In recent years, artificial intelligence technology has been empowering various industries and leading industrial upgrading. The progress of artificial intelligence in medical image analysis and surgical navigation positioning is revolutionizing the entire medical field and gradually penetrating into the diagnosis and treatment of thyroid and parathyroid diseases. This article focuses on the application of artificial intelligence in the surgical diagnosis and treatment of thyroid and parathyroid diseases, emphasizing the research and application progress of deep learning based artificial intelligence systems in preoperative evaluation, intraoperative decision-making assistance, and postoperative prognosis prediction, and exploring future development prospects.

Objective:To explore the value of mitoxantrone hydrochloride injection for tracing in endoscopic thyroidectomy (ETE) via anterior chest approach for papillary thyroid carcinoma (PTC) .Methods:A retrospective analysis was conducted on patients undergoing ETE via anterior chest approach for PTC admitted to Beijing Longfu Hospital (Medical Treatment Combination with Peking Union Medical College Hospital) from Sep. 2022 to Mar. 2024. The patients were divided into two groups: the control group (without tracer) and the tracer group (with mitoxantrone hydrochloride injection for tracing). All surgeries were performed by the same thyroid surgical team. Baseline, postoperative pathologies and complications were compared between the 2 groups.Results:A total of 25 patients (13 in the control group and 12 in the tracer group) were included in this study, and the average dissection of unilateral central region lymph nodes in the tracer group was 7.4±4.6, significantly more than in the control group (2.4±1.9) ( P=0.004). There were no instances of mistakenly resected parathyroid gland in the postoperative pathology or accidental injury of recurrent laryngeal nerve in either group. The incidence of transient hypocalcemia did not significantly different between the two groups ( P=0.503). However, the incidence of transient hypoparathyroidism in the tracer group was 1 (1/12,8.3%), significantly lower than in the control group 4 (4/13,30.8%) ( P=0.009). The tracer group exhibited more impressive levels in parathyroid hormone (5.4±8.1) pg/mL compared to the control group (20.0±11.1) pg/mL ( P=0.001) .The total volume of postoperative drainage in the tracer group (142.9±71.7) mL was more than that of the control group (87.7±38.8) mL ( P=0.030). But It did not affect the extubation time in either group ( P=0.610). No residual tracer was observed at the skin puncture site in the tracer group after 2 weeks. Conclusions:Mitoxantrone hydrochloride injection for tracing as tracer in ETE via breast approach can increase the number of pathological lymph nodes dissection in cervical central region. Combined with negative development, identifying and protecting the function of parathyroid glands show feasible and potential application value to improve the safety of thyroidectomy. The use of mitoxantrone hydrochloride injection for tracer has the risk of increased exudation from the surgical area, but does not affect the time to remove the drain.

Objective:To explore the use of near-infrared autofluorescence probe (NIRAF-P) and its application in identifying parathyroid glands during surgery.Methods:A total of 68 patients undergoing thyroid surgery at Peking Union Medical College Hospital and Beijing Longfu Hospital between Dec. 2023 and Jun. 2024 were selected. During the operation, the near-infrared parathyroid gland detector was used to identify the parathyroid gland tissue to be tested, and histopathological examination was performed. The positive predictive value and accuracy of the near-infrared parathyroid gland detector were analyzed.Results:A total of 111 parathyroid glands were identified in 68 patients, and the positive predictive value and accuracy of the NIRAF-P were 95.5% and 94.6%, respectively.Conclusions:The NIRAF-P has high accuracy in identifying parathyroid glands. The standardized application of the NIRAF-P can help improve the efficiency of identifying parathyroid glands during surgery.

Patients with severe trauma require an extremely timely treatment and transfusion plays an irreplaceable role in the emergency treatment of such patients. An increasing number of evidence-based medicinal evidences and clinical practices suggest that patients with severe traumatic bleeding benefit from early transfusion of low-titer group O whole blood or hemostatic resuscitation with red blood cells, plasma and platelet of a balanced ratio. However, the current domestic mode of blood supply cannot fully meet the requirements of timely and effective blood transfusion for emergency treatment of patients with severe trauma in clinical practice. In order to solve the key problems in blood supply and blood transfusion strategies for emergency treatment of severe trauma, Branch of Clinical Transfusion Medicine of Chinese Medical Association, Group for Trauma Emergency Care and Multiple Injuries of Trauma Branch of Chinese Medical Association, Young Scholar Group of Disaster Medicine Branch of Chinese Medical Association organized domestic experts of blood transfusion medicine and trauma treatment to jointly formulate Chinese expert consensus on blood support mode and blood transfusion strategies for emergency treatment of severe trauma patients ( version 2024). Based on the evidence-based medical evidence and Delphi method of expert consultation and voting, 10 recommendations were put forward from two aspects of blood support mode and transfusion strategies, aiming to provide a reference for transfusion resuscitation in the emergency treatment of severe trauma and further improve the success rate of treatment of patients with severe trauma.

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.

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.

Objective:To summarize the experience and the clinical data of patients with primary hyperparathyroidism undergoing endoscopic parathyroidectomy.Methods:A total of 24 patients who underwent endoscopic parathyroidectomy for primary hyperparathyroidism in Peking Union Medical College Hospital during Feb. 2021 to May. 2022 were concluded in this study (20 cases of parathyroidectomy via axillary approach and 4 cases of parathyroidectomy via thoracic and breast approach) . The operation time, postoperative drainage, length of stay, level of parathyroid hormone and serum calcium of those patients were collected. Postoperative complications and recurrence of hyperparathyroidism were also observed.Results:The postoperative levels of serum parathyroid hormone and serum calcium were significantly reduced (over 50%) compared with preoperative level ( P<0.05) . The average operation time was (96±22) min (64-157 min) . The mean postoperative drainage volume was (47±16) ml on day 1, (46±11) ml on day 2, and (30±9) ml on day 3, respectively. The average length of postoperative hospital stay was (2.8±1.1) days (2-6 days) . In one case of parathyroidectomy via axillary approach, the operation was converted to open surgery because of the low position of lesion. Other cases completed endoscopic surgery and obtained satisfactory cosmetic results. There were no postoperative complications such as bleeding, permanent hoarseness, coughing while drinking water, or surgical site infection. The mean follow-up time was (7.4±4.2) months (1-16 months) . There was no obvious discomfort and no recurrence during follow-up. Conclusion:Endoscopic parathyroidectomy is safe and effective in the treatment of primary hyperparathyroidism, which can be used as a surgical option for patients with cosmetic requirements.

Objective:To investigate the influencing factors for the development of gall-stone in population of Beijing.Methods:The retrospective cross-sectional survey was conducted. From November 2016 to September 2020, patients living in Beijing (registered residence in Beijing ≥12 months) who visited the biliary outpatient of Department of General Surgery of Peking Union Medical College Hospital, Chinese Academy of Medical Sciences for the first time were recruited to participate as respondents. The survey was conducted by the questionnaire survey on correlation between dietary habits and incidence of gallstones, in which the information of gender, age, body mass index (BMI), gallstone status, metabolic indicators (hypercholesterolemia, history of diabetes mellitus, reproductive times for female, menopause status of female, duration of menopause for female, history of weight loss), dietary indicators (dietary mix of meat and vegetable dishes, times of coffee intake per month, times of alcohol consumption per month, times of greasy diet intake per month, times of breakfast skipping per week, average overnight fasting time of breakfast skipping, times of supper skipping per week, average overnight fasting time of supper skipping), family history of gallstones, lifestyle indicators (times of staying up late per month, average overnight fasting time when staying up late, daily sedentary time, weekly physical activity score). Observation indicators: (1) results of questionnaire survey; (2) analysis of influencing factors for the occurrence of gallstone. Measurement data with normal distribution were represented as Mean± SD, and measurement data with skewed distribution were represented as M( Q1, Q3). Count data were expressed as absolute numbers or percentages. Univariate and multivariate analyses were performed using the Logistic regression model. Results:(1) Results of questionnaire survey. A total of 1 036 questionnaires were distributed, and 1 004 complete questionnaires were recovered. Of the 1 004 patients who completed the questionnaire survey, there were 329 males and 675 females, aged (44±12)years. The BMI of 1 004 patients was (24±3)kg/m 2. Of the 1 004 patients, there were 659 cases with a history of cholecystolithiasis and 345 cases without. (2) Analysis of influencing factors for the occurrence of gallstone. Results of univariate analysis showed that age, history of diabetes mellitus, history of weight loss, times of coffee intake per month, times of greasy diet intake per month, family history of gallstone and daily sedentary time were related factors for the development of gallstone in 1 004 patients ( odds ratio=1.03, 2.26, 1.74, 1.01, 1.01, 2.22, 1.06, 95% confidence intervals as 1.02?1.05, 1.09?5.18, 1.22?2.53, 1.00?1.03, 1.00?1.01, 1.60?3.11, 1.01?1.11, P<0.05). Results of multivariate analysis showed that age, history of diabetes mellitus, history of weight loss, times of greasy diet intake per month, family history of gallstone and daily sedentary time were independent influencing factors for the development of gallstone in 1 004 patients ( odds ratio=1.03, 2.26, 1.82, 1.01, 2.22, 1.06, 95% confidence intervals as 1.02?1.05, 1.11?5.13, 1.28?2.62, 1.00?1.02,1.60?3.09, 1.01?1.12, P<0.05). Conclusion:Age, history of diabetes mellitus, history of weight loss, times of greasy diet intake per month, family history of gallstone and daily sedentary time are independent influencing factors for the development of gallstone in population of Beijing.

Objective:To explore the feasibility of deep learning technology for renal artery recognition in retroperitoneal laparoscopic renal surgery videos.Methods:From January 2020 to July 2021, the video data of 87 cases of laparoscopic retroperitoneal nephrectomy, including radical nephrectomy, partial nephrectomy, and hemiurorectomy, were retrospectively analyzed. Two urological surgeons screened video clips containing renal arteries. After frame extraction, annotation, review, and proofreading, the labeled targets were divided into training set and test set by the random number table in a ratio of 4∶1. The training set was used to train the neural network model. The test set was used to test the ability of the neural network to identify the renal artery in scenes with different difficulties, which was uniformly transmitted to the YOLOv3 convolutional neural network model for training. According to the opinion of two senior doctors, the test set was divided into high, medium, and low discrimination of renal artery and surrounding tissue. High identification means a clean renal artery and a large exposed area. For middle recognition degree, the renal artery had a certain degree of blood immersion, and the exposed area was medium. Low identification means that the exposed area of the renal artery was small, often located at the edge of the lens, and the blood immersion was severe, which may lead to lens blurring. In the surgical video, the annotator annotated the renal artery truth box frame by frame. After normalization and preprocessing, all images were input into the neural network model for training. The neural network output the renal artery prediction box, and if the overlap ratio (IOU) with the true value box was higher than the set threshold, it was judged that the prediction was correct. The neural network test results of the test set were recorded, and the sensitivity and accuracy were calculated according to IOU.Results:In the training set, 1 149 targets of 13 videos had high recognition degree, 1 891 targets of 17 videos had medium recognition degree, and 349 targets of 18 videos had low recognition degree. In the test set, 267 targets in 9 videos had high recognition degree, 519 targets in 11 videos had medium recognition degree, and 349 targets in 18 videos had low recognition degree. When the IOU threshold was 0.1, the sensitivity and accuracy were 52.78% and 82.50%, respectively. When the IOU threshold was 0.5, the sensitivity and accuracy were 37.80% and 59.10%, respectively. When the IOU threshold was 0.1, the sensitivity and accuracy of high, medium and low recognition groups were 89.14% and 87.82%, 45.86% and 78.03%, 32.95%, and 76.67%, respectively. The frame rate of the YOLOv3 algorithm in real-time surgery video was ≥15 frames/second. The false detection rate and missed detection rate of neural network for renal artery identification in laparoscopic renal surgery video were 47.22% and 17.49%, respectively (IOU=0.1). The leading causes of false detection were similar tissue and reflective light. The main reasons for missed detection were image blurring, blood dipping, dark light, fascia interference, or instrument occlusion, etc.Conclusions:Deep learning-based renal artery recognition technology is feasible. It may assist the surgeon in quickly identifying and protecting the renal artery during the operation and improving the safety of surgery.

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.