International Journal of Radiation Oncology*Biology*Physics

Abstract: Purpose: Recurrence in high grade glioma (HGG) predominantly occurs within the high dose radiation field, raising the question of whether treatment failure reflects limitations in radiation target delineation or is driven by intrinsic tumor biology. This study evaluated recurrence patterns following standard chemoradiotherapy and their treatment implications. Material and Methods: This retrospective single center study included 41 patients with histologically confirmed HGG treated with surgery followed by radiotherapy with concurrent and adjuvant temozolomide (TMZ). Patients were followed through August 2018; those with recurrence were included in the analysis. Recurrence patterns were classified based on their spatial relationship to the 60 Gy isodose line as central, infield, marginal, or distant. Survival outcomes were estimated using the Kaplan-Meier method and compared using the log rank test. Results: The most common pattern of recurrence was central (15 patients, 36.5%), followed by infield (11, 26.8%), distant (6, 14.6%), marginal (5, 12.1%), and multicentric (4, 9.8%). Central and in field recurrences (local failures) accounted for 26 patients (63%). Median overall survival (OS) was 27 months, and median progression-free survival (PFS) was 12 months. Survival differed significantly by recurrence pattern (log-rank p = 0.018), with marginal recurrence associated with more favorable outcomes. Conclusion: The predominance of central and infield recurrences within the high-dose region suggests that treatment failure in HGG is not solely explained by inadequate target delineation and may also be driven, in part, by intrinsic tumor biology, including radioresistant subpopulations and tumor heterogeneity. Future strategies may benefit from incorporating biologically guided approaches alongside optimization of radiation treatment parameters.

Purpose: Manual verification of AI-based auto-contouring is labor-intensive and prone to fatigue-related errors. This study developed the large language model (LLM)-based automated Quality Assurance (QA) for auto-contouring (LAQUA) system using a multimodal LLM, Gemini 2.5 Pro, and evaluated its feasibility as a clinical primary screening tool to streamline the QA workflow. Methods: Twenty male pelvic CT scans from an open dataset were utilized. Three distinct auto-contouring software packages (OncoStudio, RatoGuide prototype and syngo.via) were evaluated. Auto-contouring results for each slice were exported as PDF images with overlaid contours and input into Gemini 2.5 Pro. The LLM was instructed to rate the contour quality on a 5-point clinical scale (5: Optimal; 4: Acceptable; 3: Suboptimal; 2: Unacceptable; redraw from scratch; 1: Unacceptable; organ not detected). Using evaluations by two board-certified radiation oncologists as ground truth, Spearman's rank correlation coefficients ({rho}) and weighted kappa coefficients ({kappa}) were calculated. Additionally, to assess screening performance, sensitivity and specificity were calculated by dichotomizing the scores into "Pass" and "Fail" using two different cutoffs (scores [≥] 3 and [≥] 4 as "Pass"). Finally, the alignment of the rationales provided by the LLM with the auto-contouring quality was evaluated by two board-certified radiation oncologists. This was conducted using a Likert scale assessing four domains (error detection, hallucination, clinical relevance, and anatomical understanding), each scored out of 2 points. Results: The LAQUA system demonstrated moderate to strong agreement with expert judgments across all evaluated organs ({rho}: 0.567 - 0.835; quadratic weighted {kappa} : 0.639 - 0.804), with the rectum showing the highest correlation. Regarding screening performance, a cutoff of [≥]3 as "Pass" achieved the highest sensitivity and specificity in specific subgroups, but with wide 95% confidence intervals (CIs). A cutoff of [≥]4 as "Pass" narrowed the CIs, yielding the highest sensitivity in the rectum (0.976) and the highest specificity in the left femoral head (0.933). Qualitatively, the LLM's rationales achieved an overall mean score of 1.70 {+/-} 0.48 (out of 2), with 155 of 291 outputs receiving perfect scores across all criteria. Conclusions: The LAQUA system demonstrated substantial agreement with expert evaluations in AI-based auto-contouring quality assessment. While potential overestimation bias (risk of missing "Fail" cases) warrants caution, the observed sensitivity suggests its feasibility as a primary screening QA tool to efficiently filter acceptable contours, thereby reducing the clinical workload.

Background Cardiovascular adverse events (CVAEs) after chemoradiotherapy (CRT) for lung cancer are major concerns in Appalachia due to high rates of smoking and pre-existing cardiovascular diseases (CVD). The objectives of this study were to characterize the incidence of CVAEs in this population and evaluate machine learning (ML) models for CVAEs risk stratification and mortality prediction. Methods A retrospective study was conducted among Appalachian patients with lung cancer treated with definitive CRT at a single institution between 2013 and 2025. Baseline clinical variables, including demographics, smoking status, pre-existing CVD, and post-CRT CVAEs were collected. Heart dosimetric parameters were also obtained. ML models [Random Forest (RF), Gradient Boosting (GBM), Support Vector Machine (SVM), Logistic Regression (LR)] were trained using 5 fold cross validation and evaluated using AUC, sensitivity, specificity, and F1 score. Feature importance was assessed using permutation analysis. Wilcoxon and Chi-squared tests were used for descriptive comparisons. Results Eighty-six patients (mean age 66 years, 47% male) were included. At diagnosis, 80% (n=69) had NSCLC and 20% (n=17) had LS-SCLC. CVAEs occurred in 51 patients (59%). The most frequent events were NSTEMI (n=15, 29.4%), pericardial disease (n=15, 29.4%), and arrhythmia (n=8, 15.7%). Mean heart dose was higher in the CVAE group (13.4 vs 9.4 Gy, p=0.27). For CVAE prediction, GBM achieved the highest AUC (0.55, 95% CI 0.44-0.69) and sensitivity (75%), while RF showed the highest sensitivity (80%, 95% CI 69-90%). Key predictors included age and cardiac dosimetrists (Heart V20, V40, V50, and mean heart dose). For mortality prediction, RF achieved the highest discrimination (AUC = 0.63, 95% CI 0.496-0.750). Age, cardiac dosimetry, disease stage, and cardiovascular comorbidity were the most influential predictors. Conclusion High incidence of CVAEs occurred among patients with lung cancer treated with CRT in this Appalachian cohort. While ML models demonstrated modest predictive performance, tree-based approaches demonstrated high sensitivity for identifying patients at risk for CVAEs and mortality. Age and cardiac radiation dose metrics consistently emerged as key predictors, highlighting the importance of cardiac dose optimization and ML-based risk stratification for cardio-oncology surveillance.

BACKGROUNDSubcutaneous white adipose tissue (scWAT), a key metabolic and endocrine organ, is inevitably exposed during radiotherapy (RT). While RT is a cornerstone of cancer treatment, its efficacy is limited by toxicity to surrounding healthy tissues. Ultra-high dose rate (FLASH) RT has emerged as a promising modality capable of preserving tumor control while reducing normal tissue damage - the so-called FLASH effect. Clinical evidence indicates that childhood exposure to conventional (CONV) RT is associated with long-term dysmetabolism and WAT dysfunction. However, the impact of FLASH-RT on WAT has not been investigated. AIMTo compare the effects of FLASH- and CONV-RT on adipocyte function and scWAT homeostasis, and to identify molecular and structural changes associated with each modality. METHODSWe evaluated the effects of FLASH- and CONV-RT on adipocytes and scWAT using a dedicated linear accelerator capable of delivering both modalities. Experiments were performed in the human SGBS preadipocyte/adipocyte cell line and in a mouse model subjected to proximal hind limb irradiation, with analyses conducted 70 days post-exposure. RESULTSRT impaired adipogenic differentiation in a dose-dependent manner, with a relative sparing effect of FLASH at 4-8 Gy. Mature adipocytes exhibited radioresistance, with protection by FLASH at 8 Gy. In vivo, both regimens reduced fat mass without affecting body weight, with greater loss following CONV-RT. Transcriptomic profiling of scWAT revealed inflammatory and neurodegenerative signatures after CONV-RT, whereas FLASH-RT induced minimal transcriptional changes. Histological and ultrastructural analyses confirmed increased cellular damage, vacuolization, lipid spill-over, and reduced PLIN1 expression, predominantly in CONV-treated mice. CONCLUSIONSWAT homeostasis is sensitive to conventional RT, whereas FLASH-RT better preserves tissue structure and function, with implications for long-term metabolic health in cancer survivors.

Humanized mice (hu-mice), which recapitulate the human immune system, have become increasingly important for preclinical immunotherapy studies. Among these models, the human peripheral blood mononuclear cells (PBMC)-engrafted hu-mice model is the simplest and fastest. However, its utility is hindered by the development of lethal graft-versus-host disease (GvHD) and the insufficient reconstitution of human leukocytes. To address these limitations, we developed PBMC hu-mice models using a novel strain, NOD-CD47nullRag2nullIL-2r{gamma}null (RTKO) focusing on the immunological defects of the NOD strain and the immunotolerance provided by CD47 deficiency. Six-week-old female NOD-Rag2nullIL-2r{gamma}null (RID) and RTKO mice were intravenously injected with three different PBMC doses (3x106, 5x106, and 1x107 cells). At standard doses (5x106 and 1x107 cells), RTKO mice exhibited enhanced engraftment of human leukocytes, though GvHD was more severe compared to the RID strain, resulting in a limited experimental window. However, in a subsequent trial using a lower dose of PBMCs (3 x 106 cells), RTKO mice demonstrated notable advantages, including stable reconstitution of human leukocytes, milder GvHD symptoms without life-threatening lesions, and a markedly prolonged experimental window. Considering the difficulties in generating hematopoietic stem cell (HSC)-engrafted hu-mice, the extended experimental window provided by this model, which is comparable to HSC hu-mice, is a significant improvement. Moreover, the radiation tolerance conferred by the Rag gene mutation in this model offers another advantage for radiotherapy research. Consequently, the low-dose PBMC RTKO model serves as a versatile and valuable platform for a broad spectrum of immunotherapy studies, especially in the field of immuno-oncology.

Optimizing radiotherapy dose distributions remain a resource-intensive bottleneck. Existing AI-based dose prediction methods often have limited generalizability because they rely on small, heterogeneous datasets. We present nnDoseNetv2, an auto-configured, end-to-end framework for dose prediction across diverse disease sites (head and neck, prostate, breast, and lung), prescription levels (1.5-84 Gy), and treatment modalities (IMRT, VMAT, and 3D-CRT). By integrating machine-specific beam geometry with 3D structural information, the framework is designed to generalize across varied clinical scenarios. A single multi-site model was trained on 1,000 clinical plans. On sites seen during training, performance was comparable to specialized site-specific models. On unseen sites (liver and whole brain), the model outperformed site-specific models, with mean absolute errors of 2.46% and 6.97% of prescription, respectively. These results suggest that geometric awareness can bridge disparate anatomical domains while eliminating the need for site-specific model maintenance, providing a scalable and high-fidelity approach for personalized radiotherapy planning.

Definitive radiotherapy (RT) for prostate cancer (PC) with dose intensification and/or focal boosting has excellent oncologic outcomes, but many patients experience adverse events. Dose escalation to the whole prostate improves outcomes at the expense of increased late adverse events. Intraprostatic recurrence after definitive RT typically occurs at the site of the primary tumor, suggesting that dose to the site of the dominant lesion is an important predictor of future failure. The efficacy and safety of tumor-focused RT compared to that of standard RT for definitive treatment of localized PC has not been assessed. RadTARGET (RAdiation Dose TAiloRing Guided by Enhanced Targeting) is a phase II randomized trial that aims to demonstrate superior safety of image-guided, tumor-focused RT compared to standard RT for acute genitourinary (GU) or gastrointestinal (GI) in the setting of definitive RT for intermediate- and high-risk PC. The study intervention is image-guided, tumor-focused RT with dose intensification of cancer visible on imaging and dose de-intensification to remaining prostate. Patients will be randomized to two arms: those who receive standard RT dose and those that receive tumor-focused RT. The study population will be patients with intermediate- or high-risk PC planning to undergo definitive RT with or without systemic therapy. The primary endpoint to compare between randomized arms is acute GU or GI grade [≥]2 adverse events. Participant and study duration are 5 years and 8 years, respectively. RadTARGET will compare the efficacy and safety of tumor-focused RT to that of standard RT for definitive treatment of localized PC. We hypothesize that the tumor-focused approach will substantially reduce adverse events after prostate RT while retaining high efficacy. If this hypothesis is confirmed, we will conclude that a phase III randomized control trial is warranted to formally establish oncologic non-inferiority compared to the current standard of whole-gland dose escalation.

Background: Glioblastoma (GBM) is the most aggressive primary brain tumor in adults. Radioresistance, partly mediated by glioma stem-like cells, represents a major clinical challenge which could be overcome by the identification of the modulators of radioresistance. Existing CRISPR screens in human GBM models have largely used two-dimensional cultures with short-term viability readouts, failing to capture the long-term clonogenic behaviour underlying tumour recurrence after radiotherapy. Method: We developed ClonoScreen3D-CRISPRi, combining CRISPRi-mediated gene knockdown with three-dimensional clonogenic survival assays. Two GBM cell lines (G7 and GBML20), differing in MGMT promoter methylation status, were engineered to express the KRAB-dCas9 editor. Nine candidate radiosensitivity modifiers, selected through transcriptomic analysis, pharmacological studies, and literature review, were examined in both lines. Target validation was performed using full radiation dose-response assays and a pharmacological inhibitor. Results: The majority of candidate genes significantly altered survival fraction following irradiation in both cell lines. Knockdown of NFKB2, RELB, and CDK9 produced the most potent radiosensitization, with sensitizer enhancement ratios of 1.39-1.70 in validation studies, exceeding those of established radiosensitizers including PARP and ATM inhibitors. Notably, knockdown of these genes induced no significant cytotoxicity in the absence of radiation. Pharmacological validation using an IKK inhibitor confirmed these findings, implicating non-canonical NF-{kappa}{beta} signalling and CDK9-dependent transcriptional elongation as critical adaptive mechanisms in GBM radioresistance. Conclusions: ClonoScreen3D-CRISPRi is a scalable, physiologically relevant platform for identifying genetic modifiers of radioresistance. The non-canonical NF-{kappa}{beta} pathway and CDK9 represent promising radiosensitizing targets, and larger screens could enable systematic prioritisation of candidates for clinical translation.

BackgroundGallium (Ga) is a promising anti-tumor agent; however, its precise molecular targets in osteosarcoma remain debated. While current paradigms largely attribute its toxicity to reactive oxygen species (ROS) and ferroptosis, understanding its true mechanism is essential for overcoming therapeutic resistance. This highlights the need for interdisciplinary approaches, such as metabolomics, to unveil novel vulnerabilities in cancer metabolism. MethodsWe employed an interdisciplinary strategy utilizing high-resolution liquid chromatography-mass spectrometry (LC-MS) metabolomics and 13C2-glutamine stable isotope tracing in osteosarcoma cells to elucidate the cytotoxic mechanisms of gallium nitrate. Scanning electron microscopy with energy-dispersive X-ray spectroscopy (SEM-EDS) was utilized for elemental mapping, and in silico modeling was applied to evaluated metal binding dynamics. Furthermore, synergistic effects were tested by combining gallium with the DNA-damaging agent cisplatin. ResultsOur metabolic profiling revealed a profound bifurcation characterized by the systemic depletion of glycolysis and pentose phosphate pathway intermediates, coupled with a novel ribonucleotide accumulation bottleneck. The observed distinct signature strongly implicated ribonucleotide reductase (RNR) as the primary enzymatic target. In silico modeling and SEM-EDS visually and thermodynamically confirmedthat gallium acts as a structural decoy for iron within the RNR active site. The co-localization induces functional iron starvation rather than canonical ferroptosis. Furthermore, isotope tracing confirmed that elevated ROS is a consequence of overall metabolic failure, not the primary driver of cell death. Crucially, gallium functioned as a metabolic DNA repair inhibitor, synergizing potently with cisplatin to prevent the repair of platinum-induced DNA lesions. ConclusionsGallium selectively sensitizes highly proliferative sarcoma cells by disrupting RNR-mediated DNA precursor synthesis, while sparing normal osteoblasts. Leveraging metabolomics to uncover this state of functional iron starvation provides a rational, interdisciplinary framework for developing gallium-based combination therapies designed to break platinum resistance in clinical oncology.

International guidelines for low-frequency electromagnetic field exposure (LF EMF) are primarily intended to prevent substantiated adverse effects. In the frameworks, limits on internal electric fields are linked to external exposure levels through computational dosimetry. However, the relationship between internal electric fields and these adverse effects remains incompletely understood. In particular, current approaches often overlook the morphological complexity and diversity of cortical neurons, which may limit the realism of neuronal activation estimates used to support these assessments. This study evaluates LF EMF-induced neural activation using 25 morphologically realistic neuron models spanning all cortical layers, embedded within 11 detailed human head models. The internal electric fields were simulated for uniform magnetic field exposures (100 Hz-100 kHz) along the three anatomical directions, and excitation thresholds were computed using a multi-scale framework combining voxel-based dosimetry with biophysical neuron simulations. A real-world exposure scenario involving a child near an acousto-magnetic article-surveillance deactivator was also analyzed. Thresholds varied across cell type, morphology, cortical location, subject anatomy, frequency, and exposure direction, with L2/3 pyramidal, L4 basket, and L5 thick-tufted pyramidal cells showing the lowest thresholds. Despite this variability, all simulated thresholds were conservative with respect to the basic restrictions and dosimetric reference limits set by IEEE ICES and ICNIRP. The smallest margin occurred at 100 kHz, where the threshold remained a factor of 2.8 above the corresponding limit. These findings indicate that current LF EMF exposure limits remain conservative when evaluated using highly detailed, morphology-based CNS activation models.

The Bayesian Ordered Lattice Design (BOLD) method for Phase I clinical trials is extended to address an important challenge. It is widely understood that conventional Phase I trial designs are not consistently effective in determining safe and active dose levels. The US FDA launched the Project Optimus, aimed at reforming the paradigms of dose optimization and selection. We propose a backfill BOLD design (BF-BOLD) that centers on BOLD for dose-finding but also adds an activity evaluation for each patient. Our method for determining the optimal biological dose (OBD) first involves identifying the maximum tolerated dose (MTD) and then assessing activity rates among dose levels below the identified MTD. This approach is straightforward and does not require complex statistical modeling. The results of the simulation indicate that performing dose-finding trials with backfilling can both enhance safety and activity assessment, thereby improving treatment sustainability while also preserving the potential for efficacy of the Recommended Phase II Dose (RP2D). We also demonstrate the applicability of the backfill design for reducing overdose rates, and as a more attractive alternative to small-scale dose expansion trials that follow dose escalation. Backfill designs are an important design approach for early phase trials.

Radiation-induced intestinal injury is a widely used model for studying mechanisms regulating tissue injury and regeneration. Traditionally, Cesium (137Cs) radiation has been used in research applications, but over the past decade, X-ray irradiation has become increasingly favored due to its improved safety and non-radioactive profile. Since each type of radiation has distinct physical characteristics that drive its performance, we sought to systematically compare the effects of the X-ray and 137Cs irradiators on intestinal epithelial injury and regeneration. Using established in vitro models, including colorectal cancer cell lines such as HCT116, RKO, and DLD-1, and mouse intestinal organoids, alongside an in vivo model, Bmi1-CreER;Rosa26eYFP, we evaluated differences in transcriptional, protein, and histopathological responses to irradiation. Our results demonstrate that X-ray produced intestinal injury and regenerative responses comparable to those induced by 137Cs, supporting its reliability as an alternative modality for studying intestinal radiation.

Ionizing radiation can be an effective therapy for prostate cancer. Unfortunately, however, more aggressive prostate cancers such as neuroendocrine prostate cancer (NEPC) are often radiation resistant, which contributes to their high degree of morbidity and mortality. In this study, we used an unbiased approach to identify novel mechanisms that contribute to resistance to radiation and that are associated with neuroendocrine differentiation. Specifically, we compared the expression of cell surface proteins by mass spectrometry in prostate cancer cell lines that had been either untreated or treated with radiation to induce resistance, a process that also promotes neuroendocrine differentiation. Among the proteins identified by this screen, we focused on folate receptor (FR) because of its known biological functions and the fact that it is a validated therapeutic target. Our data reveal that FR has a causal role in enabling prostate cancer cells to resist radiation. Importantly, we also demonstrate that the expression of FR is regulated by HIF-1, which also has a causal role in radiation resistance and neuroendocrine differentiation. Given that the ability of cells to resist damage and death in response to ionizing radiation depends largely on their ability to buffer the substantial increase in reactive oxygen species (ROS) that is generated by radiation, we also demonstrate that the folate-FR axis promotes radiation resistance by sustaining intracellular glutathione levels that buffer this increase in ROS. In summary, the data reported here highlight a novel role for FR in resistance to ionizing radiation that is intimately associated with the hypoxic microenvironment of NEPC and the ability of the folate-FRa axis to maintain redox homeostasis.

Background. Pancreatic ductal adenocarcinoma (PDAC) has a five-year survival rate of approximately 12%, largely because it is typically diagnosed at an advanced stage. CT-based computational methods for early detection exist but rely on black-box deep learning or large texture feature sets without tissue-specific interpretability. Methods. We developed Virtual Spectral Decomposition (VSD), which applies six parameterized sigmoid functions S(HU) = 1/(1+exp(-alpha x (HU - mu))) to standard portal-venous CT, decomposing each pixel into tissue-specific response channels for fat (mu=-60), fluid (mu=10), parenchyma (mu=45), stroma (mu=75), vascular (mu=130), and calcification (mu=250). Dendritic Binary Gating identifies structural content per channel using morphological filtering, enabling co-firing analysis and lone firer identification. A 25-feature signature was extracted per patient. Three independent datasets were analyzed: NIH Pancreas-CT (n=78 healthy), Medical Segmentation Decathlon Task07 (n=281 PDAC, paired tumor/adjacent tissue), and CPTAC-PDA from The Cancer Imaging Archive (n=82, multi-institutional, with DICOM time point tags). The same six sigmoid parameters were used across all datasets without retraining. Results. VSD achieved AUC 0.943 for field effect detection (healthy vs cancer-adjacent parenchyma) and AUC 0.931 for patient-stratified tumor specification on MSD. On CPTAC-PDA, VSD achieved AUC 0.961 (6 features) and 0.979 (25 features) for distinguishing healthy from cancer-bearing pancreas on scans obtained prior to pathological diagnosis. All significant features replicated across datasets in the same direction: z_fat (d=-2.10, p=3.5e-27), z_fluid (d=-2.76, p=2.4e-38), fire_fat (d=+2.18, p=1.2e-28). Critically, VSD severity did not correlate with days-from-diagnosis (r=-0.008, p=0.944) across a range of day -1394 to day +249. Patient C3N-01375, scanned 3.8 years before pathological diagnosis, had VSD severity 1.87, well above the healthy mean of 0.94 +/- 0.33. The tissue transformation signature was temporally stable, indicating an early, persistent tissue state rather than a progressively worsening process. Conclusions. VSD with Dendritic Binary Gating detects a stable pancreatic tissue composition signature on standard CT that is present years before clinical diagnosis, validated across three independent datasets without parameter adjustment. The six sigmoid channels map to biologically meaningful tissue components through a fully transparent interpretability chain. The temporal stability of the signal implies a detection window of 3-7 years, consistent with known PanIN-3 microenvironment transformation timelines. VSD functions as a single-scan screening tool applicable to any abdominal CT performed during the pre-clinical window.

Objectives: Among surgically resected non-small cell lung cancer (NSCLC) patients with similar stage and histopathological characteristics, there is variability in patient outcomes which highlights urgency of identifying biomarkers to predict recurrence. The goal of this study was to systematically develop a pre-surgical CT-based habitat-based radiomics classifier to predict recurrence-of-risk in NSCLC. Methods: This study included 293 NSCLC patients with surgically resected stage IA-IIIA disease that were randomly divided into a training (n = 195) and test cohorts (n = 98). From pre-surgical CT images, tumor habitats were generated using two-level unsupervised clustering and then radiomic features were calculated from the intratumoral region and habitat-defined subregions. Using ridge-regularized logistic regression, separate classifiers were developed to predict 3-year recurrence using intratumoral radiomics, habitat-based radiomics, and a combined model (intratumoral and habitat) which was generated using a stacked learning framework. For each classifier, probability of recurrence was calculated for each patient then numerous statistical and machine learning approaches were utilized to stratify patients for recurrence-free survival. Results: The combined radiomics classifier yielded a superior AUC (0.82) compared to the intratumoral (AUC = 0.75) and habitat radiomics (AUC = 0.81) models. When the classifiers were used to stratify high- versus low-risk patients utilizing a cut-point identified by decision tree analysis, high-risk patients were yielded the largest risk estimate (HR = 8.43; 95% CI 2.47 - 28.81) compared to the habitat (HR = 5.41; 95% CI 2.08 - 14.09) and intratumoral radiomics (HR = 3.54; 95% CI 1.45 - 8.66) models. SHAP analyses indicated that habitat-derived information contributed most strongly to recurrence prediction. Conclusions: This study revealed that habitat-based radiomics provided superior statistical performance than intratumoral radiomics for predicting recurrence in NSCLC.

Background: Immune checkpoint inhibitors (ICIs) have revolutionized cancer therapy but can cause serious immune-related adverse events (irAEs), with pneumonitis (ICI-P) being among the most severe. Early identification of high-risk patients before ICI initiation is critical for closer monitoring, timely intervention, and improved outcomes. Purpose: To develop and validate a deep learning foundation model to predict ICI-P from baseline CT scans in patients with lung cancer. Methods: We designed the Checkpoint-Inhibitor Pneumonitis Hazard EstimatoR (CIPHER), a deep learning foundation model that combines contrastive learning with a transformer-based masked autoencoder to predict ICI-P from baseline CT scans in patients with lung cancer. Using self-supervised learning, CIPHER was pre-trained on 590,284 CT slices from 2,500 non-small cell lung cancer (NSCLC) patients to capture heterogeneous lung parenchymal patterns. After pre-training, the model was fine-tuned on an internal NSCLC cohort for ICI-P risk prediction, using images from 254 patients for model development and 93 patients for internal validation. We compared CIPHER with classical radiomic models and further evaluated it on an external NSCLC cohort of 116 patients. Results: In the internal immunotherapy cohort, CIPHER consistently distinguished patients at elevated risk of ICI-P from those without the event, with AUCs ranging from 0.77 to 0.85. In head-to-head benchmarking, CIPHER achieved an AUC of 0.83, outperforming the radiomic models. In the external validation cohort, CIPHER maintained strong performance (AUC = 0.83; balanced accuracy = 81.7%), exceeding the radiomic models (DeLong p = 0.0318) and demonstrating higher specificity without sacrificing sensitivity. By contrast, the radiomic model showed high sensitivity (85.0%) but markedly lower specificity (45.8%). Confusion matrix analysis confirmed the robust classification performance of CIPHER, correctly identifying 80 of 96 non-ICI-P cases and 16 of 20 ICI-P cases. Conclusions: We developed and externally validated CIPHER for predicting future risk of ICI-P from pre-treatment CT scans. With prospective validation, CIPHER may be incorporated into routine patient management to improve outcomes.

Simulated spaceflight perturbs multiple organ systems, yet the integrated impact of spaceflight-relevant stressors on the immune-gut-brain axis remains poorly defined. We used a ground-based model combining hindlimb unloading (HU) with low-dose ionizing radiation (IR; 50 or 100cGy) to quantify neuropathology, peripheral immune phenotypes, intestinal barrier integrity, and behavioral performance in male and female C57BL/6 mice. HU and/or IR induced region-selective neurodegenerative changes consistent with axonal injury across the cortex and major white-matter tracts. In the somatosensory cortex, MAP-2+ neurons were reduced and SMI-312-labeled axonal injury increased, lowering the intact-to-dystrophic axonal area ratio. Long-range fiber pathways (corpus callosum, cingulate gyrus, external capsule) showed robust axonal damage accompanied by gliosis, with elevated Iba-1+ microglia and GFAP+ astrocytes most prominent after HU+IR (100cGy). Peripheral immunophenotyping revealed a sustained, sex-dependent innate inflammatory bias, with expanded CD11b+ myeloid cells and increased TNF-+ myeloid activation after IR and IR+HU, alongside maladaptive T-cell polarization despite largely unchanged total CD8+ and CD4+ frequencies. In parallel, the gut exhibited architectural remodeling and barrier failure, including altered mucin profiles, reduced ZO-1 tight-junction labeling, and increased CD45+ leukocyte infiltration across the jejunum, ileum, and colon. Behavioral assays demonstrated sex-dependent deficits spanning affective, motor, and cognitive domains, including increased anxiety- and depressive-like behaviors, impaired rotarod performance, reduced recognition memory, and less efficient spatial strategies. Overall, these findings identify a sex-dependent immune-gut-brain vulnerability in which combined HU and low-dose IR drive gut barrier breakdown and immune imbalance that coincide with neuroinflammatory axonopathy and measurable neurobehavioral dysfunction.

Purpose: Chemoradiotherapy (CRT) for human papillomavirus-related oropharyngeal cancer (HPV+ OPC) causes substantial treatment-related toxicity, with well-known adverse effects on quality of life (QoL), weight loss, and self-reported physical functioning. However, its impact on objectively measured cardiorespiratory fitness is unknown. This study examined changes in cardiorespiratory fitness, body composition, grip strength, and patient-reported outcomes in patients with HPV+ OPC undergoing CRT. Methods: We invited 20 patients with HPV+ OPC scheduled for CRT (age: 61.2 {+/-} 7.1 years, female: n=4) to complete assessments at three timepoints: pre-CRT (baseline), 2-weeks post-CRT, and 8-weeks post-CRT. Cardiorespiratory fitness was assessed using a maximal incremental cardiopulmonary exercise test (CPET). Body composition was estimated using segmental bioelectrical impedance analysis. QoL was assessed using the EORTC QLQ-C30 and QLQ-H&N43, and physical activity was self-reported using the International Physical Activity Questionnaire-Short Form. The primary outcome was change in oxygen consumption at the anaerobic threshold ([V]O2 at AT) measured during CPET; an objective, effort-independent marker of cardiorespiratory fitness. Results: Mean [V]O2 at AT declined from 16.0 {+/-} 3.8 ml/kg/min at baseline to 12.0 {+/-} 3.4 ml/kg/min at 2-weeks post-CRT (adjusted mean change: -4.2, 95% CI: -5.4 to -3.0 ml/kg/min) and remained low at 8-weeks post-CRT. Peak oxygen consumption ([V]O2peak: -7.4, -9.3 to -5.4 ml/kg/min), body mass (-8.5, -10.7 to -6.2 kg), fat-free mass (-6.4, -7.7 to -5.0 kg), grip strength (-4.1, -7.2 to -0.99 kg), global health status (-26.9, -39.2 to -14.6 points), fatigue (49.8, 33.7 to 65.8 points), and several disease-specific symptoms were also adversely affected at 2-weeks post-CRT and remained impaired at 8 weeks. Conclusion: This is the first study to estimate the impact of CRT on cardiopulmonary fitness in patients with HPV+ OPC. Cardiorespiratory fitness declined by ~25% following CRT and remained reduced at 8-weeks. Targeted interventions to mitigate these adverse physiological effects warrants further investigation.

Background: Current deep learning models in computational pathology, radiology, and digital pathology produce opaque predictions that lack the explainable artificial intelligence (xAI) capabilities required for clinical adoption. Despite achieving radiologist-level performance in tasks from whole-slide image (WSI) classification to mammographic screening, these models function as black boxes: clinicians cannot trace predictions to specific biological features, verify outputs against established morphological criteria, or integrate AI reasoning into precision oncology workflows and tumor board decision-making. Methods: We present Virtual Spectral Decomposition (VSD), a modality-agnostic, interpretable-by-design framework that decomposes medical images into six biologically interpretable tissue composition channels using sigmoid threshold functions - the same mathematical structure as CT windowing. Unlike post-hoc xAI methods (Grad-CAM, SHAP, LIME) applied to black-box deep learning models, VSD channels have pre-defined biological meanings derived from tissue physics, providing inherent explainability without sacrificing quantitative rigor. For whole-slide image (WSI) analysis in digital pathology, we introduce the dendritic tile selection algorithm, a biologically-inspired hierarchical architecture achieving 70-80% computational reduction while preferentially sampling the tumor immune microenvironment. VSD is validated across three cancer types and imaging modalities: pancreatic ductal adenocarcinoma (PDAC) on CT imaging, lung adenocarcinoma (LUAD) on H&E-stained pathology slides using TCGA data, and breast cancer on screening mammography. Composition entropy of the six-channel vector is computed as a visual Biological Entropy Index (vBEI) - an imaging biomarker quantifying the diversity of active biological defense systems. Results: In pancreatic cancer, the fat-to-stroma ratio (a novel CT-derived radiomics biomarker) declines from >5.0 (normal) to <0.5 (advanced PDAC), enabling early detection of desmoplastic invasion before mass formation on standard imaging. In lung cancer, composition entropy from H&E whole-slide images correlates with tumor immune microenvironment markers from RNA-seq (CD3: rho=+0.57, p=0.009; CD8: rho=+0.54, p=0.015; PD-1: rho=+0.54, p=0.013) and predicts overall survival (low entropy immune-desert phenotype: 71% mortality vs 29%, p=0.032; n=20 TCGA-LUAD), providing immune phenotyping for checkpoint immunotherapy patient selection from a $5 H&E slide without molecular assays. In breast cancer, each lesion type produces a characteristic six-channel fingerprint functioning as an interpretable computer-aided diagnosis (CAD) system for quantitative BI-RADS assessment and subtype classification (IDC vs ILC vs DCIS vs IBC). A five-level xAI audit trail provides complete traceability from clinical decision support output to specific biological structures visible on the original images. Conclusion: VSD establishes a unified, interpretable-by-design mathematical framework for explainable tissue composition analysis across imaging modalities and cancer types. Unlike black-box deep learning and post-hoc xAI approaches, VSD provides inherently interpretable, clinically verifiable cancer detection and immune phenotyping from standard clinical imaging at existing costs - without requiring foundation model infrastructure, specialized hardware, or molecular assays. The open-source pipeline (Google Colab, Supplementary Material) enables immediate reproducibility and extension to additional cancer types across the pan-cancer TCGA atlas.

Objective: To demonstrate the proof of principle that machine learning (ML) can be used to quantify Gleason Pattern (GP) 4 on digitized biopsy slides using multiple measurement approaches, allowing direct comparison of their prognostic performance. Methods: We assembled a convenience sample of 726 patients with grade group 2-4 prostate cancer on systematic biopsy who underwent radical prostatectomy between 2014 and 2023. Digitized biopsy slides were analyzed using a machine-learning algorithm (PAIGE-AI) to quantify GP4 using multiple measurement approaches, particularly with respect to how gaps between cancer foci (interfocal stroma) were handled. GP4 extent was quantified using linear measurements or a pixel-based area metric. Discrimination of each GP4 quantification approach, along with Grade Group (GG), was assessed for adverse radical prostatectomy pathology and biochemical recurrence. Results: We identified 15 different quantification approaches and observed differences between their discrimination. The highest discrimination was in the pixel-counting method (AUC 0.648). GP4 quantification outperformed GG for predicting adverse pathology (AUC 0.627 vs 0.608). Amount of GP3 was non-predictive once GP4 was known. These findings were consistent for BCR. Conclusions: We were able to measure slides using 15 distinct measurement approaches and replicated prior findings using ML to quantify GP4. Our findings support the use of ML as a research tool to compare different GP4 quantification approaches. We intend to use our method on larger cohorts to determine with which measurement approach best predicts oncologic outcome.