Skip to content

A prospective cohort study to validate deep learning models for predicting pCR in rectal cancer

A prospective cohort study to validate deep learning models for predicting pCR in rectal cancer

Status
Active, not recruiting
Phases
Unknown
Study type
Observational
Source
ChiCTR
Registry ID
ChiCTR2400085797
Enrollment
Unknown
Registered
2024-06-18
Start date
2024-06-21
Completion date
Unknown
Last updated
2024-07-08

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

Conditions

Rectal cancer

Interventions

Gold Standard:A pathological response (pCR) is diagnosed by an experienced pathologist according to the surgical specimen.
Index test:A pathological response (pCR) is predicted by a deep learning model that has been constructed in our previous work.

Sponsors

West China Hospital of Sichuan University
Lead Sponsor

Eligibility

Sex/Gender
All
Age
18 Years to No maximum

Inclusion criteria

Inclusion criteria: (1) Age = 18 years old, pathologically confirmed as rectal adenocarcinoma or mucinous adenocarcinoma; (2) Diagnosed as locally advanced rectal cancer (clinical TNM stage II/III); (3) All patients received neoadjuvant therapy (total neoadjuvant treatment, conventional neoadjuvant chemoradiotherapy, or neoadjuvant chemotherapy) followed by total mesorectal resection (4) Baseline high-resolution pelvic MRI obtained, including T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), and apparent diffusion coefficient (ADC) (5) Receive radical surgery and have a complete pathology report; (6) Postoperative pathological response confirmed by an experienced pathologist, including pathologic complete (pCR) and non-pathologic complete (non-pCR); (7) Signed written informed consent.

Exclusion criteria

Exclusion criteria: (1) History of concurrent malignancy or chemoradiotherapy; (2) Patients who do not complete neoadjuvant therapy according to the protocol; (3) Patients who have not undergone radical surgical or not obtain the pathological response evaluation of surgical specimens; (4) No baseline MRI or poor MRI image quality.

Design outcomes

Primary

MeasureTime frame
Area under the curve;Accuracy;

Secondary

MeasureTime frame
Sensitivity;Specificity;Positive predictive value;Negative predictive value;

Countries

China

Contacts

Public ContactXin Wang

West China Hospital of Sichuan University

wangxin@wchscu.edu.cn+86 189 8060 2291

Outcome results

None listed

Source: ChiCTR (via WHO ICTRP) · Data processed: May 28, 2026