Ablation Study Results for Elastic YOLO Blood Cell Detection Model

94.7% [email protected] and 87.8% [email protected]:0.95 were achieved by the Elastic YOLO model on a clinician-annotated dataset of peripheral blood smear images. The dataset contains ablation study results for this object detection framework designed to identify red blood cells, white blood cells, and platelets. It was authored by Neha Margret Issac and last updated on 2026-05-12.

Use Cases

• Benchmarking object detection architectures for multi-class cell detection based on the reported performance metrics
• Analyzing the impact of elastic adaptive convolutions on model performance for varying cell sizes and staining conditions
• Supporting the development of computer-assisted hematology workflows and telemedicine-based triage systems based on the described automated analysis

Strengths

• Performance metrics are explicitly stated: 94.7% [email protected] and 87.8% [email protected]:0.95
• Dataset is licensed under CC-BY-4.0, allowing for open sharing and modification
• The model described achieved inference speeds of up to 78 FPS on specific hardware

Limitations

• Row count is unknown, which may limit suitability assessment
• Column-level documentation is absent; field semantics must be inferred after download
• The dataset is very small at 5.5 KB, indicating limited scope

Provenance

Source

figshare

Collection Method

Likely contains experimental results from training and evaluating the Elastic YOLO model.

Freshness

Last updated 2026-05-12 17:44:45; freshness should be verified