Deep Learning ; Diagnosis, Computer-Assisted ; Humans ; Pneumoconiosis/diagnosis* ; Radiography, Thoracic/instrumentation*

Enteral Nutrition ; instrumentation ; methods ; Female ; Fluoroscopy ; methods ; Gastrostomy ; adverse effects ; instrumentation ; methods ; Humans ; Male ; Middle Aged ; Outcome and Process Assessment (Health Care) ; Postoperative Complications ; classification ; diagnosis ; therapy ; Reproducibility of Results ; Retrospective Studies ; Singapore ; Surgery, Computer-Assisted ; methods ; Treatment Outcome

OBJECTIVETo develop the prediction model of acute gastrointestinal injury (AGI) classification of critically ill patients.

METHODSThe binary channel gastrointestinal sounds (GIS) monitor system was used to gather and analyze the GIS of 60 consecutive critically ill patients who were admitted in Critical Care Medicine of PLA General Hospital from April 2015 to November 2015 (patients with chronic gastrointestinal disease or history of gastrointestinal surgery were excluded). Meanwhile, the AGI grades were evaluated according to the ESICM guidelines of AGI grading system. Correlations between GIS and AGI classification were examined with Spearman rank correlation. Then principal component analysis was performed on the significantly correlated parameters after standardization. The top 3 post-normalized main components were selected for back-propagation (BP) neural network training to establish primary AGI grade model of critically ill patients based on the neural network model.

RESULTSA total of 1 132 GIS and 333 AGI were collected from 60 patients. The number (P = 0.0005), percentage of time (P = 0.0004), mean power (P = 0.0088), maximum power (P = 0.0101) and maximum time (P = 0.0025) of GIS wave from the channel located at the stomach were negatively correlated with the AGI grades, while the parameters of GIS wave from the channel located at the intestine had no significant correlation with the AGI grades(all P > 0.05). Three main components were selected after principal component analysis of these five correlated parameters. An AGI grade network model including 9 hide layers, with a fitting degree of 0.981 64 was built by BP artificial neural network based on the analysis of these three main components of GIS. The accuracy rate of the model to predict the AGI grade was 70.83%.

CONCLUSIONThe preliminary model based on GIS in classifying AGI grade is established successfully, which can help predict the classification of AGI grade of critically ill patients.

Abdominal Injuries ; classification ; diagnosis ; Auscultation ; instrumentation ; methods ; statistics & numerical data ; Computer Simulation ; Critical Care ; methods ; Critical Illness ; classification ; Diagnosis, Computer-Assisted ; instrumentation ; methods ; Diagnostic Techniques, Digestive System ; instrumentation ; statistics & numerical data ; Humans ; Models, Biological ; Neural Networks (Computer) ; Predictive Value of Tests

Magnetic induction method aims at the noninvasive detection of liver iron overload by measuring the hepatic magnetic susceptibility. To solve the difficulty that eddy current effects interfere with the measurement of magnetic susceptibility, we proposed an improved coil system based on the static field magnetization principle in this study. We used a direct current excitation to eliminate the eddy current effect, and a rotary receiver coil to get the induced voltage. The magnetic field for a cylindrical object due to the magnetization effect was calculated and the relative change of maximum induced voltage was derived. The correlation between magnetic susceptibility of object and maximum magnetic flux, maximum induced voltage and relative change of maximum induced voltage of the receiver coil were obtained by simulation experiments, and the results were compared with those of the theory calculation. The contrast shows that the simulation results fit the theory results well, which proves our method can eliminate the eddy current effect effectively.
Computer Simulation ; Humans ; Image Processing, Computer-Assisted ; Iron Overload ; diagnosis ; Liver ; physiopathology ; Magnetic Fields ; Magnetics ; instrumentation

OBJECTIVETo investigate the value of computer-assisted slide-screening system (ThinPrep imaging system, TIS) in the diagnosis of cervical Thinprep smears.

METHODSA total of 19 600 ThinPrep smears were collected, including 9800 slides by TIS-assisted screening from September 2011 to March 2012 and 9800 slides by manual screening from September 2010 to April 2011 as control. The detection rates of abnormal cells and common microbial infection by the different screening methods were compared. With histopathological diagnosis of colposcopic biopsy as the gold standard, the screening efficiency and correlation of cytologic diagnosis among different screening methods were analyzed.

RESULTSCompared with manual screening, the detection rate of abnormal cells in 9800 cases by TIS-assisted screen was increased from 5.4% (525/9800) to 6.8% (665/9800), mainly in the categories of ASCUS and LSIL (P < 0.05). TIS had a higher accordance rate between cytologic diagnosis and histopathological diagnosis in the NILM and ASCUS than that by manual screening. False-negative rate of finding abnormal cells by TIS decreased from 8.5% (17/200) to 0.7% (2/289, P < 0.01) with an increased sensitivity compared to manual screening, although the specificity was similar. Both TIS and manual screening had advantages and disadvantages respectively in the detection of microbial organisms. TIS improved screening efficiency by 50%.

CONCLUSIONTIS improves not only the screening efficiency but also the detection of abnormal cells with a reduced false negativity, and it therefore has a broad application prospect.

Adenocarcinoma ; diagnosis ; pathology ; Adolescent ; Adult ; Aged ; Aged, 80 and over ; Candida ; isolation & purification ; Carcinoma, Squamous Cell ; diagnosis ; pathology ; Cervical Intraepithelial Neoplasia ; diagnosis ; pathology ; Cytodiagnosis ; False Negative Reactions ; Female ; Humans ; Image Processing, Computer-Assisted ; instrumentation ; Mass Screening ; Middle Aged ; Sensitivity and Specificity ; Trichomonas vaginalis ; isolation & purification ; Uterine Cervical Dysplasia ; diagnosis ; pathology ; Uterine Cervical Neoplasms ; diagnosis ; pathology ; Vaginal Smears ; Young Adult

To investigate the modulation effects of breathing movement on cardiovascular system and to study the physiological coupling relationship between respiration and cardiovascular system, we designed a comprehensive testing system for cardiorespiratory interaction research. This system, comprising three parts, i. e. physiological signal conditioning unit, data acquisition and USB medical isolation unit, and a PC based program, can acquire multiple physiological data such as respiratory flow, rib cage and abdomen movement, electrocardiograph, artery pulse wave, cardiac sounds, skin temperature, and electromyography simultaneously under certain experimental protocols. Furthermore this system can be used in research on short-term cardiovascular variability by paced breathing. Preliminary experiments showed that this system could accurately record rib cage and abdomen movement under very low breathing rate, using respiratory inductive plethysmography to acquire respiration signal in direct-current coupling mode. After calibration, this system can be used to estimate ventilation non-intrusively and correctly. The PC based program can generate audio and visual biofeedback signal, and guide the volunteers to perform a slow and regular breathing. An experiment on healthy volunteers showed that this system was able to guide the volunteers to do slow breathing effectively and simultaneously record multiple physiological data during the experiments. Signal processing techniques were used for off-line data analysis, such as non-invasive ventilation calibration, QRS complex wave detection, and respiratory sinus arrhythmia and pulse wave transit time calculation. The experiment result showed that the modulation effect on RR interval, respiratory sinus arrhythmia (RSA), pulse wave transit time (PWTT) by respiration would get stronger with the going of the slow and regular breathing.
Algorithms ; Artifacts ; Autonomic Nervous System ; physiopathology ; Diagnosis, Computer-Assisted ; methods ; Electrocardiography ; Equipment Design ; Heart ; physiology ; Humans ; Lung ; physiology ; Monitoring, Physiologic ; instrumentation ; methods ; Respiration ; Respiratory Mechanics ; physiology

Based on LCD Module and Visual C++ development environment, this paper proposes a new method which can quickly develop the human-machine interface .We define a LCD module programming interface by designing Serial Communication Class(SCS). On this basis,we achieve the transplantation on an Embedded ARM Platform to fulfil the requirements of Medical Diagnostic Instruments (MDI). Experimental results show that this method has advantages of short development cycle and high level transplantation which has broad application prospects in the field of Medical Diagnosis Instrument.
Diagnosis, Computer-Assisted ; instrumentation ; Equipment Design ; Liquid Crystals ; Robotics ; instrumentation ; methods ; Software ; User-Computer Interface

OBJECTIVE: To evaluate the effect of computer-aided detection (CAD) system on observer performance in the detection of malignant lung nodules on chest radiograph. MATERIALS AND METHODS: Two hundred chest radiographs (100 normal and 100 abnormal with malignant solitary lung nodules) were evaluated. With CT and histological confirmation serving as a reference, the mean nodule size was 15.4 mm (range, 7-20 mm). Five chest radiologists and five radiology residents independently interpreted both the original radiographs and CAD output images using the sequential testing method. The performances of the observers for the detection of malignant nodules with and without CAD were compared using the jackknife free-response receiver operating characteristic analysis. RESULTS: Fifty-nine nodules were detected by the CAD system with a false positive rate of 1.9 nodules per case. The detection of malignant lung nodules significantly increased from 0.90 to 0.92 for a group of observers, excluding one first-year resident (p = 0.04). When lowering the confidence score was not allowed, the average figure of merit also increased from 0.90 to 0.91 (p = 0.04) for all observers after a CAD review. On average, the sensitivities with and without CAD were 87% and 84%, respectively; the false positive rates per case with and without CAD were 0.19 and 0.17, respectively. The number of additional malignancies detected following true positive CAD marks ranged from zero to seven for the various observers. CONCLUSION: The CAD system may help improve observer performance in detecting malignant lung nodules on chest radiographs and contribute to a decrease in missed lung cancer.
Aged ; Algorithms ; Diagnosis, Computer-Assisted/*instrumentation ; Diagnosis, Differential ; Female ; Humans ; Image Interpretation, Computer-Assisted ; Lung Neoplasms/*radiography ; Male ; Middle Aged ; Observer Variation ; ROC Curve ; *Radiography, Thoracic ; Reproducibility of Results ; Tomography, X-Ray Computed

A total of 20 normal newborns and 8 brain injured newborns were monitored for 2 hours with domestic digital amplitude integrated cerebral function monitor (CFM 3000) and similar imported products LECTROMED CFM 5330 simultaneously. 32 newborns with seizures or suspected seizures were monitored with CFM 3000 and conventional electroencephalogram (EEG) simultaneously. The tracings of amplitude integrated electroencephalogram (aEEG) monitored by CFM 3000 and LECTROMED CFM 5330 are similar to each other. The continuous electrical activity, sleep-wake cycle, the mean of lower or upper bound voltage and duration of broad and narrow band were no significant statistical difference between different machines; The pattern of aEEG tracing of 8 infants with brain injury monitored by CFM 3000 was the same as monitored by the LECTROMED CFM 5330. The detection rate of seizure with CFM 3000 and conventional EEG were no statistically significant difference, and the consistency with Kappa test was: Kappa = 0.552, P = 0.001. The CFM 3000 can reflect the change of cerebral function and identify infants with brain injury reliably.
Brain Injuries ; diagnosis ; physiopathology ; Electroencephalography ; methods ; Female ; Humans ; Infant, Newborn ; Male ; Monitoring, Physiologic ; instrumentation ; methods ; standards ; Seizures ; diagnosis ; physiopathology ; Signal Processing, Computer-Assisted

Resection of retroperitoneal tumors is usually perfomed using the anterior retroperitoneal approach. Our report presents an innovative method utilizing a robotic surgical system. A 50-yr-old male patient visited our hospital due to a known paravertebral mass. Magnetic resonance imaging showed a well-encapsulated mass slightly abutting the abdominal aorta and left psoas muscle at the L4-L5 level. The tumor seemed to be originated from the prevertebral sympathetic plexus or lumbosacral trunk and contained traversing vessels around the tumor capsule. A full-time robotic transperitoneal tumor resection was performed. Three trocars were used for the robotic camera and working arms. The da Vinci Surgical System(R) provided delicate dissection in the small space and the tumor was completely removed without damage to the surrounding organs and great vessels. This case demonstrates the feasibility of robotic resection in retroperitoneal space. Robotic surgery offered less invasiveness in contrast to conventional open surgery.
Aorta, Abdominal ; Humans ; Image Processing, Computer-Assisted/instrumentation ; Magnetic Resonance Imaging ; Male ; Middle Aged ; Neurilemmoma/diagnosis/*surgery ; Retroperitoneal Space ; Robotics/*instrumentation ; Spinal Neoplasms/diagnosis/*surgery ; Surgery, Computer-Assisted/*instrumentation