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 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.

Objective To investigate the core fucosylated alpha 2-macroglobulin(LCA-α2M) level in patients with hepatocellular carcinoma (HCC), liver cirrhosis (LC) and chronic hepatitis B (CHB), and explore its diagnostic value in HCC. Methods A total of 193 HCC patients,104 LC patients and 71 HC patients in Shanghai Eastern Hepatobiliary Surgery Hospital and 45 CHB patients in Changzheng Hospital from January 2013 to December 2016 were included for retrospective study. The method for detecting LCA-α2M was set up, and then the levels of serum α2M and LCA-α2M in each group were detected. The diagnostic value of LCA-α2M for HCC was evaluated by receiver operating characteristic (ROC) analysis. Result The level of LCA-α2M/α2M × 100(LCA-α2M％) was significantly higher in HCC patients[31.25(26.61-35.42)] than that in LC patients [26.00(22.30-30.64)], CHB patients[26.23 (23.86-31.86)] and healthy controls[20.29(17.35-22.60)] (H values were 5.626, 3.388 and 10.942, respectively, P<0.05). The area under the receiver operating characteristic curve (AUC) of LCA-α2M％for identifying HCC was 0.768 (0.725-0.808). Combined α-fetoprotein(AFP) and LCA-α2M％, the area under the ROC curve was 0.890(0.856-0.919). For AFP negative HCC patients, the sensitivity of LCA-α2M％was 77.42％(24/31). Conclusion LCA-α2M％ has some values in assistant diagnosis of HCC, and could improve the detection of AFP negative HCC patients.

Objective To compare the effect of arterial thombolysis with urokinase and intravenous thrombolysis with recombinant tissue plasminogen activator(rt-PA) in treatment of ischemic stroke.Methods One hundred patients with ischemic stroke were divided into intravenous thrombolysis (with rt-PA) group and arterial thrombolysis (with urokinase) group with 50 cases each by random digits table method.The thrombolytic recanalization rate,mortality rate and complications after treatment were observed and compared between two groups.Results The thrombolytic recanalization rate in intravenous thrombolysis (with rt-PA) group was higher than that in arterial thrombolysis (with urokinase) group [88.0％ (44/50) vs.66.0％ (33/50)],the complication rate in intravenous thrombolysis (with rt-PA) group was lower than that in arterial thrombolysis (with urokinase) group [6.0％ (3/50) vs.28.0％ (14/50)],and there was significant difference (P ＜ 0.05).There was no significant difference in mortality between two groups (P ＞ 0.05).There was no significant difference in the National Institutes of Health Stroke Scale (NIHSS) scores before treatment between two groups (P ＞ 0.05).The NIHSS scores 1,3,10,30 d after treatment were lower than those before treatment in two groups,and there were significant differences (P ＜ 0.05).There was no significant difference in NIHSS scores at different times and modified Rankin Scale 30 d after treatment between two groups (P＞ 0.05).Conclusions The efficacy of rt-PA in ischemic stroke patients is significantly better than that of the arterial thrombolysis with urokinase,with higher recanalization rate and fewer complications.It is safe and effective,and can be as the first choice for the treatment of ischemic stroke thrombolysis.

Objective To investigate the risk factors for cerebral microbleeds (CMBs) and its correlation with the 24 h microalbuminuria (mALB) in patients with small artery occlusion (SAO).Methods The patients with SAO were enrolled.CMBs were detected with susceptibility-weighted imaging.The demographic and clinical characteristics and 24 h mALB of the patients were compared.Multivariate logistic regression analysis was used to identify the independent risk factors for CMB in patients with SAO.Spearman correlation analysis was used to investigate the correlation between the 24 h mALB and the degree of CMBs.Results A total of 90 patients with SAO were enrolled and 35 patients (38.89％) had CMBs.CMBs mainly distributed in basal ganglia/thalamus and infratentorial (62％) regions.The Age (70.8 ± 5.4 vs.67.3 ± 8.1; t =2.461,P =0.016),proportion of hypertension (80.0％ vs.52.7％ ;x2 =6.851,P =0.009),and 24 h mALB levels (16.257 ± 6.031 mg/24 h vs.11.910 ±5.458 mg/24 h; t =3.536,P =0.001) in the CBM group were significantly higher than those in the non-CMB group.Spearman rank correlation analysis showed that the 24 h mALB and the severity of CMB in patients with SAO showed a significant positive correlation (rs =0.795,P =0.000).The higher the 24 h mALB level was,the more severe the CMB degree would be.Multivariate logistic regression analysis showed that only 24 h mALB was the only independent risk factor for CMBs in patients with SAO (odds ratio,1.100,95％ confidence interval 1.031-1.176; P =0.002).Conclusions The 24 h mALB is an independent risk factor for CMB in patients with SAO.The 24 h mALB level is positively correlated with the severity of CMB,and it may be used as a marker for small vascular injury.

Objective To observe the therapeutic effect of folic acid on transient ischemic attack(TIA)patients with homocysteinaemia (Hcy ). Methods 129 patients of primary TIA with Hcy were divided into two groups randomly. The observation group ( n = 65 )was administered with conventional therapy and folic acid, and the control group ( n=64 ) was only given conventional therapy. The variances of the plasma HCA level three months later were compared, and remission rate of TIA and complete stroke incidence one year later were analyzed between two groups. Results The Hcy incidence rate of TIA patients was up to 41.4%. Three months later, the plasma HCA level of observation group was lower than control group( ( 14.27 ± 6. 13 ) μmol/L vs (24.99 ± 6.87 )μmol/L, t=2.799, P＜0. 01 ) ,and much lower than that of the control group post-treatment ( ( 14. 27 ±6. 13)μmol/L vs (24.68 ± 6.89) μmol/L, t = 2.735, P ＜ 0.01 ). One year later, the complete stroke incidence of TIA in observation group was lower than that of the control group(9.8% vs 25.0%, P＜0.05 ) ,and complete remission rate was higher than the latter(73.8% vs 50.0%, P ＜ 0. 01 ). Conclusion Folic acid can decrease the plasma HCA level of TIA patients with Hcy efficiently,and improve the prognosis of such patients.

Objective:To investigate the expression of Survivin and it's relationship with the expression of Bcl-2 in sinonasal inverted papilloma (SNIP).Method:Immunohistochemical method was used to determine the expression of Survivin and Bcl-2 in 30 cases of SNIP,10 cases of sinonasal squamous cell carcinoma(SCC) and 10 cases of normal inferior concha tissues.Result:Survivin was expressed in 22 of 30(73.3%)cases of SNIP,8 of 10(80.0%)cases of SCC and not expressed in 10(0%)cases of normal inferior concha tissues.Expression of Survivin was significantly higher in SNIP and SCC than in normal tissues.Bcl-2 was expressed in 9 of 10(90.0%)cases of SCC and 2 of 10(20.0%)cases of normal inferior concha tissues.Expression of Bcl-2 was significantly higher in SCC than in normal tissues.Bcl-2 was expressed in 14 of 30(46.7%)cases of SNIP,higher than normal tissues.Expression of Bcl-2 was positively related to expression of Survivin.Conclusion:Survivin may play an important role in the pathway of progression of SNIP and SCC.It may be identified as a new therapeutic target.Bcl-2 may play a synergic role with Survivin in progression of SNIP.

OBJECTIVE: To investigate the expression of Survivin and its relationship with the expression of Bcl-2 in sinonasal inverted papilloma (SNIP). METHOD: Immunohistochemical method was used to determine the expression of Survivin and Bcl-2 in 30 cases of SNIP, 10 cases of sinonasal squamous cell carcinoma (SCC) and 10 cases of normal inferior concha tissues. RESULT: Survivin was expressed in 22 of 30 (73.3%) cases of SNIP, 8 of 10 (80.0%) cases of SCC and not expressed in 10 (0%) cases of normal inferior concha tissues. Expression of Survivin was significantly higher in SNIP and SCC than in normal tissues. Bcl-2 was expressed in 9 of 10 (90.0%) cases of SCC and 2 of 10 (20.0%) cases of normal inferior concha tissues. Expression of Bcl-2 was significantly higher in SCC than in normal tissues. Bcl-2 was expressed in 14 of 30 (46.7%) cases of SNIP, higher than normal tissues. Expression of Bcl-2 was positively related to expression of Survivin. CONCLUSION Survivin may play an important role in the pathway of progression of SNIP and SCC. It may be identified as a new therapeutic target. Bcl-2 may play a synergic role with Survivin in progression of SNIP.
Adult ; Aged ; Aged, 80 and over ; Carcinoma, Squamous Cell ; metabolism ; pathology ; Female ; Humans ; Inhibitor of Apoptosis Proteins ; metabolism ; Male ; Middle Aged ; Nose Neoplasms ; metabolism ; pathology ; Papilloma, Inverted ; metabolism ; pathology ; Paranasal Sinus Neoplasms ; metabolism ; pathology ; Proto-Oncogene Proteins c-bcl-2 ; metabolism ; Survivin ; Young Adult