Scholars@Duke
Evan Calabrese

Scholarly Works - Conferences

An Explainable Deep Model for Risk Scoring and Accurate Radionecrosis Identification Following Brain Metastasis Stereotactic Radiosurgery.

Conference Int J Radiat Oncol Biol Phys · June 1, 2026 PURPOSE: As survival improves for patients with brain metastases (BM), distinguishing local recurrence (LR) from radionecrosis (RN) is a growing neuro-oncologic challenge. We aimed to develop an explainable deep learning model to noninvasively distinguish ... Full text Link to item Cite

Abstract 1293: A multimodal AI framework integrating spatial omics and radiomics for recurrence prediction in glioblastoma.

Conference Cancer Research · April 3, 2026 AbstractIntroduction/Rationale: Glioblastoma (GBM) has a dismal prognosis, yet times to recurrence vary substantially. We integrated multim ... Full text Cite

IMG-66. Self-supervised multimodal learning for survival prediction in glioblastoma: a multicenter study from the ReSPOND consortium

Conference Neuro-Oncology · November 11, 2025 AbstractPURPOSEGlioblastoma is the most aggressive adult brain tumor, with a median overall survival of approximately 15 months ... Full text Cite

INNV-39. Response to next interventions after treatment with off-label ivosidenib in patients with mutant IDH low grade glioma

Conference Neuro-Oncology · November 11, 2025 AbstractThe introduction of mutant IDH inhibitors (mIDHi) has transformed the treatment landscape for patients with low-grade gliomas (LGG). However, optimal strategies for tumor control following progres ... Full text Cite

TMOD-41. Evaluating Response to Mutant IDH Inhibition in Lower Grade Gliomas Using Artificial Intelligence-Based Brain Tumor Volumetrics

Conference Neuro-Oncology · November 11, 2025 AbstractOrally available inhibitors of mutant IDH (mIDHis) have emerged as a promising new therapy for patients with lower grade mIDH gliomas, yet the therapeutic response is challenging to assess objecti ... Full text Cite

SURG-35. Steroid responsiveness, not surgical procedure, predicts recovery after LITT vs resection of primary motor cortex tumors

Conference Neuro-Oncology · November 11, 2025 AbstractLaser interstitial thermal therapy (LITT) is uniquely situated to address radiographically progressive metastases after radiosurgery. Historically, open resection (OR) has been favored for eloquen ... Full text Cite

IMG-69. FeTS 2.0: Federated learning sets benchmark in post-op GBM segmentation

Conference Neuro-Oncology · November 11, 2025 AbstractBACKGROUNDProgress in automated volumetric segmentation of postoperative glioblastoma has been hindered by limited data ... Full text Cite

KS03.4.A SPATIAL MULTI-OMIC PROFILING REVEALS DETERMINANTS OF TIL EXPANDABILITY IN HIGH-GRADE GLIOMAS

Conference Neuro-Oncology · October 3, 2025 AbstractBACKGROUNDTumor-infiltrating lymphocyte (TIL) therapy has demonstrated efficacy in melanoma and is emerging as a promising mod ... Full text Cite

503 Functional Outcomes Following Laser Ablation Versus Resection of Motor Cortex Metastases

Conference Neurosurgery · April 2025 INTRODUCTION:Laser interstitial thermal therapy (LITT) is used to treat radiographically progressive brain metastases following stereotactic radiosurgery (SRS), while rese ... Full text Cite

1338 Automated Volumetric Segmentation Enables Post-Laser Interstitial Thermal Therapy Response Assessment

Conference Neurosurgery · April 2025 INTRODUCTION:Laser interstitial thermal therapy (LITT) allows for confirmatory tissue diagnosis, surgical cytoreduction, and faster return to systemic therapies for patien ... Full text Cite

Efficient Distributed Sequence Parallelism for Transformer-based Image Segmentation

Conference Is and T International Symposium on Electronic Imaging Science and Technology · January 1, 2024 We introduce an efficient distributed sequence parallel approach for training transformer-based deep learning image segmentation models. The neural network models are comprised of a combination of a Vision Transformer encoder with a convolutional decoder t ... Full text Cite