A combination of optimized threshold and deep learning-based approach to improve malaria detection and segmentation on PlasmoID dataset
Bibliographic record
Abstract
Malaria is a life-threatening parasitic disease transmitted to humans by infected female Anopheles mosquitoes. Early and accurate diagnosis is crucial to reduce the high mortality rate of the disease, especially in eastern Indonesia, where limited health facilities and resources contribute to the effortless spread of the disease. In rural areas, the lack of trained parasitologists presents a significant challenge. To address this issue, a computer-aided detection (CAD) system for malaria is needed to support parasitologists in evaluating hundreds of blood smear slides every month. This study proposes a hybrid automated malaria parasite detection and segmentation method using image processing and deep learning techniques. First, an optimized double-Otsu method is proposed to generate malaria parasite patch candidates. Then, deep learning approaches are applied to recognize and segment the parasites. The proposed method is evaluated on the PlasmoID dataset, which consists of 468 malaria-infected microscopic images containing 691 malaria parasites from Indonesia. The results demonstrate that our proposed approach achieved an F1-score of 0.91 in parasite detection. Additionally, it achieved better performance in terms of sensitivity, specificity, and F1-score for parasite segmentation compared to original semantic segmentation methods. These findings highlight the potential of this study to be implemented in CAD malaria detection, which could significantly improve malaria diagnosis in resource-limited areas.
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) | 0.002 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 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".