Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

CORTADO: hill climbing optimization for cell-type specific marker gene discovery and clustering accuracy improvement.

Bioinformatics advances·2026

Same author

Root Canal Disinfection in Primary Teeth: A Comparative Assessment of Visible Light Diode Laser and Ozonated Water.

International journal of clinical pediatric dentistry·2026

Same author

Incorporating Patient Similarity and Clinical Temporality in Disease Prognostic Modeling.

IEEE transactions on computational biology and bioinformatics·2026

Same author

Deployment of a Tailored and Hybrid Educational Strategy for Wartime Capacity Building: American Association of Physicists in Medicine/Help Ukraine Group/Ukrainian Association of Medical Physicists Training Program to Transition Ukraine From Co-60 to Intensity-Modulated Radiation Therapy.

JCO global oncology·2026

Same author

The C/EBPα-(PU.1-LOUP) regulatory circuit regulates monocyte/macrophage development and immune functions.

Blood·2026

Same author

Availability of multidisciplinary treatment modalities and outcomes among patients with resected early-stage non-small cell lung cancer.

JNCI cancer spectrum·2025

Same journal

Causal intervention validation of gene regulatory signals in scGPT.

Journal of biomedical informatics·2026

Same journal

CoAff-DTI: Fine-grained drug-target interaction prediction using pre-trained language models and affinity-guided mechanisms.

Journal of biomedical informatics·2026

Same journal

Evaluation of temporal preservation in synthetic longitudinal patient data.

Journal of biomedical informatics·2026

Same journal

ARKE: An ontology-driven framework for automated mapping of local radiology procedure terms to the LOINC-RadLex playbook using large language model.

Journal of biomedical informatics·2026

Same journal

A validation-driven training controller for cross-lingual biomedical NER via reinforcement learning-based adaptive loss weighting.

Journal of biomedical informatics·2026

Same journal

ASP-HR: An Adaptive Spatial Perception and Hierarchical Reasoning mechanism for document-level biomedical relation extraction.

Journal of biomedical informatics·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Dec 12, 2025

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

A Machine Learning method for relabeling arbitrary DICOM structure sets to TG-263 defined labels.

William C Sleeman Iv¹, Joseph Nalluri², Khajamoinuddin Syed³

¹Virginia Commonwealth University, Department of Radiation Oncology, Richmond, VA, United States of America; Virginia Commonwealth University, Department of Computer Science, Richmond, VA, United States of America; National Radiation Oncology Program, Department of Veteran Affairs, Richmond, VA, United States of America.

Journal of Biomedical Informatics

|August 11, 2020

Summary

This summary is machine-generated.

This study developed a Machine Learning pipeline to automatically relabel anatomical structures in DICOM images using standard nomenclature. The approach achieved high accuracy, enabling better data abstraction for research and quality improvement in cancer treatment.

Keywords:

Class imbalance DICOM Machine Learning Radiation Oncology Random Forest TG-263

More Related Videos

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Published on: February 15, 2017

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Related Experiment Videos

Last Updated: Dec 12, 2025

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Published on: February 15, 2017

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Area of Science:

Medical Imaging
Machine Learning
Radiotherapy

Background:

Standardizing anatomical structure nomenclature in Digital Imaging and Communications in Medicine (DICOM) is crucial for research and quality improvement.
Current manual relabeling is time-consuming and prone to errors.

Purpose of the Study:

To develop and validate a Machine Learning pipeline for automated relabeling of anatomical structures in DICOM format.
To standardize nomenclature according to American Association of Physics in Medicine's Task Group 263 (AAPM TG-263) guidelines.
To facilitate data abstraction for improved research and quality assessment in oncology.

Main Methods:

Utilized DICOM structure sets from approximately 1200 lung and prostate cancer patients.
Developed predictive models using volumetric bitmaps, bony anatomy data, and feature vectors.
Employed singular value decomposition for feature reduction and five classifier algorithms on Apache Spark.
Implemented 5-fold cross-validation and undersampling techniques to address class imbalance.

Main Results:

Random Forest achieved high F1 scores: 98.77% for lung and 95.06% for prostate on curated data.
Accuracies were 95.67% for lung and 90.22% for prostate on non-curated clinical data.
Incorporating bony anatomy and pooling patient data improved accuracy.
k-Means undersampling enhanced accuracy and significantly reduced runtime.

Conclusions:

The proposed Machine Learning pipeline accurately relabels anatomical structures, achieving over 95% accuracy on curated data.
The approach demonstrates robustness on non-curated clinical data, with some structures labeled correctly over 90% of the time.
Validation on an external test set suggests the models' generalizability to other clinical datasets.