three surgeons annotated the bounding boxes of anatomical landmarks on a total of 3200 images. The YOLOv7 model was trained to detect Rouviere's sulcus and the liver base of segment IV as anatomical landmarks. Additionally, the guided dissection line was generated between these two landmarks by the proposed algorithm. To evaluate the performance of the detection model, mean average precision (mAP), precision, and recall were calculated. Furthermore, the accuracy of the guided dissection line was evaluated by three surgeons. The performance of the detection model was compared to the scaled-YOLOv4 and YOLOv5 models. Finally, the proposed framework was deployed in the operating room for real-time detection and visualization. Results: The overall performance of the YOLOv7 model on validation set and testing set were 98.1 % and 91.3 %, respectively. Surgeons accepted the visualization of guide dissection line with a rate of 95.71 %. In the operating room, the well-trained model accurately identified the anatomical landmarks and generated the guided dissection line in real-time. Conclusions: The proposed framework effectively identifies anatomical landmarks and generates a guided dissection line in real-time during laparoscopic cholecystectomy. This research underscores the potential of using deep learning models as computer-assisted tools in surgery, providing an assistant tool to accommodate with surgeons.
RESUMEN
Background: Laparoscopic cholecystectomy (LC), a common treatment for symptomatic gallstones, has demonstrated safety in low-risk patients. However, existing data are scarce regarding the safety of LC in high-risk patients and the feasibility of early hospital discharge. Materials and methods: This retrospective study included 2296 patients diagnosed with symptomatic gallstones who underwent LC at a tertiary care centre from January 2009 through December 2019. The authors employed propensity score matching to mitigate bias between groups. Statistical significance was set at P less than 0.05. Results: The median age of the patients was 56 years (range 46-67), with a mean BMI of 25.2±4.3 kg/m2. Patients were classified as: American Society of Anesthesiologists (ASA) I (19.7%), II (68.3%), III (12.0%), and IV (0%). ASA I-II included low surgical risk patients (88%) and ASA III-IV comprised high-risk patients (12%). The LC-related 30-day reoperative rate was 0.2% and the readmission rate was 0.87%. Nine patients (0.4%) sustained major bile duct injuries, resulting in a conversion rate of 2.4%. The postoperative mortality rate was 0.04%, and the mean hospitalization time was 3.5 days. Patients in the high-risk group with a history of acute cholecystitis exhibited greater estimated blood loss, longer operative times, and were significantly more likely to be in the longer-stay group. Conclusion: These findings suggest that LC can be conducted safely on high-risk patients, and early hospital discharge is achievable. However, specific factors, such as a history of acute cholecystitis, may result in prolonged hospitalization owing to increased blood loss and longer operative times.
RESUMEN
BACKGROUND: Direct optical trocar insertion is a common procedure in laparoscopic minimally invasive surgery. However, misinterpretations of the abdominal wall anatomy can lead to severe complications. Artificial intelligence has shown promise in surgical endoscopy, particularly in the employment of deep learning models for anatomical landmark identification. This study aimed to integrate a deep learning model with an alarm system algorithm for the precise detection of abdominal wall layers during trocar placement. METHOD: Annotated bounding boxes and assigned classes were based on the six layers of the abdominal wall: subcutaneous, anterior rectus sheath, rectus muscle, posterior rectus sheath, peritoneum, and abdominal cavity. The cutting-edge YOLOv8 model was combined with a deep learning detector to train the dataset. The model was trained on still images and inferenced on laparoscopic videos to ensure real-time detection in the operating room. The alarm system was activated upon recognizing the peritoneum and abdominal cavity layers. We assessed the model's performance using mean average precision (mAP), precision, and recall metrics. RESULTS: A total of 3600 images were captured from 89 laparoscopic video cases. The proposed model was trained on 3000 images, validated with a set of 200 images, and tested on a separate set of 400 images. The results from the test set were 95.8% mAP, 89.8% precision, and 91.7% recall. The alarm system was validated and accepted by experienced surgeons at our institute. CONCLUSION: We demonstrated that deep learning has the potential to assist surgeons during direct optical trocar insertion. During trocar insertion, the proposed model promptly detects precise landmark references in real-time. The integration of this model with the alarm system enables timely reminders for surgeons to tilt the scope accordingly. Consequently, the implementation of the framework provides the potential to mitigate complications associated with direct optical trocar placement, thereby enhancing surgical safety and outcomes.
Asunto(s)
Aprendizaje Profundo , Laparoscopía , Humanos , Inteligencia Artificial , Laparoscopía/efectos adversos , Laparoscopía/métodos , Peritoneo , Instrumentos Quirúrgicos , Procedimientos Quirúrgicos Mínimamente InvasivosRESUMEN
Modified fundus-down cholecystectomy is a surgical procedure used to treat patients diagnosed with benign gallbladder disease. This technique begins with Calot's triangle dissection and attempts to identify key structures such as the cystic artery and duct. Subsequently, fundus-down dissection is performed to separate the gallbladder from the cystic plate. The cystic artery and duct are the final structures that are clipped and cut. In this study, the authors discuss the success and complication rates of this treatment based on their 10-year experience at a tertiary hospital in southern Thailand. Objectives: This study aimed to compare the operative outcomes of conventional laparoscopic cholecystectomy (LC) and modified fundus-down techniques regarding postoperative complications and consequences. Methods: A retrospective analysis of single-centre data from 2010 to 2022 was conducted at our hospital. All patients with gallstone disease who underwent conventional LC or modified fundus-down cholecystectomy were included in the study. The primary outcomes of this study were the incidence of major bile duct injury and the need for further intervention or surgical correction. Results: From a total of 1993 patients who were surveyed, 1612 patients underwent conventional LC and 381 underwent laparoscopic modified fundus-down cholecystectomy. In terms of conversion rate, estimated blood loss, length of hospital stay, and complication rate, there were no differences between the conventional LC and the modified fundus-down approach. However, modified fundus-down cholecystectomy reduced the operative time. The authors collected data from each patient's sign-in to extubation time (P<0.001). The postoperative complications (P=0.120) and conversion rates (P=0.904) were similar. Conclusion: Laparoscopic modified fundus-down cholecystectomy can be performed in simple and complex cases, including cases of severe fibrosis of the hepatocystic triangle. The study showed that this alternative technique could reduce operative time compared to the conventional technique with no difference in complications, especially common bile duct injury, postoperative common bile duct stones, and postoperative pancreatitis.
RESUMEN
BACKGROUND: Preoperative esophagogastroduodenoscopy (EGD) in patients undergoing bariatric surgery can help surgeons detect abnormalities in the upper gastrointestinal (UGI) tract that may require a change in surgical plan. However, the need for EGD before bariatric surgery is controversial. OBJECTIVES: We aimed to determine the prevalence of UGI abnormalities and evaluate the predictive factors of abnormal findings that require a change in surgical plan or cause a delay in surgical treatment in patients undergoing bariatric surgery and develop a prediction model. METHODS: The medical records from January 2012 to July 2020 were retrospectively reviewed in patients who underwent EGD before bariatric surgery. The EGD findings were classified into four groups based on their effects on management. Group 1 had normal findings. Group 2 had abnormal findings that did not require a change in surgical management. Group 3 had abnormal findings that required a change in the surgical plan or caused a delay in surgical treatment. Group 4 had contraindications to surgery. Predictive factors for Groups 3 and 4 were analyzed using univariate and multivariate analyses. A model visualized as a nomogram was developed based on significant factors. Discrimination and calibration were evaluated. RESULTS: A total of 461 patient records (63.8% female) were reviewed. The mean age was 35.1 ± 11.2 years and the mean BMI was 47.7 ± 8.7 kg/m2. The prevalence of endoscopic findings in Groups 1, 2, 3, and 4 were 42.5%, 35.6%, 21.9%, and 0%, respectively. The most common abnormal findings were non-erosive gastritis (31.2%) followed by Helicobacter pylori infection (18.7%) and hiatal hernia (10.2%). Male sex and NSAID use were significantly associated with detection of lesions in Group 3 either on univariate or multivariate analysis, while type 2 diabetes mellitus (T2DM) was a significant protective factor on multivariate analysis. On subgroup analysis in patients ≥ 40 years old, multivariate analysis revealed age, BMI, and NSAID use were significantly associated with the detection of lesions in Group 3, while T2DM was still a significant protective factor. A nomogram to predict lesions in Group 3 for this subgroup was developed and showed good discrimination (C-statistics 0.737, 95% CI 0.721â0.752). CONCLUSION: A high prevalence of abnormal endoscopic findings was observed in Thai patients who are undergoing bariatric surgery. Preoperative EGD screening is helpful in detecting UGI abnormalities that require a change in the surgical decision plan. The new nomogram may help rational utilization of EGD prior to bariatric surgery.
Asunto(s)
Cirugía Bariátrica , Diabetes Mellitus Tipo 2 , Infecciones por Helicobacter , Helicobacter pylori , Obesidad Mórbida , Humanos , Masculino , Femenino , Adulto Joven , Adulto , Persona de Mediana Edad , Obesidad Mórbida/complicaciones , Obesidad Mórbida/cirugía , Obesidad Mórbida/epidemiología , Estudios Retrospectivos , Diabetes Mellitus Tipo 2/complicaciones , Cuidados Preoperatorios , Endoscopía del Sistema DigestivoRESUMEN
BACKGROUND: Rectal cancer is a pervasive type of malignancy that accounts for one-third of colorectal cancers worldwide. Several studies have assessed the use of laparoscopic surgery as a treatment option. However, there is an ongoing debate regarding its oncological safety. METHODS: This retrospective study included 270 patients with non-metastatic rectal cancer who underwent either laparoscopic resection (LR, n = 93) or open resection (OR, n = 177) in an academic medical center. The primary outcomes were overall survival (OS) and disease-free survival (DFS), whereas the secondary outcome was postoperative complications. We performed propensity score analyses and compared outcomes. Univariate survival analyses using Kaplan-Meier plots and Cox proportional hazard regression models were also conducted. RESULTS: In the propensity score matching analyses, 93 LR- and 93 OR-matched patients were compared. The overall median follow-up time was 3.95 years (range, 1.98â5.55 years). The 3-year OS was similar between the groups (LR 79.1% vs OR 79.2%, p = 0.82). Meanwhile, the DFS rate was also comparable between the groups (LR 77.8% vs OR 73.2%, p = 0.53). No significant differences in operative blood loss or hospital stay between the groups were observed (150 vs 150 mL, p = 0.74; 9 vs 10 days, p = 0.077, respectively). Also, no difference was found in postoperative complications between the groups (p = 0.23). However, LR was associated with a longer operative time than OR (455 vs 356 min, p < 0.001) and the number of lymph nodes harvested in LR was slightly fewer than OR (10 vs 11, p = 0.045). CONCLUSION: LR of rectal cancer is safe, feasible, and comparable to standard OR in terms of the oncologic outcomes. However, LR required longer operative times. A well-designed prospective study with a large number of participants and long follow-up period is needed to show significant differences between the two groups.
.