Faculty Bibliography
Searched for:
in-biosketch:true
person:jainr04
Total Results:
241
MRI-based prediction of DNA methylation grade in IDH-mutant astrocytomas using qualitative imaging features and tumor volumetrics
PURPOSE/OBJECTIVE:Histopathological grading of IDH-mutant astrocytomas demonstrates limited prognostic accuracy. However, DNA methylation subclassification has demonstrated improved prognostication beyond histological grading. This study aimed to investigate the associations between imaging features, tumor volumetric data, and DNA methylation grade in IDH-mutant astrocytomas. METHODS:We analyzed imaging features and volumetric data for 72 patients diagnosed with IDH-mutant astrocytomas, who underwent preoperative MRI and DNA methylation profiling. VASARI features and multicompartmental volumetrics were evaluated. Logistic regression was used to identify imaging predictors of methylation subclass, WHO histologic grade, copy number variation (CNV), and CDKN2A/B homozygous deletion. Univariable and multivariable Cox proportional hazard models were also developed to assess these variables' influence on overall survival and progression-free survival. RESULTS:Patients were classified into 27 methylation high-grade (A_IDH_HG) and 45 methylation low-grade (A_IDH_LG) tumors. Tumor volumes and proportions varied by methylation grade, CNV status, and WHO histologic grade, but not by CDKN2A/B status. Imaging features distinguished methylation subclasses with 75% accuracy (AUC = 0.77). Methylation high-grade subclass was associated with imaging features such as midline crossing, ependymal extension, and poorly defined enhancing margins. Predictive performance for WHO histologic grade, CNV status, and CDKN2A/B deletion was moderate (AUC = 0.67, 0.69, and 0.65, respectively). Methylation grade, CDKN2A/B status, VASARI features, and proportions of edema and non-contrast enhancing tumor were significantly associated with survival. CONCLUSION/CONCLUSIONS:MRI-derived imaging features facilitate noninvasive prediction of DNA methylation subclass in IDH-mutant astrocytomas.
PMID: 41217503
ISSN: 1432-1920
CID: 5966632
Categorical and phenotypic image synthetic learning as an alternative to federated learning
Multi-center collaborations are crucial in developing robust and generalizable machine learning models in medical imaging. Traditional methods, such as centralized data sharing or federated learning (FL), face challenges, including privacy issues, communication burdens, and synchronization complexities. We present CATegorical and PHenotypic Image SyntHetic learnING (CATphishing), an alternative to FL using Latent Diffusion Models (LDM) to generate synthetic multi-contrast three-dimensional magnetic resonance imaging data for downstream tasks, eliminating the need for raw data sharing or iterative inter-site communication. Each institution trains an LDM to capture site-specific data distributions, producing synthetic samples aggregated at a central server. We evaluate CATphishing using data from 2491 patients across seven institutions for isocitrate dehydrogenase mutation classification and three-class tumor-type classification. CATphishing achieves accuracy comparable to centralized training and FL, with synthetic data exhibiting high fidelity. This method addresses privacy, scalability, and communication challenges, offering a promising alternative for collaborative artificial intelligence development in medical imaging.
PMCID:12550077
PMID: 41130949
ISSN: 2041-1723
CID: 5957222
A multinational study of deep learning-based image enhancement for multiparametric glioma MRI
This study aimed to validate the utility of commercially available vendor-neutral deep learning (DL) image enhancement software for improving the image quality of multiparametric MRI for gliomas in a multinational setting. A total of 294 patients from three institutions (NYU, Severance, and SNUH) who underwent glioma MRI protocols were included in this retrospective study. DL image enhancement was performed on T2-weighted (T2W), T2 FLAIR, and postcontrast T1-weighted (T1W) imaging using commercially available DL image enhancement software. Signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were calculated for both conventional and DL-enhanced images. Three neuroradiologists, one from each institution, independently evaluated the following image quality parameters in both images using a 5-point scale: overall image quality, noise, gray-white matter differentiation, truncation artifact, motion artifact, pulsation artifact, and main lesion conspicuity. The quantitative and qualitative image parameters were compared between conventional and DL-enhanced images. Compared with conventional images, DL-enhanced images showed significantly higher SNRs and CNRs in T2W, T2 FLAIR, and postcontrast T1W imaging (all P < 0.001). The average scores of radiologist assessments in overall image quality, noise, gray-white matter differentiation, and main lesion conspicuity were significantly higher for DL-enhanced images than conventional images in T2W, T2 FLAIR, and postcontrast T1W imaging (all P < 0.001). Regarding artifacts, truncation artifacts decreased (all P < 0.001), while pre-existing motion and pulsation artifacts were not further exaggerated in most structural MRI sequences. In conclusion, DL image enhancement using commercially available vendor-neutral software improved image quality and reduced truncation artifacts in multiparametric glioma MRI.
PMCID:12464267
PMID: 40998920
ISSN: 2045-2322
CID: 5937742
Towards fair decentralized benchmarking of healthcare AI algorithms with the Federated Tumor Segmentation (FeTS) challenge
Computational competitions are the standard for benchmarking medical image analysis algorithms, but they typically use small curated test datasets acquired at a few centers, leaving a gap to the reality of diverse multicentric patient data. To this end, the Federated Tumor Segmentation (FeTS) Challenge represents the paradigm for real-world algorithmic performance evaluation. The FeTS challenge is a competition to benchmark (i) federated learning aggregation algorithms and (ii) state-of-the-art segmentation algorithms, across multiple international sites. Weight aggregation and client selection techniques were compared using a multicentric brain tumor dataset in realistic federated learning simulations, yielding benefits for adaptive weight aggregation, and efficiency gains through client sampling. Quantitative performance evaluation of state-of-the-art segmentation algorithms on data distributed internationally across 32 institutions yielded good generalization on average, albeit the worst-case performance revealed data-specific modes of failure. Similar multi-site setups can help validate the real-world utility of healthcare AI algorithms in the future.
PMCID:12238412
PMID: 40628696
ISSN: 2041-1723
CID: 5890702
Machine Learning-based Prognostic Subgrouping of Glioblastoma: A Multi-center Study
BACKGROUND:Glioblastoma is the most aggressive adult primary brain cancer, characterized by significant heterogeneity, posing challenges for patient management, treatment planning, and clinical trial stratification. METHODS:We developed a highly reproducible, personalized prognostication and clinical subgrouping system using machine learning (ML) on routine clinical data, MRI, and molecular measures from 2,838 demographically diverse patients across 22 institutions and 3 continents. Patients were stratified into favorable, intermediate, and poor prognostic subgroups (I, II, III) using Kaplan-Meier analysis (Cox proportional model and hazard ratios [HR]). RESULTS:The ML model stratified patients into distinct prognostic subgroups with HRs between subgroups I-II and I-III of 1.62 (95%CI: 1.43-1.84, p<0.001) and 3.48 (95%CI: 2.94-4.11, p<0.001), respectively. Analysis of imaging features revealed several tumor properties contributing unique prognostic value, supporting the feasibility of a generalizable prognostic classification system in a diverse cohort. CONCLUSIONS:Our ML model demonstrates extensive reproducibility and online accessibility, utilizing routine imaging data rather than complex imaging protocols. This platform offers a unique approach for personalized patient management and clinical trial stratification in glioblastoma.
PMID: 39665363
ISSN: 1523-5866
CID: 5762852
A Radiologist's Guide to IDH-Wildtype Glioblastoma for Efficient Communication With Clinicians: Part II-Essential Information on Post-Treatment Imaging
Owing to recent advancements in various postoperative treatment modalities, such as radiation, chemotherapy, antiangiogenic treatment, and immunotherapy, the radiological and clinical assessment of patients with isocitrate dehydrogenase-wildtype glioblastoma using post-treatment imaging has become increasingly challenging. This review highlights the challenges in differentiating treatment-related changes such as pseudoprogression, radiation necrosis, and pseudoresponse from true tumor progression and aims to serve as a guideline for efficient communication with clinicians for optimal management of patients with post-treatment imaging.
PMID: 40015559
ISSN: 2005-8330
CID: 5801252
A Radiologist's Guide to IDH-Wildtype Glioblastoma for Efficient Communication With Clinicians: Part I-Essential Information on Preoperative and Immediate Postoperative Imaging
The paradigm of isocitrate dehydrogenase (IDH)-wildtype glioblastoma is rapidly evolving, reflecting clinical, pathological, and imaging advancements. Thus, it remains challenging for radiologists, even those who are dedicated to neuro-oncology imaging, to keep pace with this rapidly progressing field and provide useful and updated information to clinicians. Based on current knowledge, radiologists can play a significant role in managing patients with IDH-wildtype glioblastoma by providing accurate preoperative diagnosis as well as preoperative and postoperative treatment planning including accurate delineation of the residual tumor. Through active communication with clinicians, extending far beyond the confines of the radiology reading room, radiologists can impact clinical decision making. This Part 1 review provides an overview about the neuropathological diagnosis of glioblastoma to understand the past, present, and upcoming revisions of the World Health Organization classification. The imaging findings that are noteworthy for radiologists while communicating with clinicians on preoperative and immediate postoperative imaging of IDH-wildtype glioblastomas will be summarized.
PMCID:11865903
PMID: 39999966
ISSN: 2005-8330
CID: 5800792
Proceedings of SPIE (The International Society for Optical Engineering). 2025:13411.DOI: 10.1117/12.3049114
Mitigating Data Scarcity in the Classification of Glioma Molecular Subtypes: The Power of Generative Imaging
Isocitrate dehydrogenase (IDH) mutation status is a critical prognostic indicator in glioma patients. Numerous studies have focused on developing non-invasive methodologies to classify IDH status using pre-operative MRI scans. However, the challenge lies in data scarcity and class imbalance in IDH mutations. This study explores generative AI methods to augment training data and enhance IDH classification accuracy. We developed a 3D conditional latent diffusion model (LDM) for generating 3D multi-contrast brain tumor MRI data (128 × 128 × 64 with a voxel spacing of 1.5 × 1.5 × 2.0 mm) with whole tumor mask and IDH mutation status as conditions. The LDM comprises a 3D autoencoder for perceptual compression and a conditional 3D diffusion model (DM) for generating multi-contrast synthetic samples guided by tumor masks and the IDH mutation status. We incorporated two types of attention modules within the denoising UNet of the LDM to capture the semantic class-dependent data distribution driven by the provided whole tumor mask and IDH status. The LDM was trained using two brain tumor datasets: The Cancer Genome Atlas dataset and an internal dataset from the University of Texas Southwestern Medical Center. The synthetic images generated by the LDM were then used to train IDH classification models, which were subsequently tested on real brain tumor data comprising 327 mutated and 1,394 wild-type cases from the University of California San Francisco Preoperative Diffuse Glioma MRI dataset, the Erasmus Glioma Database, the University of Pennsylvania glioblastoma, and two held-out internal datasets. The IDH classification models, trained on synthetic images and tested on real data, achieved an excellent overall classification accuracy of 94.02%. This approach has the potential to be extended to other molecular markers where data scarcity presents a challenge.
PMCID:12541906
PMID: 41132899
ISSN: 0277-786x
CID: 5957312
Proceedings of SPIE--the International Society for Optical Engineering. 2025:13410.DOI: 10.1117/12.3049148
Data Harmonization with StyleTransfer-GANs: Enhancing Non-Invasive IDH Classification in Brain Tumors
Isocitrate dehydrogenase (IDH) mutation status has emerged as an important prognostic marker in brain gliomas. Accurate non-invasive determination of IDH mutation status is crucial for effective therapy and prognosis. However, the variability in imaging protocols across institutions hinders the reliability of deep learning (DL) models used for IDH classification. To address data heterogeneity, a StyleTransfer-GAN (
PMCID:12588573
PMID: 41200077
ISSN: 0277-786x
CID: 5960302
A comprehensive multicenter analysis of clinical, molecular, and imaging characteristics and outcomes of H3 K27-altered diffuse midline glioma in adults
OBJECTIVE:The objective was to comprehensively investigate the clinical, molecular, and imaging characteristics and outcomes of H3 K27-altered diffuse midline glioma (DMG) in adults. METHODS:Retrospective chart and imaging reviews were performed in 111 adult patients with H3 K27-altered DMG from two tertiary institutions. Clinical, molecular, imaging, and survival characteristics were analyzed. Characteristics were compared between adult and 365 pediatric patients from a previous multicenter meta-analysis dataset. Cox analyses were performed to determine predictors of overall survival (OS) in adult patients. RESULTS:The median (range) age of adult patients was 40 (18-75) years, and 64 males and 47 females were included. Adults had a higher male proportion (57.7% vs 45.3%, p = 0.023), lower proportion of histological grade 4 (41.4% vs 74.0%, p < 0.001), and different tumor locations (p < 0.001) compared with pediatric patients; adults commonly showed a thalamus location (41.5%) followed by the spinal cord (27.0%), whereas pediatric patients predominantly showed a pons location (64.9%). The OS of adults was longer than that of pediatric patients (30.3 vs 12.0 months, p < 0.001, log-rank test). Older age at diagnosis (HR 0.96, p = 0.001), histologically lower grade (HR 0.25, p = 0.003), and gross-total resection of nonenhancing tumor (HR 0.15, p = 0.003) were independent favorable prognostic factors. CONCLUSIONS:Adult patients with H3 K27-altered DMG showed distinct clinical, histological, and imaging characteristics compared to pediatric counterparts, with a significantly better prognosis. The authors' results suggest that aggressive surgery should be pursued when deemed feasible for better survival outcomes.
PMID: 39793011
ISSN: 1933-0693
CID: 5805342
