Scholarlink

Background <p>There are many challenges and opportunities in the clinical deployment of AI tools in radiology. The current study describes a radiology software platform called NeoMedSys that can enable efficient deployment and refinements of AI models. We evaluated the feasibility and effectiveness of running NeoMedSys for three months in real-world clinical settings and focused on improving the performance of an in-house developed AI model (VIOLA-AI) designed for intracranial hemorrhage (ICH) detection.</p> Methods <p>NeoMedSys integrates tools for deploying, testing, and optimizing AI models with a web-based medical image viewer, annotation system, and hospital-wide radiology information systems. A prospective pragmatic investigation was deployed using clinical cases of patients presenting to the largest Emergency Department in Norway (site-1) with suspected traumatic brain injury (TBI) or patients with suspected stroke (site-2). We assessed ICH classification performance as VIOLA-AI encountered new data and underwent pre-planned model retraining. Performance metrics included sensitivity, specificity, accuracy, and the area under the receiver operating characteristic curve (AUC).</p> Results <p>NeoMedSys facilitated iterative improvements in the AI model, significantly enhancing its diagnostic accuracy. Automated bleed detection and segmentation were reviewed in near real-time to facilitate re-training VIOLA-AI. The iterative refinement process yielded a marked improvement in classification sensitivity, rising to 90.3% (from 79.2%), and specificity that reached 89.3% (from 80.7%). The bleed detection ROC analysis for the entire sample demonstrated a high area-under-the-curve (AUC) of 0.949 (from 0.873). Model refinement stages were associated with notable gains, highlighting the value of real-time radiologist feedback.</p> Discussion <p>The NeoMedSys platform provided the means to evaluate and improve upon the bleed detection VIOLA-AI tool, by using prospective data collection and near real-time radiological review of incoming cases. The results of this pragmatic deployment demonstrate there is clinical value in fine-tuning an established deep-learning image analysis tool to account for local data sources and conditions. Iterative clinical feedback improved VIOLA-AI performance and informed on NeoMedSys user-experience. Ongoing efforts are to extend NeoMedSys to support a broader range of modalities, AI models, and patient groups. This in-house approach has fostered a broader interest and enthusiasm to adopt AI solutions into our clinical workflows.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Examining deployment and refinement of the VIOLA-AI intracranial hemorrhage model using an interactive NeoMedSys platform

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年8月3日

查看全文
  • Qinghui Liu,
  • Jon E. Nesvold,
  • Hanna Raaum,
  • Elakkyen Murugesu,
  • Martin Røvang,
  • Bradley J. Maclntosh,
  • Atle Bjørnerud,
  • Karoline Skogen

摘要

Background

There are many challenges and opportunities in the clinical deployment of AI tools in radiology. The current study describes a radiology software platform called NeoMedSys that can enable efficient deployment and refinements of AI models. We evaluated the feasibility and effectiveness of running NeoMedSys for three months in real-world clinical settings and focused on improving the performance of an in-house developed AI model (VIOLA-AI) designed for intracranial hemorrhage (ICH) detection.

Methods

NeoMedSys integrates tools for deploying, testing, and optimizing AI models with a web-based medical image viewer, annotation system, and hospital-wide radiology information systems. A prospective pragmatic investigation was deployed using clinical cases of patients presenting to the largest Emergency Department in Norway (site-1) with suspected traumatic brain injury (TBI) or patients with suspected stroke (site-2). We assessed ICH classification performance as VIOLA-AI encountered new data and underwent pre-planned model retraining. Performance metrics included sensitivity, specificity, accuracy, and the area under the receiver operating characteristic curve (AUC).

Results

NeoMedSys facilitated iterative improvements in the AI model, significantly enhancing its diagnostic accuracy. Automated bleed detection and segmentation were reviewed in near real-time to facilitate re-training VIOLA-AI. The iterative refinement process yielded a marked improvement in classification sensitivity, rising to 90.3% (from 79.2%), and specificity that reached 89.3% (from 80.7%). The bleed detection ROC analysis for the entire sample demonstrated a high area-under-the-curve (AUC) of 0.949 (from 0.873). Model refinement stages were associated with notable gains, highlighting the value of real-time radiologist feedback.

Discussion

The NeoMedSys platform provided the means to evaluate and improve upon the bleed detection VIOLA-AI tool, by using prospective data collection and near real-time radiological review of incoming cases. The results of this pragmatic deployment demonstrate there is clinical value in fine-tuning an established deep-learning image analysis tool to account for local data sources and conditions. Iterative clinical feedback improved VIOLA-AI performance and informed on NeoMedSys user-experience. Ongoing efforts are to extend NeoMedSys to support a broader range of modalities, AI models, and patient groups. This in-house approach has fostered a broader interest and enthusiasm to adopt AI solutions into our clinical workflows.