aiqbench analysis
This research introduces SGMCE, a post-hoc explanation framework that anchors deep learning malaria diagnoses in specific morphological features without requiring additional training data or annotations. By combining handcrafted computer-vision metrics with GPT-4o queries against WHO guidelines, the system generates auditable natural-language reports for microscopists to verify species-level predictions on thick blood smears. The approach effectively bridges the gap between black-box detection and clinical trust by ensuring that every AI claim is grounded in measurable visual evidence rather than hallucinated reasoning.
SGMCE: Segment-Grounded Morphological Concept Explanation for Malaria Parasite Species Identification in Thick Blood Smears
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. We present SGMCE (Segment-Grounded Morphological Concept Explanation), a post-hoc explanation framework that requires no additional training, no morphological annotations, and no labelled explanation data, yet produces per-detection natural-language explanations anchored in thick-smear morphology. For each detection, SGMCE extracts mask-guided crop thumbnails, computes fourteen handcrafted computer-vision morphological features (shape, colour, chromatin, haemozoin pigment) using adaptive within-mask thresholds, and queries GPT-4o with both visual evidence and computed measurements, conditioned on a thick-smear-specific knowledge base compiled from the World Health Organization bench aids. The primary output is a structured explanation identifying which morphological features support the detected species and why the competing species are excluded. Explanations are validated by four automatic metrics: Knowledge-Base Consistency (KBC), CV-Claim Faithfulness (CCF), Discriminativeness Score (DS), and LLM-as-Judge (LLMj). A sentence-level semantic scoring rule with species-aware negation filtering resolves the vocabulary mismatch between clinical prose and knowledge-base terms. Across 737 detections from 139 thick-smear images spanning four Plasmodium species and white blood cells, parasite-class mean KBC is 0.91, mean DS is 0.99, and mean CCF is 0.97, while a per-rule CCF breakdown confirms that the CV-grounded claims made by the vision-language model are consistent with the measurements they cite.
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. We present SGMCE (Segment-Grounded Morphological Concept Explanation), a post-hoc explanation framework that requires no additional training, no morphological annotations, and no labelled explanation data, yet produces per-detection natural-language explanations anchored in thick-smear morphology. For each detection, SGMCE extracts mask-guided crop thumbnails, computes fourteen handcrafted computer-vision morphological features (shape, colour, chromatin, haemozoin pigment) using adaptive within-mask thresholds, and queries GPT-4o with both visual evidence and computed measurements, conditioned on a thick-smear-specific knowledge base compiled from the World Health Organization bench aids. The primary output is a structured explanation identifying which morphological features support the detected species and why the competing species are excluded. Explanations are validated by four automatic metrics: Knowledge-Base Consistency (KBC), CV-Claim Faithfulness (CCF), Discriminativeness Score (DS), and LLM-as-Judge (LLMj). A sentence-level semantic scoring rule with species-aware negation filtering resolves the vocabulary mismatch between clinical prose and knowledge-base terms. Across 737 detections from 139 thick-smear images spanning four Plasmodium species and white blood cells, parasite-class mean KBC is 0.91, mean DS is 0.99, and mean CCF is 0.97, while a per-rule CCF breakdown confirms that the CV-grounded claims made by the vision-language model are consistent with the measurements they cite.
Accepted for publication in the 30th Conference on Medical Image Understanding and Analysis (MIUA 2026), Dublin. To appear in Springer Lecture Notes in Computer Science (LNCS)
Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
arXiv:2607.16324 [cs.CV]
(or arXiv:2607.16324v1 [cs.CV] for this version)
Full text under the publisher's open licence · 276 words
Related coverage
ConEx: Human-Interpretable Saliency Maps via Concept-Aware Attribution
arXiv · Oct 7, 2026
CFM: Language-aligned Concept Foundation Model for Vision
arXiv · Aug 24, 2026
Beyond Local Inspection: Global, Guideline-Grounded Evaluation of Post-hoc XAI Methods for ECG Classification
arXiv · Jul 28, 2026
Spatially Grounded Concept Bottleneck Models for Trustworthy Breast Ultrasound Diagnosis
arXiv · Jul 24, 2026