arXiv:2510.20864v1 Announce Type: cross 
Abstract: Rationale and Objectives: Computer-aided detection systems for chest radiographs are widely used, and concurrent reader displays, such as bounding-box (BB) highlights, may influence the reading process. This pilot study used eye tracking to conduct a preliminary experiment to quantify which aspects of visual search were affected. Materials and Methods: We sampled 180 chest radiographs from the VinDR-CXR dataset: 120 with solitary pulmonary nodules or masses and 60 without. The BBs were configured to yield an overall display sensitivity and specificity of 80%. Three radiologists (with 11, 5, and 1 years of experience, respectively) interpreted each case twice - once with BBs visible and once without - after a washout of >= 2 weeks. Eye movements were recorded using an EyeTech VT3 Mini. Metrics included interpretation time, time to first fixation on the lesion, lesion dwell time, total gaze-path length, and lung-field coverage ratio. Outcomes were modeled using a linear mixed model, with reading condition as a fixed effect and case and reader as random intercepts. The primary analysis was restricted to true positives (n=96). Results: Concurrent BB display prolonged interpretation time by 4.9 s (p<0.001) and increased lesion dwell time by 1.3 s (p<0.001). Total gaze-path length increased by 2,076 pixels (p<0.001), and lung-field coverage ratio increased by 10.5% (p<0.001). Time to first fixation on the lesion was reduced by 1.3 s (p<0.001). Conclusion: Eye tracking captured measurable alterations in search behavior associated with concurrent BB displays during chest radiograph interpretation. These findings support the feasibility of this approach and highlight the need for larger studies to confirm effects and explore implications across modalities and clinical contexts.

أجرت دراسة تجريبية حديثة استكشاف تأثير أنظمة الكشف المدعومة بالكمبيوتر على تفسير أطباء الأشعة لصور الأشعة السينية للصدر باستخدام تقنية تتبع العين. من خلال تحليل 180 صورة أشعة سينية للصدر، تهدف الدراسة إلى قياس كيفية تأثير ميزات مثل التمييز في الصندوق على البحث البصري. هذه الدراسة مهمة لأنها قد تعزز دقة وكفاءة التقييمات الإشعاعية، مما يحسن في النهاية رعاية المرضى.

Un reciente estudio piloto ha explorado el impacto de los sistemas de detección asistida por computadora en la interpretación de radiografías de tórax por parte de radiólogos, utilizando tecnología de seguimiento ocular. Al analizar 180 radiografías de tórax, la investigación busca cuantificar cómo la búsqueda visual se ve influenciada por características como los resaltados en caja. Este estudio es significativo ya que podría mejorar la precisión y eficiencia de las evaluaciones radiológicas, mejorando en última instancia la atención al paciente.

Une récente étude pilote a exploré l'impact des systèmes de détection assistée par ordinateur sur l'interprétation des radiographies thoraciques par les radiologues, en utilisant la technologie de suivi oculaire. En analysant 180 radiographies thoraciques, la recherche vise à quantifier comment la recherche visuelle est influencée par des éléments tels que les surlignages en boîte. Cette étude est importante car elle pourrait améliorer la précision et l'efficacité des évaluations radiologiques, améliorant ainsi les soins aux patients.

A recent pilot study has explored the impact of computer-aided detection systems on radiologists' interpretation of chest radiographs using eye-tracking technology. By analyzing 180 chest radiographs, the research aims to quantify how visual search is influenced by features like bounding-box highlights. This study is significant as it could enhance the accuracy and efficiency of radiological assessments, ultimately improving patient care.

Eye-Tracking as a Tool to Quantify the Effects of CAD Display on Radiologists' Interpretation of Chest Radiographs

arXiv:2511.15481v1 Announce Type: new 
Abstract: Densely annotated medical image datasets that capture not only diagnostic labels but also the underlying reasoning behind these diagnoses are scarce. Such reasoning-related annotations are essential for developing and evaluating explainable AI (xAI) models that reason similarly to radiologists: making correct predictions for the right reasons. To address this gap, we introduce FunnyNodules, a fully parameterized synthetic dataset designed for systematic analysis of attribute-based reasoning in medical AI models. The dataset generates abstract, lung nodule-like shapes with controllable visual attributes such as roundness, margin sharpness, and spiculation. Target class is derived from a predefined attribute combination, allowing full control over the decision rule that links attributes to the diagnostic class. We demonstrate how FunnyNodules can be used in model-agnostic evaluations to assess whether models learn correct attribute-target relations, to interpret over- or underperformance in attribute prediction, and to analyze attention alignment with attribute-specific regions of interest. The framework is fully customizable, supporting variations in dataset complexity, target definitions, class balance, and beyond. With complete ground truth information, FunnyNodules provides a versatile foundation for developing, benchmarking, and conducting in-depth analyses of explainable AI methods in medical image analysis.

FunnyNodules هو مجموعة بيانات طبية اصطناعية قابلة للتخصيص تم تقديمها حديثًا تهدف إلى تحسين تقييم نماذج الذكاء الاصطناعي القابلة للتفسير (xAI) في التصوير الطبي. تحتوي على صور مشروحة بكثافة تقدم ليس فقط تسميات تشخيصية ولكن أيضًا الأسباب وراء هذه التشخيصات. تتيح هذه المجموعة للباحثين تحليل كيفية تقليد نماذج الذكاء الاصطناعي لعمليات التفكير لدى أطباء الأشعة، مما يضمن توقعات دقيقة بناءً على السمات الصحيحة.

FunnyNodules es un nuevo conjunto de datos médicos sintéticos personalizables diseñado para mejorar la evaluación de modelos de IA explicables (xAI) en imágenes médicas. Presenta imágenes densamente anotadas que no solo proporcionan etiquetas diagnósticas, sino también el razonamiento detrás de estos diagnósticos. Este conjunto de datos permite a los investigadores analizar sistemáticamente cómo los modelos de IA pueden imitar los procesos de razonamiento de los radiólogos, asegurando predicciones precisas basadas en los atributos correctos.

FunnyNodules est un nouvel ensemble de données médicales synthétiques personnalisables conçu pour améliorer l'évaluation des modèles d'IA explicables (xAI) en imagerie médicale. Il présente des images annotées de manière dense qui fournissent non seulement des étiquettes diagnostiques, mais aussi le raisonnement derrière ces diagnostics. Cet ensemble de données permet aux chercheurs d'analyser systématiquement comment les modèles d'IA peuvent imiter les processus de raisonnement des radiologues, garantissant des prédictions précises basées sur les bons attributs.

FunnyNodules is a newly introduced customizable synthetic medical dataset designed to enhance the evaluation of explainable AI (xAI) models in medical imaging. It features densely annotated images that not only provide diagnostic labels but also the reasoning behind these diagnoses. This dataset allows researchers to systematically analyze how AI models can mimic the reasoning processes of radiologists, ensuring accurate predictions based on the right attributes.

FunnyNodules: A Customizable Medical Dataset Tailored for Evaluating Explainable AI

arXiv:2508.13378v3 Announce Type: replace 
Abstract: Small Language Models (SLMs) are a practical option for narrow, workflow-relevant medical imaging utilities where privacy, latency, and cost dominate. We present a governance-ready recipe that combines prompt scaffolds, calibrated abstention, and standards-compliant integration into Picture Archiving and Communication Systems (PACS). Our focus is the assistive task of AP/PA view tagging for chest radiographs. Using four deployable SLMs (Qwen2.5-VL, MiniCPM-V, Gemma 7B, LLaVA 7B) on NIH Chest X-ray, we provide illustrative evidence: reflection-oriented prompts benefit lighter models, whereas stronger baselines are less sensitive. Beyond accuracy, we operationalize abstention, expected calibration error, and oversight burden, and we map outputs to DICOM tags, HL7 v2 messages, and FHIR ImagingStudy. The contribution is a prompt-first deployment framework, an operations playbook for calibration, logging, and change management, and a clear pathway from pilot utilities to reader studies without over-claiming clinical validation. We additionally specify a human-factors RACI, stratified calibration for dataset shift, and an auditable evidence pack to support local governance reviews.

تظهر النماذج اللغوية الصغيرة (SLMs) كأدوات فعالة لمهام محددة في التصوير الطبي، خاصة في البيئات التي تهيمن عليها الخصوصية والكمون والتكلفة. يقدم هذا المقال إطار عمل جاهز للحكومة يجمع بين هياكل المطالبات، والامتناع المعاير، والتكامل المتوافق مع أنظمة أرشفة الصور والتواصل (PACS). يركز البحث على وسم عرض AP/PA للأشعة السينية للصدر، باستخدام أربعة نماذج لغوية صغيرة قابلة للنشر. تشير النتائج إلى أن المطالبات الموجهة للتفكير تفيد النماذج الأخف، بينما تكون النماذج الأقوى أقل حساسية لهذه المطالبات.

Los pequeños modelos de lenguaje (SLMs) están surgiendo como herramientas efectivas para tareas específicas de imagenología médica, especialmente en entornos donde la privacidad, la latencia y el costo son críticos. Este artículo presenta un marco listo para la gobernanza que integra andamiajes de prompts, abstención calibrada y cumplimiento con los sistemas de archivo y comunicación de imágenes (PACS). El enfoque está en el etiquetado de vistas AP/PA para radiografías de tórax, utilizando cuatro SLM desplegables. Los hallazgos indican que los prompts orientados a la reflexión mejoran el rendi…

Les petits modèles de langage (SLMs) émergent comme des outils efficaces pour des tâches spécifiques d'imagerie médicale, en particulier dans des environnements où la confidentialité, la latence et le coût sont critiques. Cet article présente un cadre prêt à la gouvernance qui intègre des échafaudages de prompts, une abstention calibrée et une conformité avec les systèmes d'archivage et de communication d'images (PACS). L'accent est mis sur le marquage de vues AP/PA pour les radiographies thoraciques, en utilisant quatre SLM déployables. Les résultats indiquent que les prompts orientés vers la…

Small Language Models (SLMs) are emerging as effective tools for specific medical imaging tasks, particularly in environments where privacy, latency, and cost are critical. This article presents a governance-ready framework that integrates prompt scaffolds, calibrated abstention, and compliance with Picture Archiving and Communication Systems (PACS). The focus is on AP/PA view tagging for chest radiographs, utilizing four deployable SLMs. The findings indicate that reflection-oriented prompts enhance performance in lighter models, while stronger models show less sensitivity to these prompts.

Eye-Tracking as a Tool to Quantify the Effects of CAD Display on Radiologists' Interpretation of Chest Radiographs

Was this article worth reading? Share it