Unifying VLM-Guided Flow Matching and Spectral Anomaly Detection for Interpretable Veterinary Diagnosis

Pu Wang; Zhixuan Mao; Jialu Li; Zhuoran Zheng; Dianjie Lu; Youshan Zhang

cs.CVApr 7, 2026

Unifying VLM-Guided Flow Matching and Spectral Anomaly Detection for Interpretable Veterinary Diagnosis

Authors: Pu Wang, Zhixuan Mao, Jialu Li, Zhuoran Zheng, Dianjie Lu, Youshan Zhang

Organizations: School of Mathematics, Shandong University · Shenzhen Loop Area Institute · Yeshiva University · Qilu University of Technology ·

Abstract

Automatic diagnosis of canine pneumothorax is challenged by data scarcity and the need for trustworthy models. To address this, we first introduce a public, pixel-level annotated dataset to facilitate research. We then propose a novel diagnostic paradigm that reframes the task as a synergistic process of signal localization and spectral detection. For localization, our method employs a Vision-Language Model (VLM) to guide an iterative Flow Matching process, which progressively refines segmentation masks to achieve superior boundary accuracy. For detection, the segmented mask is used to isolate features from the suspected lesion. We then apply Random Matrix Theory (RMT), a departure from traditional classifiers, to analyze these features. This approach models healthy tissue as predictable random noise and identifies pneumothorax by detecting statistically significant outlier eigenvalues that represent a non-random pathological signal. The high-fidelity localization from Flow Matching is crucial for purifying the signal, thus maximizing the sensitivity of our RMT detector. This synergy of generative segmentation and first-principles statistical analysis yields a highly accurate and interpretable diagnostic system (source code is available at: https://github.com/Pu-Wang-alt/Canine-pneumothorax).

Figures & tables

Fig. 1: Comparison of diagnostic approaches for canine pneumothorax. (a) The clinical challenge of subtle features. (b) The interpretability issue of ”black box” AI. (c) Our proposed framework.

Fig. 2: Overview of our proposed synergistic framework for canine pneumothorax diagnosis.

Category	Year	Model	Test Set
Category	Year	Model	mDice $\uparrow$	mIoU $\uparrow$
Unet-based	2015	Unet [ 34 ]	0.8774	0.7878
	2018	Unet++ [ 22 ]	0.8712	0.7788
	2025	PolypFlow [ 41 ]	0.8869	0.8019
	2020	$U^{2}$ Net [ 16 ]	0.8834	0.7965
	2022	Swin-UNet [ 6 ]	0.8462	0.7424

TABLE I: Performance comparison with state-of-the-art segmentation methods.

Model	Test Set
Model	Acc. $\uparrow$	Prec. $\uparrow$	Rec. $\uparrow$	F1 $\uparrow$
GoogleNet [ 37 ]	0.8270	0.6787	0.5587	0.6129
VGG16 [ 35 ]	0.2451	0.2451	1.0000	0.3938
ResNet50 [ 12 ]	0.5908	0.3494	0.7769	0.4821
DenseNet201 [ 23 ]	0.8379	0.7263	0.5438	0.6219
Inceptionv3 [ 38 ]	0.8485	0.7680	0.5471	0.6390

TABLE II: Performance comparison on the validation and test sets.

Fig. 3: (a) This chart displays the Receiver Operating Characteristic curves. The proposed model achieves the best performance with a leading Area Under the Curve (AUC) score of 0.939. This is notably higher than other models. (b) This chart displays the Precision-Recall curves. The proposed model again shows superior performance, attaining the highest Average Precision score of 0.885.

Setting	Model Components			Seg. Performance		Class. Performance
	Text Guidance	Flow Matching	RMT Input (Purification)	mDice $\uparrow$	mIoU $\uparrow$	AUC $\uparrow$	F1-Score $\uparrow$
Experiment 1: Ablation on Segmentation Components
(a)	$\times$	$\times$	–	0.8830	0.7949	–	–
(b)	✓	$\times$	–	0.8736	0.7051	–	–
(c)	✓	✓	–	0.8953	0.8114	–	–
Experiment 2: Ablation on Classification Synergy

TABLE III: Ablation study of our proposed framework.

Fig. 4: Qualitative Comparison of Unet-based Segmentation Results. This figure presents a visual comparison of the segmentation performance of our proposed model against five Unet-based methods.

Fig. S1: This figure presents a comparative analysis of the confusion matrices for the proposed model and twelve other models. Each matrix displays the counts for True Negatives (TN), False Positives (FP), False Negatives (FN), and True Positives (TP). The results highlight the superior performance of our model, which achieves a strong balance in correctly identifying both positive and negative instances while maintaining low error rates compared to the other methods.

Fig. S2: Qualitative Comparison of Segmentation Results. This figure presents a visual comparison of the segmentation performance of our proposed model against four methods.

Fig. S3: Qualitative Comparison of Transformer-based and Mamba-based Segmentation Results.

Medical Image Anomaly Detection

Medical image anomaly detection finds and localizes unusual anatomy or pathology in scans, often when labeled disease examples are scarce.

See all 87 papers

MEDIC-AD: Towards Medical Vision-Language Model's Clinical Intelligence
Mar 28, 2026Woohyeon Park, Jaeik Kim, Sunghwan Steve Cho +7Medical VLMs Medical Image Anomaly Detection
AIDAS Laboratory, Seoul National University · Samsung Changwon Hospital · Samsung Medical Center +1
External Benchmarking of Lung Ultrasound Models for Pneumothorax-Related Signs: A Manifest-Based Multi-Source Study
Mar 27, 2026Takehiro IshikawaMedical Image Benchmarks Medical Image Classification
College of Computing, Georgia Institute of Technology, 801 Atlantic Drive NW, Atlanta, GA 30332, USA
Wasserstein-Aligned Localisation for VLM-Based Distributional OOD Detection in Medical Imaging
May 6, 2026Bernhard Kainz, Johanna P Mueller, Matthew Baugh +1Medical Image Anomaly Detection Anomaly Localization
Dept. AIBE, Friedrich–Alexander University Erlangen–Nürnberg, DE · Department of Computing, Imperial College London, UK · Technical University Munich, DE +1

Mar 28, 2026J/K move · Enter open · S save

MEDIC-AD: Towards Medical Vision-Language Model's Clinical Intelligence

Woohyeon Park, Jaeik Kim, Sunghwan Steve Cho, Pa Hong+6

AIDAS Laboratory, Seoul National University · Samsung Changwon Hospital · Samsung Medical Center+1

Medical VLMs Medical Image Anomaly Detection Explainable Medical Image Analysis Longitudinal Medical Image Analysis Medical Image Segmentation

Open paper AskPDF arXiv

Lesion detection, symptom tracking, and visual explainability are central to real-world medical image analysis, yet current medical Vision-Language Models (VLMs) still lack mechanisms that translate their broad knowledge into clinically actionable outputs. To bridge this gap, we present MEDIC-AD, a clinically oriented VLM that strengthens these three capabilities through a stage-wise framework. First, learnable anomaly-aware tokens (<Ano>) encourage the model to focus on abnormal regions and build more discriminative lesion centered representations. Second, inter image difference tokens (<Diff>) explicitly encode temporal changes between studies, allowing the model to distinguish worsening, improvement, and stability in disease burden. Finally, a dedicated explainability stage trains the model to generate heatmaps that highlight lesion-related regions, offering clear visual evidence that is consistent with the model's reasoning. Through our staged design, MEDIC-AD steadily boosts performance across anomaly detection, symptom tracking, and anomaly segmentation, achieving state-of-the-art results compared with both closed source and medical-specialized baselines. Evaluations on real longitudinal clinical data collected from real hospital workflows further show that MEDIC-AD delivers stable predictions and clinically faithful explanations in practical patient-monitoring and decision-support workflows

Abstract

Medical Image Anomaly Detection

Explore similar work

MEDIC-AD: Towards Medical Vision-Language Model's Clinical Intelligence

External Benchmarking of Lung Ultrasound Models for Pneumothorax-Related Signs: A Manifest-Based Multi-Source Study

Wasserstein-Aligned Localisation for VLM-Based Distributional OOD Detection in Medical Imaging