Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

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

Efficacy of post-transplant brentuximab vedotin maintenance by pre-transplant disease status in relapsed/refractory classic Hodgkin lymphoma.

Blood cancer journal·2026
Same author

Begelomab (BEGESAND<sup>®</sup>) Salvages Steroid-Resistant Acute GVHD in Pediatric Patients.

Journal of clinical medicine·2026
Same author

Multimodal foundation models exploit text to make medical image predictions.

Nature communications·2026
Same author

Peripheral Nerve Infiltration by CAR T-cells in a Case of Mononeuritis Multiplex after Ciltacabtagene Autoleucel.

Blood cell therapy·2026
Same author

A Bloody Mimic of Crohn's Disease: Primary Intestinal EBV-Positive NK/T-Cell Lymphoma.

Digestive diseases and sciences·2026
Same author

STARC-9: A Large-scale Dataset for Multi-Class Tissue Classification for CRC Histopathology.

Advances in neural information processing systems·2026

Related Experiment Video

Updated: Nov 5, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

735

DLBCL-Morph: Morphological features computed using deep learning for an annotated digital DLBCL image set.

Damir Vrabac1, Akshay Smit1, Rebecca Rojansky2

  • 1Department of Computer Science, Stanford University, Stanford, United States.

Scientific Data
|May 21, 2021
PubMed
Summary
This summary is machine-generated.

Geometric features of tumor nuclei in Diffuse Large B-Cell Lymphoma (DLBCL) can predict patient survival. This deep learning approach offers new prognostic insights for this common non-Hodgkin lymphoma.

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

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

Published on: November 30, 2022

3.1K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.5K

Related Experiment Videos

Last Updated: Nov 5, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

735
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

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

Published on: November 30, 2022

3.1K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.5K

Area of Science:

  • Oncology
  • Pathology
  • Computational Biology

Background:

  • Diffuse Large B-Cell Lymphoma (DLBCL) is the most prevalent form of non-Hodgkin lymphoma.
  • Current histological assessments lack consistent prognostic correlation.
  • Novel biomarkers are needed for improved patient outcome prediction.

Purpose of the Study:

  • To investigate the prognostic value of geometric features of DLBCL tumor nuclei.
  • To apply deep learning for quantitative morphologic analysis.
  • To correlate nuclear geometry with patient survival outcomes.

Main Methods:

  • Morphologic analysis of 209 DLBCL cases using tissue microarrays.
  • Immunohistochemical staining for CD10, BCL6, MUM1, BCL2, and MYC.
  • Deep learning model for tumor nuclei segmentation and geometric feature extraction.
  • Cox proportional hazards model for survival analysis.

Main Results:

  • Geometric features of tumor nuclei were computed from histology sections.
  • A deep learning model achieved a C-index of 0.635 (0.574, 0.691) in predicting survival.
  • Quantitative nuclear morphology demonstrates prognostic significance.

Conclusions:

  • Geometric features of DLBCL tumor nuclei hold prognostic importance.
  • Deep learning-based morphologic analysis offers a novel approach to predicting DLBCL outcomes.
  • Further validation in prospective studies is warranted.