Glioblastoma is profoundly heterogeneous in regional microstructure and vasculature. Characterizing the spatial heterogeneity of glioblastoma could lead to more precise treatment. With unsupervised learning techniques, glioblastoma MRI-derived radiomic features have been widely utilized for tumor sub-region segmentation and survival prediction. However, the reliability of algorithm outcomes is often challenged by both ambiguous intermediate process and instability introduced by the randomness of clustering algorithms, especially for data from heterogeneous patients.
In this paper, we propose an adaptive unsupervised learning approach for efficient MRI intra-tumor partitioning and glioblastoma survival prediction. A novel and problem-specific Feature-enhanced Auto-Encoder (FAE) is developed to enhance the representation of pairwise clinical modalities and therefore improve clustering stability of unsupervised learning algorithms such as K-means. Moreover, the entire process is modelled by the Bayesian optimization (BO) technique with a custom loss function that the hyper-parameters can be adaptively optimized in a reasonably few steps. The results demonstrate that the proposed approach can produce robust and clinically relevant MRI sub-regions and statistically significant survival predictions.
Predictive Radiomics for Evaluation of Cancer Immune SignaturE in Glioblastoma: the PRECISE-GBM study
School of Biomedical Engineering & Imaging Sciences, King’s College London, UK（伦敦国王学院生物医学工程与成像科学学院）；Department of Neurosurgery, King’s College Hospital, London, UK（伦敦国王学院医院神经外科部门）；Department of Neuroradiology, Beijing Tiantan Hospital, Beijing, China（北京天坛医院神经放射科部门）；Department of Neuroradiology, King’s College Hospital, London, UK（伦敦国王学院医院神经放射科部门）
Can tumor location on pre-treatment MRI predict likelihood of pseudo-progression versus tumor recurrence in Glioblastoma? A feasibility study
Case Western Reserve University（凯斯西储大学）；Cleveland Clinic（克利夫兰诊所）
胶质母细胞瘤（GBM）管理中的一个重大挑战是在常规治疗后的常规成像中识别肿瘤复发的假进展（PsP），这是一种良性辐射诱导效应。先前的研究已经将肿瘤叶的存在和偏侧性与GBM结果联系起来，表明GBM中的疾病病因和进展可能受到肿瘤位置的影响。因此，在这项可行性研究中，我们试图研究以下问题：初治MRI上的肿瘤位置是否可以提供有关患者发生假性进展与肿瘤复发可能性的早期线索？在这项研究中，分析了74例治疗前胶质母细胞瘤MRI扫描，其中PsP（33例）和肿瘤复发（41例）。首先，Gd-T1 w MRI增强病灶和T2 w/FLAIR病灶周围高信号由专家分割，然后配准到脑图谱。使用来自两种表型的患者，我们通过量化增强病变和病变周围高信号的发生频率，通过对整个人群的体素强度进行平均来构建两个图谱。然后进行差异参与分析，以计算各图谱之间的体素显着差异（p值<0.05）。最后将统计学上显著的聚类映射到结构图谱中，以提供其位置的解剖定位。我们的研究结果表明，肿瘤复发的患者表现出突出的顶叶的初始肿瘤，而PsP患者表现出多灶性分布的初始肿瘤在额叶和颞叶，颞叶和壳核。这些初步结果表明，治疗前病变向大脑某些解剖区域的偏侧化可以提供有关评估MRI扫描上肿瘤复发发生假性进展的可能性的早期线索。
The Rio Hortega University Hospital Glioblastoma dataset: a comprehensive collection of preoperative, early postoperative and recurrence MRI scans (RHUH-GBM)
Radiomic Deformation and Textural Heterogeneity (R-DepTH) Descriptor to characterize Tumor Field Effect: Application to Survival Prediction in Glioblastoma
Patient-specific prediction of glioblastoma growth via reduced order modeling and neural networks
Mathematics Area, mathLab, SISSA（SISSA数学区mathLab）；Dipartimento di Matematica e Fisica “N. Tartaglia”, Università Cattolica del Sacro Cuore（圣心大学N. Tartaglia数学与物理系）；Department of Neurosurgery – Fondazione I.R.C.C.S. Istituto Neurologico Carlo Besta（卡尔·贝斯塔神经科学研究所神经外科部）
Quantifying intra-tumoral genetic heterogeneity of glioblastoma toward precision medicine using MRI and a data-inclusive machine learning algorithm
Georgia Institute of Technology（佐治亚理工学院）；Columbia University Medical Center（哥伦比亚大学医学中心）；Mayo Clinic Arizona（妙佑医疗国际亚利桑那分院）；Barrow Neurological Institute - St. Joseph’s Hospital and Medical Center（巴罗神经学研究所 - 圣约瑟夫医院和医疗中心）；University of Naples “Federico II”（那不勒斯“费德里科二世”大学）
A Modality-Adaptive Method for Segmenting Brain Tumors and Organs-at-Risk in Radiation Therapy Planning
Technical University of Denmark（丹麦技术大学）；Skåne University Hospital（斯科讷大学医院）；Danish Research Centre for Magnetic Resonance（丹麦磁共振研究中心）；Copenhagen University Hospital Hvidovre（哥本哈根大学医院维兹奥勒医院）；Copenhagen University Hospital Rigshospitalet（哥本哈根大学医院国立医院）；University College London（伦敦大学学院）；UCLH NHS Foundation Trust（伦敦大学学院医院NHS基金会信托）；National Hospital for Neurology and Neurosurgery（国立神经病学与神经外科医院）
Segmentation of glioblastomas in early post-operative multi-modal MRI with deep neural networks
SINTEF Digital（SINTEF数字研究所）；Norwegian University of Science and Technology（挪威科技大学）；Amsterdam University Medical Centers（阿姆斯特丹大学医学中心）；Twee Steden Hospital（双城医院）；University College London（伦敦大学学院）
TRACE: A Concept Bottleneck Model for Longitudinal 3D Glioblastoma Response Assessment
Department of Biomedical and Healthcare Data Engineering, Faculty of Engineering, Cairo University（生物医学与健康数据工程系，工程学院，开罗大学）；German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心（DFKI））；University of Oldenburg（奥尔登堡大学）
The added value for MRI radiomics and deep-learning for glioblastoma prognostication compared to clinical and molecular information
Geneva University Hospitals（日内瓦大学医院）；University of Geneva（日内瓦大学）；Lausanne University Hospital（洛桑大学医院）；University of Applied Sciences Western Switzerland (HES-SO)（瑞士西部应用科学与艺术大学 (HES-SO)）；University Hospital Zurich（苏黎世大学医院）；University of Zurich（苏黎世大学）；Cantonal Hospital Aarau（阿劳州立医院）；Basel University Hospital（巴塞尔大学医院）；University of Basel（巴塞尔大学）；University of Lausanne（洛桑大学）；Neurocenter of Southern Switzerland（瑞士南部神经中心）；Ente Ospedaliero Cantonale（提契诺州立医院组织）；Università della Svizzera Italiana（瑞士意大利语区大学）
'A net for everyone': fully personalized and unsupervised neural networks trained with longitudinal data from a single patient
German Cancer Research Center (DKFZ)（德国癌症研究中心）；Heidelberg University（海德堡大学）；University Hospital Essen (AöR)（埃森大学医院）；University Medicine Essen（埃森大学医学院）；German Cancer Consortium (DKTK)（德国癌症联盟）
Explainable histomorphology-based survival prediction of glioblastoma, IDH-wildtype
Fraunhofer Institute for Digital Medicine MEVIS（弗劳恩霍夫数字医学研究所）；Hannover Medical School（汉诺威医学院）；Institute of Neuropathology, RWTH Aachen University Hospital（亚琛工业大学医院神经病理学研究所）；Department of Neuropathology, Center for Pathology, Klinikum Bremen-Mitte（不来梅米特医院病理中心神经病理科）；Bremen Cancer Registry, Leibniz Institute for Prevention Research and Epidemiology - BIPS（不来梅癌症登记处，莱布尼茨预防研究与流行病学研究所 - BIPS）；Leibniz Institute for Prevention Research and Epidemiology - BIPS（莱布尼茨预防研究与流行病学研究所 - BIPS）；Fraunhofer Institute of Optronics, System Technologies and Image Exploitation IOSB（弗劳恩霍夫光学、系统技术与图像 exploitation 研究所 IOSB）；Robert Koch Institute（罗伯特·科赫研究所）；Department of Neurosurgery, RWTH Aachen University Hospital（亚琛工业大学医院神经外科）；Institute of Pathology, RWTH Aachen University Hospital（亚琛工业大学医院病理学研究所）；Institute of Neuropathology, Medical Center - University of Freiburg（弗莱堡大学医学中心神经病理学研究所）；Center for Integrated Oncology Aachen Bonn Cologne Duesseldorf (CIO ABCD)（亚琛-波恩-科隆-杜塞尔多夫综合肿瘤中心 (CIO ABCD)）
Quantum-Enhanced Classification of Brain Tumors Using DNA Microarray Gene Expression Profiles
Department of Physics Yildiz Technical University İstanbul, Türkiye（物理系伊兹密尔技术大学）；Department of Computer Engineering Yildiz Technical University İstanbul, Türkiye（计算机工程系伊兹密尔技术大学）；Computer Engineering Department Bolu Abant Izzet Baysal University Bolu, Türkiye（计算机工程系博卢阿班提·伊泽特·贝亚尔大学）
本文提出基于变分量子分类器的 Deep VQC 模型，利用 54,676 个基因特征的微阵列数据高精度区分四种脑肿瘤与健康样本，性能优于或媲美经典机器学习方法。
Comparison of Machine Learning Classifiers to Predict Patient Survival and Genetics of GBM: Towards a Standardized Model for Clinical Implementation
Memorial Sloan Kettering Cancer Center（纪念斯隆·凯特琳癌症中心）；Sant’Andrea Hospital, La Sapienza University（圣安德烈医院，罗马第一大学）；Bambino Gesù Children's Hospital, IRCCS（耶稣圣婴儿童医院，IRCCS）；Regina Elena National Cancer Institute, IRCCS（雷吉娜·埃琳娜国家癌症研究所，IRCCS）；Castelli Romani Hospital（卡斯特利罗马尼医院）
