Advanced biomedical imaging for identifying blood cell type: Integrating segmentation, feature extraction, and GraphSAGE model
Bibliographic record
Abstract
The analysis of blood, including red blood cells (RBC) and different types of white blood cells (WBCs) plays a major role in the diagnosis of certain diseases. Automated segmentation of blood cells and their components can assist clinicians in effectively making diagnoses; however, it is quite challenging Objective: This study proposes a computerized approach to assessing the significance of biomedical imaging. It presents a framework for segmenting blood cells as well as their nuclei from the histopathological images of multiple datasets. Additionally, a custom algorithm is developed for blood cell counting. This study introduces two automated methods for WBC analysis, including image segmentation to distinguish between WBCs and RBCs, the nuclei of the WBC, and classifying WBC types using clinically important features. An effective segmentation approach with image preprocessing algorithms is developed for automatic counting of WBCs and RBCs. An improved GraphSAGE model is constructed to classify blood cells. Clinically relevant features are extracted from segmented WBCs and nuclei for a final dataset. Feature ranking analysis identifies optimal features and reduces dimensionality, aiding graph dataset construction based on data similarity. Our proposed model achieved an accuracy of 96.67 %. A comparative analysis with benchmark models is done to assess the effectiveness of the model. The explainability of the model is addressed to enhance the transparency of the diagnostic system and provide insight into the decision-making process. Leveraging the automated, simultaneous segmentation of blood cells and exploring their relationships for effective classification substantially helps to improve the reliability and applicability of this diagnostic system and aid clinicians.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".