Standardization of imaging methods for machine learning in neuro-oncology

Navigating Neural Landscapes: A Comprehensive Review of Magnetic Resonance Imaging (MRI) and Magnetic Resonance Spectroscopy (MRS) Applications in Epilepsy

This review comprehensively explores the evolving role of neuroimaging, specifically magnetic resonance imaging (MRI) and magnetic resonance spectroscopy (MRS), in epilepsy research and clinical practice. Beginning with a concise overview of epilepsy, the discussion emphasizes the crucial importance of neuroimaging in diagnosing and managing this complex neurological disorder. The review delves into the applications of advanced MRI techniques, including high-field MRI, resting-state fMRI, and connectomics, highlighting their impact on refining our understanding of epilepsy's structural and functional dimensions. Additionally, it examines the integration of machine learning in the analysis of intricate neuroimaging data. Moving to the clinical domain, the review outlines the utility of neuroimaging in pre-surgical evaluations and the monitoring of treatment responses and disease progression. Despite significant strides, challenges and limitations are discussed in the routine clinical incorporation of neuroimaging. The review explores promising developments in MRI and MRS technology, potential advancements in imaging biomarkers, and the implications for personalized medicine in epilepsy management. The conclusion underscores the transformative potential of neuroimaging and advocates for continued exploration, collaboration, and technological innovation to propel the field toward a future where tailored, effective interventions improve outcomes for individuals with epilepsy.

Automated Quantification of Pneumonia Infected Volume in Lung CT Images: A Comparison with Subjective Assessment of Radiologists

OBJECTIVE

To help improve radiologists' efficacy of disease diagnosis in reading computed tomography (CT) images, this study aims to investigate the feasibility of applying a modified deep learning (DL) method as a new strategy to automatically segment disease-infected regions and predict disease severity.

METHODS

We employed a public dataset acquired from 20 COVID-19 patients, which includes manually annotated lung and infections masks, to train a new ensembled DL model that combines five customized residual attention U-Net models to segment disease infected regions followed by a Feature Pyramid Network model to predict disease severity stage. To test the potential clinical utility of the new DL model, we conducted an observer comparison study. First, we collected another set of CT images acquired from 80 COVID-19 patients and process images using the new DL model. Second, we asked two chest radiologists to read images of each CT scan and report the estimated percentage of the disease-infected lung volume and disease severity level. Third, we also asked radiologists to rate acceptance of DL model-generated segmentation results using a 5-scale rating method.

RESULTS

Data analysis results show that agreement of disease severity classification between the DL model and radiologists is >90% in 45 testing cases. Furthermore, >73% of cases received a high rating score (≥4) from two radiologists.

CONCLUSION

This study demonstrates the feasibility of developing a new DL model to automatically segment disease-infected regions and quantitatively predict disease severity, which may help avoid tedious effort and inter-reader variability in subjective assessment of disease severity in future clinical practice.

Applying artificial intelligence technology to assist with breast cancer diagnosis and prognosis prediction

Breast cancer remains the most diagnosed cancer in women. Advances in medical imaging modalities and technologies have greatly aided in the early detection of breast cancer and the decline of patient mortality rates. However, reading and interpreting breast images remains difficult due to the high heterogeneity of breast tumors and fibro-glandular tissue, which results in lower cancer detection sensitivity and specificity and large inter-reader variability. In order to help overcome these clinical challenges, researchers have made great efforts to develop computer-aided detection and/or diagnosis (CAD) schemes of breast images to provide radiologists with decision-making support tools. Recent rapid advances in high throughput data analysis methods and artificial intelligence (AI) technologies, particularly radiomics and deep learning techniques, have led to an exponential increase in the development of new AI-based models of breast images that cover a broad range of application topics. In this review paper, we focus on reviewing recent advances in better understanding the association between radiomics features and tumor microenvironment and the progress in developing new AI-based quantitative image feature analysis models in three realms of breast cancer: predicting breast cancer risk, the likelihood of tumor malignancy, and tumor response to treatment. The outlook and three major challenges of applying new AI-based models of breast images to clinical practice are also discussed. Through this review we conclude that although developing new AI-based models of breast images has achieved significant progress and promising results, several obstacles to applying these new AI-based models to clinical practice remain. Therefore, more research effort is needed in future studies.

MRI Response Assessment in Glioblastoma Patients Treated with Dendritic-Cell-Based Immunotherapy

Introduction: In this post hoc analysis we compared various response-assessment criteria in newly diagnosed glioblastoma (GB) patients treated with tumor lysate-charged autologous dendritic cells (Audencel) and determined the differences in prediction of progression-free survival (PFS) and overall survival (OS). Methods: 76 patients enrolled in a multicenter phase II trial receiving standard of care (SOC, n = 40) or SOC + Audencel vaccine (n = 36) were included. MRI scans were evaluated using MacDonald, RANO, Vol-RANO, mRANO, Vol-mRANO and iRANO criteria. Tumor volumes (T1 contrast-enhancing as well as T2/FLAIR volumes) were calculated by semiautomatic segmentation. The Kruskal-Wallis-test was used to detect differences in PFS among the assessment criteria; for correlation analysis the Spearman test was used. Results: There was a significant difference in median PFS between mRANO (8.6 months) and Vol-mRANO (8.6 months) compared to MacDonald (4.0 months), RANO (4.2 months) and Vol-RANO (5.4 months). For the vaccination arm, median PFS by iRANO was 6.2 months. There was no difference in PFS between SOC and SOC + Audencel. The best correlation between PFS/OS was detected for mRANO (r = 0.65) and Vol-mRANO (r = 0.69, each p < 0.001). A total of 16/76 patients developed a pure T2/FLAIR progressing disease, and 4/36 patients treated with Audencel developed pseudoprogression. Conclusion: When comparing different response-assessment criteria in GB patients treated with dendritic cell-based immunotherapy, the best correlation between PFS and OS was observed for mRANO and Vol-mRANO. Interestingly, iRANO was not superior for predicting OS in patients treated with Audencel.

Molecular Biology in Treatment Decision Processes-Neuro-Oncology Edition

Computational approaches including machine learning, deep learning, and artificial intelligence are growing in importance in all medical specialties as large data repositories are increasingly being optimised. Radiation oncology as a discipline is at the forefront of large-scale data acquisition and well positioned towards both the production and analysis of large-scale oncologic data with the potential for clinically driven endpoints and advancement of patient outcomes. Neuro-oncology is comprised of malignancies that often carry poor prognosis and significant neurological sequelae. The analysis of radiation therapy mediated treatment and the potential for computationally mediated analyses may lead to more precise therapy by employing large scale data. We analysed the state of the literature pertaining to large scale data, computational analysis, and the advancement of molecular biomarkers in neuro-oncology with emphasis on radiation oncology. We aimed to connect existing and evolving approaches to realistic avenues for clinical implementation focusing on low grade gliomas (LGG), high grade gliomas (HGG), management of the elderly patient with HGG, rare central nervous system tumors, craniospinal irradiation, and re-irradiation to examine how computational analysis and molecular science may synergistically drive advances in personalised radiation therapy (RT) and optimise patient outcomes.

TERT-Promoter Mutational Status in Glioblastoma - Is There an Association With Amino Acid Uptake on Dynamic 18F-FET PET?

Objective

The mutation of the ‘telomerase reverse transcriptase gene promoter’ (TERTp) has been identified as an important factor for individual prognostication and tumorigenesis and will be implemented in upcoming glioma classifications. Uptake characteristics on dynamic ¹⁸F-FET PET have been shown to serve as additional imaging biomarker for prognosis. However, data on the correlation of TERTp-mutational status and amino acid uptake on dynamic ¹⁸F-FET PET are missing. Therefore, we aimed to analyze whether static and dynamic ¹⁸F-FET PET parameters are associated with the TERTp-mutational status in de-novo IDH-wildtype glioblastoma and whether a TERTp-mutation can be predicted by dynamic ¹⁸F-FET PET.

Methods

Patients with de-novo IDH-wildtype glioblastoma, WHO grade IV, available TERTp-mutational status and dynamic ¹⁸F-FET PET scan prior to any therapy were included. Here, established clinical parameters maximal and mean tumor-to-background-ratios (TBR_max/TBR_mean), the biological-tumor-volume (BTV) and minimal-time-to-peak (TTP_min) on dynamic PET were analyzed and correlated with the TERTp-mutational status.

Results

One hundred IDH-wildtype glioblastoma patients were evaluated; 85/100 of the analyzed tumors showed a TERTp-mutation (C228T or C250T), 15/100 were classified as TERTp-wildtype. None of the static PET parameters was associated with the TERTp-mutational status (median TBR_max 3.41 vs. 3.32 (p=0.362), TBR_mean 2.09 vs. 2.02 (p=0.349) and BTV 26.1 vs. 22.4 ml (p=0.377)). Also, the dynamic PET parameter TTP_min did not differ in both groups (12.5 vs. 12.5 min, p=0.411). Within the TERTp-mutant subgroups (i.e., C228T (n=23) & C250T (n=62)), the median TBR_max (3.33 vs. 3.69, p=0.095), TBR_mean (2.08 vs. 2.09, p=0.352), BTV (25.4 vs. 30.0 ml, p=0.130) and TTP_min (12.5 vs. 12.5 min, p=0.190) were comparable, too.

Conclusion

Uptake characteristics on dynamic ¹⁸F-FET PET are not associated with the TERTp-mutational status in glioblastoma However, as both, dynamic ¹⁸F-FET PET parameters as well as the TERTp-mutation status are well-known prognostic biomarkers, future studies should investigate the complementary and independent prognostic value of both factors in order to further stratify patients into risk groups.