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

Search research articles

Related Experiment Video

Updated: Jan 15, 2026

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

Optimizing TB Bacteria Detection Efficiency: Utilizing RetinaNet-Based Preprocessing Techniques for Small Image Patch

Shwetha V¹, Barnini Banerjee², Vijaya Laxmi¹

¹Department of Electrical and Electronics Engineering, Manipal Institute of Technology, Manipal, Manipal Academy of Higher Education, Manipal, Karnataka, India.

International Journal of Biomedical Imaging

|October 15, 2025

Summary

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

<i>Nocardia farcinica</i> brain abscess in a patient with Evans syndrome: challenges in management.

Oxford medical case reports·2026

Same author

Association of Serum Vitamin D Status with Multidimensional Health Parameters in Patients with Diabetic Foot Infections: A Cross-Sectional Analysis in a Tertiary Healthcare Facility.

The international journal of lower extremity wounds·2025

Same author

Acute interstitial pancreatitis with <i>Burkholderia cenocepacia</i> pseudocyst in an immunocompetent host: A case report on an atypical presentation and review of literature.

IDCases·2025

Same author

Ralstonia pickettii bacteremia: A retrospective review of records.

Indian journal of medical microbiology·2024

Same author

Vitamin D attenuates biofilm-associated infections via immunomodulation and cathelicidin expression: a narrative review.

Expert review of anti-infective therapy·2022

Same author

Diabetic Foot Infection with <i>Bacteroides pyogenes</i>.

Journal of global infectious diseases·2022

This study introduces an automated system for detecting tuberculosis (TB) using Ziehl-Neelsen stained images. The AI model accurately identifies TB bacilli and white blood cells, improving diagnostic speed and accuracy.

Area of Science:

Medical Diagnostics
Computational Biology
Microscopy Imaging

Background:

Tuberculosis (TB) is a re-emerging infectious disease requiring timely and precise diagnosis.
Ziehl-Neelsen (ZN) staining visualizes Mycobacterium tuberculosis but manual detection in microscopy images is challenging due to small bacilli size.
Automated methods are crucial for accelerating TB diagnostic workflows.

Purpose of the Study:

To develop and evaluate an automated two-stage pipeline for detecting TB bacilli in ZN-stained microscopy images.
To enhance the accuracy and efficiency of TB screening through artificial intelligence.

Main Methods:

A novel two-stage pipeline utilizing a RetinaNet-based object detection model with dilated convolutional layers for localizing TB bacilli and white blood cells (WBCs).

Keywords:

RetinaNet TB bacteria detection biomedical imaging computer-aided diagnosis feature extraction image patch analysis image processing machine learning pre-processing techniques small image patch classification

More Related Videos

Transient Optical Clearing Using Absorbing Molecules for Ex Vivo and In Vivo Imaging

Transient Optical Clearing Using Absorbing Molecules for Ex Vivo and In Vivo Imaging

Published on: July 11, 2025

Related Experiment Videos

Last Updated: Jan 15, 2026

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

Transient Optical Clearing Using Absorbing Molecules for Ex Vivo and In Vivo Imaging

Transient Optical Clearing Using Absorbing Molecules for Ex Vivo and In Vivo Imaging

Published on: July 11, 2025

A patch-based convolutional neural network (CNN) classifier for analyzing extracted regions.

Utilized the ZNSM-iDB dataset comprising ~2000 ZN-stained images.

Main Results:

The RetinaNet model achieved high average precision (AP): 0.94 for WBCs and 0.97 for TB bacilli.
The proposed CNN classifier demonstrated a classification accuracy of 93%, outperforming traditional CNN architectures.
The system effectively addressed challenges of small object detection and background interference.

Conclusions:

The developed automated framework offers a robust and scalable solution for TB screening using ZN-stained microscopy.
This AI-driven approach significantly improves the accuracy and efficiency of TB diagnosis.