Tailored Intraoperative MRI Strategies in High-Grade Glioma Surgery: A Machine Learning-Based Radiomics Model Highlights Selective Benefits

被引:2
|
作者
Aichholzer, Martin [1 ]
Rauch, Philip [1 ,5 ,6 ,7 ]
Kastler, Lucia [1 ]
Pichler, Josef [2 ]
Aufschnaiter-Hiessboeck, Kathrin [1 ]
Ruiz-Navarro, Francisco [1 ]
Aspalter, Stefan [1 ]
Hartl, Saskia [1 ]
Schimetta, Wolfgang [3 ]
Boehm, Petra [1 ]
Manakov, Ilja [4 ]
Thomae, Wolfgang [1 ]
Gmeiner, Matthias [1 ]
Gruber, Andreas [1 ]
Stefanits, Harald [1 ]
机构
[1] Kepler Univ Hosp, Johannes Kepler Univ, Dept Neurosurg, Linz, Austria
[2] Kepler Univ Hosp, Inst Neurooncol, Linz, Austria
[3] Johannes Kepler Univ Linz, Inst Stat, Linz, Austria
[4] ImFusion GmbH, Munich, Germany
[5] Kepler Univ Hosp, Dept Neurosurg, Wagner Jauregg Weg 15, A-4020 Linz, Austria
[6] Johannes Kepler Univ Linz, Wagner Jauregg Weg 15, A-4020 Linz, Austria
[7] Alteberger Str 69, A-4040 Linz, Austria
关键词
Glioma; Intraoperative MRI; Machine learning; Neural network; Personalized medicine; Radiomics; 5-ALA; 5-AMINOLEVULINIC ACID; FLUORESCENCE;
D O I
10.1227/ons.0000000000001023
中图分类号
R74 [神经病学与精神病学];
学科分类号
摘要
BACKGROUND AND OBJECTIVES: In high-grade glioma (HGG) surgery, intraoperative MRI (iMRI) has traditionally been the gold standard for maximizing tumor resection and improving patient outcomes. However, recent Level 1 evidence juxtaposes the efficacy of iMRI and 5-aminolevulinic acid (5-ALA), questioning the continued justification of iMRI because of its associated costs and extended surgical duration. Nonetheless, drawing from our clinical observations, we postulated that a subset of intricate HGGs may continue to benefit from the adjunctive application of iMRI. METHODS: In a prospective study of 73 patients with HGG, 5-ALA was the primary technique for tumor delineation, complemented by iMRI to detect residual contrast-enhanced regions. Suboptimal 5-ALA efficacy was defined when (1) iMRI detected contrast-enhanced remnants despite 5-ALA's indication of a gross total resection or (2) surgeons observed residual fluorescence, contrary to iMRI findings. Radiomic features from preoperative MRIs were extracted using a U2-Net deep learning algorithm. Binary logistic regression was then used to predict compromised 5-ALA performance. RESULTS: Resections guided solely by 5-ALA achieved an average removal of 93.14% of contrast-enhancing tumors. This efficacy increased to 97% with iMRI integration, albeit not statistically significant. Notably, for tumors with suboptimal 5-ALA performance, iMRI's inclusion significantly improved resection outcomes (P-value: .00013). The developed deep learning-based model accurately pinpointed these scenarios, and when enriched with radiomic parameters, showcased high predictive accuracy, as indicated by a Nagelkerke R-2 of 0.565 and a receiver operating characteristic of 0.901. CONCLUSION: Our machine learning-driven radiomics approach predicts scenarios where 5-ALA alone may be suboptimal in HGG surgery compared with its combined use with iMRI. Although 5-ALA typically yields favorable results, our analyses reveal that HGGs characterized by significant volume, complex morphology, and left-sided location compromise the effectiveness of resections relying exclusively on 5-ALA. For these intricate cases, we advocate for the continued relevance of iMRI.
引用
收藏
页码:645 / 654
页数:10
相关论文
共 49 条
  • [31] Assessing the risk of high-grade squamous intraepithelial lesions (HSIL+) in women with LSIL biopsies: a machine learning-based study
    Dongmei Li
    Zhichao Wang
    Yan Liu
    Meiyuan Zhou
    Bo Xia
    Lin Zhang
    Keming Chen
    Yong Zeng
    Infectious Agents and Cancer, 19 (1)
  • [32] A FULLY AUTOMATED MULTI-TASK MACHINE LEARNING PROGNOSTIC MODEL INTEGRATING RADIOMICS AND CLINICAL DATA TO PREDICT OUTCOMES IN HIGH-GRADE PROSTATE CANCER
    Touma, Nawar
    Larose, Maxence
    Brodeur, Raphael
    Desroches, Felix
    Bedard-Tremblay, Daphnee
    Raymond, Nicolas
    Leblanc, Danahe
    Rasekh, Fatemeh
    Hovington, Helene
    Neveu, Bertrand
    Vallieres, Martin
    Archambault, Louis
    Pouliot, Frederic
    JOURNAL OF UROLOGY, 2024, 211 (05): : E107 - E107
  • [33] Deriving quantitative information from multiparametric MRI via Radiomics: Evaluation of the robustness and predictive value of radiomic features in the discrimination of low-grade versus high-grade gliomas with machine learning
    Ubaldi, Leonardo
    Saponaro, Sara
    Giuliano, Alessia
    Talamonti, Cinzia
    Retico, Alessandra
    PHYSICA MEDICA-EUROPEAN JOURNAL OF MEDICAL PHYSICS, 2023, 107
  • [34] Machine Learning-Based Integration Develops a Pyroptosis-Related lncRNA Model to Enhance the Predicted Value of Low-Grade Glioma Patients
    Wu, Jie
    Lu, Lichun
    Wang, Chen
    Jiang, Feng
    JOURNAL OF ONCOLOGY, 2022, 2022
  • [35] On differentiation between vasogenic edema and non-enhancing tumor in high-grade glioma patients using a support vector machine classifier based upon pre and post-surgery MRI images
    Sengupta, Anirban
    Agarwal, Sumeet
    Gupta, Pradeep Kumar
    Ahlawat, Sunita
    Patir, Rana
    Gupta, Rakesh Kumar
    Singh, Anup
    EUROPEAN JOURNAL OF RADIOLOGY, 2018, 106 : 199 - 208
  • [36] Machine learning-based survival model optimizes the outcome prediction in high-grade T1 bladder carcinoma: Improving selection of suitable candidates for timely radical cystectomy
    Henriquez, J. D. Subiela
    Krajewski, W.
    Gonzalez-Padilla, D. A.
    Basile, G.
    Moschini, M.
    Montorsi, F.
    Aumatell, J.
    Gallioli, A.
    Minguez, C.
    Rivas, J. Gomez
    Nowak, L.
    Contieri, R.
    D', Andrea D.
    Afferi, L.
    Pradere, B.
    Soria, F.
    Mertens, L. S.
    Tully, K.
    Cimadamore, A.
    Laukhtina, E.
    Szydelko, T.
    Dos Santos, V. Gomez
    Cidre, M. A. Jimenez
    Revilla, F. J. Burgos
    EUROPEAN UROLOGY, 2023, 83 : S399 - S400
  • [37] Combined structural and perfusion MRI enhanced by machine learning may outperform standalone modalities and radiological expertise in high-grade glioma surveillance: A proof-of-concept study.
    Roettger, Diana
    Siakallis, Loizos
    Sudre, Carole
    Panovska-Griffiths, Jasmina
    Mulholland, Paul
    Thorne, Lewis
    Shaikh, Faiq
    Bisdas, Sotirios
    JOURNAL OF CLINICAL ONCOLOGY, 2020, 38 (15)
  • [38] Fuhrman nuclear grade prediction of clear cell renal cell carcinoma: influence of volume of interest delineation strategies on machine learning-based dynamic enhanced CT radiomics analysis
    Shiwei Luo
    Ruili Wei
    Songlin Lu
    Shengsheng Lai
    Jialiang Wu
    Zhe Wu
    Xinrui Pang
    Xinhua Wei
    Xinqing Jiang
    Xin Zhen
    Ruimeng Yang
    European Radiology, 2022, 32 : 2340 - 2350
  • [39] Fuhrman nuclear grade prediction of clear cell renal cell carcinoma: influence of volume of interest delineation strategies on machine learning-based dynamic enhanced CT radiomics analysis
    Luo, Shiwei
    Wei, Ruili
    Lu, Songlin
    Lai, Shengsheng
    Wu, Jialiang
    Wu, Zhe
    Pang, Xinrui
    Wei, Xinhua
    Jiang, Xinqing
    Zhen, Xin
    Yang, Ruimeng
    EUROPEAN RADIOLOGY, 2022, 32 (04) : 2340 - 2350
  • [40] Development of a machine learning-based model for predicting positive margins in high-grade squamous intraepithelial lesion (HSIL) treatment by Cold Knife Conization(CKC): a single-center retrospective study
    Zhang, Lin
    Zheng, Yahong
    Lei, Lingyu
    Zhang, Xufeng
    Yang, Jing
    Zeng, Yong
    Chen, Keming
    BMC WOMENS HEALTH, 2024, 24 (01)