Translational modeling-based evidence for enhanced efficacy of standard-of-care drugs in combination with anti-microRNA-155 in non-small-cell lung cancer.

BACKGROUND: Elevated microRNA-155 (miR-155) expression in non-small-cell lung cancer (NSCLC) promotes cisplatin resistance and negatively impacts treatment outcomes. However, miR-155 can also boost anti-tumor immunity by suppressing PD-L1 expression. Therapeutic targeting of miR-155 through its antagonist, anti-miR-155, has proven challenging due to its dual molecular effects. METHODS: We developed a multiscale mechanistic model, calibrated with in vivo data and then extrapolated to humans, to investigate the therapeutic effects of nanoparticle-delivered anti-miR-155 in NSCLC, alone or in combination with standard-of-care drugs. RESULTS: Model simulations and analyses of the clinical scenario revealed that monotherapy with anti-miR-155 at a dose of 2.5 mg/kg administered once every three weeks has substantial anti-cancer activity. It led to a median progression-free survival (PFS) of 6.7 months, which compared favorably to cisplatin and immune checkpoint inhibitors. Further, we explored the combinations of anti-miR-155 with standard-of-care drugs, and found strongly synergistic two- and three-drug combinations. A three-drug combination of anti-miR-155, cisplatin, and pembrolizumab resulted in a median PFS of 13.1 months, while a two-drug combination of anti-miR-155 and cisplatin resulted in a median PFS of 11.3 months, which emerged as a more practical option due to its simple design and cost-effectiveness. Our analyses also provided valuable insights into unfavorable dose ratios for drug combinations, highlighting the need for optimizing dose regimens to prevent antagonistic effects. CONCLUSIONS: This work bridges the gap between preclinical development and clinical translation of anti-miR-155 and unravels the potential of anti-miR-155 combination therapies in NSCLC.

Hybridizing mechanistic modeling and deep learning for personalized survival prediction after immune checkpoint inhibitor immunotherapy.

We present a study where predictive mechanistic modeling is combined with deep learning methods to predict individual patient survival probabilities under immune checkpoint inhibitor (ICI) immunotherapy. This hybrid approach enables prediction based on both measures that are calculable from mechanistic models of key mechanisms underlying ICI therapy that may not be directly measurable in the clinic and easily measurable quantities or patient characteristics that are not always readily incorporated into predictive mechanistic models. A deep learning time-to-event predictive model trained on a hybrid mechanistic + clinical data set from 93 patients achieved higher per-patient predictive accuracy based on event-time concordance, Brier score, and negative binomial log-likelihood-based criteria than when trained on only mechanistic model-derived values or only clinical data. Feature importance analysis revealed that both clinical and model-derived parameters play prominent roles in increasing prediction accuracy, further supporting the advantage of our hybrid approach.

Outcomes and Pattern of Care for Spinal Myxopapillary Ependymoma in the Modern Era-A Population-Based Observational Study.

(1) Background: Myxopapillary ependymoma (MPE) is a rare tumor of the spine, typically slow-growing and low-grade. Optimal management strategies remain unclear due to limited evidence given the low incidence of the disease. (2) Methods: We analyzed data from 1197 patients with spinal MPE from the Surveillance, Epidemiology, and End Results (SEER) database (2000-2020). Patient demographics, treatment modalities, and survival outcomes were examined using statistical analyses. (3) Results: Most patients were White (89.9%) with a median age at diagnosis of 42 years. Surgical resection was performed in 95% of cases. The estimated 10-year overall survival was 91.4%. Younger age (hazard ratio (HR) = 1.09, p < 0.001) and receipt of surgery (HR = 0.43, p = 0.007) were associated with improved survival. Surprisingly, male sex was associated with worse survival (HR = 1.86, p = 0.008) and a younger age at diagnosis compared to females. (4) Conclusions: This study, the largest of its kind, underscores the importance of surgical resection in managing spinal MPE. The unexpected association between male sex and worse survival warrants further investigation into potential sex-specific pathophysiological factors influencing prognosis. Despite limitations, our findings contribute valuable insights for guiding clinical management strategies for spinal MPE.

Response of treatment-naive brain metastases to stereotactic radiosurgery.

With improvements in survival for patients with metastatic cancer, long-term local control of brain metastases has become an increasingly important clinical priority. While consensus guidelines recommend surgery followed by stereotactic radiosurgery (SRS) for lesions >3 cm, smaller lesions (≤3 cm) treated with SRS alone elicit variable responses. To determine factors influencing this variable response to SRS, we analyzed outcomes of brain metastases ≤3 cm diameter in patients with no prior systemic therapy treated with frame-based single-fraction SRS. Following SRS, 259 out of 1733 (15%) treated lesions demonstrated MRI findings concerning for local treatment failure (LTF), of which 202 /1733 (12%) demonstrated LTF and 54/1733 (3%) had an adverse radiation effect. Multivariate analysis demonstrated tumor size (>1.5 cm) and melanoma histology were associated with higher LTF rates. Our results demonstrate that brain metastases ≤3 cm are not uniformly responsive to SRS and suggest that prospective studies to evaluate the effect of SRS alone or in combination with surgery on brain metastases ≤3 cm matched by tumor size and histology are warranted. These studies will help establish multi-disciplinary treatment guidelines that improve local control while minimizing radiation necrosis during treatment of brain metastasis ≤3 cm.

Hypofractionated radiotherapy for glioblastoma: A large institutional retrospective assessment of 2 approaches.

Background: Glioblastoma (GBM) poses therapeutic challenges due to its aggressive nature, particularly for patients with poor functional status and/or advanced disease. Hypofractionated radiotherapy (RT) regimens have demonstrated comparable disease outcomes for this population while allowing treatment to be completed more quickly. Here, we report our institutional outcomes of patients treated with 2 hypofractionated RT regimens: 40 Gy/15fx (3w-RT) and 50 Gy/20fx (4w-RT). Methods: A single-institution retrospective analysis was conducted of 127 GBM patients who underwent 3w-RT or 4w-RT. Patient characteristics, treatment regimens, and outcomes were analyzed. Univariate and multivariable Cox regression models were used to estimate progression-free survival (PFS) and overall survival (OS). The impact of chemotherapy and RT schedule was explored through subgroup analyses. Results: Median OS for the entire cohort was 7.7 months. There were no significant differences in PFS or OS between 3w-RT and 4w-RT groups overall. Receipt and timing of temozolomide (TMZ) emerged as the variable most strongly associated with survival, with patients receiving adjuvant-only or concurrent and adjuvant TMZ having significantly improved PFS and OS (P < .001). In a subgroup analysis of patients that did not receive TMZ, patients in the 4w-RT group demonstrated a trend toward improved OS as compared to the 3w-RT group (P = .12). Conclusions: This study demonstrates comparable survival outcomes between 3w-RT and 4w-RT regimens in GBM patients. Receipt and timing of TMZ were strongly associated with survival outcomes. The potential benefit of dose-escalated hypofractionation for patients not receiving chemotherapy warrants further investigation and emphasizes the importance of personalized treatment approaches.

Additive Value of Magnetic Resonance Simulation Before Chemoradiation in Evaluating Treatment Response and Pseudoprogression in High-Grade Gliomas.

PURPOSE: A dedicated magnetic resonance imaging simulation (MRsim) for radiation treatment (RT) planning in patients with high-grade glioma (HGG) can detect early radiologic changes, including tumor progression after surgery and before standard of care chemoradiation. This study aimed to determine the effect of using postoperative magnetic resonance imaging (MRI) versus MRsim as the baseline for response assessment and reporting pseudoprogression on follow-up imaging at 1 month (FU1) after chemoradiation. METHODS AND MATERIALS: Histologically confirmed patients with HGG were planned for 6 weeks of RT in a prospective study for adaptive RT planning. All patients underwent postoperative MRI, MRsim, and follow-up MRI scans every 2 to 3 months. Tumor response was assessed by 3 independent blinded reviewers using Response Assessment in Neuro-Oncology criteria when baseline was either postoperative MRI or MRsim. Interobserver agreement was calculated using Light's kappa. RESULTS: Thirty patients (median age, 60.5 years; IQR, 54.5-66.3) were included. Median interval between surgery and RT was 34 days (IQR, 27-41). Response assessment at FU1 differed in 17 patients (57%) when the baseline was postoperative MRI versus MRsim, including true progression versus partial response or stable disease in 11 (37%) and stable disease versus partial response in 6 (20%) patients. True progression was reported in 19 patients (63.3%) on FU1 when the baseline was postoperative MRI versus 8 patients (26.7%) when the baseline was MRsim (P = .004). Pseudoprogression was observed at FU1 in 12 (40%) versus 4 (13%) patients, when the baseline was postoperative MRI versus MRsim (P = .019). Interobserver agreement between observers was moderate (κ = 0.579; P < .001). CONCLUSIONS: Our study demonstrates the value of acquiring an updated MR closer to RT in patients with HGG to improve response assessment, and accuracy in evaluation of pseudoprogression even at the early time point of first follow-up after RT. Earlier identification of patients with true progression would enable more timely salvage treatments including potential clinical trial enrollment to improve patient outcomes.

Enhancing NSCLC recurrence prediction with PET/CT habitat imaging, ctDNA, and integrative radiogenomics-blood insights.

While we recognize the prognostic importance of clinicopathological measures and circulating tumor DNA (ctDNA), the independent contribution of quantitative image markers to prognosis in non-small cell lung cancer (NSCLC) remains underexplored. In our multi-institutional study of 394 NSCLC patients, we utilize pre-treatment computed tomography (CT) and 18F-fluorodeoxyglucose positron emission tomography (FDG-PET) to establish a habitat imaging framework for assessing regional heterogeneity within individual tumors. This framework identifies three PET/CT subtypes, which maintain prognostic value after adjusting for clinicopathologic risk factors including tumor volume. Additionally, these subtypes complement ctDNA in predicting disease recurrence. Radiogenomics analysis unveil the molecular underpinnings of these imaging subtypes, highlighting downregulation in interferon alpha and gamma pathways in the high-risk subtype. In summary, our study demonstrates that these habitat imaging subtypes effectively stratify NSCLC patients based on their risk levels for disease recurrence after initial curative surgery or radiotherapy, providing valuable insights for personalized treatment approaches.

Evaluating the relationship between magnetic resonance image quality metrics and deep learning-based segmentation accuracy of brain tumors.

BACKGROUND: Magnetic resonance imaging (MRI) scans are known to suffer from a variety of acquisition artifacts as well as equipment-based variations that impact image appearance and segmentation performance. It is still unclear whether a direct relationship exists between magnetic resonance (MR) image quality metrics (IQMs) (e.g., signal-to-noise, contrast-to-noise) and segmentation accuracy. PURPOSE: Deep learning (DL) approaches have shown significant promise for automated segmentation of brain tumors on MRI but depend on the quality of input training images. We sought to evaluate the relationship between IQMs of input training images and DL-based brain tumor segmentation accuracy toward developing more generalizable models for multi-institutional data. METHODS: We trained a 3D DenseNet model on the BraTS 2020 cohorts for segmentation of tumor subregions enhancing tumor (ET), peritumoral edematous, and necrotic and non-ET on MRI; with performance quantified via a 5-fold cross-validated Dice coefficient. MRI scans were evaluated through the open-source quality control tool MRQy, to yield 13 IQMs per scan. The Pearson correlation coefficient was computed between whole tumor (WT) dice values and IQM measures in the training cohorts to identify quality measures most correlated with segmentation performance. Each selected IQM was used to group MRI scans as "better" quality (BQ) or "worse" quality (WQ), via relative thresholding. Segmentation performance was re-evaluated for the DenseNet model when (i) training on BQ MRI images with validation on WQ images, as well as (ii) training on WQ images, and validation on BQ images. Trends were further validated on independent test sets derived from the BraTS 2021 training cohorts. RESULTS: For this study, multimodal MRI scans from the BraTS 2020 training cohorts were used to train the segmentation model and validated on independent test sets derived from the BraTS 2021 cohort. Among the selected IQMs, models trained on BQ images based on inhomogeneity measurements (coefficient of variance, coefficient of joint variation, coefficient of variation of the foreground patch) and the models trained on WQ images based on noise measurement peak signal-to-noise ratio (SNR) yielded significantly improved tumor segmentation accuracy compared to their inverse models. CONCLUSIONS: Our results suggest that a significant correlation may exist between specific MR IQMs and DenseNet-based brain tumor segmentation performance. The selection of MRI scans for model training based on IQMs may yield more accurate and generalizable models in unseen validation.

Translational modeling-based evidence for enhanced efficacy of standard-of-care drugs in combination with anti-microRNA-155 in non-small-cell lung cancer.

Elevated microRNA-155 (miR-155) expression in non-small-cell lung cancer (NSCLC) promotes cisplatin resistance and negatively impacts treatment outcomes. However, miR-155 can also boost anti-tumor immunity by suppressing PD-L1 expression. We developed a multiscale mechanistic model, calibrated with in vivo data and then extrapolated to humans, to investigate the therapeutic effects of nanoparticle-delivered anti-miR-155 in NSCLC, alone or in combination with standard-of-care drugs. Model simulations and analyses of the clinical scenario revealed that monotherapy with anti-miR-155 at a dose of 2.5 mg/kg administered once every three weeks has substantial anti-cancer activity. It led to a median progression-free survival (PFS) of 6.7 months, which compared favorably to cisplatin and immune checkpoint inhibitors. Further, we explored the combinations of anti-miR-155 with standard-of-care drugs, and found strongly synergistic two- and three-drug combinations. A three-drug combination of anti-miR-155, cisplatin, and pembrolizumab resulted in a median PFS of 13.1 months, while a two-drug combination of anti-miR-155 and cisplatin resulted in a median PFS of 11.3 months, which emerged as a more practical option due to its simple design and cost-effectiveness. Our analyses also provided valuable insights into unfavorable dose ratios for drug combinations, highlighting the need for optimizing dose regimen to prevent antagonistic effects. Thus, this work bridges the gap between preclinical development and clinical translation of anti-miR-155 and unravels the potential of anti-miR-155 combination therapies in NSCLC.

Hybridizing mechanistic mathematical modeling with deep learning methods to predict individual cancer patient survival after immune checkpoint inhibitor therapy.

We present a study where predictive mechanistic modeling is used in combination with deep learning methods to predict individual patient survival probabilities under immune checkpoint inhibitor (ICI) therapy. This hybrid approach enables prediction based on both measures that are calculable from mechanistic models (but may not be directly measurable in the clinic) and easily measurable quantities or characteristics (that are not always readily incorporated into predictive mechanistic models). The mechanistic model we have applied here can predict tumor response from CT or MRI imaging based on key mechanisms underlying checkpoint inhibitor therapy, and in the present work, its parameters were combined with readily-available clinical measures from 93 patients into a hybrid training set for a deep learning time-to-event predictive model. Analysis revealed that training an artificial neural network with both mechanistic modeling-derived and clinical measures achieved higher per-patient predictive accuracy based on event-time concordance, Brier score, and negative binomial log-likelihood-based criteria than when only mechanistic model-derived values or only clinical data were used. Feature importance analysis revealed that both clinical and model-derived parameters play prominent roles in neural network decision making, and in increasing prediction accuracy, further supporting the advantage of our hybrid approach. We anticipate that many existing mechanistic models may be hybridized with deep learning methods in a similar manner to improve predictive accuracy through addition of additional data that may not be readily implemented in mechanistic descriptions.

Synthetic PET from CT improves diagnosis and prognosis for lung cancer: Proof of concept.

[18F]Fluorodeoxyglucose positron emission tomography (FDG-PET) and computed tomography (CT) are indispensable components in modern medicine. Although PET can provide additional diagnostic value, it is costly and not universally accessible, particularly in low-income countries. To bridge this gap, we have developed a conditional generative adversarial network pipeline that can produce FDG-PET from diagnostic CT scans based on multi-center multi-modal lung cancer datasets (n = 1,478). Synthetic PET images are validated across imaging, biological, and clinical aspects. Radiologists confirm comparable imaging quality and tumor contrast between synthetic and actual PET scans. Radiogenomics analysis further proves that the dysregulated cancer hallmark pathways of synthetic PET are consistent with actual PET. We also demonstrate the clinical values of synthetic PET in improving lung cancer diagnosis, staging, risk prediction, and prognosis. Taken together, this proof-of-concept study testifies to the feasibility of applying deep learning to obtain high-fidelity PET translated from CT.

Clinical Benefit from Docetaxel +/- Ramucirumab Is Not Associated with Mutation Status in Metastatic Non-Small-Cell Lung Cancer Patients Who Progressed on Platinum Doublets and Immunotherapy.

Docetaxel +/- ramucirumab remains the standard-of-care therapy for patients with metastatic non-small-cell lung cancer (NSCLC) after progression on platinum doublets and immune checkpoint inhibitors (ICIs). The aim of our study was to investigate whether the cancer gene mutation status was associated with clinical benefits from docetaxel +/- ramucirumab. We also investigated whether platinum/taxane-based regimens offered a better clinical benefit in this patient population. A total of 454 patients were analyzed (docetaxel +/- ramucirumab n=381; platinum/taxane-based regimens n=73). Progression-free survival (PFS) and overall survival (OS) were compared among different subpopulations with different cancer gene mutations and between patients who received docetaxel +/- ramucirumab versus platinum/taxane-based regimens. Among patients who received docetaxel +/- ramucirumab, the top mutated cancer genes included TP53 (n=167), KRAS (n=127), EGFR (n=65), STK11 (n=32), ERBB2 (HER2) (n=26), etc. None of these cancer gene mutations or PD-L1 expression was associated with PFS or OS. Platinum/taxane-based regimens were associated with a significantly longer mQS (13.00 m, 95% Cl: 11.20-14.80 m versus 8.40 m, 95% Cl: 7.12-9.68 m, LogRank P=0.019) than docetaxel +/- ramcirumab. Key prognostic factors including age, histology, and performance status were not different between these two groups. In conclusion, in patients with metastatic NSCLC who have progressed on platinum doublets and ICIs, the clinical benefit from docetaxel +/- ramucirumab is not associated with the cancer gene mutation status. Platinum/taxane-based regimens may offer a superior clinical benefit over docetaxel +/- ramucirumab in this patient population.

Designing clinical trials for patients who are not average.

The heterogeneity inherent in cancer means that even a successful clinical trial merely results in a therapeutic regimen that achieves, on average, a positive result only in a subset of patients. The only way to optimize an intervention for an individual patient is to reframe their treatment as their own, personalized trial. Toward this goal, we formulate a computational framework for performing personalized trials that rely on four mathematical techniques. First, mathematical models that can be calibrated with patient-specific data to make accurate predictions of response. Second, digital twins built on these models capable of simulating the effects of interventions. Third, optimal control theory applied to the digital twins to optimize outcomes. Fourth, data assimilation to continually update and refine predictions in response to therapeutic interventions. In this perspective, we describe each of these techniques, quantify their "state of readiness", and identify use cases for personalized clinical trials.

Expert-centered Evaluation of Deep Learning Algorithms for Brain Tumor Segmentation.

Purpose To present results from a literature survey on practices in deep learning segmentation algorithm evaluation and perform a study on expert quality perception of brain tumor segmentation. Materials and Methods A total of 180 articles reporting on brain tumor segmentation algorithms were surveyed for the reported quality evaluation. Additionally, ratings of segmentation quality on a four-point scale were collected from medical professionals for 60 brain tumor segmentation cases. Results Of the surveyed articles, Dice score, sensitivity, and Hausdorff distance were the most popular metrics to report segmentation performance. Notably, only 2.8% of the articles included clinical experts' evaluation of segmentation quality. The experimental results revealed a low interrater agreement (Krippendorff α, 0.34) in experts' segmentation quality perception. Furthermore, the correlations between the ratings and commonly used quantitative quality metrics were low (Kendall tau between Dice score and mean rating, 0.23; Kendall tau between Hausdorff distance and mean rating, 0.51), with large variability among the experts. Conclusion The results demonstrate that quality ratings are prone to variability due to the ambiguity of tumor boundaries and individual perceptual differences, and existing metrics do not capture the clinical perception of segmentation quality. Keywords: Brain Tumor Segmentation, Deep Learning Algorithms, Glioblastoma, Cancer, Machine Learning Clinical trial registration nos. NCT00756106 and NCT00662506 Supplemental material is available for this article. © RSNA, 2023.

Development and benchmarking diffusion magnetic resonance imaging analysis for integration into radiation treatment planning.

PURPOSE: The rising promise in the utility of advanced multi-parametric magnetic resonance (MR) imaging in radiotherapy (RT) treatment planning creates a necessity for testing and enhancing the accuracy of quantitative imaging analysis. Standardizing the analysis of diffusion weighted imaging (DWI) and diffusion tensor imaging (DTI) to generate meaningful and reproducible apparent diffusion coefficient (ADC) and fractional anisotropy (FA) lays the requisite needed for clinical integration. The aim of the demonstrated work is to benchmark the generation of the ADC and FA parametric map analyses using integrated tools in a commercial treatment planning system against the currently used ones. METHODS: Three software packages were used for generating ADC and FA maps in this study; one tool was developed within a commercial treatment planning system, another by the Functional Magnetic Resonance Imaging of the Brain (FMRIB) Software Library FSL (Analysis Group, FMRIB, Oxford, United Kingdom), and an in-house tool developed at the M.D. Anderson Cancer Center. The ADC and FA maps generated by all three packages for 35 subjects were subtracted from one another, and the standard deviation of the images' differences was used to compare the reproducibility. The reproducibility of the ADC maps was compared with the Quantitative Imaging Biomarkers Alliance (QIBA) protocol, while that of the FA maps was compared to data in published literature. RESULTS: Results show that the discrepancies between the ADC maps calculated for each patient using the three different software algorithms are less than 2% which meets the 3.6% recommended QIBA requirement. Except for a small number of isolated points, the majority of differences in FA maps for each patient produced by the three methods did not exceed 0.02 which is 10 times lower than the differences seen in healthy gray and white matter. The results were also compared to the maps generated by existing MR Imaging consoles and showed that the robustness of console generated ADC and FA maps is largely dependent on the correct application of scaling factors, that only if correctly placed; the differences between the three tested methods and the console generated values were within the recommended QIBA guidelines. CONCLUSIONS: Cross-comparison difference maps demonstrated that quantitative reproducibility of ADC and FA metrics generated using our tested commercial treatment planning system were comparable to in-house and established tools as benchmarks. This integrated approach facilitates the clinical utility of diffusion imaging in radiation treatment planning workflow.

The Future of MR-Guided Radiation Therapy.

Magnetic resonance image guided radiation therapy (MRIgRT) is a relatively new technology that has already shown outcomes benefits but that has not yet reached its clinical potential. The improved soft-tissue contrast provided with MR, coupled with the immediacy of image acquisition with respect to the treatment, enables expansion of on-table adaptive protocols, currently at a cost of increased treatment complexity, use of human resources, and longer treatment slot times, which translate to decreased throughput. Many approaches are being investigated to meet these challenges, including the development of artificial intelligence (AI) algorithms to accelerate and automate much of the workflow and improved technology that parallelizes workflow tasks, as well as improvements in image acquisition speed and quality. This article summarizes limitations of current available integrated MRIgRT systems and gives an outlook about scientific developments to further expand the use of MRIgRT.

Cancer Informatics for Cancer Centers: Sharing Ideas on How to Build an Artificial Intelligence-Ready Informatics Ecosystem for Radiation Oncology.

In August 2022, the Cancer Informatics for Cancer Centers brought together cancer informatics leaders for its biannual symposium, Precision Medicine Applications in Radiation Oncology, co-chaired by Quynh-Thu Le, MD (Stanford University), and Walter J. Curran, MD (GenesisCare). Over the course of 3 days, presenters discussed a range of topics relevant to radiation oncology and the cancer informatics community more broadly, including biomarker development, decision support algorithms, novel imaging tools, theranostics, and artificial intelligence (AI) for the radiotherapy workflow. Since the symposium, there has been an impressive shift in the promise and potential for integration of AI in clinical care, accelerated in large part by major advances in generative AI. AI is now poised more than ever to revolutionize cancer care. Radiation oncology is a field that uses and generates a large amount of digital data and is therefore likely to be one of the first fields to be transformed by AI. As experts in the collection, management, and analysis of these data, the informatics community will take a leading role in ensuring that radiation oncology is prepared to take full advantage of these technological advances. In this report, we provide highlights from the symposium, which took place in Santa Barbara, California, from August 29 to 31, 2022. We discuss lessons learned from the symposium for data acquisition, management, representation, and sharing, and put these themes into context to prepare radiation oncology for the successful and safe integration of AI and informatics technologies.

Bilateral uveitis, retinal periphlebitis, and optic neuritis associated with non-pineal central nervous system germinoma.

PURPOSE: To report a case of bilateral uveitis, retinal periphlebitis, and optic neuritis associated with a non-pineal central nervous system (CNS) germinoma. METHODS: Case report. RESULTS: A 32-year-old male presented with episodes of acute painless visual disturbance in each eye, and was found to have decreased visual acuity, abnormal color vision, an afferent pupillary defect in the left eye, bilateral optic disc edema, perivenous sheathing, and candle-wax dripping exudates. Optical coherence tomography revealed bilateral intraretinal fluid and posterior vitreous hyperreflective opacities. Fluorescein angiography revealed bilateral optic disc leakage without active small vessel leakage. Magnetic resonance imaging of the brain and orbits revealed enhancing periventricular lesions and enhancement of the left optic nerve and bilateral perioptic nerve sheaths, posterior globes, and optic nerve heads. Brain biopsy was consistent with a CNS germinoma. His ocular signs and symptoms improved with chemotherapy for the germinoma. CONCLUSION: CNS germinomas, including those located outside the pineal region, can be associated with optic neuritis, uveitis, and periphlebitis including characteristic candle-wax dripping exudates. Ocular signs and symptoms typically improve with treatment of the underlying germinoma.