scholarly journals Automatic Surgical Instrument Recognition—A Case of Comparison Study between the Faster R-CNN, Mask R-CNN, and Single-Shot Multi-Box Detectors

2021 ◽  
Vol 11 (17) ◽  
pp. 8097
Author(s):  
Jiann-Der Lee ◽  
Jong-Chih Chien ◽  
Yu-Tsung Hsu ◽  
Chieh-Tsai Wu
Keyword(s):  
Operating Room ◽  
Recognition Rate ◽  
Experimental Studies ◽  
Surgical Instruments ◽  
Single Shot ◽  
Learning Networks ◽  
Video Information ◽  
Detection And Identification ◽  
Instrument Recognition ◽  
Causes Of Delays

In various studies, problems with surgical instruments in the operating room are usually one of the major causes of delays and errors. It would be of great help, in surgery, to quickly and automatically identify and keep count of the surgical instruments in the operating room using only video information. In this study, the recognition rate of fourteen surgical instruments is studied using the Faster R-CNN, Mask R-CNN, and Single Shot Multi-Box Detectors, which are three deep learning networks in recent studies that exhibited near real-time object detection and identification performance. In our experimental studies using screen captures of real surgery video clips for training and testing, this study found that that acceptable accuracy and speed tradeoffs can be achieved by the Mask R-CNN classifier, which exhibited an overall average precision of 98.94% for all the instruments.

Improved SSD-assisted algorithm for surface defect detection of electromagnetic luminescence

2021 ◽  
pp. 1748006X2199538
Author(s):  
Zhenying Xu ◽  
Ziqian Wu ◽  
Wei Fan
Keyword(s):  
Defect Detection ◽  
Feature Fusion ◽  
Recognition Rate ◽  
Detection Methods ◽  
Small Scale ◽  
Detection Accuracy ◽  
Single Shot ◽  
Surface Defect Detection ◽  
Feature Pyramid ◽  
Small Feature

Defect detection of electromagnetic luminescence (EL) cells is the core step in the production and preparation of solar cell modules to ensure conversion efficiency and long service life of batteries. However, due to the lack of feature extraction capability for small feature defects, the traditional single shot multibox detector (SSD) algorithm performs not well in EL defect detection with high accuracy. Consequently, an improved SSD algorithm with modification in feature fusion in the framework of deep learning is proposed to improve the recognition rate of EL multi-class defects. A dataset containing images with four different types of defects through rotation, denoising, and binarization is established for the EL. The proposed algorithm can greatly improve the detection accuracy of the small-scale defect with the idea of feature pyramid networks. An experimental study on the detection of the EL defects shows the effectiveness of the proposed algorithm. Moreover, a comparison study shows the proposed method outperforms other traditional detection methods, such as the SIFT, Faster R-CNN, and YOLOv3, in detecting the EL defect.

scholarly journals Application of portrait recognition system for emergency evacuation in mass emergencies

2021 ◽  
Vol 30 (1) ◽  
pp. 893-902
Author(s):  
Ke Xu
Keyword(s):  
Detection Rate ◽  
Characteristic Curve ◽  
Recognition Rate ◽  
Recognition System ◽  
Emergency Evacuation ◽  
Shopping Mall ◽  
Single Shot ◽  
Data Set ◽  
Linear Discriminant ◽  
Adaboost Algorithm

Abstract A portrait recognition system can play an important role in emergency evacuation in mass emergencies. This paper designed a portrait recognition system, analyzed the overall structure of the system and the method of image preprocessing, and used the Single Shot MultiBox Detector (SSD) algorithm for portrait detection. It also designed an improved algorithm combining principal component analysis (PCA) with linear discriminant analysis (LDA) for portrait recognition and tested the system by applying it in a shopping mall to collect and monitor the portrait and establish a data set. The results showed that the missing detection rate and false detection rate of the SSD algorithm were 0.78 and 2.89%, respectively, which were lower than those of the AdaBoost algorithm. Comparisons with PCA, LDA, and PCA + LDA algorithms demonstrated that the recognition rate of the improved PCA + LDA algorithm was the highest, which was 95.8%, the area under the receiver operating characteristic curve was the largest, and the recognition time was the shortest, which was 465 ms. The experimental results show that the improved PCA + LDA algorithm is reliable in portrait recognition and can be used for emergency evacuation in mass emergencies.

scholarly journals Audit on induction time delays in operating room at Kibogora District Hospital: A quality improvement project

2021 ◽  
Vol 9 (2) ◽  
pp. 163-168
Author(s):  
Jean Claude Uwimana
Keyword(s):  
Operating Room ◽  
Induction Time ◽  
Time Delays ◽  
High Rate ◽  
Improvement Project ◽  
Study Results ◽  
Induction Times ◽  
Or Team ◽  
Causes Of Delays ◽  
Operating Unit

Background: Induction time delays in Operating room (OR) is an issue that affects the productivity of an operating unit especially in a setting with limited resources. It can also results in providing inappropriate services to the patients and their families. The aim of this study was to determine the causes of induction time delays and to propose solutions on how to avoid the reasons of delays. Methods: A prospective observational study was conducted. It focused on elective general surgeries and orthopedic surgeries as they were mainly being performed during the study period. The data on the type of operation, the type of anesthesia, delay or no delay of induction (DOI) of anesthesia, causes of DOI were collected. DOI was considered as the time between the previous patient out of the OR and the next one in of more than 30 minutes. Emergency surgeries and elective obstetric surgeries were excluded from the study. Results: 24.8% of surgeries were done after delays of induction of anesthesia as opposed to 75.2% surgeries for which anesthesia was induced without delay. 48.6% of delays of induction to anesthesia were due to the hospital issues followed by anesthesia provision related issues. (40.0%). The surgery related and patient related issues accounted each one 5.7%. Conclusions: There was a high rate of surgeries that had delays in induction times. The OR managers need to work more with the hospital administration and the OR team to correct causes of delays.

scholarly journals A Piezoelectric Tactile Sensor for Tissue Stiffness Detection with Arbitrary Contact Angle

Sensors ◽  
2020 ◽  
Vol 20 (22) ◽  
pp. 6607
Author(s):  
Yingxuan Zhang ◽  
Feng Ju ◽  
Xiaoyong Wei ◽  
Dan Wang ◽  
Yaoyao Wang
Keyword(s):  
Contact Angle ◽  
Recognition Rate ◽  
Tactile Sensor ◽  
Normal Direction ◽  
Surgical Instruments ◽  
Tissue Stiffness ◽  
Design And Optimization ◽  
Detection Model ◽  
Sensor Optimization ◽  
Simulation And Experiment

In this paper, a piezoelectric tactile sensor for detecting tissue stiffness in robot-assisted minimally invasive surgery (RMIS) is proposed. It can detect the stiffness not only when the probe is normal to the tissue surface, but also when there is a contact angle between the probe and normal direction. It solves the problem that existing sensors can only detect in the normal direction to ensure accuracy when the degree of freedom (DOF) of surgical instruments is limited. The proposed senor can distinguish samples with different stiffness and recognize lump from normal tissue effectively when the contact angle varies within [0°, 45°]. These are achieved by establishing a new detection model and sensor optimization. It deduces the influence of contact angle on stiffness detection by sensor parameters design and optimization. The detection performance of the sensor is confirmed by simulation and experiment. Five samples with different stiffness (including lump and normal samples with close stiffness) are used. Through blind recognition test in simulation, the recognition rate is 100% when the contact angle is randomly selected within 30°, 94.1% within 45°, which is 38.7% higher than the unoptimized sensor. Through blind classification test and automatic k-means clustering in experiment, the correct rate is 92% when the contact angle is randomly selected within 45°. We can get the proposed sensor can easily recognize samples with different stiffness with high accuracy which has broad application prospects in the medical field.

Man-Computer Communication Techniques: Two Experiments

1967 ◽  
Vol 9 (6) ◽  
pp. 521-528 ◽  
Author(s):  
Robert T. Root ◽  
Robert Sadacca
Keyword(s):  
Image Interpretation ◽  
Experimental Studies ◽  
Data Entry ◽  
Aerial Imagery ◽  
Report Generation ◽  
Computer Communication ◽  
Communication Techniques ◽  
Detection And Identification ◽  
Report Data ◽  
Computer Based

Two experimental studies are reported that were intended to evaluate alternative man-computer communication techniques within the context of a computer-based image interpretation facility. The first experiment, comparing five different data entry procedures, indicated that, although a procedure requiring the interpreter to enter report data directly using a teletype keyboard resulted in the shortest overall throughput time, a procedure involving message composition by the image interpreter with subsequent transcription by a communicator minimizes the time spent by the interpreter in report generation and maximizes the time available for the detection and identification of targets on aerial imagery. The second experiment evaluating alternative word form-data entry format combinations, showed no differences among the six combinations studied.

scholarly journals Opium Poppy Detection Using Deep Learning

2018 ◽  
Vol 10 (12) ◽  
pp. 1886 ◽  
Author(s):  
Xiangyu Liu ◽  
Yichen Tian ◽  
Chao Yuan ◽  
Feifei Zhang ◽  
Guang Yang
Keyword(s):  
Remote Sensing ◽  
Deep Learning ◽  
Local Governments ◽  
Graphics Processing Unit ◽  
Recognition Rate ◽  
Lao Pdr ◽  
Opium Poppy ◽  
Processing Unit ◽  
Single Shot ◽  
Physical And Mental Health

Opium poppies are a major source of traditional drugs, which are not only harmful to physical and mental health, but also threaten the economy and society. Monitoring poppy cultivation in key regions through remote sensing is therefore a crucial task; the location coordinates of poppy parcels represent particularly important information for their eradication by local governments. We propose a new methodology based on deep learning target detection to identify the location of poppy parcels and map their spatial distribution. We first make six training datasets with different band combinations and slide window sizes using two ZiYuan3 (ZY3) remote sensing images and separately train the single shot multibox detector (SSD) model. Then, we choose the best model and test its performance using 225 km2 verification images from Lao People’s Democratic Republic (Lao PDR), which exhibits a precision of 95% for a recall of 85%. The speed of our method is 4.5 km2/s on 1080TI Graphics Processing Unit (GPU). This study is the first attempt to monitor opium poppies with the deep learning method and achieve a high recognition rate. Our method does not require manual feature extraction and provides an alternative way to rapidly obtain the exact location coordinates of opium poppy cultivation patches.

Gestonurse: a robotic surgical nurse for handling surgical instruments in the operating room

2011 ◽  
Vol 6 (1) ◽  
pp. 53-63 ◽  
Author(s):  
Mithun Jacob ◽  
Yu-Ting Li ◽  
George Akingba ◽  
Juan P. Wachs
Keyword(s):  
Operating Room ◽  
Surgical Instruments

scholarly journals Performance Analysis of the Ventilation System for a Surgical Operating Room in Egypt: A Case Study of Mataria Teaching Hospital in Cairo

2021 ◽  
Author(s):  
Philip Maxemos ◽  
abouelmagd abdelsamie ◽  
Hatem Sadek
Keyword(s):  
Laminar Flow ◽  
Operating Room ◽  
Teaching Hospital ◽  
Ventilation System ◽  
Experimental Studies ◽  
Airborne Particles ◽  
Airflow Distribution ◽  
Proposed Modification ◽  
High Level

Abstract The Design of the ventilation system in a hospital operating room plays a very important role, not only in providing thermal comfort and hygienic environment for the patients or staff, but also to ensure the scavenging of any contaminants or airborne particles in the operating room theatre that might leak from outside to the operating room or emitting from patients’ infections. The present study focuses at airflow distribution, temperature, humidity and velocity profiles in a surgical operating room. An operating room inside the Mataria teaching hospital in Cairo (Egypt) has been chosen for the study. Numerical and experimental studies were carried out, where the room was ventilated through laminar flow diffuser system and 100% fresh air. The air was released by four outlet grills: two grills at a low level of the floor and two grills at a high level of the floor. In this work, two cases are investigated. In case I, the air outlets have been installed on one side of the room (which already exists in the hospital); and in Case II, the air outlets have been installed on two opposite sides (the suggested case). The results showed that the proposed modification (Case II) performed better distribution of ventilation than Case I. Therefore, it is recommended to install air outlets in two different side areas inside the room in order to avoid the accumulation of contaminants.

scholarly journals A Structured Program for Teaching Pancreatojejunostomy Outside the Operating Room

2020 ◽  
Author(s):  
Kenichi Oshiro ◽  
Kazuhiro Endo ◽  
Kazue Morishima ◽  
Yuji Kaneda ◽  
Masaru Koizumi ◽  
...  
Keyword(s):  
Patient Safety ◽  
Learning Curve ◽  
Operating Room ◽  
Simulation Training ◽  
Surgical Instruments ◽  
Training Materials ◽  
Didactic Knowledge ◽  
Actual Operation ◽  
Organ Models ◽  
Structured Program

Abstract Background: Pancreatojejunostomy (PJ) is one of the most difficult and challenging abdominal surgical procedures. Most trainees learn this procedure in the operating room (OR) because there are no appropriate training systems available outside the OR. This extends the learning curve and may affect patient safety. We developed a structured program for teaching PJ to increase training opportunities outside the OR. Methods: We have created this structured program to help trainees acquire both didactic knowledge and technical skills to perform PJ. A manual was created to provide general knowledge about PJ and the specific PJ procedure used in our institution. Based on questionnaires completed by trainers and trainees, the procedure for PJ was divided into twelve steps and described in detail. After creating the manual, we developed organ models, needles and a frame box for simulation training.Results: Trainees learn about PJ by reading the procedure manual, acquiring both general and specific knowledge. We conducted simulation training outside the OR using the training materials created for this system. Training was performed with participants referring to the procedure manual while performing the simulation training. They simulate the procedure with surgical instruments as both primary and assistant surgeon. After finishing the anastomosis, trainees inspect the resulting structures from all angles including the posterior side and intraluminally, which cannot be observed during the actual operation. Conclusion: We developed a structured program for teaching PJ. By implementing this program, it is expected that a trainee’s learning curve will be shortened while ensuring patient safety.

Sign in / Sign up

Export Citation Format

Share Document