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 Videos

Deep learning-based cervical cancer T-staging using MRI: multi-structure segmentation and classification.

Shanshan Xu^1,2, Yuxin Zou^1,3,2, Zhe Wu^4,5

¹Department of Digital Medicine, College of Biomedical Engineering and Medical Imaging, Army Medical University, (Third Military Medical University), Chongqing, 400038, China.

BMC Medical Imaging

|May 30, 2026

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

Rational design of active pharmaceutical ingredient-based co-assembled nanoparticles for cancer immunotherapy.

Journal of controlled release : official journal of the Controlled Release Society·2026

Same author

Detection of clinically significant drug-drug interactions in serotonin syndrome: a multisource real-world data and pharmacovigilance study.

Therapeutic advances in drug safety·2026

Same author

Corrigendum to "P2X4 receptor mediates macrophage infiltration leading to endometriotic cyst epithelium proliferation and hyperalgesia in mouse model" [F S Sci 2025;6:73-84].

F&S science·2026

Same author

Microbially induced hydroxyapatite improves simultaneous nitrogen and phosphorus removal in aerobic granular sludge.

Bioresource technology·2026

Same author

Risk of bias among Chinese-language randomized controlled trials on Chinese herbal medicine included in meta-analyses published in 2021-2022: A cross-sectional study.

Integrative medicine research·2026

Same author

Revealing symptom-level vulnerabilities between academic involution and anxiety: a network analysis.

BMC psychology·2026

Same journal

Radiomics-based causal machine learning for exploratory treatment-effect estimation of neoadjuvant chemotherapy cycle intensity in osteosarcoma: a proof-of-concept study.

BMC medical imaging·2026

Same journal

Gestational age-specific MRI reference values for fetal renal morphology and ADC.

BMC medical imaging·2026

Same journal

MRI findings of intrahepatic cholangiocarcinoma with sarcomatoid differentiation: a retrospective case series.

BMC medical imaging·2026

Same journal

Multimodal deep learning for papillary thyroid carcinoma diagnosis using ultrasound and cytology.

BMC medical imaging·2026

Same journal

MonoGID: geometry and illumination aware enhancement with distillation for self-supervised monocular endoscopic depth estimation.

BMC medical imaging·2026

Same journal

Application of transformer attention mechanism-based multimodal deep learning model in the diagnosis of papillary thyroid carcinoma.

BMC medical imaging·2026

See all related articles

This summary is machine-generated.

This study introduces CPANet and Swin Transformer for automated cervical cancer segmentation and staging using MRI scans. These deep learning models significantly improve diagnostic accuracy and efficiency, aiding in underserved healthcare.

Area of Science:

Medical Imaging
Artificial Intelligence
Oncology

Background:

Cervical cancer presents a high incidence and mortality rate, posing a significant threat to women's health.
Current cervical cancer T-staging relies on subjective clinical experience, leading to potential misdiagnosis.

Purpose of the Study:

To develop a deep learning-based technique for automatic segmentation and T-staging of cervical cancer.
Enhance the clinical diagnostic accuracy and efficiency for cervical cancer management.

Main Methods:

A dataset of 17,479 fT1WI MRI scans from 144 patients was utilized.
A novel segmentation network, CPANet, was designed integrating global pyramid guidance and atrous spatial pyramid pooling.
T-staging models were developed using ResNet50, DenseNet121, and Swin Transformer, with pathological T-staging as ground truth.

Keywords:

Cervical cancer Deep learning MRI Segmentation T-staging diagnosis

Related Experiment Videos

Main Results:

CPANet demonstrated superior segmentation performance with high Dice similarity coefficients for tumors and organs.
The Swin Transformer model achieved the best T-staging performance, with high AUCs for main and sub-stages.
The developed models improved diagnostic accuracy and efficiency, with an average processing time of 1.60 seconds per case.

Conclusions:

CPANet and Swin Transformer enable accurate automatic segmentation and T-staging of cervical cancer from MRI images.
These advancements improve diagnostic accuracy and efficiency, conserve medical resources, and support intelligent healthcare systems.