ADAtman Desai

Atman Desai

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Atman Desai has a total of 151 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Novel Magnetic Resonance Imaging (MRI) Features Predicting Relapse After Clinical Remission in Pyogenic Spondylodiscitis: A Study Using Simultaneous ¹⁸F-Fluorodeoxyglucose Positron Emission Tomography/MRI Data

    by Seongmin Jeon, Heesung Yang, Eunjung Kong, Dongwoo Yu, Atman Desai, Vivek Sanker, You Seon Song, Ikchan Jeon

    Objective: This study aimed to identify magnetic resonance (MR) imaging features that can predict relapse after clinical remission in pyogenic spondylodiscitis (PSD) based on simultaneous ¹⁸F-fluorodeoxyglucose positron emission tomography/MR (¹⁸F-FDG PET/MR) imaging data.Methods: This retrospective study included 101 patients (67 men and 34 women) with thoracic, lumbar, and/or sacral PSD who received at least 4 weeks of parenteral antibiotic therapy. All patients underwent ¹⁸F-FDG PET/MR imaging and blood inflammatory markers at the time of clinical remission and antibiotic discontinuation, and were followed for at least 12 months to detect relapse. Clinical variables and ¹⁸F-FDG PET/MR imaging features associated with relapse were analyzed.Results: Relapse occurred in 21 patients (20.8%) and was significantly associated with PSD lesions confined to the thoracic spine (p=0.016), a higher maximum standardized ¹⁸F-fluorodeoxyglucose uptake value (p=0.048), and higher mean signal intensity of edema at the PSD lesion on MR imaging (p=0.005). Regarding Contrast-Edema Mismatch (relative reduction in the edematous area compared with contrast-enhanced area, grades I–III), grade I (50% difference) in patients with relapse (p=0.016). Additionally, the mean signal intensity of the contrast area remained similar across grades (p=0.320), whereas the mean signal intensity of edema decreased progressively with increasing grade (p<0.001).Conclusion: Persistent and extensive edematous change on MR imaging was significantly associated with relapse after clinical remission in PSD, and may serve as a potential imaging marker for monitoring treatment response and predicting relapse.

  • Open Access

    Does Tumor-Mask Guidance Improve Glioma Grade Classification from T2-Weighted MRI Alone? An Out-of-Fold Evaluation with nnU-Net and Ground-Truth Localization

    by Vivek Sanker, Dhanya Mahesh, Zhikai Li, Alexander Thaller, Philip Heesen, Linda Liverani, David Wang, Maria Jose Cavagnaro, Ravi Teja Medikonda, Laura Prolo, et al.

    Multi-sequence MRI is the standard for glioma assessment, but complete or contrast-enhanced protocols are not always available (withheld gadolinium, low-field MRI, incomplete archives). We asked whether tumor localization improves grade classification from T2-weighted MRI alone. In this retrospective study of the BraTS2020 training cohort (369 patients; legacy labels 293 high-grade [HGG], 76 low-grade [LGG]), 74 patients (15 LGG) were held out at the patient level for internal testing. A 2D U-Net trained in five development folds supplied out-of-fold whole-tumor masks for training 3D CNN classifiers; nnU-Net served as a segmentation benchmark. Classifiers received T2 alone or T2 plus a mask, which at test time came from the 2D U-Net, nnU-Net, the ground truth (oracle) or random noise. Analyses used five seeds, DeLong tests with Holm correction and development-set cross-validation. Whole-tumor Dice was 0.807 (95% CI 0.773–0.840) for the 2D U-Net and 0.877 (0.857–0.895) for nnU-Net. The T2-only CNN reached an ROC-AUC of 0.814 (95% CI 0.702–0.913). Mask-guided variants reached 0.677–0.742, none above T2-only (Holm-adjusted p = 1.00 for all four confirmatory comparisons of informative masks). Cross-validation reproduced this ranking (0.782 vs. 0.707). With LGG as the positive class, PR-AUC was 0.571 (no-skill 0.203). Tumor-mask guidance did not improve T2-only grading at any level of mask quality, including ground truth. The results concern a legacy grade label in one public cohort and require external testing.

  • The role of stereotactic radiosurgery for prostate cancer spine metastasis - impact on hormone sensitivity and treatment outcomes: a systematic review of literature

    by Aaditya Dravid, Suvan Sundaresh, David Wang, Philip Heesen, Vivek Sanker, Amirhossein Akhavan-Sigari, Maria Jose Cavagnaro, Harminder Singh, John Ratliff, Atman Desai

  • CX3CL1/CX3CR1 signaling in spinal metastasis: mechanisms and translational opportunities

    by Vivek Sanker, Zhikai Li, Adrian Urdaneta, Aaditya Dravid, Philip Heesen, Joseph Frantzias, Maria Jose Cavagnaro, John Ratliff, Irimpan Mathews, Atman Desai

  • Open Access

    3D Deep Learning for Brain Tumor Segmentation and Survival Prediction: A Comprehensive Multi-Modal Analysis Using the BraTS2020 Dataset

    by Vivek Sanker, Dhanya Mahesh, Zhikai Li, Alexander Thaller, Philip Heesen, Linda Liverani, David Wang, Maria Jose Cavagnaro, Ravi Teja Medikonda, Laura Prolo, et al.

    Introduction: Three-dimensional deep learning offers promise for automated accurate brain tumor segmentation and survival prediction but requires robust validation across multiple MRI modalities to be effectively implemented in clinical practice. Methods: This study presents a comprehensive 3D deep learning framework using 369 cases from the BraTS2020 dataset. A 3D U-Net architecture was developed for tumor segmentation utilizing combined imaging data and optimized for computational efficiency and memory. The final 3D U-Net model segmentations were used to build machine learning 6-month and 12-month survival classifiers. Segmentation models were evaluated using multiple metrics, including the Dice Similarity Coefficient, Hausdorff Distance, and Cohen’s d. The classification models were evaluated using AUC-ROC and balanced accuracy. Results: Segmentation achieved a modest, but promising, performance across 30 epochs and with 295 training patients, achieving the best mean validation Dice = 0.8388 and a final-epoch mean Dice of 0.8263. Survival classification with a hybrid clinical and imaging logistic regression showed promising results, with 12-month prediction achieving AUC = 0.746 and 69% accuracy. The top contributing features for the 12-month prediction classifier were extent of resection, T1 contrast-enhanced tumor median, and FLAIR tumor median. Conclusions: This comprehensive framework demonstrates that a multi-modal approach provides meaningful performance gains, while segmentation-derived features show a promising ability to enable survival prediction.

  • Open Access

    From Pixels to Precision: Generative Artificial Intelligence as a Paradigm Shift in Spine Imaging—Technical Foundations, Clinical Applications, and the Path to Safe Clinical Deployment

    by Daniyal Ashraf, Vivek Sanker, Linda Liverani, Chelsea Park, Ravi Teja Medikonda, Maria Jose Cavagnaro, Ikchan Jeon, John Ratliff, Atman Desai

    Spine imaging represents a complex diagnostic frontier characterized by anatomical variability, motion artifacts, metallic instrumentation interference, and significant inter-reader diagnostic variability (κ=0.20 across institutions). While conventional discriminative artificial intelligence (AI) models achieve >95% accuracy in detecting degenerative changes, they remain limited by data scarcity, heterogeneous protocols, and poor generalizability. In the spine, these limitations are particularly relevant because clinical decisions can often depend on subtle distinctions (such as differentiating levels of canal or foraminal stenosis, characterizing Modic endplate changes, or assessing pedicle and vertebral morphology), where small inconsistencies can meaningfully alter management or surgical planning. Generative AI (GenAI) systems—including generative adversarial networks (GANs), diffusion models, and vision-language models (VLMs)—offer a paradigm shift by learning underlying data structures to generate high-quality synthetic outputs rather than merely classifying existing data. This narrative review, conducted using SANRA (scale for the assessment of narrative review articles) methodology across PubMed, Scopus, Embase, and Cochrane Library, examined GenAI applications in spine imaging. Eligible studies included observational designs through randomized controlled trials exploring image reconstruction, synthetic computed tomography (CT) generation, segmentation, and surgical planning applications. GAN-generated synthetic magnetic resonance imaging sequences reduce scan times by ~40% while maintaining diagnostic confidence; diffusion models enable radiation-free synthetic CT for preoperative planning; and VLMs generate structured radiology reports with hallucination rates <1.12%. However, critical barriers impede clinical translation: external validation gaps reveal AI performance collapse in real-world cohorts (sensitivity drops to 54.9% in cervical fracture detection); hallucinations and anatomical inaccuracies risk misguiding implant sizing; bias amplification magnifies demographic underrepresentation; and fragmented, small datasets lack standardized benchmarks. Technical fragility, computational demands, clinician trust deficits, and unresolved regulatory frameworks for iteratively-updating systems remain unaddressed. Successful integration requires coordinated development across 5 priorities: (1) multi-institutional datasets with cross-vendor harmonization, (2) federated learning frameworks preserving privacy, (3) uncertainty quantification and explainability tools, (4) outcome-linked clinical validation replacing technical metrics, and (5) workflow-integrated systems with DICOM-native interfaces and provenance tracking.


  • Open Access

    Robot-assisted excision of presacral ganglioneuroma: illustrative case

    by Srinath Hariharan, Vivek Sanker, Chelsea Park, Joseph Frantzias, Maria Jose Cavagnaro, Aaron J. Dawes, Atman Desai

    BACKGROUND: Presacral ganglioneuromas are extremely rare tumors, with only 37 documented cases in the literature. For a successful outcome, resection is crucial because it is currently the only effective treatment option. With the advancement in resection techniques, robotic surgery is now being utilized for achieving optimal surgical outcomes, with only 2 previous cases being documented in the literature for the resection of presacral ganglioneuroma. Since ganglioneuromas are benign, radiation therapy and adjuvant chemotherapy are not recommended; however, frequent monitoring is required to detect possible local recurrences early. OBSERVATIONS: The authors present the case of presacral ganglioneuroma in a 62-year-old male who underwent robot-assisted excision. Robot-assisted surgery allowed for a positive surgical outcome, including the absence of intra- or postoperative complications and a decreased length of hospital stay. LESSONS: The presacral location poses challenges to resection due to many exiting nerve roots. Robotic surgery facilitates positive patient outcomes for tumors in challenging anatomical locations like the presacral location. https://thejns.org/doi/10.3171/CASE25462

  • Thoracic corpectomy and vertebral body reconstruction (TCVBR): a systematic review and meta-analysis

    by Amr Badary, Toka Aziz El-Ramly, Ahmed Kertam, Esraa Y. Salama, Vivek Sanker, Noura E. Abomera, Rafael De la Garza Ramos, Oday Atallah, Alan Hernández-Hernández, Mohammed Khalil Al-Barbarawi, et al.

  • Open Access

    Current Trends and Future Prospects of Radiomics and Machine Learning (ML) Models in Spinal Tumors—A Narrative Review

    by Vivek Sanker, Suhrud Panchawgh, Anmol Kaur, Vinay Suresh, Dhanya Mahesh, Eeman Ahmad, Srinath Hariharan, Dhiraj Pangal, Maria Jose Cavgnaro, Mirabela Rusu, et al.

    The intersection between radiomics, the computational analysis of imaging data, and machine learning (ML) may lead to new developments in the diagnosis, prognosis, and management of diseases. For spinal tumors specifically, applications of these fields appear promising. In this educational narrative review, we provide a summary of the current advancements in radiomics and artificial intelligence (AI), as well as applications of both fields in the diagnosis and management of spinal tumors. We also provide a suggested workflow of radiomics and machine learning analysis of spinal tumors for researchers, including a list and description of commonly used radiomic features. Future directions in the field of radiomics and machine learning applications to spinal tumors may involve validating already proposed algorithms with larger datasets, ensuring that all computational applications to patient care maintain high ethical standards, and continuing work in developing novel and highly accurate computational techniques to enhance patient outcomes.

  • Open Access

    Artificial Intelligence Models for Predicting Outcomes in Spinal Metastasis: A Systematic Review and Meta-Analysis

    by Vivek Sanker, Prachi Dawer, Alexander Thaller, Zhikai Li, Philip Heesen, Srinath Hariharan, Emil O. R. Nordin, Maria Jose Cavagnaro, John Ratliff, Atman Desai

    Background: Spinal metastases can cause significant impairment of neurological function and quality of life. Hence, personalized clinical decision-making based on prognosis and likely outcome is desirable. The effectiveness of AI in predicting complications and treatment outcomes for patients with spinal metastases is assessed. Methods: A thorough search was carried out through the PubMed, Scopus, Web of Science, Embase, and Cochrane databases up until 27 January 2025. Included were studies that used AI-based models to predict outcomes for adult patients with spinal metastases. Three reviewers independently extracted the data, and screening was conducted in accordance with PRISMA principles. AUC results were pooled using a random-effects model, and the PROBAST program was used to evaluate the study’s quality. Results: Included were 47 articles totaling 25,790 patients. For training, internal validation, and external validation, the weighted average AUCs were 0.762, 0.876, and 0.810, respectively. The Skeletal Oncology Research Group machine learning algorithms (SORG-MLAs) were the ones externally validated the most, continuously producing AUCs > 0.84 for 90-day and 1-year mortality. Models based on radiomics showed promise in preoperative planning, especially for outcomes of radiation and concealed blood loss. Most research concentrated on breast, lung, and prostate malignancies, which limited its applicability to less common tumors. Conclusions: AI models have shown reasonable accuracy in predicting mortality, ambulatory status, blood loss, and surgical complications in patients with spinal metastases. Wider implementation necessitates additional validation, data standardization, and ethical and regulatory framework evaluation. Future work should concentrate on creating multimodal, hybrid models and assessing their practical applications.