Deep learning-based quantification of temporalis muscle has prognostic value in patients with glioblastoma

Comparative analysis of deep learning and radiomic signatures for overall survival prediction in recurrent high-grade glioma treated with immunotherapy

BACKGROUND

Radiomic analysis of quantitative features extracted from segmented medical images can be used for predictive modeling of prognosis in brain tumor patients. Manual segmentation of the tumor components is time-consuming and poses significant reproducibility issues. We compare the prediction of overall survival (OS) in recurrent high-grade glioma(HGG) patients undergoing immunotherapy, using deep learning (DL) classification networks along with radiomic signatures derived from manual and convolutional neural networks (CNN) automated segmentation.

MATERIALS AND METHODS

We retrospectively retrieved 154 cases of recurrent HGG from multiple centers. Tumor segmentation was performed by expert radiologists and a convolutional neural network (CNN). From the segmented tumors, 2553 radiomic features were extracted for each case. A robust feature subset was selected using intraclass correlation coefficient analysis between manual and automated segmentations. The data was divided into a 9:1 ratio and validated through ten-fold cross-validation and tested on a rotating test set. Features selection was done by the Kruskal-Wallis test. The Radiomics-based OS predictions, generated using Support Vector Machine (SVM), were compared between the two segmentation approaches and against OS prediction by the CNN model adapted for classification. Model efficacy was evaluated using the area under the receiver operating characteristic curve (AUC).

RESULTS

The clinical model AUC for OS prediction was 0.640 ± 0.013 (mean ± 95% confidence interval) in the training set and 0.610 ± 0.131 in the test set. The radiomics prediction of OS based on manual segmentation outperformed automatic segmentation (AUC of 0.662 ± 0.122 vs. 0.471 ± 0.086, respectively) in the test set. Robust features improved the performance of manual segmentation to AUC of 0.700 ± 0.102, of automated segmentation to 0.554 ± 0.085. The CNN prognosis model demonstrated promising results, with an average AUC of 0.755 ± 0.071 for training sets and 0.700 ± 0.101 for the test set.

CONCLUSION

Manual segmentation-derived radiomic features outperformed automated segmentation-derived features for predicting OS in recurrent high-grade glioma patients undergoing immunotherapy. The end-to-end CNN prognosis model performed similarly to radiomics modeling using manual-segmentation-derived features without the need for segmentation. The potential time-saving must be weighed against the lower interpretability of end-to-end black box modeling.

Age- and sex-adjusted CT-based reference values for temporal muscle thickness, cross-sectional area and radiodensity

Muscle mass has been traditionally assessed by measuring paraspinal muscle areas at the level of the third lumbar vertebra on computed tomography (CT). Neurological or neurosurgical patients seldom undergo CT scans of the lumbar region. Instead, temporal muscle thickness (TMT), cross-sectional area (TMA) and radiodensity measured from head CT scans are readily available measures of muscle mass and quality in these patient cohorts. The purpose of this retrospective study was to establish CT-based reference values for TMT, TMA and radiodensity for each decade of age from 0 to 100 years normalized by age and sex, and to define cut-off values for subjects at risk for sarcopenia as defined by the European Working Group on Sarcopenia in Older People (EWGSOP). Subjects diagnosed with a concussion at the Oulu University Hospital between January 2014 and December 2022 (n = 9254) were identified to obtain a reference population. Subjects with significant pre-existing co-morbidities were excluded. TMT, TMA and radiodensity were measured, measurement reliability was quantified, and sex-adjusted reference values were calculated for each age decade. Quantile regression was used to model age-related changes in muscle morphomics. A total of 500 subjects [250 (50.0%) males] with a mean age of 49.2 ± 27.9 years were evaluated. Inter- and intra-observer reliability was almost perfect for TMT and TMA, and substantial-to-almost perfect for radiodensity. The mean TMT, TMA and radiodensity were 5.2 ± 1.9 mm, 284 ± 159 mm2 and 44.6 ± 17.7HU, respectively. The cut-off values for reduced TMT, TMA and radiodensity for males/females using the European Working Group on Sarcopenia in Older People compliant criteria were ≤ 4.09 mm/≤3.44 mm, ≤ 166 mm2/≤156 mm2, and ≤ 35.5HU/≤35.2HU, respectively. We described a standardized CT-based TMT and TMA measurement protocol practical for clinical use with almost perfect reliability. Using the protocol, we produced quantile regression models for the detection of reduced TMT, TMA and radiodensity at the lowest 5th, 10th, 20th, 30th, 40th and 50th percentiles as well as the EWGSOP compliant criteria cut-off values for reduced muscle mass to facilitate generalizable radiological sarcopenia research.

Abdominal myosteatosis measured with computed tomography predicts poor outcomes in patients with glioblastoma

Background

Alterations in cellular metabolism affect cancer survival and can manifest in metrics of body composition. We investigated the effects of various body composition metrics on survival in patients with glioblastoma (GBM).

Methods

We retrospectively analyzed patients who had an abdominal and pelvic computed tomography (CT) scan performed within 1 month of diagnosis of GBM (178 participants, 102 males, 76 females, median age: 62.1 years). Volumetric body composition metrics were derived using automated CT segmentation of adipose tissue, skeletal muscle, and aortic calcification from L1 to L5. Univariable and multivariable Cox proportional hazards models were performed separately in males and females using known predictors of GBM overall survival (OS) as covariates. A sex-specific composite score of predisposing and protective factors was constructed using the relative importance of each metric in GBM OS.

Results

Higher skeletal muscle volume and lower skeletal muscle fat fraction were associated with better OS in the entire dataset. A robust and independent effect on GBM OS was seen specifically for fraction of inter/intramuscular adipose tissue to total adipose tissue after correction for known survival predictors and comorbidities. Worse OS was observed with increased abdominal aortic calcification volume in both sexes. There was a significant difference in GBM OS among participants stratified into quartiles based on sex-specific composite predisposing and protective scores.

Conclusion

The relationship between body composition and GBM OS provides an actionable advancement toward precision medicine in GBM management, as lifestyle and dietary regimens can alter body composition and metabolism and from there GBM survival.

Glioblastoma and radiotherapy: A multicenter AI study for Survival Predictions from MRI (GRASP study)

BACKGROUND

The aim was to predict survival of glioblastoma at 8 months after radiotherapy (a period allowing for completing a typical course of adjuvant temozolomide), by applying deep learning to the first brain MRI after radiotherapy completion.

METHODS

Retrospective and prospective data were collected from 206 consecutive glioblastoma, isocitrate dehydrogenase -wildtype patients diagnosed between March 2014 and February 2022 across 11 UK centers. Models were trained on 158 retrospective patients from 3 centers. Holdout test sets were retrospective (n = 19; internal validation), and prospective (n = 29; external validation from 8 distinct centers). Neural network branches for T2-weighted and contrast-enhanced T1-weighted inputs were concatenated to predict survival. A nonimaging branch (demographics/MGMT/treatment data) was also combined with the imaging model. We investigated the influence of individual MR sequences; nonimaging features; and weighted dense blocks pretrained for abnormality detection.

RESULTS

The imaging model outperformed the nonimaging model in all test sets (area under the receiver-operating characteristic curve, AUC P = .038) and performed similarly to a combined imaging/nonimaging model (P > .05). Imaging, nonimaging, and combined models applied to amalgamated test sets gave AUCs of 0.93, 0.79, and 0.91. Initializing the imaging model with pretrained weights from 10 000s of brain MRIs improved performance considerably (amalgamated test sets without pretraining 0.64; P = .003).

CONCLUSIONS

A deep learning model using MRI images after radiotherapy reliably and accurately determined survival of glioblastoma. The model serves as a prognostic biomarker identifying patients who will not survive beyond a typical course of adjuvant temozolomide, thereby stratifying patients into those who might require early second-line or clinical trial treatment.

The prognostic utility of temporalis muscle thickness measured on magnetic resonance scans in patients with intra-axial malignant brain tumours: A systematic review and meta-analysis

Introduction

Sarcopenia is associated with worsened outcomes in solid cancers. Temporalis muscle thickness (TMT) has emerged as a measure of sarcopenia. Hence, this study aims to evaluate the relationship between TMT and outcome measures in patients with malignant intra-axial neoplasms.

Method

We searched Medline, Embase, Scopus and Cochrane databases for relevant studies. Event ratios with 95% confidence intervals (CI) were analysed using the RevMan 5.4 software. Where meta-analysis was impossible, vote counting was used to determine the effect of TMT on outcomes. The GRADE framework was used to determine the certainty of the evidence.

Results

Four outcomes were reported for three conditions across 17 studies involving 4430 patients. Glioblastoma: thicker TMT was protective for overall survival (OS) (HR 0.59; 95% CI 0.46-0.76) (GRADE low), progression free survival (PFS) (HR 0.40; 95% CI 0.26-0.62) (GRADE high), and early discontinuation of treatment (OR 0.408; 95% CI 0.168-0.989) (GRADE high); no association with complications (HR 0.82; 95% CI 0.60-1.10) (GRADE low). Brain Metastases: thicker TMT was protective for OS (HR 0.73; 95% CI 0.67-0.78) (GRADE moderate); no association with PFS (GRADE low). Primary CNS Lymphoma: TMT was protective for overall survival (HR 0.34; 95% CI 0.19-0.60) (GRADE moderate) and progression free survival (HR 0.23; 95% CI 0.09-0.56) (GRADE high).

Conclusion

TMT has significant prognostic potential in intra-axial malignant neoplasms, showing a moderate to high certainty for its association with outcomes following GRADE evaluation. This will enable shared decision making between patients and clinicians.

Neuroimaging and artificial intelligence for assessment of chronic painful temporomandibular disorders-a comprehensive review

Chronic Painful Temporomandibular Disorders (TMD) are challenging to diagnose and manage due to their complexity and lack of understanding of brain mechanism. In the past few decades' neural mechanisms of pain regulation and perception have been clarified by neuroimaging research. Advances in the neuroimaging have bridged the gap between brain activity and the subjective experience of pain. Neuroimaging has also made strides toward separating the neural mechanisms underlying the chronic painful TMD. Recently, Artificial Intelligence (AI) is transforming various sectors by automating tasks that previously required humans' intelligence to complete. AI has started to contribute to the recognition, assessment, and understanding of painful TMD. The application of AI and neuroimaging in understanding the pathophysiology and diagnosis of chronic painful TMD are still in its early stages. The objective of the present review is to identify the contemporary neuroimaging approaches such as structural, functional, and molecular techniques that have been used to investigate the brain of chronic painful TMD individuals. Furthermore, this review guides practitioners on relevant aspects of AI and how AI and neuroimaging methods can revolutionize our understanding on the mechanisms of painful TMD and aid in both diagnosis and management to enhance patient outcomes.

Artificial intelligence in neuroimaging of brain tumors: reality or still promise?

PURPOSE OF REVIEW

To provide an updated overview of artificial intelligence (AI) applications in neuro-oncologic imaging and discuss current barriers to wider clinical adoption.

RECENT FINDINGS

A wide variety of AI applications in neuro-oncologic imaging have been developed and researched, spanning tasks from pretreatment brain tumor classification and segmentation, preoperative planning, radiogenomics, prognostication and survival prediction, posttreatment surveillance, and differentiating between pseudoprogression and true disease progression. While earlier studies were largely based on data from a single institution, more recent studies have demonstrated that the performance of these algorithms are also effective on external data from other institutions. Nevertheless, most of these algorithms have yet to see widespread clinical adoption, given the lack of prospective studies demonstrating their efficacy and the logistical difficulties involved in clinical implementation.

SUMMARY

While there has been significant progress in AI and neuro-oncologic imaging, clinical utility remains to be demonstrated. The next wave of progress in this area will be driven by prospective studies measuring outcomes relevant to clinical practice and go beyond retrospective studies which primarily aim to demonstrate high performance.

Automated temporalis muscle quantification and growth charts for children through adulthood

Lean muscle mass (LMM) is an important aspect of human health. Temporalis muscle thickness is a promising LMM marker but has had limited utility due to its unknown normal growth trajectory and reference ranges and lack of standardized measurement. Here, we develop an automated deep learning pipeline to accurately measure temporalis muscle thickness (iTMT) from routine brain magnetic resonance imaging (MRI). We apply iTMT to 23,876 MRIs of healthy subjects, ages 4 through 35, and generate sex-specific iTMT normal growth charts with percentiles. We find that iTMT was associated with specific physiologic traits, including caloric intake, physical activity, sex hormone levels, and presence of malignancy. We validate iTMT across multiple demographic groups and in children with brain tumors and demonstrate feasibility for individualized longitudinal monitoring. The iTMT pipeline provides unprecedented insights into temporalis muscle growth during human development and enables the use of LMM tracking to inform clinical decision-making.

Advances in the relationship between temporal muscle thickness and prognosis of patients with glioblastoma: a narrative review

The most dangerous variety of glioma, glioblastoma, has a high incidence and fatality rate. The prognosis for patients is still bleak despite numerous improvements in treatment approaches. We urgently need to develop clinical parameters that can evaluate patients' conditions and predict their prognosis. Various parameters are available to assess the patient's preoperative performance status and degree of frailty, but most of these parameters are subjective and therefore subject to interobserver variability. Sarcopenia can be used as an objective metric to measure a patient's physical status because studies have shown that it is linked to a bad prognosis in those with cancers. For the purpose of identifying sarcopenia, temporal muscle thickness has demonstrated to be a reliable alternative for a marker of skeletal muscle content. As a result, patients with glioblastoma may use temporal muscle thickness as a potential marker to correlate with the course and fate of their disease. This narrative review highlights and defines the viability of using temporal muscle thickness as an independent predictor of survival in glioblastoma patients, and it evaluates recent research findings on the association between temporal muscle thickness and prognosis of glioblastoma patients.

Prognostic value of temporal muscle thickness, a novel radiographic marker of sarcopenia, in patients with brain tumor: A systematic review and meta-analysis

Sarcopenia has been identified as a prognostic factor among certain types of cancer. However, it is unclear whether there is prognostic value of temporalis muscle thickness (TMT), a potential surrogate for sarcopenia, in adults patients with brain tumors. Therefore, we searched the Medline, Embase, and PubMed to systematically review and meta-analyze the relationship between TMT and overall survival, progression-free survival, and complications in patients with brain tumors and the hazard ratio (HR) or odds ratios (OR), and 95% confidence interval (CI) were evaluated. The quality in prognostic studies (QUIPS) instrument was employed to evaluate study quality. Nineteen studies involving 4570 patients with brain tumors were included for qualitative and quantitative analysis. Meta-analysis revealed thinner TMT was associated with poor overall survival (HR, 1.72; 95% CI, 1.45-2.04; P < 0.01) in patients with brain tumors. Sub-analyses showed that the association existed for both primary brain tumors (HR, 2.02; 95% CI, 1.55-2.63) and brain metastases (HR, 1.39; 95% CI, 1.30-1.49). Moreover, thinner TMT also was the independent predictor of progression-free survival in patients with primary brain tumors (HR, 2.88; 95% CI, 1.85-4.46; P < 0.01). Therefore, to improve clinical decision making it is important to integrate TMT assessment into routine clinical settings in patients with brain tumors.

Deep Learning in MRI-guided Radiation Therapy: A Systematic Review

MRI-guided radiation therapy (MRgRT) offers a precise and adaptive approach to treatment planning. Deep learning applications which augment the capabilities of MRgRT are systematically reviewed. MRI-guided radiation therapy offers a precise, adaptive approach to treatment planning. Deep learning applications which augment the capabilities of MRgRT are systematically reviewed with emphasis placed on underlying methods. Studies are further categorized into the areas of segmentation, synthesis, radiomics, and real time MRI. Finally, clinical implications, current challenges, and future directions are discussed.

Emerging role of artificial intelligence in diagnosis, classification and clinical management of glioma

Glioma represents a dominant primary intracranial malignancy in the central nervous system. Artificial intelligence that mainly includes machine learning, and deep learning computational approaches, presents a unique opportunity to enhance clinical management of glioma through improving tumor segmentation, diagnosis, differentiation, grading, treatment, prediction of clinical outcomes (prognosis, and recurrence), molecular features, clinical classification, characterization of the tumor microenvironment, and drug discovery. A growing body of recent studies apply artificial intelligence-based models to disparate data sources of glioma, covering imaging modalities, digital pathology, high-throughput multi-omics data (especially emerging single-cell RNA sequencing and spatial transcriptome), etc. While these early findings are promising, future studies are required to normalize artificial intelligence-based models to improve the generalizability and interpretability of the results. Despite prominent issues, targeted clinical application of artificial intelligence approaches in glioma will facilitate the development of precision medicine of this field. If these challenges can be overcome, artificial intelligence has the potential to profoundly change the way patients with or at risk of glioma are provided with more rational care.

Multimodal Deep Learning-Based Prognostication in Glioma Patients: A Systematic Review

Malignant brain tumors pose a substantial burden on morbidity and mortality. As clinical data collection improves, along with the capacity to analyze it, novel predictive clinical tools may improve prognosis prediction. Deep learning (DL) holds promise for integrating clinical data of various modalities. A systematic review of the DL-based prognostication of gliomas was performed using the Embase (Elsevier), PubMed MEDLINE (National library of Medicine), and Scopus (Elsevier) databases, in accordance with PRISMA guidelines. All included studies focused on the prognostication of gliomas, and predicted overall survival (13 studies, 81%), overall survival as well as genotype (2 studies, 12.5%), and response to immunotherapy (1 study, 6.2%). Multimodal analyses were varied, with 6 studies (37.5%) combining MRI with clinical data; 6 studies (37.5%) integrating MRI with histologic, clinical, and biomarker data; 3 studies (18.8%) combining MRI with genomic data; and 1 study (6.2%) combining histologic imaging with clinical data. Studies that compared multimodal models to unimodal-only models demonstrated improved predictive performance. The risk of bias was mixed, most commonly due to inconsistent methodological reporting. Overall, the use of multimodal data in DL assessments of gliomas leads to a more accurate overall survival prediction. However, due to data limitations and a lack of transparency in model and code reporting, the full extent of multimodal DL as a resource for brain tumor patients has not yet been realized.

MiR-33a targets FOSL1 and EN2 as a clinical prognostic marker for sarcopenia by glioma

To determine the relationship between glioma and muscle aging and to predict prognosis by screening for co-expressed genes, this study examined the relationship between glioma and sarcopenia. The study identified eight co-downregulated miRNAs, three co-upregulated miRNAs, and seven genes associated with overall glioma survival, namely, KRAS, IFNB1, ALCAM, ERBB2, STAT3, FOSL1, and EN2. With a multi-factor Cox regression model incorporating FOSL1 and EN2, we obtained ROC curves of 0.702 and 0.709, respectively, suggesting that glioma prognosis can be predicted by FOSL1 and EN2, which are differentially expressed in both cancer and aged muscle. FOSL1 and EN2 were analyzed using Gene Set Enrichment Analysis to identify possible functional pathways. RT-qPCR and a dual-luciferase reporter gene system verified that hsa-miR-33a targets FOSL1 and EN2. We found that hsa-mir-33a co-targeting FOSL1 and EN2 has a good predictive value for glioblastoma and skeletal muscle reduction.

Temporal Muscle and Stroke-A Narrative Review on Current Meaning and Clinical Applications of Temporal Muscle Thickness, Area, and Volume

BACKGROUND

Evaluating muscle mass and function among stroke patients is important. However, evaluating muscle volume and function is not easy due to the disturbances of consciousness and paresis. Temporal muscle thickness (TMT) has been introduced as a novel surrogate marker for muscle mass, function, and nutritional status. We herein performed a narrative literature review on temporal muscle and stroke to understand the current meaning of TMT in clinical stroke practice.

METHODS

The search was performed in PubMed, last updated in October 2021. Reports on temporal muscle morphomics and stroke-related diseases or clinical entities were collected.

RESULTS

Four studies reported on TMT and subarachnoid hemorrhage, two studies on intracerebral hemorrhage, two studies on ischemic stroke, two studies on standard TMT values, and two studies on nutritional status. TMT was reported as a prognostic factor for several diseases, a surrogate marker for skeletal muscle mass, and an indicator of nutritional status. Computed tomography, magnetic resonance imaging, and ultrasonography were used to measure TMT.

CONCLUSIONS

TMT is gradually being used as a prognostic factor for stroke or a surrogate marker for skeletal muscle mass and nutritional status. The establishment of standard methods to measure TMT and large prospective studies to further investigate the relationship between TMT and diseases are needed.

Machine learning in neuroimaging: from research to clinical practice

Neuroimaging is critical in clinical care and research, enabling us to investigate the brain in health and disease. There is a complex link between the brain's morphological structure, physiological architecture, and the corresponding imaging characteristics. The shape, function, and relationships between various brain areas change during development and throughout life, disease, and recovery. Like few other areas, neuroimaging benefits from advanced analysis techniques to fully exploit imaging data for studying the brain and its function. Recently, machine learning has started to contribute (a) to anatomical measurements, detection, segmentation, and quantification of lesions and disease patterns, (b) to the rapid identification of acute conditions such as stroke, or (c) to the tracking of imaging changes over time. As our ability to image and analyze the brain advances, so does our understanding of its intricate relationships and their role in therapeutic decision-making. Here, we review the current state of the art in using machine learning techniques to exploit neuroimaging data for clinical care and research, providing an overview of clinical applications and their contribution to fundamental computational neuroscience.