1
|
Nacul Mora NG, Akkurt BH, Kasap D, Blömer D, Heindel W, Mannil M, Musigmann M. Comparison of MRI Sequences to Predict ATRX Status Using Radiomics-Based Machine Learning. Diagnostics (Basel) 2023; 13:2216. [PMID: 37443610 DOI: 10.3390/diagnostics13132216] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/30/2023] [Revised: 06/23/2023] [Accepted: 06/26/2023] [Indexed: 07/15/2023] Open
Abstract
ATRX is an important molecular marker according to the 2021 WHO classification of adult-type diffuse glioma. We aim to predict the ATRX mutation status non-invasively using radiomics-based machine learning models on MRI and to determine which MRI sequence is best suited for this purpose. In this retrospective study, we used MRI images of patients with histologically confirmed glioma, including the sequences T1w without and with the administration of contrast agent, T2w, and the FLAIR. Radiomics features were extracted from the corresponding MRI images by hand-delineated regions of interest. Data partitioning into training data and independent test data was repeated 100 times to avoid random effects. Feature preselection and subsequent model development were performed using Lasso regression. The T2w sequence was found to be the most suitable and the FLAIR sequence the least suitable for predicting ATRX mutations using radiomics-based machine learning models. For the T2w sequence, our seven-feature model developed with Lasso regression achieved a mean AUC of 0.831, a mean accuracy of 0.746, a mean sensitivity of 0.772, and a mean specificity of 0.697. In conclusion, for the prediction of ATRX mutation using radiomics-based machine learning models, the T2w sequence is the most suitable among the commonly used MRI sequences.
Collapse
Affiliation(s)
- Nabila Gala Nacul Mora
- Clinic for Radiology, University of Münster and University Hospital Münster Muenster, Albert-Schweitzer-Campus 1, 48149 Muenster, Germany
| | - Burak Han Akkurt
- Clinic for Radiology, University of Münster and University Hospital Münster Muenster, Albert-Schweitzer-Campus 1, 48149 Muenster, Germany
| | - Dilek Kasap
- Clinic for Radiology, University of Münster and University Hospital Münster Muenster, Albert-Schweitzer-Campus 1, 48149 Muenster, Germany
| | - David Blömer
- Clinic for Radiology, University of Münster and University Hospital Münster Muenster, Albert-Schweitzer-Campus 1, 48149 Muenster, Germany
| | - Walter Heindel
- Clinic for Radiology, University of Münster and University Hospital Münster Muenster, Albert-Schweitzer-Campus 1, 48149 Muenster, Germany
| | - Manoj Mannil
- Clinic for Radiology, University of Münster and University Hospital Münster Muenster, Albert-Schweitzer-Campus 1, 48149 Muenster, Germany
| | - Manfred Musigmann
- Clinic for Radiology, University of Münster and University Hospital Münster Muenster, Albert-Schweitzer-Campus 1, 48149 Muenster, Germany
| |
Collapse
|
2
|
Kiesel B, Freund J, Reichert D, Wadiura L, Erkkilae MT, Woehrer A, Hervey-Jumper S, Berger MS, Widhalm G. 5-ALA in Suspected Low-Grade Gliomas: Current Role, Limitations, and New Approaches. Front Oncol 2021; 11:699301. [PMID: 34395266 PMCID: PMC8362830 DOI: 10.3389/fonc.2021.699301] [Citation(s) in RCA: 22] [Impact Index Per Article: 7.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/23/2021] [Accepted: 07/19/2021] [Indexed: 11/13/2022] Open
Abstract
Radiologically suspected low-grade gliomas (LGG) represent a special challenge for the neurosurgeon during surgery due to their histopathological heterogeneity and indefinite tumor margin. Therefore, new techniques are required to overcome these current surgical drawbacks. Intraoperative visualization of brain tumors with assistance of 5-aminolevulinic acid (5-ALA) induced protoporphyrin IX (PpIX) fluorescence is one of the major advancements in the neurosurgical field in the last decades. Initially, this technique was exclusively applied for fluorescence-guided surgery of high-grade glioma (HGG). In the last years, the use of 5-ALA was also extended to other indications such as radiologically suspected LGG. Here, we discuss the current role of 5-ALA for intraoperative visualization of focal malignant transformation within suspected LGG. Furthermore, we discuss the current limitations of the 5-ALA technology in pure LGG which usually cannot be visualized by visible fluorescence. Finally, we introduce new approaches based on fluorescence technology for improved detection of pure LGG tissue such as spectroscopic PpIX quantification fluorescence lifetime imaging of PpIX and confocal microscopy to optimize surgery.
Collapse
Affiliation(s)
- Barbara Kiesel
- Department of Neurosurgery, Medical University of Vienna, Vienna, Austria
| | - Julia Freund
- Department of Neurosurgery, Medical University of Vienna, Vienna, Austria
| | - David Reichert
- Center for Medical Physics and Biomedical Engineering, Medical University of Vienna, Vienna, Austria.,Christian Doppler Laboratory OPTRAMED, Medical University of Vienna, Vienna, Austria
| | - Lisa Wadiura
- Department of Neurosurgery, Medical University of Vienna, Vienna, Austria
| | - Mikael T Erkkilae
- Center for Medical Physics and Biomedical Engineering, Medical University of Vienna, Vienna, Austria
| | - Adelheid Woehrer
- Department of Neurology, Institute for Neuropathology and Neurochemistry, Medical University of Vienna, Vienna, Austria
| | - Shawn Hervey-Jumper
- Department of Neurological Surgery, University of California San Francisco (UCSF), San Francisco, CA, United States
| | - Mitchel S Berger
- Department of Neurological Surgery, University of California San Francisco (UCSF), San Francisco, CA, United States
| | - Georg Widhalm
- Department of Neurosurgery, Medical University of Vienna, Vienna, Austria
| |
Collapse
|
3
|
Petridis PD, Horenstein C, Pereira B, Wu P, Samanamud J, Marie T, Boyett D, Sudhakar T, Sheth SA, McKhann GM, Sisti MB, Bruce JN, Canoll P, Grinband J. BOLD Asynchrony Elucidates Tumor Burden in IDH-Mutated Gliomas. Neuro Oncol 2021; 24:78-87. [PMID: 34214170 DOI: 10.1093/neuonc/noab154] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/20/2023] Open
Abstract
BACKGROUND Gliomas comprise the most common type of primary brain tumor, are highly invasive, and often fatal. IDH-mutated gliomas are particularly challenging to image and there is currently no clinically accepted method for identifying the extent of tumor burden in these neoplasms. This uncertainty poses a challenge to clinicians who must balance the need to treat the tumor while sparing healthy brain from iatrogenic damage. The purpose of this study was to investigate the feasibility of using resting-state blood oxygen level dependent (BOLD) functional magnetic resonance imaging (fMRI) to detect glioma-related asynchrony in vascular dynamics for distinguishing tumor from healthy brain. METHODS Twenty-four stereotactically localized biopsies were obtained during open surgical resection from ten treatment-naïve patients with IDH-mutated gliomas who received standard of care preoperative imaging as well as echo-planar resting-state BOLD fMRI. Signal intensity for BOLD asynchrony and standard of care imaging was compared to cell counts of total cellularity (H&E), tumor density (IDH1 & Sox2), cellular proliferation (Ki67), and neuronal density (NeuN), for each corresponding sample. RESULTS BOLD asynchrony was directly related to total cellularity (H&E, p = 4 x 10 -5), tumor density (IDH1, p = 4 x 10 -5; Sox2, p = 3 x 10 -5), cellular proliferation (Ki67, p = 0.002), and as well as inversely related to neuronal density (NeuN, p = 1 x 10 -4). CONCLUSIONS Asynchrony in vascular dynamics, as measured by resting-state BOLD fMRI, correlates with tumor burden and provides a radiographic delineation of tumor boundaries in IDH-mutated gliomas.
Collapse
Affiliation(s)
- Petros D Petridis
- Vagelos College of Physicians & Surgeons, Columbia University, New York, New York USA.,Department of Psychiatry, New York University, New York, New York, USA
| | - Craig Horenstein
- Department of Radiology, School of Medicine at Hofstra/Northwell, Manhasset, New York USA
| | - Brianna Pereira
- Vagelos College of Physicians & Surgeons, Columbia University, New York, New York USA
| | - Peter Wu
- Vagelos College of Physicians & Surgeons, Columbia University, New York, New York USA
| | - Jorge Samanamud
- Department of Neurological Surgery, Columbia University, New York, New York USA
| | - Tamara Marie
- Department of Pediatrics Oncology, Columbia University, New York, New York USA
| | - Deborah Boyett
- Department of Neurological Surgery, Columbia University, New York, New York USA
| | - Tejaswi Sudhakar
- Department of Neurological Surgery, Columbia University, New York, New York USA
| | - Sameer A Sheth
- Department of Neurological Surgery, Baylor College of Medicine, Houston, Texas, USA
| | - Guy M McKhann
- Department of Neurological Surgery, Columbia University, New York, New York USA
| | - Michael B Sisti
- Department of Neurological Surgery, Columbia University, New York, New York USA
| | - Jeffrey N Bruce
- Department of Neurological Surgery, Columbia University, New York, New York USA
| | - Peter Canoll
- Department of Pathology & Cell Biology, Columbia University, New York, New York USA
| | - Jack Grinband
- Department of Radiology, Columbia University, New York, New York, USA.,Department of Psychiatry, Columbia University, New York, New York, USA
| |
Collapse
|
4
|
Abstract
PURPOSE OF REVIEW Low-grade gliomas (LGG) are a group of primary brain tumors that arise from supporting glial cells. They are characterized by a mutation in the isocitrate dehydrogenase (IDH) enzyme and include astrocytomas and oligodendrogliomas. They usually affect young adults, and their main treatment consists of surgical resection, followed by radiation and chemotherapy in selected patients. This article reviews recent research on the clinical and molecular aspects of the disease and innovative therapeutic modalities in the process. RECENT FINDINGS Newly identified clinical and molecular features are currently used in the classification of LGG and applied in treatment-planning decisions. Advanced studies on the cellular level have an advanced understanding of the metabolic effects induced by IDH mutations, offering opportunities for specific targeted therapies that may improve patient outcomes. Such findings may lead to a paradigm shift in the treatment of these tumors. Although LGG are sensitive to radiation and chemotherapy, these therapies are not curative, and patient survival remains limited, raising the need for more creative and effective interventions.
Collapse
Affiliation(s)
- Gilbert Youssef
- Pappas Center for Neuro-Oncology, Department of Neurology, Massachusetts General Hospital, Boston, MA, USA
| | - Julie J Miller
- Pappas Center for Neuro-Oncology, Department of Neurology, Massachusetts General Hospital, Boston, MA, USA.
| |
Collapse
|
5
|
Eichberg DG, Di L, Morell AA, Shah AH, Semonche AM, Chin CN, Bhatia RG, Jamshidi AM, Luther EM, Komotar RJ, Ivan ME. Incidence of high grade gliomas presenting as radiographically non-enhancing lesions: experience in 111 surgically treated non-enhancing gliomas with tissue diagnosis. J Neurooncol 2020; 147:671-679. [PMID: 32221785 DOI: 10.1007/s11060-020-03474-z] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/14/2020] [Accepted: 03/23/2020] [Indexed: 02/03/2023]
Abstract
PURPOSE Although non-enhancing lesions suspicious for glioma are usually assumed to be low grade glioma (LGG), some high grade glioma (HGG) do not enhance, which may lead to a delay in biopsy and/or resection, diagnosis, and treatment initiation. Thus, there is a clear need for a large-sample study that quantifies the rate of malignant, non-enhancing gliomas. METHODS We retrospectively reviewed our series of 561 consecutive surgically treated gliomas with tissue diagnosis, 111 of which were non-enhancing, to determine the prevalence of high-grade histology in radiographically presumed LGG. Relative expression of tumor markers were also reported for non-enhancing lesions to investigate genetic correlates. RESULTS We identified 561 surgically treated gliomas with tissue diagnosis from August 2012 to July 2018 and found that 111 patients (19.8%) demonstrated non-enhancing lesions suspicious for glioma on preoperative MRI. Thirty-one (27.9%) of the non-enhancing lesions were classified as HGGs (WHO Grade III or IV). Non-enhancing lesions were four times more likely to be HGG in patients older than 60 years than patients younger than 35 years (41.2% vs. 11.4%, Pearson Chi2 p < 0.001). Binomial logistic regression showed a significant inverse effect of age on the presence of IDH mutation in non-enhancing HGGs (p = 0.007). CONCLUSION A clinically significant proportion (27.9%) of non-enhancing lesions were found to be HGG on final pathologic diagnosis. Thus, in patients with good functional and health status, especially those older than 60 years, we recommend obtaining tissue diagnosis of all lesions suspected to be glioma, even those that are non-enhancing, to guide diagnosis as well as early initiation of chemotherapy and radiation therapy.
Collapse
Affiliation(s)
- Daniel G Eichberg
- Department of Neurological Surgery, University of Miami Miller School of Medicine, Lois Pope Life Center, 1095 NW 14th Terrace (D4-6), Miami, FL, 33146, USA.
| | - Long Di
- Department of Neurological Surgery, University of Miami Miller School of Medicine, Lois Pope Life Center, 1095 NW 14th Terrace (D4-6), Miami, FL, 33146, USA
| | - Alexis A Morell
- Department of Neurological Surgery, University of Miami Miller School of Medicine, Lois Pope Life Center, 1095 NW 14th Terrace (D4-6), Miami, FL, 33146, USA
| | - Ashish H Shah
- Department of Neurological Surgery, University of Miami Miller School of Medicine, Lois Pope Life Center, 1095 NW 14th Terrace (D4-6), Miami, FL, 33146, USA
| | - Alexa M Semonche
- Department of Neurological Surgery, University of Miami Miller School of Medicine, Lois Pope Life Center, 1095 NW 14th Terrace (D4-6), Miami, FL, 33146, USA
| | - Christopher N Chin
- Department of Neurological Surgery, University of Miami Miller School of Medicine, Lois Pope Life Center, 1095 NW 14th Terrace (D4-6), Miami, FL, 33146, USA
| | - Rita G Bhatia
- Department of Radiology, University of Miami Miller School of Medicine, Miami, FL, USA
| | - Aria M Jamshidi
- Department of Neurological Surgery, University of Miami Miller School of Medicine, Lois Pope Life Center, 1095 NW 14th Terrace (D4-6), Miami, FL, 33146, USA
| | - Evan M Luther
- Department of Neurological Surgery, University of Miami Miller School of Medicine, Lois Pope Life Center, 1095 NW 14th Terrace (D4-6), Miami, FL, 33146, USA
| | - Ricardo J Komotar
- Department of Neurological Surgery, University of Miami Miller School of Medicine, Lois Pope Life Center, 1095 NW 14th Terrace (D4-6), Miami, FL, 33146, USA
- Sylvester Comprehensive Cancer Center, Miami, FL, USA
| | - Michael E Ivan
- Department of Neurological Surgery, University of Miami Miller School of Medicine, Lois Pope Life Center, 1095 NW 14th Terrace (D4-6), Miami, FL, 33146, USA
- Sylvester Comprehensive Cancer Center, Miami, FL, USA
| |
Collapse
|