1.The clinical analysis of severe complications induced by esophageal foreign bodies.
Yitao MAO ; Zhiying NIE ; Fuwei YANG ; Weijing WU
Journal of Clinical Otorhinolaryngology Head and Neck Surgery 2012;26(24):1111-1115
OBJECTIVE:
To explore and analyze the clinical characteristics and treatment strategy of severe complications caused by esophageal foreign bodies.
METHOD:
A retrospective study was carried out on 49 cases with foreign bodies in esophagus through careful analysis of their clinical data to explore the associated problems with etiology and therapy. Among this complications, there were cases of 13 periesophageal abscess, 20 cases of abscess in the neck, 11 cases of mediastinal abscess, 3 tracheoesophageal fistula, 1 case of aorta injury and 1 septicemia.
RESULT:
Forty-eight (97.96%) of the patients recovered while one died.
CONCLUSION
Hard esophagoscopy under general anesthesia is the main therapeutic strategy to take out the esophageal foreign bodies. When it failed or severe complications such as perforation or others emerged, open surgery like lateral neck incision or thoracotomy supplemented with positive and timely supporting therapy are vital and essential.
Adolescent
;
Adult
;
Aged
;
Child
;
Child, Preschool
;
Esophagus
;
Female
;
Foreign Bodies
;
complications
;
surgery
;
Humans
;
Male
;
Middle Aged
;
Retrospective Studies
;
Young Adult
2.Prophylactic and therapeutic effect of oxymatrine on D-galactosamine-induced rat liver fibrosis.
Wenzhuo YANG ; Minde ZENG ; Zhuping FAN ; Yimin MAO ; Yulin SONG ; Yitao JIA ; Lungen LU ; Cheng Wei CHEN ; Yan Shen PENG ; Hong Yin ZHU
Chinese Journal of Hepatology 2002;10(3):193-196
OBJECTIVETo investigate the prophylactic and therapeutic effect of oxymatrine on experimental liver fibrosis and to reveal its mechanism.
METHODSBy establishing D-galactosamine-induced rat liver fibrosis model, we observed the effect of oxymatrine on serum and tissue biochemical indexes, content of liver hydroxyline, expression of TGF?1 mRNA and changes of tissue pathology.
RESULTSThere was a decline of liver hydroxyline and serum AST and ALT in oxymatrine group compared to those of the D-GalN group. The hydroxyline content in oxymatrine pretreatment group was (0.50 0.11)mug/mg compared with (0.99 0.14)mug/mg in D-GalN group (t=8.366, P<0.01). The content in oxymatrine treatment group was (0.44 0.04)mug/mg compared with 0.70 0.06 in D-GalN group (t=9.839, P<0.01). The SOD activity was (149.81 15.28) NU/mg in oxymatrine pretreatment group and (95.22 16.33) NU/mg in the model group (t=7.309, P<0.01); (157.68 19.54) NU/mg in the treatment group compared with (119.88 14.94) NU/mg in the model group (t=4.348, P<0.01). MDA in the pretreatment group was (2.06 0.17) nmol/mg, lower than (4.57 0.37) nmol/mg in the model group (t=17.529, P<0.01). In the treatment group, it was (1.76 0.24)nmol/mg, lower than (3.10 0.17) nmol/mg in the model group (t=12.697, P<0.01). TGF?1 mRNA reduced in the pretreatment and treatment groups as compared with that in the model group (0.21 0.01 vs 0.50 0.01, t=48.665, P<0.01; 0.18 0.02 vs 0.38 0.01, t=22.464, P<0.01). Electron microscopy showed that oxymatrine group had milder hepatocyte degeneration and less fibrosis accumulation than did the model group. Microscopy revealed wide septa expansion from the portal area to the central venous, piecemeal and confluent necrosis and pseudo-nodular formation in part of the lobular in the model group. While in oxymatrine group these lesions were much improved.
CONCLUSIONSOxymatrine shows prophylactic and therapeutic effect in D-galactosamine induced rat liver fibrosis. This is partly by protecting hepatocyte and suppressing fibrosis accumulation through anti-lipoperoxidation.
Alkaloids ; therapeutic use ; Animals ; Anti-Arrhythmia Agents ; therapeutic use ; Calcium Hydroxide ; metabolism ; Chemoprevention ; Disease Models, Animal ; Galactosamine ; Liver Cirrhosis ; chemically induced ; drug therapy ; metabolism ; pathology ; prevention & control ; Liver Function Tests ; Male ; Quinolizines ; RNA, Messenger ; metabolism ; Rats ; Rats, Wistar ; Superoxide Dismutase ; metabolism ; Transforming Growth Factor beta ; genetics ; metabolism
3.A diffusion kurtosis imaging based nomogram for assessment of bowel fibrosis in patients with Crohn disease
Jinfang DU ; Li HUANG ; Yitao MAO ; Siyun HUANG ; Baolan LU ; Yingkui ZHONG ; Jixin MENG ; Canhui SUN ; Shiting FENG ; Xuehua LI
Chinese Journal of Radiology 2020;54(8):792-798
Objective:To explore the diagnostic efficacy of nomogram based on multi-parameter MRI for assessment of bowel fibrosis in patients with Crohn disease(CD).Methods:The clinical and imaging data of CD patients diagnosed by surgical histopathology in the First Affiliated Hospital of Sun Yat-sen University from June 2015 to March 2018 were prospectively collected. All the patients underwent conventional MRI and diffusion kurtosis imaging(DKI) within 2 weeks before surgery. Patients who underwent surgery between June 2015 and September 2017 were included in the model building group, and those who underwent surgery between October 2017 and March 2018 were included in the model validation group. We measured the apparent diffusion coefficient(ADC) from monoexponential model of diffusion-weighted imaging(DWI), apparent diffusional kurtosis(K app), and apparent diffusion for non-Gaussian distribution(D app) from non-Gaussian DKI model, and observed T 2WI signal intensity and enhancement pattern of the same segment. One to three intestinal specimens per patient were stained with Masson′s trichrome for the histological grading of fibrosis. Correlations between qualitative/quantitative MRI indexes and histological grades were evaluated using the Spearman rank test. Multivariate logistic regression analysis was performed to identify independent factors to be included into the nomogram for predicting the degree of bowel fibrosis and its diagnostic performance was assessed by internal and external validation. Results:A total of 40 CD patients were included, including 31 in the model construction group and 9 in the model verification group. A total of 81 intestinal specimens from 31 patients were graded as none-to-mild bowel fibrosis( n=32) and moderate-to-severe bowel fibrosis( n=49) according to a scoring system of fibrosis. In the training cohort, the K app value of moderate-to-severely fibrotic bowel walls was significantly higher than that of none-to-mildly fibrotic bowel walls, and the D appand ADC values of moderate-to-severely fibrotic bowel walls were significantly lower than those of none-to-mildly fibrotic bowel walls( Z=-5.999, -4.521 and -3.893; P<0.001). There was no significant difference in T 2WI signal intensity or enhancement pattern between these two groups(χ2=1.571 and 0.103; P>0.05). Moderate and mild correlations of histological fibrosis grades with K appand D app( r=0.721 and -0.483; P<0.001), and a mild correlation with ADC( r=-0.445, P<0.001) were found. Independent factors derived from multivariate logistic regression analysis to predict the degree of bowel fibrosis were K app and D app. Internal and external validation revealed good performance of the nomogram with concordance index of 0.901(95% confidence interval, 0.824-0.978) and 1.000, respectively, for differentiating none-to-mild from moderate-to-severe fibrosis. Conclusion:The DKI-based nomogram can be used to evaluate the bowel fibrosis in CD patients and provides a visual and simple prediction method for clinic.
4. The application of artificial neural network on the assessment of lexical tone production of pediatric cochlear implant users
Yitao MAO ; Zhuoming CHEN ; Li XU
Chinese Journal of Otorhinolaryngology Head and Neck Surgery 2017;52(8):573-579
Objective:
The present study was carried out to explore the tone production ability of the Mandarin-speaking children with cochlear implants (CI) by using an artificial neural network model and to examine the potential contributing factors underlining their tone production performance. The results of this study might provide useful guidelines for post-operative rehabilitation processes of pediatric CI users.
Methods:
Two hundred and seventy-eight prelingually deafened children who received unilateral CI participated in this study. As controls, 170 similarly-aged children with normal hearing (NH) were recruited. A total of 36 Chinese monosyllabic words were selected as the tone production targets. Vocal production samples were recorded and the fundamental frequency (F0) contour of each syllable was extracted using an auto-correlation algorithm followed by manual correction. An artificial neural network was created in MATLAB to classify the tone production. The relationships between tone production and several demographic factors were evaluated.
Results:
Pediatric CI users produced Mandarin tones much less accurately than did the NH children (58.8% vs. 91.5% correct). Tremendous variability in tone production performance existed among the CI children. Tones 2 and 3 were produced less accurately than tones 1 and 4 for both groups. For the CI group, all tones when in error tended to be judged as tone 1. The tone production accuracy was negatively correlated with age at implantation and positively correlated with CI use duration with correlation coefficients (
5.Application of high resolution computed tomography image assisted classification model of middle ear diseases based on 3D-convolutional neural network.
Ri SU ; Jian SONG ; Zheng WANG ; Shuang MAO ; Yitao MAO ; Xuewen WU ; Muzhou HOU
Journal of Central South University(Medical Sciences) 2022;47(8):1037-1048
OBJECTIVES:
Chronic suppurative otitis media (CSOM) and middle ear cholesteatoma (MEC) are the 2 most common chronic middle ear diseases. In the process of diagnosis and treatment, the 2 diseases are prone to misdiagnosis and missed diagnosis due to their similar clinical manifestations. High resolution computed tomography (HRCT) can clearly display the fine anatomical structure of the temporal bone, accurately reflect the middle ear lesions and the extent of the lesions, and has advantages in the differential diagnosis of chronic middle ear diseases. This study aims to develop a deep learning model for automatic information extraction and classification diagnosis of chronic middle ear diseases based on temporal bone HRCT image data to improve the classification and diagnosis efficiency of chronic middle ear diseases in clinical practice and reduce the occurrence of missed diagnosis and misdiagnosis.
METHODS:
The clinical records and temporal bone HRCT imaging data for patients with chronic middle ear diseases hospitalized in the Department of Otorhinolaryngology, Xiangya Hospital from January 2018 to October 2020 were retrospectively collected. The patient's medical records were independently reviewed by 2 experienced otorhinolaryngologist and the final diagnosis was reached a consensus. A total of 499 patients (998 ears) were enrolled in this study. The 998 ears were divided into 3 groups: an MEC group (108 ears), a CSOM group (622 ears), and a normal group (268 ears). The Gaussian noise with different variances was used to amplify the samples of the dataset to offset the imbalance in the number of samples between groups. The sample size of the amplified experimental dataset was 1 806 ears. In the study, 75% (1 355) samples were randomly selected for training, 10% (180) samples for validation, and the remaining 15% (271) samples for testing and evaluating the model performance. The overall design for the model was a serial structure, and the deep learning model with 3 different functions was set up. The first model was the regional recommendation network algorithm, which searched the middle ear image from the whole HRCT image, and then cut and saved the image. The second model was image contrast convolutional neural network (CNN) based on twin network structure, which searched the images matching the key layers of HRCT images from the cut images, and constructed 3D data blocks. The third model was based on 3D-CNN operation, which was used for the final classification and diagnosis of the 3D data block construction, and gave the final prediction probability.
RESULTS:
The special level search network based on twin network structure showed an average AUC of 0.939 on 10 special levels. The overall accuracy of the classification network based on 3D-CNN was 96.5%, the overall recall rate was 96.4%, and the average AUC under the 3 classifications was 0.983. The recall rates of CSOM cases and MEC cases were 93.7% and 97.4%, respectively. In the subsequent comparison experiments, the average accuracy of some classical CNN was 79.3%, and the average recall rate was 87.6%. The precision rate and the recall rate of the deep learning network constructed in this study were about 17.2% and 8.8% higher than those of the common CNN.
CONCLUSIONS
The deep learning network model proposed in this study can automatically extract 3D data blocks containing middle ear features from the HRCT image data of patients' temporal bone, which can reduce the overall size of the data while preserve the relationship between corresponding images, and further use 3D-CNN for classification and diagnosis of CSOM and MEC. The design of this model is well fitting to the continuous characteristics of HRCT data, and the experimental results show high precision and adaptability, which is better than the current common CNN methods.
Algorithms
;
Ear Diseases
;
Humans
;
Neural Networks, Computer
;
Retrospective Studies
;
Tomography, X-Ray Computed/methods*
6.Epidemic features of coronavirus disease 2019 in Hunan Province.
Yitao MAO ; Huihui ZENG ; Ying WANG ; Juxiong XIAO ; Wei YANG ; Gaofeng ZHOU ; Weihua LIAO
Journal of Central South University(Medical Sciences) 2020;45(5):576-581
OBJECTIVES:
To explore and analyze the epidemic features of coronavirus disease 2019 (COVID-19) in Hunan Province from January 21, 2020 to March 14, 2020, as well as to investigate the COVID-19 epidemics in each city of Hunan Province.
METHODS:
The epidemic data was obtained from the official website of Hunan Province's Health Commission. The data of each city of Hunan Province was analyzed separately. Spatial distribution of cumulative confirmed COVID-19 patients and the cumulative occurrence rate was drawn by ArcGIS software for each city in Hunan Province. Some regional indexes were also compared with that in the whole country.
RESULTS:
The first patient was diagnosed in January 21, sustained patient growth reached its plateau in around February 17. Up to March 14, the cumulative confirmed COVID-19 patients stopped at 1 018. The cumulative occurrence rate of COVID-19 patients was 0.48 per 0.1 million person. The number of cumulative severe patients was 150 and the number of cumulative dead patients was 4. The mortality rate (0.39%) and the cure rate (99.6%) in Hunan Province was significantly lower and higher respectively than the corresponding average rate in the whole country (0.90% and 96.2%, Hubei excluded). The first 3 cities in numbers of the confirmed patients were Changsha, Yueyang, and Shaoyang. While sorted by the cumulative occurrence rate, the first 3 cities in incidence were Changsha, Yueyang, and Zhuzhou.
CONCLUSIONS
The epidemic of COVID-19 spread out smoothly in Hunan Province. The cities in Hunan Province implement anti-disease strategies based on specific situations on their own and keep the epidemic in the range of controllable.
Betacoronavirus
;
China
;
epidemiology
;
Cities
;
epidemiology
;
Coronavirus Infections
;
epidemiology
;
mortality
;
Humans
;
Pandemics
;
Pneumonia, Viral
;
epidemiology
;
mortality
7.A logistic regression model for prediction of glioma grading based on radiomics.
Xianting SUN ; Weihua LIAO ; Dong CAO ; Yuelong ZHAO ; Gaofeng ZHOU ; Dongcui WANG ; Yitao MAO
Journal of Central South University(Medical Sciences) 2021;46(4):385-392
OBJECTIVES:
Glioma is the most common intracranial primary tumor in central nervous system. Glioma grading possesses important guiding significance for the selection of clinical treatment and follow-up plan, and the assessment of prognosis. This study aims to explore the feasibility of logistic regression model based on radiomics to predict glioma grading.
METHODS:
Retrospective analysis was performed on 146 glioma patients with confirmed pathological diagnosis from January, 2012 to December, 2018. A total of 41 radiomics features were extracted from contrast-enhanced T
RESULTS:
A total of 5 imaging features selected by LASSO were used to establish a logistic regression model for predicting glioma grading. The model showed good discrimination with AUC value of 0.919. Hosmer-Lemeshow test showed no significant difference between the calibration curve and the ideal curve (
CONCLUSIONS
The logistic regression model using radiomics exhibits a relatively high accuracy for predicting glioma grading, which may serve as a complementary tool for preoperative prediction of giloma grading.
Brain Neoplasms/diagnostic imaging*
;
Glioma/diagnostic imaging*
;
Humans
;
Logistic Models
;
Magnetic Resonance Imaging
;
ROC Curve
;
Retrospective Studies
8.An artificial neural network model for glioma grading using image information.
Yitao MAO ; Weihua LIAO ; Dong CAO ; Luqing ZHAO ; Xunhua WU ; Lingyu KONG ; Gaofeng ZHOU ; Yuelong ZHAO ; Dongcui WANG
Journal of Central South University(Medical Sciences) 2018;43(12):1315-1322
To explore the feasibility and efficacy of artificial neural network for differentiating high-grade glioma and low-grade glioma using image information.
Methods: A total of 130 glioma patients with confirmed pathological diagnosis were selected retrospectively from 2012 to 2017. Forty one imaging features were extracted from each subjects based on 2-dimension magnetic resonance T1 weighted imaging with contrast-enhancement. An artificial neural network model was created and optimized according to the performance of feature selection. The training dataset was randomly selected half of the whole dataset, and the other half dataset was used to verify the performance of the neural network for glioma grading. The training-verification process was repeated for 100 times and the performance was averaged.
Results: A total of 5 imaging features were selected as the ultimate input features for the neural network. The mean accuracy of the neural network for glioma grading was 90.32%, with a mean sensitivity at 87.86% and a mean specificity at 92.49%. The area under the curve of receiver operating characteristic curve was 0.9486.
Conclusion: As a technique of artificial intelligence, neural network can reach a relatively high accuracy for the grading of glioma and provide a non-invasive and promising computer-aided diagnostic process for the pre-operative grading of glioma.
Brain Neoplasms
;
diagnostic imaging
;
pathology
;
Glioma
;
diagnostic imaging
;
pathology
;
Humans
;
Magnetic Resonance Imaging
;
Neoplasm Grading
;
Neural Networks, Computer
;
ROC Curve
;
Retrospective Studies
;
Sensitivity and Specificity