Efficient AI-Enabled Pneumonia Detection in Chest X-ray Images

Wang, Jiangkun; Nakamura, Miyuka; Abdallah, Abderazek Ben

doi:10.1109/lifetech53646.2022.9754850

Cited by 11 publications

(6 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, historically, artificial neural networks, particularly Deep Learning Neural Networks (DNNs), are only put into practice after extensive training and learning. Bionics devices have proven fast for COVID‐19 disease to measure heart rate, CT scan, chest X‐ray, 58 and so on, using AI‐enabled mobile and help to provide accurate treatment, testing, and disease identification.…”

Section: Discussionmentioning

confidence: 99%

Study on early accurate diagnosis and treatment of COVID‐19 with smart phone tracking using bionics

Gupta

Kumar

2023

Security and Privacy

View full text Add to dashboard Cite

The replication of biological systems by mechanical and electronic devices is referred to as bionics. The bionics industry has grown along four primary application areas, in addition to hearing, vision, orthopedics, and a small, dispersed group of implants that enhance cardiac and neurological functions. The SARS‐CoV‐2 virus is the infectious disease known as coronavirus disease (COVID‐19). The virus‐infected people require assistance to better understand the situation caused by COVID‐19 and to bring some easy, efficient, and effective solutions. One of the solutions mentioned for the early stages involves wearable sensors with temperature sensors for early Covid‐19 identification and photos delivered to an AI‐enabled smartphone, robotic sensor, or robot itself. In severe situations, lung X‐ray images are captured by robotic and remote sensors, and the lungs are given the right medication to finish off the virus. The paper presents the study on the overview, applications of artificial intelligence, and deep learning from the bionics point of view. Deep learning and machine learning will be used for reducing the Covid‐19 outbreak. Wearable sensors provide important data by having temperature‐embedded sensors in several physical devices that reveal details about the environment and body that are connected. Covid‐19 probability prediction is aided by smartphones with artificial intelligence and machine learning capabilities. Case history, doctor notes, chest X‐ray reports, details on the sites of breakouts, and other criteria can help forecast the severity of Covid‐19 when it is in its severe phases and direct the administration of medication to a specific area of the lungs.

show abstract

Section: Discussionmentioning

confidence: 99%

Study on early accurate diagnosis and treatment of COVID‐19 with smart phone tracking using bionics

Gupta

Kumar

2023

Security and Privacy

View full text Add to dashboard Cite

show abstract

“…To evaluate the proposed system for accuracy, average inference time, and fault tolerance, we use a lung X-ray image testing dataset with 1400 images, of which 50% are COVID-positive, as shown in Table 2. We also evaluate the design complexity regarding power consumption, area, and fault tolerance and compare the results with AIRBiS-1 [31] (ANN-based) and other existing works.…”

Section: Evaluation Methodologymentioning

confidence: 99%

“…The SNN model achieved an inference accuracy of 88.43% with images encoded at 25 timesteps per X-ray image. The ANN-based system (AIRBiS-1) on the other hand, achieved an accuracy of 94.4%, as calculated using Equation (3) [31] below.…”

Section: Diagnosis/detection Evaluationmentioning

confidence: 99%

“…However, an ANN model was used, and it achieved less accuracy than the proposed system. Compared to our previously proposed work AIRBiS-1 [31], which is the same as the evaluated ANNbased model that we evaluated, a similar dataset was used, and a higher accuracy of 94.4% was achieved. However, the proposed system consumes less power, area, and lower inference time, as described in Section 4.3.…”

Section: Comparison With Existing Workmentioning

confidence: 99%

“…In our previous work, we proposed an AI-Enabled Real-time Biomedical System (AIRBiS-1) [31,32] for pneumonia (i.e., COVID-19) detection and health monitoring. It consists of a high-performance, reconfigurable inference AI chip with a robust collaborativelearning mechanism for privacy preservation and an interactive user interface for operation and effective monitoring.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Spike-Event X-ray Image Classification for 3D-NoC-Based Neuromorphic Pneumonia Detection

Wang¹,

Ikechukwu²,

Dang³

et al. 2022

Electronics

Self Cite

View full text Add to dashboard Cite

The success of deep learning in extending the frontiers of artificial intelligence has accelerated the application of AI-enabled systems in addressing various challenges in different fields. In healthcare, deep learning is deployed on edge computing platforms to address security and latency challenges, even though these platforms are often resource-constrained. Deep learning systems are based on conventional artificial neural networks, which are computationally complex, require high power, and have low energy efficiency, making them unsuitable for edge computing platforms. Since these systems are also used in critical applications such as bio-medicine, it is expedient that their reliability is considered when designing them. For biomedical applications, the spatio-temporal nature of information processing of spiking neural networks could be merged with a fault-tolerant 3-dimensional network on chip (3D-NoC) hardware to obtain an excellent multi-objective performance accuracy while maintaining low latency and low power consumption. In this work, we propose a reconfigurable 3D-NoC-based neuromorphic system for biomedical applications based on a fault-tolerant spike routing scheme. The performance evaluation results over X-ray images for pneumonia (i.e., COVID-19) detection show that the proposed system achieves 88.43% detection accuracy over the collected test data and could be accelerated to achieve 4.6% better inference latency than the ANN-based system while consuming 32% less power. Furthermore, the proposed system maintains high accuracy for up to 30% inter-neuron communication faults with increased latency.

show abstract

Efficient Pneumonia Detection Method and Implementation in Chest X-ray Images Based on a Neuromorphic Spiking Neural Network

Fukuchi

Ikechukwu

Wang

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Efficient AI-Enabled Pneumonia Detection in Chest X-ray Images

Cited by 11 publications

References 17 publications

Study on early accurate diagnosis and treatment of COVID‐19 with smart phone tracking using bionics

Study on early accurate diagnosis and treatment of COVID‐19 with smart phone tracking using bionics

Spike-Event X-ray Image Classification for 3D-NoC-Based Neuromorphic Pneumonia Detection

Efficient Pneumonia Detection Method and Implementation in Chest X-ray Images Based on a Neuromorphic Spiking Neural Network

Contact Info

Product

Resources

About