Tumor Subregions Research Articles

DNAR-04. TUMOUR TREATING FIELDS (TTFIELDS) AND DNA DAMAGE RESPONSE (DDR) INHIBITORS ENHANCE GLIOMA CELL DEATH THROUGH CHEMO-/RADIOSENSITISATION

Abstract High grade gliomas are the most common primary brain cancer malignancies with ~300,000 global diagnoses each year with glioblastomas (WHO grade IV) conferring the worst prognoses. This arises from their treatment resistance, rationalised by the presence of glioma stem cell-like (GSC) tumour sub-regions and high intratumoural spatio-heterogeneity. TTFields are clinically approved alternating electric fields of intermediate frequency that exert anti-mitotic effects and invoke downregulation of the DDR. Therefore, TTFields alongside clinically developed, and blood brain barrier (BBB) penetrating DDR inhibitors (DDRi) could boost cell death and overcome treatment resistance through chemo-/radiosensitisation. Primary GSC cell lines were derived from surgically resected and clinically defined tumour core and invasive edge regions and grown in more biologically relevant 3D-printed AlvetexTM scaffolds, offering highly clinically relevant models. Cells were then pre-treated with DDRi, subjected to chemo-/radiotherapy and then incubated under TTFields (200 kHz, 72 hrs) with their survival measured by clonogenic assays after 3 weeks. Immunofluorescence and western blot analysis were used to analyse the combination treatment effects on the DDR. In multiple 3D-grown core/edge GSC models, western blot analyses revealed that the DDR was altered by TTFields and clonogenic survival assays revealed that TTFields alongside DDRi led to significant chemo-/radiosensitisation. TTFields alongside DDRi effectively enhances cell death by significant treatment sensitisation effects in clinically relevant 3D GSCs which exhibit extensive intra and intertumoral spatio-heterogeneity. Given that all the DDRi used are BBB penetrable and are either clinically approved or in clinical trials, TTFields could additionally compliment these treatment regimens in gliomas to boost their efficacy.

NIMG-65. SYNTHETIC MRI GENERATION TO FACILITATE AUTOSEGMENTATION OF PEDIATRIC BRAIN TUMORS IN LIMITED DATA SCENARIOS

Abstract BACKGROUND The availability of standard multiparametric MRI sequences, including pre-contrast T1w (T1w-pre), post-contrast T1w (T1w-post), T2w, and FLAIR images, is essential for accurate segmentation of tumor subregions and subsequent response assessment in pediatric brain tumors (PBTs). However, clinical MRI sets are often incomplete due to imaging artifacts or inconsistent acquisition protocols across different centers. This study leverages Generative Adversarial Networks (GANs) to synthesize missing FLAIR and T1w-pre images from T2w and T1w-post images, respectively, to facilitate tumor segmentation in PBTs. METHODS We developed two GAN models based on the pix2pix framework, trained, validated, and tested on FLAIR-T2w and T1w-post-T1w-pre pairs from a multi-histology and multi-institutional cohort of 476 subjects with PBTs from the Children’s Brain Tumor Network (CBTN). The perceptual quality of the synthesized T1w-pre and FLAIR images was evaluated using the Structural Similarity Index (SSI; ideal value = 1). The robustness of the synthesized sequences to replace missing MRI sequences was evaluated by comparing the segmentation performance (Dice score) of our pre-trained autosegmentation model using all real modalities versus replacing real sequences with their synthesized counterparts. RESULTS The T1w-pre and FLAIR synthesis GANs achieved mean SSI values of 0.95 and 0.93, respectively. Median Dice scores for segmentation of whole tumor (WT), enhancing tumor (ET), and tumor core (TC) were calculated for real sequences: 0.90, 0.83, 0.89, replacing real FLAIR with synthetic: 0.86, 0.81, 0.86, and replacing real T1w-pre with synthetic: 0.90, 0.75, 0.89. No statistical significance (p>0.05) was observed in segmentation performance for WT, TC, ET when replacing real T1w-pre with synthetic, and for ET when replacing real with synthetic FLAIR sequences. CONCLUSION This method achieves robust segmentation performance in limited data scenarios by synthesizing missing MRI sequences. Future work includes improving FLAIR synthesis and segmentation performance for WT and ET by implementing and comparing other GAN architectures.

BIOM-18. MAPPING TUMOR HABITATS IN IDH-WILD TYPE GLIOBLASTOMA: INTEGRATING MR IMAGING, PATHOLOGIC, AND RNA DATA FROM IVY GLIOBLASTOMA ATLAS PROJECT

Abstract BACKGROUND To identify biologic correlates and spatially validate intratumoral subregions (tumor habitat) using diffusion-weighted and dynamic susceptibility contrast-imaging on a comprehensive pathology map of the isocitrate dehydrogenase (IDH)-wild type whole glioblastoma sample using the Ivy Glioblastoma Atlas Project (Ivy GAP). METHODS Complete data of 20 patients with 168 slides of IDH-wild type glioblastoma were obtained from the IvyGAP (http://glioblastoma.alleninstitute.org/). On MRI, tumor habitats were defined using voxel-wise clustering of apparent diffusion coefficient (ADC) and cerebral blood volume (CBV) maps for contrast-enhancing lesion (CEL) and peritumoral non-enhancing lesion (NEL). On pathology slides, normalized areas of leading edge (LE), infiltrating tumor (IT), cellular tumor (CT), hypervascular lesion (CThypervascular), and perinecrotic lesion (CTperinecrotic) were obtained. Gross specimen pictures were co-registered on MRI images for co-localization and correlation between MRI tumor habitats. Pathologic areas were calculated using Pearson’s correlation coefficient. RNA sequencing of 67 RNA-seq samples was assessed using 4 Neftel subtypes and further correlated with pathology. RESULTS Six tumor habitats were correlated: hypervascular, hypovascular cellular, and hypovascular hypocellular habitats for CEL and NEL. CT was strongly correlated with hypovascular cellular habitat in CEL (C2, r = 0.238, p =.005). IT was strongly correlated with hypovascular cellular habitat in NEL (C5, r = 0.294, p =.017). CThypervascular was correlated with hypervascular habitat in NEL (r = 0.195, p =.023). CTperinecrotic was correlated with imaging necrosis (r = 0.199, p =.005). Astrocyte-like subtypes were positively correlated with IT (r = 0.256, p <.001), while mesenchymal-like subtypes were positively correlated with CTperinecrotic area (r = 0.246, p <.001). CONCLUSION Pathologically matched tumor subregions were cellular tumor with hypovascular cellular habitat in CEL and infiltrative tumor with hypovascular cellular habitat in NEL. Identification of the most aggressive tumor portion, and infiltrative tumor portion using non-invasive imaging can be achieved using MRI tumor habitats.

Multimodal Connectivity‐Guided Glioma Segmentation From Magnetic Resonance Images via Cascaded 3D Residual U‐Net

ABSTRACTGlioma is a type of brain tumor with a high mortality rate. Magnetic resonance imaging (MRI) is commonly used for examination, and the accurate segmentation of tumor regions from MR images is essential to computer‐aided diagnosis. However, due to the intrinsic heterogeneity of brain glioma, precise segmentation is very challenging, especially for tumor subregions. This article proposed a two‐stage cascaded method for brain tumor segmentation that considers the hierarchical structure of the target tumor subregions. The first stage aims to identify the whole tumor (WT) from the background area; and the second stage aims to achieve fine‐grained segmentation of the subregions, including enhanced tumor (ET) region and tumor core (TC) region. Both stages apply a deep neural network structure combining modified 3D U‐Net with a residual connection scheme to tumor region and subregion segmentation. Moreover, in the training phase, the 3D masks generation of subregions with potential incomplete connectivity are guided by the completely connected regions. Experiments were performed to evaluate the performance of the methods on both area and boundary accuracy. The average dice score of the WT, TC, and ET regions on BraTS 2020 dataset is 0.9168, 0.0.8992, 0.8489, and the Hausdorff distance is 6.021, 9.203, 12.171, respectively. The proposed method outperforms current works, especially in segmenting fine‐grained tumor subregions.

Optimising hypoxia PET imaging and its applications in guiding targeted radiation therapy for non-small cell lung cancer: a scoping review.

Non-small cell lung cancer (NSCLC) is the leading cause of cancer-related death. Definitive treatment includes chemotherapy and radiation therapy. Tumour hypoxia impacts the efficacy of these treatment modalities. Novel positron-emission tomography (PET) imaging has been developed to non-invasively quantify hypoxic tumour subregions, and to guide personalised treatment strategies. This review evaluates the reliability of hypoxia imaging in NSCLC in relation to various tracers, its correlations to treatment-related outcomes, and to assess if this imaging modality can be meaningfully applied into radiation therapy workflows. A literature search was conducted on the Medline (Ovid) and Embase databases. Searches included terms related to 'hypoxia', 'positron-emission tomography', 'magnetic resonance imaging' and 'lung cancer'. Results were filtered to exclude studies prior to 2011, and animal studies were excluded. Only studies referring to a confirmed pathology of NSCLC were included, while disease staging was not a limiting factor. Full-text English language and translated literature examined included clinical trials, clinical cohort studies and feasibility studies. Quantification of hypoxic volumes in a pre-treatment setting is of prognostic value, and indicative of treatment response. Dosimetric comparisons have highlighted potential to significantly dose escalate to hypoxic volumes without risk of additional toxicity. However, clinical data to support these strategies are lacking. Heterogenous study design and non-standardised imaging parameters have led to a lack of clarity regarding the application of hypoxia PET imaging in NSCLC. PET imaging using nitroimidazole tracers is the most investigated method of non-invasively measuring tumour hypoxia and has potential to guide hypoxia-targeted radiation therapy. Further clinical research is required to elucidate the benefits versus risks of dose-escalation strategies.

Assessing tumor microstructure with time-dependent diffusion imaging: Considerations and feasibility on clinical MRI and MRI-Linac.

Quantitative imaging biomarkers (QIBs) can characterize tumor heterogeneity and provide information for biological guidance in radiotherapy (RT). Time-dependent diffusion MRI (TDD-MRI) derived parameters are promising QIBs, as they describe tissue microstructure with more specificity than traditional diffusion-weighted MRI (DW-MRI). Specifically, TDD-MRI can provide information about both restricted diffusion and diffusional exchange, which are the two time-dependent effects affecting diffusion in tissue, and relevant in tumors. However, exhaustive modeling of both effects can require long acquisitions and complex model fitting. Furthermore, several introduced TDD-MRI measurements can require high gradient strengths and/or complex gradient waveforms that are possibly not available in RT settings. In this study, we investigated the feasibility of a simple analysis framework for the detection of restricted diffusion and diffusional exchange effects in the TDD-MRI signal. To promote the clinical applicability, we use standard gradient waveforms on a conventional 1.5 T MRI system with moderate gradient strength (Gmax=45 mT/m), and on a hybrid 1.5 T MRI-Linac system with low gradient strength (Gmax=15 mT/m). Restricted diffusion and diffusional exchange were simulated in geometries mimicking tumor microstructure to investigate the DW-MRI signal behavior and to determine optimal experimental parameters. TDD-MRI was implemented using pulsed field gradient spin echo with the optimized parameters on a conventional MRI system and a MRI-Linac. Experiments in green asparagus and 10 patients with brain lesions were performed to evaluate the time-dependent diffusion (TDD) contrast in the source DW-images. Simulations demonstrated how the TDD contrast was able to differentiate only dominating diffusional exchange in smaller cells from dominating restricted diffusion in larger cells. The maximal TDD contrast in simulations with typical cancer cell sizes and in asparagus measurements exceeded 5% on the conventional MRI but remained below 5% on the MRI-Linac. In particular, the simulated TDD contrast in typical cancer cell sizes (r=5-10µm) remained below or around 2% with the MRI-Linac gradient strength. In patients measured with the conventional MRI, we found sub-regions reflecting either dominating restricted diffusion or dominating diffusional exchange in and around brain lesions compared to the noisy appearing white matter. On the conventional MRI system, the TDD contrast maps showed consistent tumor sub-regions indicating different dominating TDD effects, potentially providing information on the spatial tumor heterogeneity. On the MRI-Linac, the available TDD contrast measured in asparagus showed the same trends as with the conventional MRI but remained close to typical measurement noise levels when simulated in common cancer cell sizes. On conventional MRI systems with moderate gradient strengths, the TDD contrast could potentially be used as a tool to identify which time-dependent effects to include when choosing a biophysical model for more specific tumor characterization.

Assessing the Tumor Immune Landscape Across Multiple Spatial Scales to Differentiate Immunotherapy Response in Metastatic Non-Small Cell Lung Cancer

Although immune checkpoint inhibitor-based therapy has shown promising results in non-small cell lung cancer patients with high programmed death-ligand 1 expression, not all patients respond to therapy. The tumor microenvironment (TME) is complex and heterogeneous, making it challenging to understand the key agents and features that influence response to therapies. In this study, we leverage multiplex fluorescent immunohistochemistry to quantitatively assess interactions between tumor and immune cells in an effort to identify patterns occurring at multiple spatial levels of the TME. To do so, we introduce several computational methods novel to a data set of 1,269 multiplex fluorescent immunohistochemistry images from a cohort of 52 patients with metastatic non-small cell lung cancer. With the spatial G-cross function, we quantify the degree of cell interaction at an entire image level, where we see significantly increased activity of cytotoxic T cells and helper T cells with epithelial tumor cells in responders to immune checkpoint inhibitor-based (P = .022 and P < .001, respectively) and decreased activity of T-regulatory cells with epithelial tumor cells compared with nonresponders (P = .010). By leveraging spatial overlap methods, we define tumor subregions (which we call the tumor “periphery,” “edge.” and “center”) and discover more localized immune-immune interactions influencing positive response, including those between cytotoxic T cells and helper T cells with antigen presenting cells in these subregions specifically. Finally, we trained an interpretable deep learning model that identified key cellular regions of interest that most influenced response classification (area under the curve = 0.71 ± 0.02). Assessing spatial interactions within these subregions further revealed new insights that were not significant at the whole image level, particularly the elevated association of antigen presenting cells and T-regulatory cells with one another in responder groups (P = .024). Altogether, we demonstrate that elucidating patterns of cell composition and interplay across multiple levels of spatial analyses can improve our understanding of the TME and better differentiate patient responses to immunotherapy.

Diffusion MRI is superior to quantitative T2-FLAIR mismatch in predicting molecular subtypes of human non-enhancing gliomas.

This study compared the classification performance of normalized apparent diffusion coefficient (nADC) with percentage T2-FLAIR mismatch-volume (%T2FM-volume) for differentiating between IDH-mutant astrocytoma (IDHm-A) and other glioma molecular subtypes. A total of 105 non-enhancing gliomas were studied. T2-FLAIR digital subtraction maps were used to identify T2FM and T2-FLAIR non-mismatch (T2FNM) subregions within tumor volumes of interest (VOIs). Median nADC from the whole tumor, T2FM, and T2NFM subregions and %T2FM-volume were obtained. IDHm-A classification analyses using receiver-operating characteristic curves and multiple logistic regression were performed in addition to exploratory survival analyses. T2FM subregions had significantly higher nADC than T2FNM subregions within IDHm-A with ≥ 25% T2FM-volume (P < 0.0001). IDHm-A with ≥ 25% T2FM-volume demonstrated significantly higher whole tumor nADC compared to IDHm-A with < 25% T2FM-volume (P < 0.0001), and both IDHm-A subgroups demonstrated significantly higher nADC compared to IDH-mutant oligodendroglioma and IDH-wild-type gliomas (P < 0.05). For classification of IDHm-A vs. other gliomas, the area under curve (AUC) of nADC was significantly greater compared to the AUC of %T2FM-volume (P = 0.01, nADC AUC = 0.848, %T2FM-volume AUC = 0.714) along with greater sensitivity. In exploratory survival analyses within IDHm-A, %T2FM-volume was not associated with overall survival (P = 0.2), but there were non-significant trends for nADC (P = 0.07) and tumor volume (P = 0.051). T2-FLAIR subtraction maps are useful for characterizing IDHm-A imaging characteristics. nADC outperforms %T2FM-volume for classifying IDHm-A amongst non-enhancing gliomas with preserved high specificity and increased sensitivity, which may be related to inherent diffusivity differences regardless of T2FM. In line with previous findings on visual T2FM-sign, quantitative %T2FM-volume may not be prognostic.

Patient-based multilevel transcriptome exploration highlights relevant chemokines and chemokine receptor axes in glioblastoma

Chemokines and their receptors form a complex interaction network, crucial for precise leukocyte positioning and trafficking. In cancer, they promote malignant cell proliferation and survival but are also critical for immune cell infiltration in the tumor microenvironment. Glioblastoma (GBM) is the most common and lethal brain tumor, characterized by an immunosuppressive TME, with restricted immune cell infiltration. A better understanding of chemokine-receptor interactions is therefore essential for improving tumor immunogenicity. In this study, we assessed the expression of all human chemokines in adult-type diffuse gliomas, with particular focus on GBM, based on patient-derived samples. Publicly available bulk RNA sequencing datasets allowed us to identify the chemokines most abundantly expressed in GBM, with regard to disease severity and across different tumor subregions. To gain insight into the chemokines–receptor network at the single cell resolution, we explored GBmap, a curated resource integrating multiple scRNAseq datasets from different published studies. Our study constitutes the first patient–based handbook highlighting the relevant chemokine–receptor crosstalks, which are of significant interest in the perspective of a therapeutic modulation of the TME in GBM.

Mapping Tumor Habitats in IDH-Wild Type Glioblastoma: Integrating MR Imaging, Pathologic, and RNA Data from Ivy Glioblastoma Atlas Project.

To spatially validate intratumoral subregions (tumor habitat) using physiologic MRI on pathology of the isocitrate dehydrogenase (IDH)-wildtype whole-glioblastoma sample. Data of 20 patients (168 slides) were obtained from the Ivy Glioblastoma Atlas Project. On MRI, tumor habitats were defined using voxel-wise clustering of apparent diffusion coefficient (ADC) and cerebral blood volume (CBV) maps for contrast-enhancing lesion (CEL) and non-enhancing lesion (NEL). On pathology slides, normalized areas of leading edge (LE), infiltrating tumor (IT), cellular tumor (CT), hypervascular lesion (CThypervascular), and perinecrotic lesion (CTperinecrotic) were obtained. Gross specimen was co-registered on MRI and correlation between pathology-MRI habitats was calculated. RNA sequencing of 67 samples was assessed using 4 Neftel subtypes and further correlated with pathology. Six tumor habitats were identified: hypervascular, hypovascular cellular, and hypovascular hypocellular habitats for CEL and NEL. CT was correlated with hypovascular cellular habitat in CEL (r= 0.238, p =.005). IT was correlated with hypovascular cellular habitat in NEL (r= 0.294, p =.017). CThypervascular was correlated with hypervascular habitat in NEL (r= 0.195, p = .023). CTperinecrotic was correlated with imaging necrosis (r= 0.199, p =.005). Astrocyte-like subtypes were correlated with IT (r= 0.256, p <.001), while mesenchymal-like subtypes were correlated with CTperinecrotic area (r= 0.246, p <.001). Pathologically matched tumor subregions were cellular tumor with hypovascular cellular habitat in CEL and infiltrative tumor with hypovascular cellular habitat in NEL. Identification of the most aggressive as well as infiltrative tumor portion can be achieved using non-invasive MRI tumor habitats.

DUNET D UNET Dilated UNET for Brain Tumor Sub Region Segmentation using MRI Images

The precise diagnosis and treatment planning of brain tumors significantly rely on the accurate segmentation of sub-regions from Magnetic Resonance Imaging (MRI) data. In this research, we propose a framework, D-UNET (Dilated-UNET), which enhances the traditional UNET architecture by incorporating dilated convolutions. UNET is the deep CNN architecture widely adopted for biomedical image segmentation tasks. D-UNET is specifically designed for brain tumor sub-region segmentation from multi-modal (T1, T2, T1ce, Flair) MRI images in nifti file format, each comprising 155 slices. The framework comprises of four distinct steps viz. data collection, data preprocessing, model training, and outcome evaluation. D-UNET employs two key modules during training, the dilated encoding module and the dilated decoding module. These modules enable the model to efficiently capture multi-scale contextual information, facilitating better representation learning for complex and varied tumor sub[1]regions. We evaluated the performance of D-UNET using Intersection over Union and Dice Coefficient metrics. The experimental results demonstrate that D-UNET outperforms the traditional UNET and other benchmark models in terms of segmentation accuracy. Notably, D-UNET excels in capturing finer details and intricate shapes of tumor sub-regions, contributing to its superiority in brain tumor segmentation. The ability to precisely delineate tumor sub-regions from different modalities provides crucial insights for medical professionals in treatment planning and decision-making.

Habitat Imaging With Tumoral and Peritumoral Radiomics for Prediction of Lung Adenocarcinoma Invasiveness on Preoperative Chest CT: A Multicenter Study.

Background: Tumors' growth processes result in spatial heterogeneity, with the development of tumor subregions (i.e., habitats) having unique biologic characteristics. Objective: To develop and validate a habitat model combining tumor and peritumoral radiomics features on chest CT for predicting invasiveness of lung adenocarcinoma. Methods: This retrospective study included 1156 patients (mean age, 57.5 years; 464 male, 692 female) from three centers and a public dataset, who underwent chest CT before lung adenocarcinoma resection (variable date ranges across datasets). Patients from one center formed training (n=500) and validation (n=215) sets; patients from the other sources formed three external test sets (n=249, 113, 79). For each patient, a single nodule was manually segmented on chest CT. The nodule segmentation was combined with an automatically generated 4-mm peritumoral region into a whole-volume volume-of-interest (VOI). A Gaussian mixture model (GMM) identified voxel clusters with similar first-order energy across patients. GMM results were used to divide each patient's whole-volume VOI into multiple habitats, defined consistently across patients. Radiomic features were extracted from each habitat. After feature selection, a habitat model was developed for predicting invasiveness, using pathologic assessment as a reference. An integrated model was constructed, combining features extracted from habitats and whole-volume VOIs. Model performance was evaluated, including in subgroups based on nodule density (pure ground-glass, part-solid, solid). Results: Invasive cancer was diagnosed in 625/1156 patients. GMM identified four as the optimal number of voxel clusters and thus of per-patient tumor habitats. The habitat model had AUC of 0.932 in the validation set, and 0.881, 0.880, and 0.764 in the three external test sets. The integrated model had AUC of 0.947 in the validation set and 0.936, 0.908, and 0.800 in the three external test sets. In the three external test sets combined, across nodule densities, AUCs for the habitat model were 0.836-0.969 and for the integrated model were 0.846-0.917. Conclusions: Habitat imaging combining tumoral and peritumoral radiomic features could help predict lung adenocarcinoma invasiveness. Prediction is improved when combining information on tumor subregions and the tumor overall. Clinical Impact: The findings may aid personalized preoperative assessments to guide clinical decision-making in lung adenocarcinoma.

A 3D hierarchical cross-modality interaction network using transformers and convolutions for brain glioma segmentation in MR images.

Precise glioma segmentation from multi-parametric magnetic resonance (MR) images is essential for brain glioma diagnosis. However, due to the indistinct boundaries between tumor sub-regions and the heterogeneous appearances of gliomas in volumetric MR scans, designing a reliable and automated glioma segmentation method is still challenging. Although existing 3D Transformer-based or convolution-based segmentation networks have obtained promising results via multi-modal feature fusion strategies or contextual learning methods, they widely lack the capability of hierarchical interactions between different modalities and cannot effectively learn comprehensive feature representations related to all glioma sub-regions. To overcome these problems, in this paper, we propose a 3D hierarchical cross-modality interaction network (HCMINet) using Transformers and convolutions for accurate multi-modal glioma segmentation, which leverages an effective hierarchical cross-modality interaction strategy to sufficiently learn modality-specific and modality-shared knowledge correlated to glioma sub-region segmentation from multi-parametric MR images. In the HCMINet, we first design a hierarchical cross-modality interaction Transformer (HCMITrans) encoder to hierarchically encode and fuse heterogeneous multi-modal features by Transformer-based intra-modal embeddings and inter-modal interactions in multiple encoding stages, which effectively captures complex cross-modality correlations while modeling global contexts. Then, we collaborate an HCMITrans encoder with a modality-shared convolutional encoder to construct the dual-encoder architecture in the encoding stage, which can learn the abundant contextual information from global and local perspectives. Finally, in the decoding stage, we present a progressive hybrid context fusion (PHCF) decoder to progressively fuse local and global features extracted by the dual-encoder architecture, which utilizes the local-global context fusion (LGCF) module to efficiently alleviate the contextual discrepancy among the decoding features. Extensive experiments are conducted on two public and competitive glioma benchmark datasets, including the BraTS2020 dataset with 494 patients and the BraTS2021 dataset with 1251 patients. Results show that our proposed method outperforms existing Transformer-based and CNN-based methods using other multi-modal fusion strategies in our experiments. Specifically, the proposed HCMINet achieves state-of-the-art mean DSC values of 85.33% and 91.09% on the BraTS2020 online validation dataset and the BraTS2021 local testing dataset, respectively. Our proposed method can accurately and automatically segment glioma regions from multi-parametric MR images, which is beneficial for the quantitative analysis of brain gliomas and helpful for reducing the annotation burden of neuroradiologists.

GWO+RuleFit: rule-based explainable machine-learning combined with heuristics to predict mid-treatment FDG PET response to chemoradiation for locally advanced non-small cell lung cancer.

Objective.Vital rules learned from fluorodeoxyglucose positron emission tomography (FDG-PET) radiomics of tumor subregional response can provide clinical decision support for precise treatment adaptation. We combined a rule-based machine learning (ML) model (RuleFit) with a heuristic algorithm (gray wolf optimizer, GWO) for mid-chemoradiation FDG-PET response prediction in patients with locally advanced non-small cell lung cancer.Approach.Tumors subregions were identified using K-means clustering. GWO+RuleFit consists of three main parts: (i) a random forest is constructed based on conventional features or radiomic features extracted from tumor regions or subregions in FDG-PET images, from which the initial rules are generated; (ii) GWO is used for iterative rule selection; (iii) the selected rules are fit to a linear model to make predictions about the target variable. Two target variables were considered: a binary response measure (ΔSUVmean ⩾ 20% decline) for classification and a continuous response measure (ΔSUVmean) for regression. GWO+RuleFit was benchmarked against common ML algorithms and RuleFit, with leave-one-out cross-validated performance evaluated by the area under the receiver operating characteristic curve (AUC) in classification and root-mean-square error (RMSE) in regression.Main results.GWO+RuleFit selected 15 rules from the radiomic feature dataset of 23 patients. For treatment response classification, GWO+RuleFit attained numerically better cross-validated performance than RuleFit across tumor regions and sets of features (AUC: 0.58-0.86 vs. 0.52-0.78,p= 0.170-0.925). GWO+Rulefit also had the best or second-best performance numerically compared to all other algorithms for all conditions. For treatment response regression prediction, GWO+RuleFit (RMSE: 0.162-0.192) performed better numerically for low-dimensional models (p= 0.097-0.614) and significantly better for high-dimensional models across all tumor regions except one (RMSE: 0.189-0.219,p< 0.004).Significance. The GWO+RuleFit selected rules were interpretable, highlighting distinct radiomic phenotypes that modulated treatment response. GWO+Rulefit achieved parsimonious models while maintaining utility for treatment response prediction, which can aid clinical decisions for patient risk stratification, treatment selection, and biologically driven adaptation. Clinical trial: NCT02773238.

IMG-08. SYNTHESIZING MISSING MRI SEQUENCES IN PEDIATRIC BRAIN TUMORS USING GENERATIVE ADVERSARIAL NETWORKS; TOWARDS IMPROVED VOLUMETRIC TUMOR ASSESSMENT

Abstract BACKGROUND Standard MRI sequences, such as pre- and post-contrast T1w, T2w, and FLAIR images, are essential for optimizing segmentation of tumor subregions and evaluating treatment responses in pediatric brain tumors (PBTs). However, MRI sets are often incomplete due to imaging artifacts or inconsistent acquisition protocols across various centers. Generative Adversarial Networks (GANs) have been effectively utilized to generate missing MRI sequences for adult brain tumors. This study applies image-to-image translation models using GANs to synthesize missing FLAIR images from T2w images in PBTs. METHODS This retrospective study developed two GAN models, pix2pix in both 2D and 3D, trained and validated on T2w and FLAIR image pairs from 79 and 19 patients, respectively, with pediatric-type diffuse high-grade gliomas (diffuse midline glioma (DMG) including diffuse intrinsic pontine glioma (DIPG)), collected from the Children’s Brain Tumor Network (CBTN). The 2D pix2pix model processes each T2w MRI volume slice-by-slice, generating corresponding FLAIR slices to reconstruct the complete image volume. The 3D pix2pix model allows translation of 3D FLAIR volumes directly from T2w volumes without the need for individual slice processing and reconstruction. The quality of the generated FLAIR volumes was evaluated using Structural Similarity Index (SSI; best closer to 1) and Mean Squared Error (MSE; best near 0) on the validation set. RESULTS The 2D and 3D models achieved robust performance with median SSI, MSE of 0.88, 0.004, and 0.92, 0.002, respectively. CONCLUSIONS The GAN models developed in this study effectively generate missing FLAIR MRI volumes from corresponding T2w images in PBTs. The 3D model, outperforming 2D, speeds the overall processing pipeline by eliminating volume slicing and reconstruction. Future work includes assessing the impact of these synthesized images on the accuracy of our pretrained autosegmentation models in differentiating tumor subregions and measuring tumor volumes in longitudinal MRIs.

CT-based quantification of intratumoral heterogeneity for predicting pathologic complete response to neoadjuvant immunochemotherapy in non-small cell lung cancer.

To investigate the prediction of pathologic complete response (pCR) in patients with non-small cell lung cancer (NSCLC) undergoing neoadjuvant immunochemotherapy (NAIC) using quantification of intratumoral heterogeneity from pre-treatment CT image. This retrospective study included 178 patients with NSCLC who underwent NAIC at 4 different centers. The training set comprised 108 patients from center A, while the external validation set consisted of 70 patients from center B, center C, and center D. The traditional radiomics model was contrasted using radiomics features. The radiomics features of each pixel within the tumor region of interest (ROI) were extracted. The optimal division of tumor subregions was determined using the K-means unsupervised clustering method. The internal tumor heterogeneity habitat model was developed using the habitats features from each tumor sub-region. The LR algorithm was employed in this study to construct a machine learning prediction model. The diagnostic performance of the model was evaluated using criteria such as area under the receiver operating characteristic curve (AUC), accuracy, specificity, sensitivity, positive predictive value (PPV), and negative predictive value (NPV). In the training cohort, the traditional radiomics model achieved an AUC of 0.778 [95% confidence interval (CI): 0.688-0.868], while the tumor internal heterogeneity habitat model achieved an AUC of 0.861 (95% CI: 0.789-0.932). The tumor internal heterogeneity habitat model exhibits a higher AUC value. It demonstrates an accuracy of 0.815, surpassing the accuracy of 0.685 achieved by traditional radiomics models. In the external validation cohort, the AUC values of the two models were 0.723 (CI: 0.591-0.855) and 0.781 (95% CI: 0.673-0.889), respectively. The habitat model continues to exhibit higher AUC values. In terms of accuracy evaluation, the tumor heterogeneity habitat model outperforms the traditional radiomics model, achieving a score of 0.743 compared to 0.686. The quantitative analysis of intratumoral heterogeneity using CT to predict pCR in NSCLC patients undergoing NAIC holds the potential to inform clinical decision-making for resectable NSCLC patients, prevent overtreatment, and enable personalized and precise cancer management.

Radiomics Analysis of Quantitative Maps from Synthetic MRI for Predicting Grades and Molecular Subtypes of Diffuse Gliomas.

To investigate the feasibility of using radiomics analysis of quantitative maps from synthetic MRI to preoperatively predict diffuse glioma grades, isocitrate dehydrogenase (IDH) subtypes, and 1p/19q codeletion status. Data from 124 patients with diffuse glioma were used for analysis (n = 87 for training, n = 37 for testing). Quantitative T1, T2, and proton density (PD) maps were obtained using synthetic MRI. Enhancing tumour (ET), non-enhancing tumour and necrosis (NET), and peritumoral edema (PE) regions were segmented followed by manual fine-tuning. Features were extracted using PyRadiomics and then selected using Levene/T, BorutaShap and maximum relevance minimum redundancy algorithms. Asupport vector machine was adopted for classification. Receiver operating characteristic curve analysis and integrated discrimination improvement analysis were implemented to compare the performance of different radiomics models. Radiomics models constructed using features from multiple tumour subregions (ET + NET + PE) in the combined maps (T1 + T2 + PD) achieved the highest AUC in all three prediction tasks, among which the AUC for differentiating lower-grade and high-grade diffuse gliomas, predicting IDH mutation status and predicting 1p/19q codeletion status were 0.92, 0.95 and 0.86 respectively. Compared with those constructed on individual T1, T2, and PD maps, the discriminant ability of radiomics models constructed on the combined maps separately increased by 11, 17 and 10% in predicting glioma grades, 35, 52 and 19% in predicting IDH mutation status, and 16, 15 and 14% in predicting 1p/19q codeletion status (p < 0.05). Radiomics analysis of quantitative maps from synthetic MRI provides anew quantitative imaging tool for the preoperative prediction of grades and molecular subtypes in diffuse gliomas.

Deep learning automatic semantic segmentation of glioblastoma multiforme regions on multimodal magnetic resonance images.

In patients having naïve glioblastoma multiforme (GBM), this study aims to assess the efficacy of Deep Learning algorithms in automating the segmentation of brain magnetic resonance (MR) images to accurately determine 3D masks for 4 distinct regions: enhanced tumor, peritumoral edema, non-enhanced/necrotic tumor, and total tumor. A 3D U-Net neural network algorithm was developed for semantic segmentation of GBM. The training dataset was manually delineated by a group of expert neuroradiologists on MR images from the Brain Tumor Segmentation Challenge 2021 (BraTS2021) image repository, as ground truth labels for diverse glioma (GBM and low-grade glioma) subregions across four MR sequences (T1w, T1w-contrast enhanced, T2w, and FLAIR) in 1251 patients. The in-house test was performed on 50GBM patients from our cohort (PerProGlio project). By exploring various hyperparameters, the network's performance was optimized, and the most optimal parameter configuration was identified. The assessment of the optimized network's performance utilized Dice scores, precision, and sensitivity metrics. Our adaptation of the 3D U-net with additional residual blocks demonstrated reliable performance on both the BraTS2021 dataset and the in-house PerProGlio cohort, employing only T1w-ce sequences for enhancement and non-enhanced/necrotic tumor models and T1w-ce + T2w + FLAIR for peritumoral edema and total tumor. The mean Dice scores (training and test) were 0.89 and 0.75; 0.75 and 0.64; 0.79 and 0.71; and 0.60 and 0.55, for total tumor, edema, enhanced tumor, and non-enhanced/necrotic tumor, respectively. The results underscore the high precision with which our network can effectively segment GBM tumors and their distinct subregions. The level of accuracy achieved agrees with the coefficients recorded in previous GBM studies. In particular, our approach allows model specialization for each of the different tumor subregions employing only those MR sequences that provide value for segmentation.

Mixture-of-experts and semantic-guided network for brain tumor segmentation with missing MRI modalities.

Accurate brain tumor segmentation with multi-modal MRI images is crucial, but missing modalities in clinical practice often reduce accuracy. The aim of this study is to propose a mixture-of-experts and semantic-guided network to tackle the issue of missing modalities in brain tumor segmentation. We introduce a transformer-based encoder with novel mixture-of-experts blocks. In each block, four modality experts aim for modality-specific feature learning. Learnable modality embeddings are employed to alleviate the negative effect of missing modalities. We also introduce a decoder guided by semantic information, designed to pay higher attention to various tumor regions. Finally, we conduct extensive comparison experiments with other models as well as ablation experiments to validate the performance of the proposed model on the BraTS2018 dataset. The proposed model can accurately segment brain tumor sub-regions even with missing modalities. It achieves an average Dice score of 0.81 for the whole tumor, 0.66 for the tumor core, and 0.52 for the enhanced tumor across the 15 modality combinations, achieving top or near-top results in most cases, while also exhibiting a lower computational cost. Our mixture-of-experts and sematic-guided network achieves accurate and reliable brain tumor segmentation results with missing modalities, indicating its significant potential for clinical applications. Our source code is already available at https://github.com/MaggieLSY/MESG-Net .

Hypoxia coordinates the spatial landscape of myeloid cells within glioblastoma to affect survival.

Myeloid cells are highly prevalent in glioblastoma (GBM), existing in a spectrum of phenotypic and activation states. We now have limited knowledge of the tumor microenvironment (TME) determinants that influence the localization and the functions of the diverse myeloid cell populations in GBM. Here, we have utilized orthogonal imaging mass cytometry with single-cell and spatial transcriptomic approaches to identify and map the various myeloid populations in the human GBM tumor microenvironment (TME). Our results show that different myeloid populations have distinct and reproducible compartmentalization patterns in the GBM TME that is driven by tissue hypoxia, regional chemokine signaling, and varied homotypic and heterotypic cellular interactions. We subsequently identified specific tumor subregions in GBM, based on composition of identified myeloid cell populations, that were linked to patient survival. Our results provide insight into the spatial organization of myeloid cell subpopulations in GBM, and how this is predictive of clinical outcome.