Artificial intelligence solution to accelerate the acquisition of MRI images: Impact on the therapeutic care in oncology in radiology and radiotherapy departments

IF 1.5 4区医学 Q4 ONCOLOGY Cancer Radiotherapie Pub Date : 2024-06-01 DOI:10.1016/j.canrad.2023.11.004

R. Lemaire , C. Raboutet , T. Leleu , C. Jaudet , L. Dessoude , F. Missohou , Y. Poirier , P.-Y. Deslandes , A. Lechervy , J. Lacroix , I. Moummad , S. Bardet , J. Thariat , D. Stefan , A. Corroyer-Dulmont

{"title":"Artificial intelligence solution to accelerate the acquisition of MRI images: Impact on the therapeutic care in oncology in radiology and radiotherapy departments","authors":"R. Lemaire , C. Raboutet , T. Leleu , C. Jaudet , L. Dessoude , F. Missohou , Y. Poirier , P.-Y. Deslandes , A. Lechervy , J. Lacroix , I. Moummad , S. Bardet , J. Thariat , D. Stefan , A. Corroyer-Dulmont","doi":"10.1016/j.canrad.2023.11.004","DOIUrl":null,"url":null,"abstract":"<div><h3>Purpose</h3><p>MRI is essential in the management of brain tumours. However, long waiting times reduce patient accessibility. Reducing acquisition time could improve access but at the cost of spatial resolution and diagnostic quality. A commercially available artificial intelligence (AI) solution, SubtleMR™, can increase the resolution of acquired images. The objective of this prospective study was to evaluate the impact of this algorithm that halves the acquisition time on the detectability of brain lesions in radiology and radiotherapy.</p></div><div><h3>Material and methods</h3><p>The T1/T2 MRI of 33 patients with brain metastases or meningiomas were analysed. Images acquired quickly have a matrix divided by two which halves the acquisition time. The visual quality and lesion detectability of the AI images were evaluated by radiologists and radiation oncologist as well as pixel intensity and lesions size.</p></div><div><h3>Results</h3><p>The subjective quality of the image is lower for the AI images compared to the reference images. However, the analysis of lesion detectability shows a specificity of 1 and a sensitivity of 0.92 and 0.77 for radiology and radiotherapy respectively. Undetected lesions on the IA image are lesions with a diameter less than 4mm and statistically low average gadolinium-enhancement contrast.</p></div><div><h3>Conclusion</h3><p>It is possible to reduce MRI acquisition times by half using the commercial algorithm to restore the characteristics of the image and obtain good specificity and sensitivity for lesions with a diameter greater than 4mm.</p></div>","PeriodicalId":9504,"journal":{"name":"Cancer Radiotherapie","volume":"28 3","pages":"Pages 251-257"},"PeriodicalIF":1.5000,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Cancer Radiotherapie","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S127832182400060X","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"ONCOLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

Purpose

MRI is essential in the management of brain tumours. However, long waiting times reduce patient accessibility. Reducing acquisition time could improve access but at the cost of spatial resolution and diagnostic quality. A commercially available artificial intelligence (AI) solution, SubtleMR™, can increase the resolution of acquired images. The objective of this prospective study was to evaluate the impact of this algorithm that halves the acquisition time on the detectability of brain lesions in radiology and radiotherapy.

Material and methods

The T1/T2 MRI of 33 patients with brain metastases or meningiomas were analysed. Images acquired quickly have a matrix divided by two which halves the acquisition time. The visual quality and lesion detectability of the AI images were evaluated by radiologists and radiation oncologist as well as pixel intensity and lesions size.

Results

The subjective quality of the image is lower for the AI images compared to the reference images. However, the analysis of lesion detectability shows a specificity of 1 and a sensitivity of 0.92 and 0.77 for radiology and radiotherapy respectively. Undetected lesions on the IA image are lesions with a diameter less than 4 mm and statistically low average gadolinium-enhancement contrast.

Conclusion

It is possible to reduce MRI acquisition times by half using the commercial algorithm to restore the characteristics of the image and obtain good specificity and sensitivity for lesions with a diameter greater than 4 mm.

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

加速磁共振成像图像采集的人工智能解决方案：对放射科和放疗科肿瘤治疗护理的影响。

目的：核磁共振成像对脑肿瘤的治疗至关重要。然而，漫长的等待时间降低了患者的可及性。缩短采集时间可以改善就诊情况，但代价是空间分辨率和诊断质量下降。市售的人工智能（AI）解决方案 SubtleMR™ 可以提高采集图像的分辨率。这项前瞻性研究的目的是评估这种将采集时间减半的算法对放射学和放射治疗中脑部病变可探测性的影响：对 33 名脑转移瘤或脑膜瘤患者的 T1/T2 MRI 进行了分析。快速采集的图像矩阵除以二，采集时间减半。放射科医生和放射肿瘤科医生对 AI 图像的视觉质量和病灶可探测性以及像素强度和病灶大小进行了评估：结果：与参考图像相比，人工智能图像的主观质量较低。然而，对病灶可探测性的分析表明，放射科和放疗科的特异性为 1，灵敏度分别为 0.92 和 0.77。IA 图像上未检测到的病灶是指直径小于 4 毫米且平均钆增强对比度较低的病灶：使用商业算法恢复图像特征，可以将 MRI 采集时间缩短一半，并对直径大于 4 毫米的病变获得良好的特异性和灵敏度。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊

Cancer Radiotherapie 医学-核医学

CiteScore

2.20

自引率

23.10%

发文量

129

审稿时长

63 days

期刊介绍： Cancer/radiothérapie se veut d''abord et avant tout un organe francophone de publication des travaux de recherche en radiothérapie. La revue a pour objectif de diffuser les informations majeures sur les travaux de recherche en cancérologie et tout ce qui touche de près ou de loin au traitement du cancer par les radiations : technologie, radiophysique, radiobiologie et radiothérapie clinique.