scholarly journals Rib fracture detection system based on deep learning

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Liding Yao ◽  
Xiaojun Guan ◽  
Xiaowei Song ◽  
Yanbin Tan ◽  
Chun Wang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Learning Algorithm ◽  
Detection System ◽  
Rib Fracture ◽  
Diagnostic Efficiency ◽  
Fracture Detection ◽  
Deep Learning Algorithm ◽  
Experienced Radiologist ◽  
Comparable Performance ◽  
Detection And Diagnosis

AbstractRib fracture detection is time-consuming and demanding work for radiologists. This study aimed to introduce a novel rib fracture detection system based on deep learning which can help radiologists to diagnose rib fractures in chest computer tomography (CT) images conveniently and accurately. A total of 1707 patients were included in this study from a single center. We developed a novel rib fracture detection system on chest CT using a three-step algorithm. According to the examination time, 1507, 100 and 100 patients were allocated to the training set, the validation set and the testing set, respectively. Free Response ROC analysis was performed to evaluate the sensitivity and false positivity of the deep learning algorithm. Precision, recall, F1-score, negative predictive value (NPV) and detection and diagnosis were selected as evaluation metrics to compare the diagnostic efficiency of this system with radiologists. The radiologist-only study was used as a benchmark and the radiologist-model collaboration study was evaluated to assess the model’s clinical applicability. A total of 50,170,399 blocks (fracture blocks, 91,574; normal blocks, 50,078,825) were labelled for training. The F1-score of the Rib Fracture Detection System was 0.890 and the precision, recall and NPV values were 0.869, 0.913 and 0.969, respectively. By interacting with this detection system, the F1-score of the junior and the experienced radiologists had improved from 0.796 to 0.925 and 0.889 to 0.970, respectively; the recall scores had increased from 0.693 to 0.920 and 0.853 to 0.972, respectively. On average, the diagnosis time of radiologist assisted with this detection system was reduced by 65.3 s. The constructed Rib Fracture Detection System has a comparable performance with the experienced radiologist and is readily available to automatically detect rib fracture in the clinical setting with high efficacy, which could reduce diagnosis time and radiologists’ workload in the clinical practice.

scholarly journals Using artificial intelligence to assist radiologists in distinguishing COVID-19 from other pulmonary infections

2020 ◽  
pp. 1-17
Author(s):  
Yanhong Yang ◽  
Fleming Y.M. Lure ◽  
Hengyuan Miao ◽  
Ziqi Zhang ◽  
Stefan Jaeger ◽  
...  
Keyword(s):  
Deep Learning ◽  
Learning Algorithm ◽  
Model Development ◽  
Training Data ◽  
Test Accuracy ◽  
Pulmonary Infections ◽  
Deep Learning Algorithm ◽  
Average Accuracy ◽  
Independent Test ◽  
Comparable Performance

Background: Accurate and rapid diagnosis of coronavirus disease (COVID-19) is crucial for timely quarantine and treatment. Purpose: In this study, a deep learning algorithm-based AI model using ResUNet network was developed to evaluate the performance of radiologists with and without AI assistance in distinguishing COVID-19 infected pneumonia patients from other pulmonary infections on CT scans. Methods: For model development and validation, a total number of 694 cases with 111,066 CT slides were retrospectively collected as training data and independent test data in the study. Among them, 118 are confirmed COVID-19 infected pneumonia cases and 576 are other pulmonary infections cases (e.g. tuberculosis cases, common pneumonia cases and non-COVID-19 viral pneumonia cases). The cases were divided into training and testing datasets. The independent test was performed by evaluating and comparing the performance of three radiologists with different years of practice experience in distinguishing COVID-19 infected pneumonia cases with and without the AI assistance. Results: Our final model achieved an overall test accuracy of 0.914 with an area of the receiver operating characteristic (ROC) curve (AUC) of 0.903 in which the sensitivity and specificity are 0.918 and 0.909, respectively. The deep learning-based model then achieved a comparable performance by improving the radiologists’ performance in distinguish COVOD-19 from other pulmonary infections, yielding better average accuracy and sensitivity, from 0.941 to 0.951 and from 0.895 to 0.942, respectively, when compared to radiologists without using AI assistance. Conclusion: A deep learning algorithm-based AI model developed in this study successfully improved radiologists’ performance in distinguishing COVID-19 from other pulmonary infections using chest CT images.

Malaria Detection System Using Convolutional Neural Network Algorithm

2020 ◽  
pp. 219-230
Author(s):  
Kanika Gautam ◽  
Sunil Kumar Jangir ◽  
Manish Kumar ◽  
Jay Sharma
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Learning Algorithm ◽  
Detection System ◽  
Learning Algorithms ◽  
Anopheles Mosquito ◽  
Deep Learning Algorithm ◽  
Blood Smears ◽  
Neural Network Algorithm ◽  
Modern Technologies

Malaria is a disease caused when a female Anopheles mosquito bites. There are over 200 million cases recorded per year with more than 400,000 deaths. Current methods of diagnosis are effective; however, they work on technologies that do not produce higher accuracy results. Henceforth, to improve the prediction rate of the disease, modern technologies need to be performed for obtain accurate results. Deep learning algorithms are developed to detect, learn, and determine the containing parasites from the red blood smears. This chapter shows the implementation of a deep learning algorithm to identify the malaria parasites with higher accuracy.

scholarly journals Vision-Based Deep Learning Algorithm for Detecting Potholes

2021 ◽  
Author(s):  
Kanushka Gajjar ◽  
Theo van Niekerk ◽  
Thomas Wilm ◽  
Paolo Mercorelli
Keyword(s):  
Deep Learning ◽  
Real Time ◽  
Autonomous Vehicles ◽  
Learning Algorithm ◽  
Detection System ◽  
Detection Methods ◽  
Deep Learning Algorithm ◽  
Learning Techniques ◽  
Pothole Detection ◽  
Adequate Data

Potholes on roads pose a major threat to motorists and autonomous vehicles. Driving over a pothole has the potential to cause serious damage to a vehicle, which in turn may result in fatal accidents. Currently, many pothole detection methods exist. However, these methods do not utilize deep learning techniques to detect a pothole in real-time, determine the location thereof and display its location on a map. The success of determining an effective pothole detection method, which includes the aforementioned deep learning techniques, is dependent on acquiring a large amount of data, including images of potholes. Once adequate data had been gathered, the images were processed and annotated. The next step was to determine which deep learning algorithms could be utilized. Three different models, including Faster R-CNN, SSD and YOLOv3 were trained on the custom dataset containing images of potholes to determine which network produces the best results for real-time detection. It was revealed that YOLOv3 produced the most accurate results and performed the best in real-time, with an average detection time of only 0.836s per image. The final results revealed that a real-time pothole detection system, integrated with a cloud and maps service, can be created to allow drivers to avoid potholes.

scholarly journals Fully Convolutional Variational Autoencoder For Feature Extraction Of Fire Detection System

2020 ◽  
Vol 13 (1) ◽  
pp. 9
Author(s):  
Herminarto Nugroho ◽  
Meredita Susanty ◽  
Ade Irawan ◽  
Muhamad Koyimatu ◽  
Ariana Yunita
Keyword(s):  
Deep Learning ◽  
Large Scale ◽  
Learning Algorithm ◽  
Detection System ◽  
Fire Detection ◽  
Features Extraction ◽  
Essential Information ◽  
Deep Learning Algorithm ◽  
Specific Direction ◽  
Variational Autoencoder

This paper proposes a fully convolutional variational autoencoder (VAE) for features extraction from a large-scale dataset of fire images. The dataset will be used to train the deep learning algorithm to detect fire and smoke. The features extraction is used to tackle the curse of dimensionality, which is the common issue in training deep learning with huge datasets. Features extraction aims to reduce the dimension of the dataset significantly without losing too much essential information. Variational autoencoders (VAEs) are powerfull generative model, which can be used for dimension reduction. VAEs work better than any other methods available for this purpose because they can explore variations on the data in a specific direction.

scholarly journals Further evaluation and validation of the VETSCAN IMAGYST: in-clinic feline and canine fecal parasite detection system integrated with a deep learning algorithm

2021 ◽  
Vol 14 (1) ◽  
Author(s):  
Yoko Nagamori ◽  
Ruth Hall Sedlak ◽  
Andrew DeRosa ◽  
Aleah Pullins ◽  
Travis Cree ◽  
...  
Keyword(s):  
Deep Learning ◽  
Learning Algorithm ◽  
Detection System ◽  
Correlation Coefficients ◽  
Preparation Technique ◽  
Toxocara Cati ◽  
Deep Learning Algorithm ◽  
Flotation Technique ◽  
Flotation Method ◽  
Diagnostic Sensitivity And Specificity

Abstract Background Fecal examinations in pet cats and dogs are key components of routine veterinary practice; however, their accuracy is influenced by diagnostic methodologies and the experience level of personnel performing the tests. The VETSCAN IMAGYST system was developed to provide simpler and easier fecal examinations which are less influenced by examiners’ skills. This system consists of three components: a sample preparation device, an automated microscope scanner, and analysis software. The objectives of this study were to qualitatively evaluate the performance of the VETSCAN IMAGYST system on feline parasites (Ancylostoma and Toxocara cati) and protozoan parasites (Cystoisospora and Giardia) and to assess and compare the performance of the VETSCAN IMAGYST centrifugal flotation method to reference centrifugal and passive flotation methods. Methods To evaluate the diagnostic performance of the scanning and algorithmic components of the VETSCAN IMAGYST system, fecal slides were prepared by the VETSCAN IMAGYST centrifugal flotation technique with pre-screened fecal samples collected from dogs and cats and examined by both an algorithm and parasitologists. To assess the performance of the VETSCAN IMAGYST centrifugal flotation technique, diagnostic sensitivity and specificity were calculated and compared to those of conventional flotation techniques. Results The performance of the VETSCAN IMAGYST algorithm closely correlated with evaluations by parasitologists, with sensitivity of 75.8–100% and specificity of 93.1-100% across the targeted parasites. For samples with 50 eggs or less per slide, Lin’s concordance correlation coefficients ranged from 0.70 to 0.95 across the targeted parasites. The results of the VETSCAN IMAGYST centrifugal flotation method correlated well with those of the conventional centrifugal flotation method across the targeted parasites: sensitivity of 65.7–100% and specificity of 97.6–100%. Similar results were observed for the conventional passive flotation method compared to the conventional centrifugal flotation method: sensitivity of 56.4–91.7% and specificity of 99.4–100%. Conclusions The VETSCAN IMAGYST scanning and algorithmic systems with the VETSCAN IMAGYST fecal preparation technique demonstrated a similar qualitative performance to the parasitologists’ examinations with conventional fecal flotation techniques. Given the deep learning nature of the VETSCAN IMAGYST system, its performance is expected to improve over time, enabling it to be utilized in veterinary clinics to perform fecal examinations accurately and efficiently.

Sign in / Sign up

Export Citation Format

Share Document