The study examined whether white blood cells (WBCs) cause false‑positive malaria detections in Giemsa‑stained blood smears. Two YOLOv12 models—one trained only on parasite labels and another on both parasite and WBC labels—were evaluated on 8,000 images from Uganda and Ghana. Across seven spatial and statistical tests, false positives did not cluster near WBCs; instead, most were background detections, and the multi‑task model (with WBC labels) performed better overall, suggesting that WBC labeling alone does not reduce false positives but that stain artifacts and unannotated ring forms are the true sources of error.
arXiv:2607. 00385v1 Announce Type: cross Abstract: Automated malaria diagnosis from blood smear microscopy is a critical challenge in global health AI; in resource-limited settings, the scarcity of expert microscopists remains the primary bottleneck to timely and accurate diagnosis.
arXiv:2607. 00385v2 Announce Type: replace-cross Abstract: Automated malaria diagnosis from blood smear microscopy is a critical global health AI challenge; expert scarcity remains the primary diagnostic bottleneck.
arXiv:2607. 16324v1 Announce Type: cross Abstract: Malaria diagnosis in endemic regions depends on species-level identification of Plasmodium parasites in thick blood smears, but deep learning detectors classify detections without providing morphological evidence for their predictions, limiting the ability of microscopists to audit those predictions at the case level.
EMFE (Efficient Mathematical Feature Extraction) is a lightweight, explainable machine‑learning framework that classifies single red‑blood‑cell images as parasitized or uninfected using five engineered features: Gray World color normalization, adaptive green‑channel thresholding, morphological spot detection, and classical classifiers. On the NIH LHNCBC malaria dataset (27,558 images from 200 patients), a tuned Random Forest achieved 94.6% pooled out‑of‑fold accuracy, 94.3% on a 40‑patient holdout, and outperformed deep‑learning baselines in an accuracy‑efficiency trade‑off. Ablation studies, synthetic perturbations, and explainability analyses identified spot saturation as the dominant discriminative feature and quantified the framework’s failure modes and patient‑level performance.
arXiv:2608. 08566v1 Announce Type: cross Abstract: Malaria remains a leading cause of mortality in resource-limited settings, where expert microscopists are scarce.
CoSWA-YOLOv12 is a compact YOLOv12 instance‑segmentation detector designed to improve detection of tiny malaria parasites in microscopy images. It introduces a Cooperative Scale‑adaptive Wasserstein Assignment that applies a Wasserstein distance‑based label assignment inversely proportional to object size, a wavelet detail residual, and a min‑max Gaussian regression loss, all of which preserve pretrained weights. On a five‑class Rwandan thick‑smear dataset, the method raises P. falciparum recall from 0.63 to 0.74, increases mAP@50 from 0.73 to 0.81, and reduces missed detections from 38% to 15%.
arXiv:2607. 04486v1 Announce Type: new Abstract: Diagnosing and monitoring diseases frequently involves the analysis of human biological samples, with blood analysis being pivotal.
arXiv:2609.23714v1 Announce Type: new Abstract: Infectious bovine pinkeye is a contagious ocular disease that adversely affects cattle health, welfare, and agricultural productivity. Conventional dia...
arXiv:2602. 02124v2 Announce Type: replace-cross Abstract: Drug-induced toxicity is a leading cause of preclinical and early-clinical failure, making early detection critical.
The study evaluates 15 frozen hematology foundation-model embeddings across four single‑cell acquisition domains, finding that while in‑domain accuracy is near‑saturated (macro‑F1 0.98–0.997), cross‑dataset performance drops dramatically (34–72%) and model rankings shift. Probe‑dependent rank transfer is observed, with 1‑NN retrieval more stable than linear heads, yet neither reliably predicts target robustness. Calibration deteriorates off‑domain (ECE rises from 0.004 to 0.35), and exposure to internal cohorts confounds shift analysis; a training‑free pseudo‑label‑balanced feature normalization (CBR) modestly improves target‑prior robustness and calibration. whyItMatters":"The findings highlight that frozen hematology foundation models, though accurate in‑domain, may fail under realistic scanner, site, and class‑prior shifts, underscoring the need for comprehensive audits of accuracy, calibration, exposure, and robustness before clinical deployment."
The study evaluates the robustness of medical vision‑language models for tuberculosis screening on chest X‑rays by testing them across multiple datasets, prompts, and evaluation settings. Three specialized models (BioMedCLIP, CheXficient, MedSigLIP) and a general OpenCLIP model were audited on 12,200 images, producing 244,000 model–image–prompt scores. Results show that no model consistently outperforms others across all cohorts and reliability criteria, with prompt changes and control group composition significantly affecting AUROC, and that high training‑set performance does not reliably transfer to external cohorts.
Frozen hematology foundation-model (FM) embeddings reach near-saturated in-domain white-blood-cell (WBC) accuracy, but clinical deployment demands reliability across scanners, sites, stains and prepar...