RNA-BioLens: A Novel Raspberry Pi-Based Digital Microscope With Image Processing for Acute Lymphoblastic Leukemia Detection
Blood analysis plays a critical role in understanding an individual’s health, particularly by examining the morphology and concentration of blood cells. Accurate blood cell analysis is essential for precise diagnosis, especially in identifying cancerous cells, such as Acute Lymphoblastic...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10848089/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Blood analysis plays a critical role in understanding an individual’s health, particularly by examining the morphology and concentration of blood cells. Accurate blood cell analysis is essential for precise diagnosis, especially in identifying cancerous cells, such as Acute Lymphoblastic Leukemia (ALL) — Indonesia’s most common childhood cancer, according to the Indonesian Pediatric Society (IDAI). Morphological examination relies on each cell type’s consistent and defining traits, traditionally performed through blood smears and bone marrow aspiration, where cell morphology is assessed under light or digital microscopes. However, manual examination methods can be prone to bias and require extended processing times. While digital microscopes offer a more advanced alternative, they often come with high implementation costs and complexity. To address these challenges, this study presents a simplified digital microscope system integrated with the YOLOv4 (You Only Look Once) algorithm combined with additional segmentation and feature extraction methods designed explicitly for ALL cell detection. This system aims to enhance detection accuracy and speed while balancing complexity and procurement costs. The microscope, equipped with a 10X eyepiece lens, a 100X objective lens, and a Raspberry Pi camera module, successfully achieved cellular-level magnification and was further developed into the “RNA BioLens” application. This application achieved a detection accuracy of 97.67% for the overall detection system, demonstrating its potential as a reliable tool for efficient and accurate diagnosis. |
|---|---|
| ISSN: | 2169-3536 |