Gliomas, the most common malignant primary brain tumors, present significant challenges in classification and grading, which are crucial for treatment planning and prognosis. Despite advancements, current methods face limitations due to high costs, limited accessibility, and time-consuming results. This paper presents a novel hybrid quantum or classical-quantum computing model to differentiate between low-grade and high-grade gliomas using data from The Cancer Genome Atlas (TCGA). The study combines classical and quantum computing methods, with the quantum model achieving the highest classification accuracy. Molecular markers and clinical features play a significant role in the classification process.
Introduction to Glioma Tumor Classification
Gliomas are the most common malignant primary brain tumors, presenting significant challenges in terms of varying survival rates, treatment modalities, and prognostic processes between patients with low-grade gliomas (LGGs) and high-grade gliomas (HGGs). Accurate classification and grading of LGGs and HGGs are crucial for appropriate treatment planning and assessment of overall prognosis. The classification and grading of gliomas have undergone an evolution over time, with the inclusion of molecular markers in the classification of glioma tumors by the WHO Central Nervous System (CNS) Tumors Classification in 2016 and the incorporation of advanced molecular diagnostics in 2021.
Limitations of Current Classification Methods
Despite these advancements, the high cost and limited accessibility of molecular genetic tests, coupled with the time-consuming nature of obtaining results, can lead to delays in critical treatment decisions. Various classical artificial intelligence methods such as machine learning and deep learning have been applied to problems in this field, yielding a certain level of success. However, the continuous expansion of medical data dimensions, the inherent noise level in the data, and the limitations of the classical vector space pose significant challenges that classical artificial intelligence methods struggle to overcome.
The Role of Quantum Computing in Healthcare
Recent studies have demonstrated that the use of quantum computing and quantum artificial intelligence technologies in healthcare not only addresses these problems but also accelerates complex data analyses and processes large datasets more efficiently. This paper presents a novel hybrid quantum or classical-quantum computing model aimed at differentiating between LGGs and HGGs using data from The Cancer Genome Atlas (TCGA).
The Study’s Approach to Glioma Tumor Classification
In the classical part of the study, an ensemble feature selection method was used to identify the most important molecular markers and clinical features within the TCGA glioma dataset. In the quantum section, six variational quantum classifier (VQC) models with different hyperparameters are proposed. These classifiers are subsequently used to differentiate between LGGs and HGGs using the features obtained from the ensemble model.
Results of the Study
The computational results show that among the six VQC models, the VQC1 model, which incorporates 𝑅𝑥 and CX gates in the feature map and 𝑅𝑦, 𝑅𝑧, and CY gates in the parameterized quantum circuit and utilizes the AQCD optimization method, achieves the highest classification accuracy of 0.74. This study provides a novel perspective on the classification of glioma tumors by combining classical and quantum computing methods.
The Importance of Molecular Markers in Glioma Tumor Classification
Molecular markers such as IDH mutation, TP53, ATRX, and chromosome 1p19q codeletion status play a significant role in the classification of gliomas. For instance, mutations in IDH characterize the majority of LGGs in adults and are associated with a more favorable prognosis than mutations in non-mutated IDH. Additionally, TP53 and ATRX mutations are more commonly observed in astrocytomas and serve as significant markers of clinical behavior.
The Role of The Cancer Genome Atlas (TCGA) in Cancer Research
The Cancer Genome Atlas (TCGA) research project has been established to provide a comprehensive analysis of various cancer genome profiles such as gliomas. To generate these genomic profiles, TCGA was generated with high-throughput technologies based on microarray and next-generation sequencing methods. Furthermore, for optimal patient management, clinical features such as age and gender have been included in combination with molecular markers as they contribute to the tumor classification process.
In the article “Beyond Limits: Charting New Horizons in Glioma Tumor Classification through Hybrid Quantum Computing with The Cancer Genome Atlas (TCGA) Data”, authors Emine Akpinar and Murat OduncuoÄźlu explore the potential of hybrid quantum computing in the classification of glioma tumors. The research, published on January 22, 2024, utilizes data from The Cancer Genome Atlas (TCGA) to push the boundaries of current understanding and methodologies in the field. The full article can be accessed through its DOI: 10.21203/rs.3.rs-3876410/v1.
