![References
• [1] C. Chola et al., “BCNet: A Deep Learning Computer-Aided Diagnosis Framework for Human Peripheral Blood Cell
Identification,” Diagnostics, vol. 12, no. 11, p. 2815, Nov. 2022, doi: https://doi.org/10.3390/diagnostics12112815.
• [2] S.-J. Lee, P.-Y. Chen, and J.-W. Lin, “Complete Blood Cell Detection and Counting Based on Deep Neural
Networks,” Applied Sciences, vol. 12, no. 16, p. 8140, Aug. 2022, doi: https://doi.org/10.3390/app12168140.
• [3] M. M. Alam and M. T. Islam, “Machine learning approach of automatic identification and counting of blood
cells,” Healthcare Technology Letters, vol. 6, no. 4, pp. 103–108, Aug. 2019, doi: https://doi.org/10.1049/htl.2018.5098.
• [4] N. K.T., K. Prasad, and B. M. K. Singh, “Analysis of red blood cells from peripheral blood smear images for anemia
detection: a methodological review,” Medical & Biological Engineering & Computing, vol. 60, no. 9, Jul. 2022, doi:
https://doi.org/10.1007/s11517-022-02614-z.](https://image.slidesharecdn.com/titledefensefinalized-240228110459-0b85d8db/85/Title-Defense-on-AI-based-portable-CBC-kit-pptx-13-320.jpg)
Title Defense on AI based portable CBC kit .pptx
- 1. Portable CBC Analysis Kit Precise Blood Cell Inspection using AI and Embedded System NUST COLLEGE OF ELECTRICAL & MECHANICAL ENGINEERING, RAWALPINDI.
- 3. ABSTRACT • Our research focuses on developing an AI-driven system for Complete Blood Count (CBC). • By utilizing machine learning algorithms, deep learning models, and computer vision techniques, we aim to streamline the analysis process and improve diagnostic accuracy. DATA SET (BLOOD SAMPLES) MACHINE LEARNING AND DEEP LEARNING ALGORITHMS USER FRIENDLY INTERFACE / HARDWARE
- 4. Raw Data Spliting Data Image sharpening, augmentation & enlargement Model Selection & Customization Model Training Cell Counting & Classification Testing & Validation Implementation on Raspberry Pi 4 GUI Data & Result Storage on Cloud Methodology
- 6. Sr. No. Title, Author(s),Year Aim of Study Methods Results 1 Complete Blood Cell Detection and Counting Based on Deep Neural Networks Shin Lee, Pei-Yun & Jeng Lin, 2022 Detecting blood cells using AI Preprocessing images, VGG-16 for image recognition and Fast R-CNN ● RBC detection-Model 3: 82.3% - 86.7%. ●WBC detection- Model 1 : 76.1% - 95%. ●Platelet detection: lower recalls were recorded. 2 BCNet: A Deep Learning Computer- Aided Diagnosis Framework for Human Peripheral Blood Cell Identification Channabasava Chola, Abdullah Y. Muaad, Md Belal Bin Heyat, J. V. Bibal Benifa, 2022. Classification of blood cells in diff classes Development of an AI based deep learning framework convolved with the NN. ●Best evaluation performance using the RMSP optimizer with 98.51% accuracy and 96.24% F1-score. ●Baseline model, the BCNet clearly improved the prediction accuracy : 1.94%, 3.33%, and 1.65% using the optimizers of ADAM, RMSP, and SGD, respectively. 3 Machine Learning approach of Automatic Identification and counting of blood cells Mohammad Mahmudul Alam, Mohammad Tariqul Islam, 2019. Detection and counting of blood cells using YOLO Tiny Using YOLO to detect cells directly for smear image. Application of algorithm using other CNN architectures. ●For RBC detection, accuracy achieved was 96.09%, WBC 86.36% and whopping 96.36% was achieved for platlets. ●Some platelets were counted twice that was resolved using KNN algorithm. 4 Analysis of red blood cells from peripheral blood smear images for anemia detection: Navya K.T.1 · Keerthana Prasad · Brij Mohan Kumar Singh , 2020 Assessing RBCs in detail for anemia detection Using K-means clustering , Iterative structured circle detection, YOLO algorithm Canny edge, MLP , Deep neural network models ●Anemia detection: of 83–94% accuracy obtained using ANN, SVM. ●Classification: An accuracy of 85% for normal RBCs, 83% for abnormal cells was obtained in RBCs. ●Edge based segmentation method: 74% accuracy for 59 RBCs and 59 non-RBCswas obtained using (MLP).
- 7. Objectives • Data Integration • AI Model Development • Automation • Individual Blood Count • Detection of Anomalies • GUI Interface • Hardware Implementation
- 8. Sustainable Development Goals (SDGs): • SDG-03: Good Health and Well Being: • SDG-09: Industry, Innovation and Infrastructure • SDG-10: Reduced Inequality • SDG-11: Sustainable Cities and Communities • SDG-17: Partnership for the Goals
- 9. Motivation • Rapid and Accurate Results • Reduced Human Error • Cost-Efficiency • Expanded Accessibility • Real-time Monitoring • Early Disease Detection • Data Integration • Improved Patient Experience • Research and Population Health
- 10. Advantages/Educational Outcomes • Machine Learning Algorithms • Digital Image Processing techniques / Computer Vision • Interface development • Embedded System • Research Opportunities • Professional Development
- 11. TimeLine/Gantt Chart 2-Oct 22-Oct 11-Nov 1-Dec 21-Dec 10-Jan 30-Jan 19-Feb 10-Mar 30-Mar 19-Apr Learning Basics of Machine Learning and Computer Vision Techniques Data Collection from Laboratory Training Model on Dataset Validation/Testing/Optimization User Interface Development / Hardware Development Hardware Implementation (Real Time Data) Documentation / Thesis Writing Days to Complete
- 12. Conclusions • AI Revolutionizing CBC Analysis and Improving Healthcare • Innovation in Medical Equipment • Learning Possibilities • SDGs Aligned • Future Direction
- 13. References • [1] C. Chola et al., “BCNet: A Deep Learning Computer-Aided Diagnosis Framework for Human Peripheral Blood Cell Identification,” Diagnostics, vol. 12, no. 11, p. 2815, Nov. 2022, doi: https://doi.org/10.3390/diagnostics12112815. • [2] S.-J. Lee, P.-Y. Chen, and J.-W. Lin, “Complete Blood Cell Detection and Counting Based on Deep Neural Networks,” Applied Sciences, vol. 12, no. 16, p. 8140, Aug. 2022, doi: https://doi.org/10.3390/app12168140. • [3] M. M. Alam and M. T. Islam, “Machine learning approach of automatic identification and counting of blood cells,” Healthcare Technology Letters, vol. 6, no. 4, pp. 103–108, Aug. 2019, doi: https://doi.org/10.1049/htl.2018.5098. • [4] N. K.T., K. Prasad, and B. M. K. Singh, “Analysis of red blood cells from peripheral blood smear images for anemia detection: a methodological review,” Medical & Biological Engineering & Computing, vol. 60, no. 9, Jul. 2022, doi: https://doi.org/10.1007/s11517-022-02614-z.
- 14. Questions