Unsupervised Clustering of COVID-19 Chest X-Ray Images with a Self-Organizing Feature Map

King, Bayley; Barve, Siddharth; Ford, Andrew J.; Jha, Rashmi

doi:10.1109/mwscas48704.2020.9184493

Cited by 25 publications

(14 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Discrete states in the FeFET devices and the projection of a large dataset on few neurons will result in a non-zero quantization error. However, a low topographic and quantization error for the COVID-19 results and intrinsic explainability of SOFMs [21] shows the practicality of the network in real world applications. Additionally, the quality preservation in all tests shows that the decaying plasticity of the network can prevent over-training while the network is still functional.…”

Section: Resultsmentioning

confidence: 99%

NeuroSOFM: A Neuromorphic Self-Organizing Feature Map Heterogeneously Integrating RRAM and FeFET

Barve

Mayersky

Ford

et al. 2021

IEEE J. Explor. Solid-State Comput. Devices Circuits

Self Cite

View full text Add to dashboard Cite

Many currently available hardware implementations of the unsupervised self-organizing feature map (SOFM) algorithm utilize CMOS-only circuits that often compromise key behaviors of the SOFM algorithm due to complexity. We propose a neuromorphic architecture harnessing the unique properties of FeFETs and gated-RRAM for in-memory computing to implement the SOFM algorithm. The FeFET-based synapse, organized in a novel circuit, is able to compute the input-weight Euclidean error in memory via the saturation drain current. The selfdecaying states of the gated-RRAM allow for a self-decaying neighborhood and learning rate implementation to allow for convergence and lifelong learning. This novel architecture is able to successfully cluster benchmarks (RGB colors and MNIST handwritten digits) and real-life datasets such as COVID-19 patient chest x-rays completely unsupervised. The architecture also demonstrates a significant amount of robustness to device variability and damaged neurons. Additionally, the proposed architecture is completely parallelized and provides a power efficient platform for implementing the SOFM algorithm.

show abstract

Section: Resultsmentioning

confidence: 99%

NeuroSOFM: A Neuromorphic Self-Organizing Feature Map Heterogeneously Integrating RRAM and FeFET

Barve

Mayersky

Ford

et al. 2021

IEEE J. Explor. Solid-State Comput. Devices Circuits

Self Cite

View full text Add to dashboard Cite

show abstract

“…It can also show which properties in the input space influenced the classification the most, which can be used to evaluate the significance of features in an unsupervised network. As proven in this paper, unsupervised learning can extract features from medical data, such as COVID-19 patients' chest x-rays, while also successfully recognizing the image [19].…”

Section: Related Workmentioning

confidence: 91%

A Combined Image Segmentation and Classification Approach for COVID-19 Infected Lungs

Sangeetha¹,

Afreen²,

Ahmad³

2021

RCES

View full text Add to dashboard Cite

Lung infection or sickness is one of the most common acute ailments in humans. Pneumonia is one of the most common lung infections, and the annual global mortality rate from untreated pneumonia is increasing. Because of its rapid spread, pneumonia caused by the Coronavirus Disease (COVID-19) has emerged as a global danger as of December 2019. At the clinical level, the COVID-19 is frequently measured using a Computed Tomography Scan Slice (CTS) or a Chest X-ray. The goal of this study is to develop an image processing method for analysing COVID-19 infection in CT Scan patients. The images in this study were preprocessed using the Hybrid Swarm Intelligence and Fuzzy DPSO algorithms. According to extensive computer simulations, the persistent learning strategy for CT image segmentation using image enhancement is more efficient and adaptive than the Medical Image Segmentation (MIS) method. The findings suggest that the proposed method is more dependable, accurate, and simple than existing methods.

show abstract

“…X-ray images with COVID-19 were applied to an SOFM network to search and classify patients sickness. Their work showed that unsupervised learning could extract features from x-rays images [23]. Chowdhury et al [24] used in their research a dataset that contains 423 COVID-19 x-ray images, 1485 viral pneumonia x-ray images, and 1579 normal x-ray images.…”

Section: Related Workmentioning

confidence: 99%

BEMD-3DCNN-Based Method for COVID-19 Detection

Riahi

Elharrouss

Almaadeed

et al. 2021

Preprint

View full text Add to dashboard Cite

Coronavirus outbreak continues to spread around the world and none knows when it will stop. Therefore, from the first day of the virus identification in Wuhan, scientists have launched numerous research projects to understand the nature of the virus, how to detect it, and search for the right medicine to help and protect patients. A fast diagnostic and detection system is a priority and should be found to stop COVID-19 from spreading. Medical imaging techniques has been used for this purpose. The existing works used transfer learning by exploiting different backbones like VGG, ResNet, DenseNet or combine them to detect COVID-19. By using these backbones many aspect can not be analysed like the spatial and contextual information in the images, while these information's can be useful for a better detection performance. For that in this paper, we used 3D representation of the data (video) as input of the 3DCNN-based deep learning model. The Bi-dimensional empirical mode decomposition (BEMD) technique to decompose the original image into IMFs, then built a video of these IMFs images. The formed video is used as input of 3DCNN model to classify and detect COVID-19 virus. 3DCNN model consists of a 3D VGG-16 backbone followed by a Context-aware attention (CAA) modules then fully connected layers for classification. Each CAA module takes the feature maps of different blocks of the backbone, which allows a learning from different feature maps. In the experiments we used 6484 X-Ray images, 1802 of them were COVID-19 positive cases, 1910 normal cases, and 2772 pneumonia cases. The experiment results showed that our proposed techniques achieved the desired results on the selected dataset. Also, the use of 3DCNN model with contextual information processing exploiting CAA networks helps to achieve better performance.

show abstract

Unsupervised Clustering of COVID-19 Chest X-Ray Images with a Self-Organizing Feature Map

Cited by 25 publications

References 7 publications

NeuroSOFM: A Neuromorphic Self-Organizing Feature Map Heterogeneously Integrating RRAM and FeFET

NeuroSOFM: A Neuromorphic Self-Organizing Feature Map Heterogeneously Integrating RRAM and FeFET

A Combined Image Segmentation and Classification Approach for COVID-19 Infected Lungs

BEMD-3DCNN-Based Method for COVID-19 Detection

Contact Info

Product

Resources

About