Comparing spatial distributions of ALA-PpIX and indocyanine green in a whole pig brain glioma model using 3D fluorescence cryotomography.

Significance: ALA-PpIX and second-window indocyanine green (ICG) have been studied widely for guiding the resection of high-grade gliomas. These agents have different mechanisms of action and uptake characteristics, which can affect their performance as surgical guidance agents. Elucidating these differences in animal models that approach the size and anatomy of the human brain would help guide the use of these agents. Herein, we report on the use of a new pig glioma model and fluorescence cryotomography to evaluate the 3D distributions of both agents throughout the whole brain. Aim: We aim to assess and compare the 3D spatial distributions of ALA-PpIX and second-window ICG in a glioma-bearing pig brain using fluorescence cryotomography. Approach: A glioma was induced in the brain of a transgenic Oncopig via adeno-associated virus delivery of Cre-recombinase plasmids. After tumor induction, the pro-drug 5-ALA and ICG were administered to the animal 3 and 24 h prior to brain harvest, respectively. The harvested brain was imaged using fluorescence cryotomography. The fluorescence distributions of both agents were evaluated in 3D in the whole brain using various spatial distribution and contrast performance metrics. Results: Significant differences in the spatial distributions of both agents were observed. Indocyanine green accumulated within the tumor core, whereas ALA-PpIX appeared more toward the tumor periphery. Both ALA-PpIX and second-window ICG provided elevated tumor-to-background contrast (13 and 23, respectively). Conclusions: This study is the first to demonstrate the use of a new glioma model and large-specimen fluorescence cryotomography to evaluate and compare imaging agent distribution at high resolution in 3D.

Precision meets generalization: Enhancing brain tumor classification via pretrained DenseNet with global average pooling and hyperparameter tuning.

Brain tumors pose significant global health concerns due to their high mortality rates and limited treatment options. These tumors, arising from abnormal cell growth within the brain, exhibits various sizes and shapes, making their manual detection from magnetic resonance imaging (MRI) scans a subjective and challenging task for healthcare professionals, hence necessitating automated solutions. This study investigates the potential of deep learning, specifically the DenseNet architecture, to automate brain tumor classification, aiming to enhance accuracy and generalizability for clinical applications. We utilized the Figshare brain tumor dataset, comprising 3,064 T1-weighted contrast-enhanced MRI images from 233 patients with three prevalent tumor types: meningioma, glioma, and pituitary tumor. Four pre-trained deep learning models-ResNet, EfficientNet, MobileNet, and DenseNet-were evaluated using transfer learning from ImageNet. DenseNet achieved the highest test set accuracy of 96%, outperforming ResNet (91%), EfficientNet (91%), and MobileNet (93%). Therefore, we focused on improving the performance of the DenseNet, while considering it as base model. To enhance the generalizability of the base DenseNet model, we implemented a fine-tuning approach with regularization techniques, including data augmentation, dropout, batch normalization, and global average pooling, coupled with hyperparameter optimization. This enhanced DenseNet model achieved an accuracy of 97.1%. Our findings demonstrate the effectiveness of DenseNet with transfer learning and fine-tuning for brain tumor classification, highlighting its potential to improve diagnostic accuracy and reliability in clinical settings.

Use of artificial intelligence and radio genomics in neuroradiology and the future of brain tumour imaging and surgical planning in low- and middleincome countries.

Brain tumour diagnosis involves assessing various radiological and histopathological parameters. Imaging modalities are an excellent resource for disease monitoring. However, manual inspection of imaging is laborious, and performance varies depending on expertise. Artificial Intelligence (AI) driven solutions a non-invasive and low-cost technology for diagnostics compared to surgical biopsy and histopathological diagnosis. We analysed various machine learning models reported in the literature and assess its applicability to improve neuro-oncological management. A scoping review of 47 full texts published in the last 3 years pertaining to the use of machine learning for the management of different types of gliomas where radiomics and radio genomic models have proven to be useful. Use of AI in conjunction with other factors can result in improving overall neurooncological management within LMICs. AI algorithms can evaluate medical imaging to aid in the early detection and diagnosis of brain tumours. This is especially useful where AI can deliver reliable and efficient screening methods, allowing for early intervention and treatment.

High-throughput fluorescence lifetime imaging flow cytometry.

Flow cytometry is a vital tool in biomedical research and laboratory medicine. However, its accuracy is often compromised by undesired fluctuations in fluorescence intensity. While fluorescence lifetime imaging microscopy (FLIM) bypasses this challenge as fluorescence lifetime remains unaffected by such fluctuations, the full integration of FLIM into flow cytometry has yet to be demonstrated due to speed limitations. Here we overcome the speed limitations in FLIM, thereby enabling high-throughput FLIM flow cytometry at a high rate of over 10,000 cells per second. This is made possible by using dual intensity-modulated continuous-wave beam arrays with complementary modulation frequency pairs for fluorophore excitation and acquiring fluorescence lifetime images of rapidly flowing cells. Moreover, our FLIM system distinguishes subpopulations in male rat glioma and captures dynamic changes in the cell nucleus induced by an anti-cancer drug. FLIM flow cytometry significantly enhances cellular analysis capabilities, providing detailed insights into cellular functions, interactions, and environments.

MR-guided focused ultrasound in pediatric neurosurgery: current insights, technical challenges, and lessons learned from 45 treatments at Children's National Hospital.

OBJECTIVE: MR-guided focused ultrasound (MRgFUS) is an evolving technology with numerous present and potential applications in pediatric neurosurgery. The aim of this study was to describe the use of MRgFUS, technical challenges, complications, and lessons learned at a single children's hospital. METHODS: A retrospective analysis was performed of a prospectively collected database of all pediatric patients undergoing investigational use of MRgFUS for treatment of various neurosurgical pathologies at Children's National Hospital. Treatment details, clinical workflow, and standard operating procedures are described. Patient demographics, procedure duration, and complications were obtained through a chart review of anesthesia and operative reports. RESULTS: In total, 45 MRgFUS procedures were performed on 14 patients for treatment of diffuse intrinsic pontine glioma (n = 12), low-grade glioma (n = 1), or secondary dystonia (n = 1) between January 2022 and April 2024. The mean age at treatment was 9 (range 5-22) years, and 64% of the patients were male. With increased experience, the total anesthesia time, sonication time, and change in core body temperature during treatment all significantly decreased. Complications affected 4.4% of patients, including 1 case of scalp edema and 1 patient with a postprocedure epidural hematoma. Device malfunction requiring abortion of the procedure occurred in 1 case (2.2%). Technical challenges related to transducer malfunction and sonication errors occurred in 6.7% and 11.1% of cases, respectively, all overcome by subsequent user modifications. CONCLUSIONS: The authors describe the largest series on MRgFUS technical aspects in pediatric neurosurgery at a single institution, comprising 45 total treatments. This study emphasizes potential technical challenges and provides valuable insights into the nuances of its application in pediatric patients.

[Clinicopathological and molecular characteristics of pediatric gliomas: analysis of 111 cases].

Objective: To summarize the clinical, pathological and molecular characteristics of various types of pediatric glioma, and to explore the differences in the morphology and clinical significance among various types of pediatric glioma. Methods: Based on the fifth edition of the World Health Organization classification of central nervous system tumors, this study classified or reclassified 111 pediatric gliomas that were diagnosed at Guangzhou Medical University Affiliated Women and Children's Medical Center from January 2020 to June 2023. The clinical manifestations, imaging findings, histopathology, and molecular characteristics of these tumors were analyzed. Relevant literature was also reviewed. Results: The 111 patients with pediatric glioma included 56 males and 55 females, with the age ranging from 10 days to 13 years (average age, 5.5 years). Clinically, manifestations presented from 5 days to 8 years before the diagnosis, including epilepsy in 16 cases, increased intracranial pressure in 48 cases and neurological impairment in 66 cases. MRI examinations revealed tumor locations as supratentorial in 43 cases, infratentorial in 65 cases, and spinal cord in 3 cases. There were 73 cases presented with a solid mass and 38 cases with cystic-solid lesions. The largest tumor diameter ranged from 1.4 to 10.6 cm. Among the 111 pediatric gliomas, there were 6 cases of pediatric diffuse low-grade glioma (pDLGG), 63 cases of circumscribed astrocytoma glioma (CAG), and 42 cases of pediatric diffuse high-grade glioma (pDHGG). Patients with pDLGG and CAG were younger than those with pDHGG. The incidence of pDLGG and CAG was significantly lower in the midline of the infratentorial region compared to that of pDHGG. They were more likely to be completely resected surgically. The pDLGG and CAG group included 4 cases of pleomorphic xanthoastrocytoma, showing histological features of high-grade gliomas. Among the high-grade gliomas, 13 cases were diffuse midline gliomas and also showed histological features of low-grade glioma. Immunohistochemical studies of H3K27M, H3K27ME3, p53, ATRX, BRAF V600E, and Ki-67 showed significant differences between the pDLGG and CAG group versus the pDHGG group (P<0.01). Molecular testing revealed that common molecular variations in the pDLGG and CAG group were KIAA1549-BRAF fusion and BRAF V600E mutation, while the pDHGG group frequently exhibited mutations in HIST1H3B and H3F3A genes, 1q amplification, and TP53 gene mutations. With integrated molecular testing, 2 pathological diagnoses were revised, and the pathological subtypes of 35.3% (12/34) of the pediatric gliomas that could not be reliably classified by histology were successfully classified. Conclusions: There are significant differences in clinical manifestations, pathological characteristics, molecular variations, and prognosis between the pDLGG, CAG and pDHGG groups. The integrated diagnosis combining histology and molecular features is of great importance for the accurate diagnosis and treatment of pediatric gliomas.

Optimization and validation of echo times of point-resolved spectroscopy for cystathionine detection in gliomas.

BACKGROUND: Cystathionine accumulates selectively in 1p/19q-codeleted gliomas, and can serve as a possible noninvasive biomarker. This study aims to optimize the echo time (TE) of point-resolved spectroscopy (PRESS) for cystathionine detection in gliomas, and evaluate the diagnostic accuracy of PRESS for 1p/19q-codeletion identification. METHODS: The TE of PRESS was optimized with numerical and phantom analysis to better resolve cystathionine from the overlapping aspartate multiplets. The optimized and 97 ms TE PRESS were then applied to 84 prospectively enrolled patients suspected of glioma or glioma recurrence to examine the influence of aspartate on cystathionine quantification by fitting the spectra with and without aspartate. The diagnostic performance of PRESS for 1p/19q-codeleted gliomas were assessed. RESULTS: The TE of PRESS was optimized as (TE1, TE2) = (17 ms, 28 ms). The spectral pattern of cystathionine and aspartate were consistent between calculation and phantom. The mean concentrations of cystathionine in vivo fitting without aspartate were significantly higher than those fitting with full basis-set for 97 ms TE PRESS (1.97 ± 2.01 mM vs. 1.55 ± 1.95 mM, p < 0.01), but not significantly different for 45 ms method (0.801 ± 1.217 mM and 0.796 ± 1.217 mM, p = 0.494). The cystathionine concentrations of 45 ms approach was better correlated with those of edited MRS than 97 ms counterparts (r = 0.68 vs. 0.49, both p < 0.01). The sensitivity and specificity for discriminating 1p/19q-codeleted gliomas were 66.7% and 73.7% for 45 ms method, and 44.4% and 52.5% for 97 ms method, respectively. CONCLUSION: The 45 ms TE PRESS yields more precise cystathionine estimates than the 97 ms method, and is anticipated to facilitate noninvasive diagnosis of 1p/19q-codeleted gliomas, and treatment response monitoring in those patients. Medium diagnostic performance of PRESS for 1p/19q-codeleted gliomas were observed, and warrants further investigations.

The application value of support vector machine model based on multimodal MRI in predicting IDH-1mutation and Ki-67 expression in glioma.

PURPOSE: To investigate the application value of support vector machine (SVM) model based on diffusion-weighted imaging (DWI), dynamic contrast-enhanced (DCE) and amide proton transfer- weighted (APTW) imaging in predicting isocitrate dehydrogenase 1(IDH-1) mutation and Ki-67 expression in glioma. METHODS: The DWI, DCE and APTW images of 309 patients with glioma confirmed by pathology were retrospectively analyzed and divided into the IDH-1 group (IDH-1(+) group and IDH-1(-) group) and Ki-67 group (low expression group (Ki-67 ≤ 10%) and high expression group (Ki-67 > 10%)). All cases were divided into the training set, and validation set according to the ratio of 7:3. The training set was used to select features and establish machine learning models. The SVM model was established with the data after feature selection. Four single sequence models and one combined model were established in IDH-1 group and Ki-67 group. The receiver operator characteristic (ROC) curve was used to evaluate the diagnostic performance of the model. Validation set data was used for further validation. RESULTS: Both in the IDH-1 group and Ki-67 group, the combined model had better predictive efficiency than single sequence model, although the single sequence model had a better predictive efficiency. In the Ki-67 group, the combined model was built from six selected radiomics features, and the AUC were 0.965 and 0.931 in the training and validation sets, respectively. In the IDH-1 group, the combined model was built from four selected radiomics features, and the AUC were 0.997 and 0.967 in the training and validation sets, respectively. CONCLUSION: The radiomics model established by DWI, DCE and APTW images could be used to detect IDH-1 mutation and Ki-67 expression in glioma patients before surgery. The prediction performance of the radiomics model based on the combination sequence was better than that of the single sequence model.

Diffusion-weighted MR image analysis based on gamma distribution model for differentiating benign and malignant brain tumors.

BACKGROUND: Considering the invasiveness of the biopsy method, we attempted to evaluate the ability of the gamma distribution model using magnetic resonance imaging images to stage and grade benign and malignant brain tumors. METHODS: A total of 42 patients with malignant brain tumors (including glioma, lymphoma, and choroid plexus papilloma) and 24 patients with benign brain tumors (meningioma) underwent diffusion-weighted imaging using five b-values ranging from 0 to 2000 s/mm2 with a 1.5 T scanner. The gamma distribution model is expected to demonstrate the probability of water molecule distribution based on the apparent diffusion coefficient. For all tumors, the apparent diffusion coefficient, shape parameter (κ), and scale parameter (θ) were calculated for each b-value. In the staging step, the fractions (ƒ1, ƒ2, ƒ3) expected to reflect the intracellular, and extracellular diffusion and perfusion were investigated. Diffusion <1 × 10-4 mm2/s (ƒ1), 1 × 10-4 mm2/s < Diffusion > 3 × 10-4 mm2/s (ƒ2), and Diffusion >3 × 10-4 mm2/s (ƒ3); in the grading step, fractions were determined to check heavily restricted diffusion. Diffusion lower than 0.3 × 10-4 mm2/s (ƒ11). Diffusion lower than 0.5 × 10-4 mm2/s (ƒ12). Diffusion lower than 0.8 × 10-4 mm2/s (ƒ13). RESULTS: The findings were analyzed using nonparametric statistics and receiver operating characteristic curve diagnostic performance. Gamma model parameters (κ, ƒ1, ƒ2, ƒ3) showed a satisfactory difference in differentiating meningioma from glioma. For b value = 2000 s/mm2, ƒ1 had a better diagnostic performance than κ and apparent diffusion coefficient (sensitivity, 88%; specificity, 68%; P < .001). The best diagnostic performance was related to ƒ3 in b = 2000 s/mm2 (area under the curve = 0.891, sensitivity = 83%, specificity = 80%, P < .001). In the grading step, ƒ12 (area under the curve = 0.870, sensitivity = 92%, specificity = 72%, P < .001) had the best diagnostic performance in differentiating high-grade from low-grade gliomas with b = 2000 s/mm2. CONCLUSION: The findings of our study highlight the potential of using a gamma distribution model with diffusion-weighted imaging based on multiple b-values for grading and staging brain tumors. Its potential integration into routine clinical practice could advance neurooncology and improve patient outcomes through more accurate diagnosis and treatment planning.

Prediction of Glioma enhancement pattern using a MRI radiomics-based model.

Contrast-MRI scans carry risks associated with the chemical contrast agents. Accurate prediction of enhancement pattern of gliomas has potential in avoiding contrast agent administration to patients. This study aimed to develop a machine learning radiomics model that can accurately predict enhancement pattern of gliomas based on T2 fluid attenuated inversion recovery images. A total of 385 cases of pathologically-proven glioma were retrospectively collected with preoperative magnetic resonance T2 fluid attenuated inversion recovery images, which were divided into enhancing and non-enhancing groups. Predictive radiomics models based on machine learning with 6 different classifiers were established in the training cohort (n = 201), and tested both in the internal validation cohort (n = 85) and the external validation cohort (n = 99). Receiver-operator characteristic curve was used to assess the predictive performance of these radiomics models. This study demonstrated that the radiomics model comprising of 15 features using the Gaussian process as a classifier had the highest predictive performance in both the training cohort and the internal validation cohort, with the area under the curve being 0.88 and 0.80, respectively. This model showed an area under the curve, sensitivity, specificity, positive predictive value and negative predictive value of 0.81, 0.98, 0.61, 0.82, 0.76 and 0.96, respectively, in the external validation cohort. This study suggests that the T2-FLAIR-based machine learning radiomics model can accurately predict enhancement pattern of glioma.

Transportable hyperspectral imaging setup based on fast, high-density spectral scanning for in situ quantitative biochemical mapping of fresh tissue biopsies.

Significance: Histopathological examination of surgical biopsies, such as in glioma and glioblastoma resection, is hindered in current clinical practice by the long time required for the laboratory analysis and pathological screening, typically taking several days or even weeks to be completed. Aim: We propose here a transportable, high-density, spectral scanning-based hyperspectral imaging (HSI) setup, named HyperProbe1, that can provide in situ, fast biochemical analysis, and mapping of fresh surgical tissue samples, right after excision, and without the need for fixing, staining nor compromising the integrity of the tissue properties. Approach: HyperProbe1 is based on spectral scanning via supercontinuum laser illumination filtered with acousto-optic tunable filters. Such methodology allows the user to select any number and type of wavelength bands in the visible and near-infrared range between 510 and 900 nm (up to a maximum of 79) and to reconstruct 3D hypercubes composed of high-resolution (4 to 5 µ m ), widefield images ( 0.9 × 0.9 mm 2 ) of the surgical samples, where each pixel is associated with a complete spectrum. Results: The HyperProbe1 setup is here presented and characterized. The system is applied to 11 fresh surgical biopsies of glioma from routine patients, including different grades of tumor classification. Quantitative analysis of the composition of the tissue is performed via fast spectral unmixing to reconstruct the mapping of major biomarkers, such as oxy-( HbO 2 ) and deoxyhemoglobin (HHb), as well as cytochrome-c-oxidase (CCO). We also provided a preliminary attempt to infer tumor classification based on differences in composition in the samples, suggesting the possibility of using lipid content and differential CCO concentrations to distinguish between lower and higher-grade gliomas. Conclusions: A proof of concept of the performances of HyperProbe1 for quantitative, biochemical mapping of surgical biopsies is demonstrated, paving the way for improving current post-surgical, histopathological practice via non-destructive, in situ streamlined screening of fresh tissue samples in a matter of minutes after excision.

[An MRI multi-sequence feature imputation and fusion mutual-aid model based on sequence deletion for differentiation of high-grade from low-grade glioma].

OBJECTIVE: To evaluate the performance of magnetic resonance imaging (MRI) multi-sequence feature imputation and fusion mutual model based on sequence deletion in differentiating high-grade glioma (HGG) from low-grade glioma (LGG). METHODS: We retrospectively collected multi-sequence MR images from 305 glioma patients, including 189 HGG patients and 116 LGG patients. The region of interest (ROI) of T1-weighted images (T1WI), T2-weighted images (T2WI), T2 fluid attenuated inversion recovery (T2_FLAIR) and post-contrast enhancement T1WI (CE_T1WI) were delineated to extract the radiomics features. A mutual-aid model of MRI multi-sequence feature imputation and fusion based on sequence deletion was used for imputation and fusion of the feature matrix with missing data. The discriminative ability of the model was evaluated using 5-fold cross-validation method and by assessing the accuracy, balanced accuracy, area under the ROC curve (AUC), specificity, and sensitivity. The proposed model was quantitatively compared with other non-holonomic multimodal classification models for discriminating HGG and LGG. Class separability experiments were performed on the latent features learned by the proposed feature imputation and fusion methods to observe the classification effect of the samples in twodimensional plane. Convergence experiments were used to verify the feasibility of the model. RESULTS: For differentiation of HGG from LGG with a missing rate of 10%, the proposed model achieved accuracy, balanced accuracy, AUC, specificity, and sensitivity of 0.777, 0.768, 0.826, 0.754 and 0.780, respectively. The fused latent features showed excellent performance in the class separability experiment, and the algorithm could be iterated to convergence with superior classification performance over other methods at the missing rates of 30% and 50%. CONCLUSION: The proposed model has excellent performance in classification task of HGG and LGG and outperforms other non-holonomic multimodal classification models, demonstrating its potential for efficient processing of non-holonomic multimodal data.

[68 Ga]Ga-CXCR4 PET/CT imaging in high-grade glioma for assessment of CXCR4 receptor expression.

PURPOSE: Gliomas account for 75 % of primary malignant CNS tumors. High-grade glioma (CNS WHO grades 3 and 4) have an unfavorable treatment response and poor outcome. CXCR4 is a G protein-coupled receptor that plays an important part in the signaling pathway between cancer cells and tumor microenvironment. CXCR4 overexpression has been shown in a variety of cancers. In this study, we evaluate the potential value of [68Ga]Ga-Pentixafor as a PET/CT CXCR4-probe for in vivo assessment of CXCR4 expression in patients with high-grade glioma and its correlation with tumor grade. MATERIALS AND METHODS: [68Ga]Ga-CXCR4 PET/CT was performed in the prospective single-center study in treatment-naïve biopsy-proven patients with high-grade glioma. The acquired images were analyzed qualitatively and semi-quantitatively. RESULT: A total of 26 patients (mean age: 53.3±14.4 years, 11 women, 15 men) were enrolled. CNS WHO grade 3 pathology was seen in 19 % (5/26) of the sample. The patient-based sensitivity of 68Ga-CXCR4 was 96.2 %. Overall, 28 pathologic lesions were detected, leading to a lesion-based sensitivity of 96.4 %. The median (IQR) SUVmax of grade 4 lesions was substantially greater than the grade 3(3.03(2.5-3.7) vs. 1.51(1.2-1.8), p = 0.0145).). The highest tracer activity of organs -beside bladder as the main excretion reservoir-was in lymphoid tissue of Waldeyer's ring (mean SUVmax: 7.41), and spleen (mean SUVmax: 6.62). CONCLUSION: In conclusion, this new application for [68Ga]Ga-Pentixafor PET tracer exhibits excellent visual and semi-quantitative diagnostic properties. Further studies are warranted.

ASL, DSC, DCE perfusion MRI and 18F-DOPA PET/CT in differentiating glioma recurrence from post-treatment changes.

OBJECTIVES: To discriminate between post-treatment changes and tumor recurrence in patients affected by glioma undergoing surgery and chemoradiation with a new enhancing lesion is challenging. We aimed to evaluate the role of ASL, DSC, DCE perfusion MRI, and 18F-DOPA PET/CT in distinguishing tumor recurrence from post-treatment changes in patients with glioma. MATERIALS AND METHODS: We prospectively enrolled patients with treated glioma (surgery plus chemoradiation) and a new enhancing lesion doubtful for recurrence or post-treatment changes. Each patient underwent a 1.5T MRI examination, including ASL, DSC, and DCE PWI, and an 18F-DOPA PET/CT examination. For each lesion, we measured ASL-derived CBF and normalized CBF, DSC-derived rCBV, DCE-derived Ktrans, Vp, Ve, Kep, and PET/CT-derived SUV maximum. Clinical and radiological follow-up determined the diagnosis of tumor recurrence or post-treatment changes. RESULTS: We evaluated 29 lesions (5 low-grade gliomas and 24 high-grade gliomas); 14 were malignancies, and 15 were post-treatment changes. CBF ASL, nCBF ASL, rCBV DSC, and PET SUVmax were associated with tumor recurrence from post-treatment changes in patients with glioma through an univariable logistic regression. Whereas the multivariable logistic regression results showed only nCBF ASL (p = 0.008) was associated with tumor recurrence from post-treatment changes in patients with glioma with OR = 22.85, CI95%: (2.28-228.77). CONCLUSION: In our study, ASL was the best technique, among the other two MRI PWI and the 18F-DOPA PET/CT PET, in distinguishing disease recurrence from post-treatment changes in treated glioma.

Molecular imaging with 68Ga-PSMA PET/CT in high grade glioma: A biomarker for tumour neo-angiogenesis.

There are several promising radiotracers used for both staging and restaging of primary and recurrent brain tumours based on various mechanisms of tracer localization in tumour cells. 68Ga-PSMA PET has extremely low background uptake in normal brain tissue and consequently high tumour-to-brain ratio making it a promising imaging radiotracer for gliomas. 68Ga-PSMA demonstrates utility in evaluating high grade glioma during both initial workup or when suspecting recurrence. Herein the authors evaluate the role of this imaging modality and the potential future it holds in the management of high grade gliomas.

Reproducibility of Radiomic Features in Glial Brain Tumors.

In our recent research, we have effectively demonstrated the feasibility of classifying magnetic resonance images (MRI) of glial tumors into four histological types utilizing standardized volume of interest (VOI), radiomics and machine learning. This research aims to determine the reproducibility of our approach when the locations of VOI are changed. We were able to demonstrate high reproducibility of ML results when the same feature selection methodology was employed across different VOIs. However, the reproducibility of radiomic features and their sets among various VOIs was not ensured for the sample size (n = 85) studied. The limited reproducibility of radiomic features should be taken into account when evaluating radiomics studies in glial tumors.

Deep learning for rapid virtual H&E staining of label-free glioma tissue from hyperspectral images.

Hematoxylin and eosin (H&E) staining is a crucial technique for diagnosing glioma, allowing direct observation of tissue structures. However, the H&E staining workflow necessitates intricate processing, specialized laboratory infrastructures, and specialist pathologists, rendering it expensive, labor-intensive, and time-consuming. In view of these considerations, we combine the deep learning method and hyperspectral imaging technique, aiming at accurately and rapidly converting the hyperspectral images into virtual H&E staining images. The method overcomes the limitations of H&E staining by capturing tissue information at different wavelengths, providing comprehensive and detailed tissue composition information as the realistic H&E staining. In comparison with various generator structures, the Unet exhibits substantial overall advantages, as evidenced by a mean structure similarity index measure (SSIM) of 0.7731 and a peak signal-to-noise ratio (PSNR) of 23.3120, as well as the shortest training and inference time. A comprehensive software system for virtual H&E staining, which integrates CCD control, microscope control, and virtual H&E staining technology, is developed to facilitate fast intraoperative imaging, promote disease diagnosis, and accelerate the development of medical automation. The platform reconstructs large-scale virtual H&E staining images of gliomas at a high speed of 3.81 mm2/s. This innovative approach will pave the way for a novel, expedited route in histological staining.

Integrated diagnosis of glioma based on magnetic resonance images with incomplete ground truth labels.

BACKGROUND: Since the 2016 WHO guidelines, glioma diagnosis has entered an era of integrated diagnosis, combining tissue pathology and molecular pathology. The WHO has focused on promoting the application of molecular diagnosis in the classification of central nervous system tumors. Genetic information such as IDH1 and 1p/19q are important molecular markers, and pathological grading is also a key clinical indicator. However, obtaining genetic pathology labels is more costly than conventional MRI images, resulting in a large number of missing labels in realistic modeling. METHOD: We propose a training strategy based on label encoding and a corresponding loss function to enable the model to effectively utilize data with missing labels. Additionally, we integrate a graph model with genes and pathology-related clinical prior knowledge into the ResNet backbone to further improve the efficacy of diagnosis. Ten-fold cross-validation experiments were conducted on a large dataset of 1072 patients. RESULTS: The classification area under the curve (AUC) values are 0.93, 0.91, and 0.90 for IDH1, 1p/19q status, and grade (LGG/HGG), respectively. When the label miss rate reached 59.3 %, the method improved the AUC by 0.09, 0.10, and 0.04 for IDH1, 1p/19q, and pathological grade, respectively, compared to the same backbone without the missing label strategy. CONCLUSIONS: Our method effectively utilizes data with missing labels and integrates clinical prior knowledge, resulting in improved diagnostic performance for glioma genetic and pathological markers, even with high rates of missing labels.