Emir Amaro Syailendra

Dr. Emir Amaro Syailendra

Russel H. Morgan Department of Radiology, Johns Hopkins Medicine, Baltimore, Maryland, USA
orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 August 2025 in Radiology Advances
Verified
Journal Article
Open access
FLFelipe Lopez-Ramirez
Felipe Lopez-Ramirez
ESEmir Amaro Syailendra
Emir Amaro Syailendra
FTFlorent Tixier
Florent Tixier
SKSatomi Kawamoto
Satomi Kawamoto
EFEliot Keith Fishman
Eliot Keith Fishman
LCLinda C. Chu
Linda C. Chu
Advancements in artificial intelligence (AI) are transforming medical imaging diagnostics, offering new possibilities for automated pancreatic tumor detection in computed tomography scans. Pancreatic ductal adenocarcinoma continues to be one of the most lethal malignancies, with early detection being critical for improving survival rates. Deep learning models can learn hierarchical feature representations directly from imaging data, enhancing tumor detection accuracy. However, variations in model performance, impaired generalizability, and limited interpretability remain critical barriers to clinical adoption. This article provides a comprehensive overview of deep learning-based pancreatic tumor detection, discussing fundamental concepts, recent advancements, and challenges for clinical adoption. Implementation of deep learning tumor detection models into imaging workflows holds promise for improving early detection rates of pancreatic tumors. Addressing issues of standardization, external validation, and model transparency will be essential to enable the integration of AI into pancreatic cancer screening and diagnostics, ultimately improving early detection and patient outcomes.

19 February 2026 in Diagnostic and Interventional Imaging
Verified
Journal Article
Closed access
ESEmir Amaro Syailendra
Emir Amaro Syailendra
FLFelipe Lopez-Ramirez
Felipe Lopez-Ramirez
FTFlorent Tixier
Florent Tixier
ABAlejandra Blanco
Alejandra Blanco
HAHajra Arshad
Hajra Arshad
EFEliot Keith Fishman
Eliot Keith Fishman

4 December 2025 in JMIR Public Health and Surveillance
Verified
Journal Article
Open access
PSPaulina Sosa
Paulina Sosa
ESEmir Amaro Syailendra
Emir Amaro Syailendra
HLHarold P Lehmann
Harold P Lehmann
HKHadi Kharrazi
Hadi Kharrazi
Background: The COVID-19 pandemic was a critical time for public health, and though dashboards remained a source of critical health information for decision-makers, key gaps in equity-based decision support were revealed. The DIRE (Dashboard Instrument to Review Equity) Framework and Checklist tool was developed to be a practical tool for public health departments to use in evaluating equity-based decision support mechanisms in their dashboards. Objective: The objective of this agreement and reliability study was to validate the DIRE Checklist tool as a practical and reliable instrument for data practitioners to use in evaluating dashboards. Methods: This study was divided into 5 steps to conduct the necessary analysis for agreement and reliability. Step 1 completed the development of the DIRE Checklist tool in Qualtrics (Qualtrics International Inc). Step 2 focused on the parameters required for the selection of the 26 US state–based dashboards. Step 3 was the user testing and assessment process during which each reviewer applied the DIRE tool to each dashboard. Step 4 involved conducting different assessment methods to specifically calculate the comparative analysis, interrater agreement, intraclass correlation coefficients, and the cosine similarity for the Qualtrics, reviewer, and categorical scores. Finally, Step 5 involved conducting any qualitative assessment required on the notes. Results: A total of 26 dashboards were evaluated using the DIRE Checklist tool by 2 reviewers. The overall percentage comparison for the Qualtrics Score was 31.7% (28.24/89) for Reviewer 1 and 41.8% () for Reviewer 2, resulting in a relative percent agreement of 72.7%. Additionally, the categorical scores showed substantial to high agreement across most categories based on percent agreement within each category. The intraclass correlation coefficient scores indicated varying levels of agreement across different categories, with good agreement observed for the Qualtrics score. Conclusions: The reliability and agreement result of the study confirmed strong performance of the DIRE checklist tool. The scores calculated were evaluated consistently and reliably by both raters—demonstrating the DIRE Checklist tool’s ability to robustly evaluate different dashboards across a number of different categories and parameters.

1 August 2025 in Cancers
Verified
Journal Article
Open access
PDF file
FTFlorent Tixier
Florent Tixier
FLFelipe Lopez-Ramirez
Felipe Lopez-Ramirez
ESEmir Amaro Syailendra
Emir Amaro Syailendra
ABAlejandra Blanco
Alejandra Blanco
Ammar Asrar JavedAmmar Asrar Javed
Ammar Asrar Javed
EFEliot Keith Fishman
Eliot Keith Fishman
Background/Objectives: To evaluate the importance of image processing in a previously validated model for detecting pancreatic neuroendocrine tumors (PanNETs) and to introduce Image2Radiomics, a new framework that ensures reproducibility of the image processing pipeline and facilitates the deployment of radiomics models. Methods: A previously validated model for identifying PanNETs from CT images served as the reference. Radiomics features were re-extracted using Image2Radiomics and compared to those from the original model using performance metrics. The impact of nine alterations to the image processing pipeline was evaluated. Prediction discrepancies were quantified using the mean ± SD of absolute differences in PanNET probability and the percentage of classification disagreement. Results: The reference model was successfully replicated with Image2Radiomics, achieving a Cohen’s kappa coefficient of 1. Alterations to the image processing pipeline led to reductions in model performance, with AUC dropping from 0.87 to 0.71 when image windowing was removed. Prediction disagreements were observed in up to 45% of patients. Even minor changes, such as switching the library used for spatial resampling, resulted in up to 21% disagreement. Conclusions: Reproducing image processing pipelines remains challenging and limits the clinical deployment of radiomics models. While this study is limited to one model and imaging modality, the findings underscore a common risk in radiomics reproducibility. The Image2Radiomics framework addresses this issue by allowing researchers to define and share complete processing pipelines in a standardized way, improving reproducibility and facilitating model deployment in clinical and multicenter settings.

1 January 2026 in Korean Journal of Radiology
Verified
Journal Article
Open access
PDF file
ESEmir Amaro Syailendra
Emir Amaro Syailendra
HAHajra Arshad
Hajra Arshad
FLFelipe Lopez-Ramirez
Felipe Lopez-Ramirez
FTFlorent Tixier
Florent Tixier
SKSatomi Kawamoto
Satomi Kawamoto
LCLinda C. Chu
Linda C. Chu
Syailendra EA, et al. Korean J Radiol. 2026 ;27:e37. https://doi.org/10.3348/kjr.2026.0003

1 October 2025 in Radiology
Verified
Journal Article
Closed access
LCLinda C. Chu
Linda C. Chu
ESEmir Amaro Syailendra
Emir Amaro Syailendra