An Automatic Nucleus Segmentation and Classification of White Blood Cell with ResUNet
Bibliographic record
Abstract
Leukocytes, another name for white blood cells, or WBCs, are essential components of our immune system, playing a crucial role in protecting our bodies from infection and disease.When we look at immune disorders and bacterial infections, we see that lymphocytes play a central role in the adaptive immune response, while neutrophils are essential in the fight against bacterial infections, and basophils are involved in allergic and inflammatory reactions.When one of these three types of white blood cell (WBC) is affected, it can have a variety of consequences for the immune system and the body's overall health, leading to serious illnesses such as AIDS, leukemia and severe allergic reactions such as anaphylaxis.The diagnosis of some disorders can benefit greatly from the segmentation of the white blood cell nucleus.Analysis of cell morphology, in particular the shape and size of the nucleus in microscopic images, can provide indications of a cell's state of health.In this work, we suggest a fully automatic method for segmenting the nuclei of the three types of WBC (neutrophils, lymphocytes, basophils) using a convolutional neural network named WCSegNet based on the Unet architecture consisting of residual convolution blocks activated by the LeakyRlu activation function.Our technique succeeded in segmenting the cell nucleus and classifying microscopic images according to their type.The results obtained are encouraging, with precision scores in excess of 0.90.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 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".