Review of the Application of Radiomics in Acute Ischemic Stroke

doi:10.3969/j.issn.1673-5765.2023.08.013

Abstract

Abstract: Radiomics, a rapidly expanding field of study, can extract and quantify information from medical images, derive features that reflect lesions, and aid in the resolution of clinical problems. Radiomics based on CT and MRI provides a wide range of potential applications in the diagnosis of acute ischemic stroke (AIS). The workflow of radiomics mainly includes image acquisition, segmentation of regions of interest and volumes of interest, high throughput radiomics feature extraction, statistical analysis, and predictive model development. Radiomics in AIS is primarily used to diagnose stroke and its subtypes, guide therapeutic treatment decisions, and predict the prognosis of AIS. Currently, the use and research of radiomics in AIS are limited by relatively single sequence, lack of comparison with other artificial intelligence technologies, and relatively small sample size of the studies. However, as the technology matures, its clinical application prospects are extensive.

Key words: Radiomics; Acute ischemic stroke; Big data

摘要： 作为一个快速发展的研究领域，影像组学可以提取和量化医学图像中的信息，获取反映病变的特征，帮助解决临床问题。基于CT和MRI的影像组学在急性缺血性卒中（acute ischemic stroke, AIS）的诊断中具有非常广阔的应用前景。影像组学的工作流程主要有图像采集、感兴趣区和感兴趣体积的分割、高通量影像组学特征提取以及统计学分析和预测模型建立。影像组学在AIS中的应用侧重于诊断卒中及其亚型、指导临床治疗决策以及预测AIS的预后等方面。目前，影像组学在AIS中的应用和研究尚存在序列相对单一、缺乏与其他人工智能技术的比较、研究样本量相对较小等局限性，但随着技术的成熟，其临床应用前景广阔。

关键词: 影像组学; 急性缺血性卒中; 大数据

FAN Ping, YUE Kuitao, LI Aiyuan, ZHAO Zhe, XIE Hai, WU Chunyan ( Contributed equally). . Review of the Application of Radiomics in Acute Ischemic Stroke[J]. Chinese Journal of Stroke, 2023, 18(8): 952-957.

范萍, 岳奎涛, 李爱媛, 赵喆, 谢海, 吴春艳（第一作者）. 影像组学在急性缺血性卒中中的应用进展[J]. 中国卒中杂志, 2023, 18(8): 952-957.

References

[1] FEIGIN V L，BRAININ M，NORRVING B，et al. World Stroke Organization（WSO）：global stroke fact sheet 2022[J]. Int J Stroke，2022，17（1）：18-29.
[2] YIP S S，AERTS H J. Applications and limitations of radiomics[J]. Phys Med Biol，2016，61（13）：150-166.
[3] SOUN J E，CHOW D S，NAGAMINE M，et al. Artificial intelligence and acute stroke imaging[J]. Am J Neuroradiol，2021，42（1）：2-11.
[4] MAYERHOEFER M E，MATERKA A，LANGS G，et al. Introduction to radiomics[J]. J Nucl Med，2020，61（4）：488-495.
[5] BENELLI M，BARUCCI A，ZOPPETTI N，et al. Comprehensive analysis of radiomic datasets by RadAR[J]. Cancer Res，2020，80（15）：3170-3174.
[6] SHAFAAT O，BERNSTOCK J D，SHAFAAT A，et al. Leveraging artificial intelligence in ischemic stroke imaging[J]. J Neuroradiol，2022，49（4）：343-351.
[7] BOGOWICZ M，RIESTERER O，STARK L S，et al. Comparison of PET and CT radiomics for prediction of local tumor control in head and neck squamous cell carcinoma[J]. Acta Oncol，2017，56（11）：1531-1536.
[8] GUO Y W，YANG Y J，CAO F Q，et al. A focus on the role of DSC-PWI dynamic radiomics features in diagnosis and outcome prediction of ischemic stroke[J/OL]. J Clin Med，2022，11（18）：5364[2022-08-09]. https://doi.org/10.3390/jcm11185364.
[9] QUAN G M，BAN R R，REN J L，et al. FLAIR and ADC image-based radiomics features as predictive biomarkers of unfavorable outcome in patients with acute ischemic stroke[J/OL]. Front Neurosci，2021，15：730879[2022-08-09]. https://doi.org/10.3389/fnins.2021.730879.
[10] TRAVERSO A，WEE L，DEKKER A，et al. Repeatability and reproducibility of radiomic features：a systematic review[J]. Int J Radiat Oncol Biol Phys，2018，102（4）：1143-1158.
[11] SHETH S A，GIANCARDO L，COLASURDO M，et al. Machine learning and acute stroke imaging[J]. J Neurointerv Surg，2023，15（2）：195-199.
[12] CHAVVA I R，CRAWFORD A L，MAZUREK M H，et al. Deep learning applications for acute stroke management[J]. Ann Neurol，2022，92（4）：574-587.
[13] MOKLI Y，PFAFF J，DOS SANTOS D P，et al. Computer-aided imaging analysis in acute ischemic stroke - background and clinical applications[J/OL]. Neurol Res Pract，2019，1：23[2022-08-09]. https://doi.org/10.1186/s42466-019-0028-y.
[14] STIB M T，VASQUEZ J，DONG M P，et al. Detecting large vessel occlusion at multiphase CT angiography by using a deep convolutional neural network[J]. Radiology，2020，297（3）：640-649.
[15] TAKAHASHI N，LEE Y，TSAI D Y，et al. An automated detection method for the MCA dot sign of acute stroke in unenhanced CT[J]. Radiol Phys Technol，2014，7（1）：79-88.
[16] ORTIZ-RAMÓN R，VALDÉS HERNÁNDEZ M D C，GONZÁLEZ-CASTRO V，et al. Identification of the presence of ischaemic stroke lesions by means of texture analysis on brain magnetic resonance images[J/OL]. Comput Med Imaging Graph，2019，74：12-24[2022-08-09]. https://doi.org/10.1016/j.compmedimag.2019.02.006.
[17] WU O，WINZECK S，GIESE A K，et al. Big data approaches to phenotyping acute ischemic stroke using automated lesion segmentation of multi-center magnetic resonance imaging data[J]. Stroke，2019，50（7）：1734-1741.
[18] CHEN Y，HE Y W，JIANG Z Y，et al. Ischemic stroke subtyping method combining convolutional neural network and radiomics[J]. J Xray Sci Technol，2023，31（2）：223-235.
[19] 吴岩峰，刘庆萍，丁红. 提高急性缺血性卒中静脉溶栓有效性和安全性的研究进展[J]. 中国卒中杂志，2016，11（2）：126-130.
WU Y F，LIU Q P，DING H. Study progress of improvement of safety and efifcacy of intravenous thrombolysis on acute ischaemic stroke[J]. Chin J Stroke，2016，11（2）：126-130.
[20] REN H H，SONG H J，WANG J J，et al. A clinical-radiomics model based on noncontrast computed tomography to predict hemorrhagic transformation after stroke by machine learning：a multicenter study[J/OL]. Insights Imaging，2023，14（1）：52[2022-08-10]. https://doi.org/10.1186/s13244-023-01399-5.
[21] MENG Y C，WANG H R，WU C F，et al. Prediction model of hemorrhage transformation in patient with acute ischemic stroke based on multiparametric MRI radiomics and machine learning[J/OL]. Brain Sci，2022，12（7）：858[2022-08-09]. https://doi.org/10.3390/brainsci12070858.
[22] ERMINE C M，BIVARD A，PARSONS M W，et al. The ischemic penumbra：from concept to reality[J]. Int J Stroke，2021，16（5）：497-509.
[23] ZHANG R，ZHU L，ZHU Z Q，et al. Apparent diffusion coefficient map based radiomics model in identifying the ischemic penumbra in acute ischemic stroke[J]. Ann Palliat Med，2020，9（5）：2684-2692.
[24] WANG K，SHOU Q Y，MA S J，et al. Deep learning detection of penumbral tissue on arterial spin labeling in stroke[J]. Stroke，2020，51（2）：489-497.
[25] QIU W，KUANG H，NAIR J，et al. Radiomics-based intracranial thrombus features on CT and CTA predict recanalization with intravenous Alteplase in patients with acute ischemic stroke[J]. Am J Neuroradiol，2019，40（1）：39-44.
[26] WANG H，SUN Y，GE Y Q，et al. A Clinical-radiomics nomogram for functional outcome predictions in ischemic stroke[J]. Neurol Ther，2021，10（2）：819-832.
[27] HAN N N，ZHANG X B，ZHANG Y，et al. Nomogram to predict unfavorable outcome of endovascular thrombectomy for large ischemic core[J]. Ann Clin Transl Neurol，2023，10（8）：1353-1364.
[28] ZHOU Y R，WU D，YAN S，et al. Feasibility of a clinical-radiomics model to predict the outcomes of acute ischemic stroke[J]. Korean J Radiol，2022，23（8）：811-820.
[29] BETROUNI N，YASMINA M，BOMBOIS S，et al. Texture features of magnetic resonance images：an early marker of post-stroke cognitive impairment[J]. Transl Stroke Res，2020，11（4）：643-652.
[30] OGE D D，TOPCUOGLU M A，ARSAVA E M. Apparent diffusion coefficient signature of ischemic tissue predicts neurological progression in isolated pontine infarcts[J]. Eur Stroke J，2022，7（1）：66-70.
[31] WANG H，SUN Y，ZHU J，et al. Diffusion-weighted imaging-based radiomics for predicting 1-year ischemic stroke recurrence[J/OL]. Front Neurol，2022，13：1012896[2022-08-09]. https://doi.org/10.3389/fneur.2022.1012896.