ABSTRACT
Objective:To explore whether deep learning could apply to recognize the recurrent laryngeal nerve (RLN) in videos of endoscopic thyroidectomy (ETE) via breast approach.Methods:Videos of ETE via breast approach in Peking Union Medical College Hospital from Feb. 2020 to Aug. 2021 were collected. Videos containing RLN were selected, and the outline of RLN was marked by two thyroid surgeons. Then data were divided into a training set and a test set in a ratio of 5:1 and classified into the high and low difficulty group according to a senior thyroid surgeon’s opinion. Those pictures were input to D-LinkNet model. Precision, sensitivity and mean dice index was calculated.Results:A total of 46 videos including 153, 520 frames of pictures were included in this study. 131,039 frames of 39 videos were in the training set and 22,481 frames of 7 videos were in the test set. When the intersection over union threshold was 0.1, the sensitivity and precision was 92.9%/72.8% and 47.6%/54.9% in high and low recognition group, respectively. When the intersection over union threshold was 0.5, the sensitivity and precision turned to 85.8%/67.2% and 37.6%/43.5% in high and low difficulty group, respectively. Mean Dice index was 0.781 and 0.663 in high and low difficulty group, respectively.Conclusions:RLN recognition based on deep learning is feasible and has potential application value in ETE, which may help surgeons reduce the risk of accidental injury of RLN and improve the safety of thyroidectomy.
ABSTRACT
Objective:To explore whether deep learning could apply to recognize the recurrent laryngeal nerve in the video of unilateral axillary approach endoscopic thyroidectomy.Methods:Videos of endoscopic thyroidectomy via unilateral axillary approach in Peking Union Medical College Hospital from Jul. 1st, 2020 to May. 1st, 2021 were collected. Videos containing the recurrent laryngeal nerve were selected, and the outline of recurrent laryngeal nerve were marked by two senior thyroid surgeons and staffs. Data were divided into training set and test set in a ratio of 5:1, and classified into high, medium and low recognition group according to difficulty of recognizing the outline of the nerve. The neuron network was based on PSPNet combined with Resnet50. All data were analyzed by R (ver. 4.0.2) .Results:A total of 38 videos including 35,501 frames of pictures were included in this study. 29, 704 frames of 32 videos were in our training set and 5797 frames of 6 videos were in the test set. When the intersection over union (IOU) threshold is 0.1, the sensitivity and precision is 100.0%/92.1%, 95.8%/80.2% and 81.0%/80.6% in high, medium and low recognition group respectively. When the IOU threshold is 0.5, the sensitivity and precision is 92.6%/85.3%, 71.7%/60.5% and 38.1%/37.9% in high, medium and low recognition group respectively, indicating that neuron network could located the outline of recurrent laryngeal nerve in high and medium recognition group. False negatives were often due to small targets and unclear boundaries.Conclusion:Recurrent laryngeal nerve recognition based on deep learning is feasible and has potential application value in endoscopic thyroidectomy, which may help surgeons reduce the risk of accidental injury of recurrent laryngeal nerve and improve the safety of thyroidectomy.
ABSTRACT
Peking Union Medical College Hospital, as one of the most stressful medical institutions in China, is facing the problem of emergency department overcrowding. In order to effectively alleviate the emergency overcrowding, improve the medical quality and patients′ medical experience, the hospital firmly grasped the two incremental links of " throughput" and " output" factors, established a multidisciplinary and multi-department cooperation team, constructed a close medical alliance cooperation mode, and innovated and explored a harmonious emergency overcrowding relief mode with the goal of unblocking the " exit" of patients. The practice showed that the comprehensive measures could effectively alleviate the problem of emergency overcrowding, and improve the medical environment and medical quality.
ABSTRACT
Objective:To investigate the application value of machine learning algorithms for gauze detection in laparoscopic pancreatic surgery.Methods:The retrospective and descriptive study was conducted. The 80 intact laparoscopic pancreatic surgery videos from Peking Union Medical College Hospital of Chinese Academy of Medical Sciences with timing of July 2017 to July 2020 were collected. The training set was used to train the neural network, and the test set was used to test the ability of neural network for gauze detection under different difficulties. Under the supervision of two superior doctors, videos that containing gauze were selected and classified according to recognition difficulty into three difficulty level including easy, normal and hard difficulty, and further divided based on random number method into training set with 61 videos and test set with 19 videos in a ratio of 3:1 roughly. The minimum enclosing rectangle of the gauze were marked frame by frame. All images were input to the neural network model for training after normalization and preprocessing. For every image, the output of neural network is the predicted minimum enclosing rectangle of gauze. The intersection over union >0.5 was identified as positive result. Observation indicators: (1) video annotation and classification; (2) test outcomes of neural network for test set.Count data were represented as absolute numbers or percentages.Results:(1) Video annotation and classification: a total of 26 893 frames of images form 80 videos were annotated, with 61 videos including 22 564 frames of images as the training set and 19 videos including 4 329 frames of images as the test set. Of the training set, 19 videos including 5 791 frames of images were classifed as easy difficulty, 38 videos including 15 771 frames of images were classifed as normal difficulty, 4 videos including 1 002 frames of images were classifed as hard difficulty, respectively. Of the test set, 4 videos including 1 684 frames of images were classifed as easy difficulty, 6 videos including 1 016 frames of images were classifed as normal difficulty, 9 videos including 1 629 frames of images were classifed as hard difficulty, respectively. (2) Test outcomes of neural network for test set: the overall sensitivity and accuracy of gauze detection by neural network in the test set were 78.471%(3 397/4 329) and 69.811%(3 397/4 866), respectively. The sensitivity and accuracy of gauze detection by neural network were 94.478%(1 591/1 684) and 83.168%(1 591/1 913) in easy difficulty test set. The sensitivity and accuracy of gauze detection by neural network were 80.413%(817/1 016) and 70.859%(817/1 153) in normal difficulty test set, 60.712%(989/1 629) and 54.944%(989/1 800)in hard difficulty test set. The frame rate reached more than or equally to 15 fps. The overall false negative rate and false positive rate of gauze detection by neural network in the test set were 21.529%(932/4 329) and 30.189%(1 469/4 866), respectively. The false negative was mainly due to the existence of blurred images, too small gauze exposure or blood immersion of gauze. The false positive was caused by the reflection of connective tissue or body fluids.Conclusion:The machine learning algorithms for gauze detection in laparoscopic pancreatic surgery is feasible, which could help medical staff identify gauze.
ABSTRACT
Objective@#To discuss the impact of updated definition and classification system of pancreatic fistula published in 2016 on the postoperative classification of pancreatic fistula.@*Methods@#Retrospective analysis was made on patients who underwent pancreatic surgery at ward 1 in Department of General Surgery, Peking Union Medical College Hospital from January 2015 to December 2016.A total of 408 patients were included in this retrospective study, male/female was 184/224, aged from 9 to 81 years with mean age of 51.6 years.One hundred and fifty-two cases were performed pancreaticoduodenectomy, 125 cases for distal pancreatectomy, 43 cases for spleen preservation distal pancreatectomy, 61 cases for partital pancreatectomy or enucleation, 8 cases for middle pancreatectomy, 6 cases for pancreaticojejunostomy and 13 cases for other procedures.Clinical data including postoperative drainage fluid volume, amylase concentration, duration of hospitalization and drainage were obtained, revaluated and re-analyzed, classified grounded on 2005 edition and 2016 edition, respectively.t-test was adopted for data analysis.@*Results@#According to the previous standards, the incident rate of pancreatic fistula was 57.4%, and the incident rate of B-level plus C-level pancreatic fistula was 35.8%, which decreased to 13.7% based on 2016 edition.Nine patients who received percutaneous puncture or endoscopic drainage was regraded from C-level to B-level. The average duration of postoperative hospitalization of patients without pancreatic fistula was (12.5±6.0)days, demonstrating no significant difference compared to (14.1±7.7)days, duration of postoperative hospitalization of A-level(under 2005 edition of criteria) pancreatic fistula group(t=1.66, P=0.09) and (12.4±6.1)days, duration of postoperative hospitalization of biochemical leakage group(t=0.14, P=0.89). Nevertheless, there was statistical significant difference between the average postoperative duration of hospitalization(30.7±16.9) days of B-level(under 2016 criteria) pancreatic fistula patients and pancreatic fistula-free patients as well as the biochemical leakage group patients (t=7.10, 7.13; both P<0.01).@*Conclusions@#Based on the new diagnostic criteria, the incidence of postoperative pancreatic fistula decreased dramatically.New classification system downgraded part of cases graded C-level pancreatic fistula to B-level and some B-level to biochemical fistula.The new diagnostic classification and criteria facilitated clinical practice, accomplished better conformity to clinical reality and potentially enacted clinical outcome.
ABSTRACT
<p><b>OBJECTIVE</b>To evaluate the effect and safety of enucleation of insulinoma under the Da Vinci robotic surgical system combination with intraoperative ultrasonography(IOUS) for the localization.</p><p><b>METHODS</b>The clinical materials of 50 insulinoma cases which underwent IOUS and assisted by the robotic surgical system from September 2012 to September 2014 in Peking Union Medical College Hospital were reviewed retrospectively. The patients were followed up by outpatient review and telephone until October 2014. The diagnostic accuracy rate, operation time, blood loss, complications and cure rate were analyzed by t-test.</p><p><b>RESULTS</b>The locations of tumors were 13 in the head, 21 in the body and 13 in the tail of pancreas, 2 were multiple insulinoma, 1 was ectopic to mesenterium.The average operation time was 142 minutes; the average blood loss was 165 ml.Three(6.0%) patients were transformed to open.One patient experienced postoperative bleeding about 300 ml on the 7(th) day after operation and no infection and perioperative death.Thirty-five cases were of class A and 14 of class B according to the clinical grading of postoperative pancreatic fistula.The blood glucose 60 minutes after tumor dissection was significantly elevated than that before operation ((6.2±1.8)mmol/L vs.(3.7±1.2)mmol/L)(t=-6.89, P<0.01). The cure rate was 100% as all the patients' symptoms were disappeared during follow-up time.</p><p><b>CONCLUSIONS</b>Combination IOUS is a highly sensitive method for the localization of insulinoma, which is helpful in localizing tumors precisely in insulinoma cases assisted by robotic surgical system and shortening operation time.It is safe and effective for insulinoma enucleation.</p>