Salvato in:
Dettagli Bibliografici
Autori principali: Khoobi, Mahta, von der Stueck, Marc Sebastian, Ordonez, Felix Barajas, Iancu, Anca-Maria, Corban, Eric, Nowak, Julia, Kargaliev, Aleksandar, Perelygina, Valeria, Schott, Anna-Sophie, Santos, Daniel Pinto dos, Kuhl, Christiane, Truhn, Daniel, Nebelung, Sven, Siepmann, Robert
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2510.16070
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910016056852480
author Khoobi, Mahta
von der Stueck, Marc Sebastian
Ordonez, Felix Barajas
Iancu, Anca-Maria
Corban, Eric
Nowak, Julia
Kargaliev, Aleksandar
Perelygina, Valeria
Schott, Anna-Sophie
Santos, Daniel Pinto dos
Kuhl, Christiane
Truhn, Daniel
Nebelung, Sven
Siepmann, Robert
author_facet Khoobi, Mahta
von der Stueck, Marc Sebastian
Ordonez, Felix Barajas
Iancu, Anca-Maria
Corban, Eric
Nowak, Julia
Kargaliev, Aleksandar
Perelygina, Valeria
Schott, Anna-Sophie
Santos, Daniel Pinto dos
Kuhl, Christiane
Truhn, Daniel
Nebelung, Sven
Siepmann, Robert
contents Structured reporting (SR) and artificial intelligence (AI) may transform how radiologists interact with imaging studies. This prospective study (July to December 2024) evaluated the impact of three reporting modes: free-text (FT), structured reporting (SR), and AI-assisted structured reporting (AI-SR), on image analysis behavior, diagnostic accuracy, efficiency, and user experience. Four novice and four non-novice readers (radiologists and medical students) each analyzed 35 bedside chest radiographs per session using a customized viewer and an eye-tracking system. Outcomes included diagnostic accuracy (compared with expert consensus using Cohen's $κ$), reporting time per radiograph, eye-tracking metrics, and questionnaire-based user experience. Statistical analysis used generalized linear mixed models with Bonferroni post-hoc tests with a significance level of ($P \le .01$). Diagnostic accuracy was similar in FT ($κ= 0.58$) and SR ($κ= 0.60$) but higher in AI-SR ($κ= 0.71$, $P < .001$). Reporting times decreased from $88 \pm 38$ s (FT) to $37 \pm 18$ s (SR) and $25 \pm 9$ s (AI-SR) ($P < .001$). Saccade counts for the radiograph field ($205 \pm 135$ (FT), $123 \pm 88$ (SR), $97 \pm 58$ (AI-SR)) and total fixation duration for the report field ($11 \pm 5$ s (FT), $5 \pm 3$ s (SR), $4 \pm 1$ s (AI-SR)) were lower with SR and AI-SR ($P < .001$ each). Novice readers shifted gaze towards the radiograph in SR, while non-novice readers maintained their focus on the radiograph. AI-SR was the preferred mode. In conclusion, SR improves efficiency by guiding visual attention toward the image, and AI-prefilled SR further enhances diagnostic accuracy and user satisfaction.
format Preprint
id arxiv_https___arxiv_org_abs_2510_16070
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Effect of Reporting Mode and Clinical Experience on Radiologists' Gaze and Image Analysis Behavior in Chest Radiography
Khoobi, Mahta
von der Stueck, Marc Sebastian
Ordonez, Felix Barajas
Iancu, Anca-Maria
Corban, Eric
Nowak, Julia
Kargaliev, Aleksandar
Perelygina, Valeria
Schott, Anna-Sophie
Santos, Daniel Pinto dos
Kuhl, Christiane
Truhn, Daniel
Nebelung, Sven
Siepmann, Robert
Computer Vision and Pattern Recognition
Artificial Intelligence
Human-Computer Interaction
Image and Video Processing
H.5.5; H.1.2; I.4.0
Structured reporting (SR) and artificial intelligence (AI) may transform how radiologists interact with imaging studies. This prospective study (July to December 2024) evaluated the impact of three reporting modes: free-text (FT), structured reporting (SR), and AI-assisted structured reporting (AI-SR), on image analysis behavior, diagnostic accuracy, efficiency, and user experience. Four novice and four non-novice readers (radiologists and medical students) each analyzed 35 bedside chest radiographs per session using a customized viewer and an eye-tracking system. Outcomes included diagnostic accuracy (compared with expert consensus using Cohen's $κ$), reporting time per radiograph, eye-tracking metrics, and questionnaire-based user experience. Statistical analysis used generalized linear mixed models with Bonferroni post-hoc tests with a significance level of ($P \le .01$). Diagnostic accuracy was similar in FT ($κ= 0.58$) and SR ($κ= 0.60$) but higher in AI-SR ($κ= 0.71$, $P < .001$). Reporting times decreased from $88 \pm 38$ s (FT) to $37 \pm 18$ s (SR) and $25 \pm 9$ s (AI-SR) ($P < .001$). Saccade counts for the radiograph field ($205 \pm 135$ (FT), $123 \pm 88$ (SR), $97 \pm 58$ (AI-SR)) and total fixation duration for the report field ($11 \pm 5$ s (FT), $5 \pm 3$ s (SR), $4 \pm 1$ s (AI-SR)) were lower with SR and AI-SR ($P < .001$ each). Novice readers shifted gaze towards the radiograph in SR, while non-novice readers maintained their focus on the radiograph. AI-SR was the preferred mode. In conclusion, SR improves efficiency by guiding visual attention toward the image, and AI-prefilled SR further enhances diagnostic accuracy and user satisfaction.
title Effect of Reporting Mode and Clinical Experience on Radiologists' Gaze and Image Analysis Behavior in Chest Radiography
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Human-Computer Interaction
Image and Video Processing
H.5.5; H.1.2; I.4.0
url https://arxiv.org/abs/2510.16070