Research output: Contribution to conference - Without ISBN/ISSN › Conference paper › peer-review
Research output: Contribution to conference - Without ISBN/ISSN › Conference paper › peer-review
}
TY - CONF
T1 - AI-enabled Microscopic Blood Analysis for Microfluidic COVID-19 Hematology
AU - Xia, T.
AU - Fu, Y.Q.
AU - Jin, N.
AU - Chazot, P.
AU - Angelov, P.
AU - Jiang, R.
N1 - Conference code: 162690 Export Date: 14 October 2020 References: Chin, C.D., Linder, V., Sia, S.K., Commercialization of microfluidic point-ofCare diagnostic devices (2012) Lab on A Chip, 12 (12), p. 2118; Clerk Maxwell, J., (1892) A Treatise on Electricity and Magnetism, 2, pp. 68-73. , 3rd ed., Oxford: Clarendon; Quesada-Gonzalez, D., Merkoci, A., NanomaterialBased devices for point-ofCare diagnostic applications (2018) Chemical Society Reviews; Williams, L.W., Interpretation of diagnostic tests (2000) Indian Journal of Pediatrics, 67 (1), pp. 49-53; Hassan, U., (2013) Microfluidic Sensor for White Blood Cell Counting and Flow Metering; Temiz, Y., Lab-on-AChip devices: How to close and plug the lab Microelectronic Engineering, 132 (2015), pp. 156-175; Cha, C.H., Erythrocyte sedimentation rate measurements by test 1 better reflect inflammation than do those by the westergren method in Patients with Malignancy, Autoimmune Disease, or Infection Am J Clin Pathol, 131 (2), pp. 189-194. , http://www.oxfordbiosystems.com/Portals/0/PDF/Biomedomics/COVID19Flyer.pdf, BioMedomics COVID-19 IgM/IgG Rapid test,2009 Feb; Jiang, R., Crookes, D., Luo, N., Davidson, M.W., LiveCell tracking using SIFT features in DIC microscopic videos (2010) IEEE Trans. Biomed Eng., 57, pp. 2219-2228; Fernyhough, E.N., (2016) Automated Segmentation of Structures Essential to Cell Movement, , Diss.University of Leeds; Xia, T., Jiang, R., Fu, Y.Q., Jin, N., Automated blood cell detection and counting via deep learning for microfluidic point-ofcare medical devices 2019 3rd International Conference on Artificial Intelligence Applications and Technologies AIAAT 2019, , 1-3 August 2019, Beijing, China; Storey, G., Jiang, R., Bouridane, A., Role for 2D image generated 3D face models in the rehabilitation of facial palsy (2017) IET Healthcare Technology Letters; Storey, G., Bouridane, A., Jiang, R., Integrated deep model for face detection and landmark localisation from 'in the wild' images IEEE Access, , in press; Storey, G., Jiang, R., Bouridane, A., Role for 2D image generated 3D face models in the rehabilitation of facial palsy (2017) IET Healthcare Technology Letters; Jiang, Z., Chazot, P.L., Celebi, M.E., Crookes, D., Jiang, R., Social behavioral phenotyping of drosophila with a 2d-3d hybrid cnn framework (2019) IEEE Access, pp. 67972-67982; Jiang, R., Crookes, D., Shallow unorganized neural networks using smart neuron model for visual perception (2019) IEEE Access, pp. 152701-152714; Girshick, R., Rich feature hierarchies for accurate object detection and semantic segmentation (2014) Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; Girshick, R., Fast rCnn (2015) Proceedings of the IEEE International Conference on Computer Vision; Ren, S., Faster rCnn: Towards realTime object detection with region proposal networks (2015) Advances in Neural Information Processing Systems; Kaiming, H., Mask rCnn (2017) Proceedings of the IEEE International Conference on Computer Vision; Redmon, J., You only look once: Unified, realTime object detection (2016) Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; Redmon, J., Farhadi, A., (2018) YOLOv3: An Incremental Improvement, , http://github.com/ultralytics/YOLOv3; Redmon, J., Farhadi, A., YOLO9000: Better, faster, stronger (2017) Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; BCCD Dataset, , http://github.com/Shenggan/BCCDDatset; Mitra, A., Leukoerythroblastic reaction in a patient with covid-19 infection American Journal of Hematology, , Mar 25 2020; Jiang, R., Almaadeed, S., Bouridane, A., Crookes, D., Celebi, M.E., Face recognition in the scrambled domain via salience-Aware ensembles of many kernels (2016) IEEE Trans. Information Forensics and Security, 11 (8), pp. 1807-1817; Jiang, R., Bouridane, A., Crookes, D., Celebi, M., Wei, H.L., PrivacyProtected facial biometric verification via fuzzy forest learning (2016) IEEE Trans. Fuzzy Systems, 24 (4), pp. 779-790; Jiang, R., Sadka, A.H., Crookes, D., Multimodal biometric human recognition for perceptual human-computer interaction (2010) IEEE Trans. Systems, Man, & Cybernetics Part C, 40 (5), p. 676; Jiang, R., Ho, A., Cheheb, I., Almaadeed, N., Almaadeed, S., Bouridane, A., Emotion recognition from scrambled facial images via many graph embedding (2017) Pattern Recognition, 67, pp. 245-251; Soares, E., Angelov, P., Novelty Detection and Learning with Extremely Weak Supervision, , http://arxiv.org/pdf/1911.00616.pdf
PY - 2020/6/21
Y1 - 2020/6/21
N2 - Microscopic blood cell analysis is an important methodology for medical diagnosis, and complete blood cell counts (CBCs) are one of the routine tests operated in hospitals. Results of the CBCs include amounts of red blood cells, white blood cells and platelets in a unit blood sample. It is possible to diagnose diseases such as anemia when the numbers or shapes of red blood cells become abnormal. The percentage of white blood cells is one of the important indicators of many severe illnesses such as infection and cancer. The amounts of platelets are decreased when the patient suffers hemophilia. Doctors often use these as criteria to monitor the general health conditions and recovery stages of the patients in the hospital. However, many hospitals are relying on expensive hematology analyzers to perform these tests, and these procedures are often time consuming. There is a huge demand for an automated, fast and easily used CBCs method in order to avoid redundant procedures and minimize patients' burden on costs of healthcare. In this research, we investigate a new CBC detection method by using deep neural networks, and discuss state of the art machine learning methods in order to meet the medical usage requirements. The approach we applied in this work is based on YOLOv3 algorithm, and our experimental results show the applied deep learning algorithms have a great potential for CBCs tests, promising for deployment of deep learning methods into microfluidic point-of-care medical devices. As a case of study, we applied our blood cell detector to the blood samples of COVID-19 patients, where blood cell clots are a typical symptom of COVID-19. © 2020 IEEE.
AB - Microscopic blood cell analysis is an important methodology for medical diagnosis, and complete blood cell counts (CBCs) are one of the routine tests operated in hospitals. Results of the CBCs include amounts of red blood cells, white blood cells and platelets in a unit blood sample. It is possible to diagnose diseases such as anemia when the numbers or shapes of red blood cells become abnormal. The percentage of white blood cells is one of the important indicators of many severe illnesses such as infection and cancer. The amounts of platelets are decreased when the patient suffers hemophilia. Doctors often use these as criteria to monitor the general health conditions and recovery stages of the patients in the hospital. However, many hospitals are relying on expensive hematology analyzers to perform these tests, and these procedures are often time consuming. There is a huge demand for an automated, fast and easily used CBCs method in order to avoid redundant procedures and minimize patients' burden on costs of healthcare. In this research, we investigate a new CBC detection method by using deep neural networks, and discuss state of the art machine learning methods in order to meet the medical usage requirements. The approach we applied in this work is based on YOLOv3 algorithm, and our experimental results show the applied deep learning algorithms have a great potential for CBCs tests, promising for deployment of deep learning methods into microfluidic point-of-care medical devices. As a case of study, we applied our blood cell detector to the blood samples of COVID-19 patients, where blood cell clots are a typical symptom of COVID-19. © 2020 IEEE.
KW - blood analysis haematology
KW - COVID-19
KW - deep learning at edge
KW - microfluidic device
KW - microscopic imaging
KW - Cytology
KW - Deep learning
KW - Deep neural networks
KW - Diagnosis
KW - Diseases
KW - Hospitals
KW - Intelligent computing
KW - Learning algorithms
KW - Learning systems
KW - Microfluidics
KW - Patient rehabilitation
KW - Platelets
KW - Detection methods
KW - Diagnose disease
KW - Health condition
KW - Learning methods
KW - Medical Devices
KW - Recovery stages
KW - State-of-the-art machine learning methods
KW - White blood cells
KW - Cells
U2 - 10.1109/ICCIA49625.2020.00026
DO - 10.1109/ICCIA49625.2020.00026
M3 - Conference paper
SP - 98
EP - 102
T2 - 5th International Conference on Computational Intelligence and Applications 2020
Y2 - 19 June 2020 through 21 June 2021
ER -