AI-based imaging diagnostic systems for rectal cancer

Not Applicable

Recruiting

• Conditions: rectal cancer; large intestine, rectum; D012004

• Registration Number: JPRN-jRCT1040210050
• Lead Sponsor: Ouchi Akira

Brief Summary

Not available

Detailed Description

Not available

Study Timeline

• Results First Posted: 1900-01-01
• Study Start: 2021-08-06
• Last Update Posted: 17 October 2023

Recruitment & Eligibility

• Status: Recruiting
• Sex: All
• Target Recruitment: 200

Inclusion Criteria

1) Pathologically diagnosed as adenocarcinoma (including mucinous, signet-cell, and medullary carcinoma) based on the Japanese Classification of Colorectal, Appendiceal, and Anal Carcinoma (JCCAAC), 3rd English Edition on the resected specimen for rectal cancer
2) Performed abdominal and pelvic contrast-enhanced CT (aortic bifurcation to pelvis) or abdominal and pelvic contrast-enhanced MRI (aortic bifurcation to pelvis) before surgery.
3) Inversion depth was suspected cT2 or deeper on JCCAAC 3rd English Edition, mainly located at the low rectum or anal canal.
4) No preoperative chemotherapy or radiotherapy, and performed bilateral lateral pelvic lymph node dissection and primary rectal cancer resection.
5) No treatment history of surgery, chemotherapy, or radiotherapy for pelvic malignancies (including rectal, gynecologic, and urologic cancers).
6) No distant organ metastasis, distant lymph node metastasis, or peritoneal dissemination (not cStage IV) on preoperative images.

Exclusion Criteria

none

Study & Design

• Study Type: Observational
• Study Design: Not specified

Primary Outcome Measures

Name	Time	Method
Construction of imaging diagnostic systems based on AI for rectal cancer

Secondary Outcome Measures

Name	Time	Method
Validation of AI-based imaging diagnostic systems: false-positive rate, false-negative rate, positive predicting value, sensitivity, specificity, negative predicting value