Skip to content

Multicenter Study of Deep Learning for Predicting Chemoradiotherapy Response in Locally Advanced Cervical Cancer Based on Multimodal Imaging and Clinical Variables

Multicenter study of deep learning model for predicting chemoradiotherapy efficacy in locally advanced cervical cancer based on pelvic magnetic resonance imaging, digital pathological images and clinical variables

Status
Active, not recruiting
Phases
Unknown
Study type
Observational
Source
ChiCTR
Registry ID
ChiCTR2600124789
Enrollment
Unknown
Registered
2026-05-18
Start date
2026-06-01
Completion date
Unknown
Last updated
2026-05-25

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Locally advanced squamous cell carcinoma of the cervix treated with definitive radiotherapy

Interventions

Sponsors

Zhejiang Cancer Hospital
Lead Sponsor

Eligibility

Sex/Gender
Female
Age
18 Years to 75 Years

Inclusion criteria

Inclusion criteria: 1. Pathologically confirmed primary cervical cancer, with histological types including squamous cell carcinoma, adenocarcinoma, and adenosquamous carcinoma. 2. Clinical stage IB3, II, III or IVA according to the 2018 FIGO staging system; no prior history of surgery, radiotherapy, chemotherapy, immunotherapy or other systemic anti-tumor treatment. 3. Received definitive concurrent chemoradiotherapy at Zhejiang Cancer Hospital, Sichuan Cancer Hospital, or the Affiliated Hospital of Southwest Medical University. The treatment regimen consisted of external beam radiotherapy, brachytherapy, and platinum-based concurrent chemotherapy. 4. Pelvic magnetic resonance imaging completed within 2 weeks before the initiation of radiotherapy, with complete imaging data available for analysis. 5. Cervical biopsy specimens obtained prior to radiotherapy, with analyzable whole-slide digital pathological H&E images available. 6. Complete baseline clinical data, laboratory data, treatment records and follow-up data. 7. Follow-up duration of no less than 24 months, or occurrence of a study endpoint within 24 months.

Exclusion criteria

Exclusion criteria: 1. Prior pelvic radiotherapy, pelvic tumor surgery, or any other anti-tumor treatment for cervical cancer. 2. Presence of a second primary malignant tumor, or suspected dual/multiple primary malignancies that cannot be ruled out. 3. Lack of pathological confirmation before radiotherapy, or poor-quality digital pathological images unsuitable for analysis. 4. Severe artifacts, missing key sequences on pelvic MRI, or images that do not meet the requirements for radiological analysis. 5. Severe missing data of radiotherapy plans, dosimetric parameters or concurrent chemotherapy records, making collection of key variables impossible. 6. Underwent curative or debulking surgery within 6 months after concurrent chemoradiotherapy, which may significantly affect the assessment of the primary endpoint. 7. Severe loss to follow-up or unreliable determination of study endpoints. 8. Any other conditions deemed inappropriate for enrollment in this study by the investigators.

Design outcomes

Primary

MeasureTime frame
Hand-engineered radiomic features;

Countries

China

Contacts

Public ContactZhuomin Yin

Zhejiang Cancer Hospital

yinzm@zjcc.org.cn+86 571 88122032

Outcome results

None listed

Source: ChiCTR (via WHO ICTRP) · Data processed: May 30, 2026