膀胱がんの予後予測のためのスライド全体画像と CT ラジオミクスに基づく深層学習システム
Bladder cancer (BLCA), with its diverse histopathological features and varying patient outcomes, poses significant challenges in diagnosis and prognosis. Postoperative survival stratification based on radiomics feature and whole slide image feature may be useful for treatment decisions to improve prognosis. In this research, we aim to develop a deep learning-based prognostic-stratification system for automatic prediction of overall and cancer-specific survival in patients with BLCA.This observational study evaluates a deep learning system that combines CT images and digitized pathology slides to predict outcomes in patients with bladder cancer. It includes a retrospective cohort and a prospective cohort of newly enrolled patients. The prospective cohort will assess the system in patients enrolled during (2024-2026), with follow-up for survival and recurrence.
調査の概要
状態
状態
条件
条件
介入・治療
介入・治療
詳細な説明
Study structure The study includes an initial retrospective phase and a subsequent prospective observational phase involving newly enrolled patients. The two phases are analyzed separately according to the specified analysis plan.
Retrospective phase The retrospective phase included patients from [2012-2024] and was used for model construction. Results from this phase were reported in npj series.
Prospective phase Enrollment of newly recruited patients began on [2024]. The prospective phase follows protocol, with ethics approval from the first affliated hospital of chongqing medical, university. Recruitment is consecutive, as specified in the protocol.
Model evaluation The prospective cohort is used for validation. The model version, preprocessing procedures and prediction thresholds used in this phase. Any model updating using this cohort is documented separately.
Registry update This update distinguishes the retrospective phase from the subsequently enrolled cohort. The prospective phase enrollment dates and the dates of protocol development and ethics approval are reported separately.
研究の種類
研究の種類
入学 (推定)
入学
連絡先と場所
研究連絡先
研究連絡先
- 名前:QuanHao He
- 電話番号:800-555-5555
- メール:2020120460@stu.cqmu.edu.cn
研究連絡先のバックアップ
- 名前:Mingzhao Xiao, PHD
- 電話番号:800-555-5555
- メール:2023140134@stu.cqmu.edu.cn
研究場所
-
-
Chongqing Municipality
-
Chongqing、Chongqing Municipality、中国、400016
- 募集
- Department of Urology, The First Affiliated Hospital of Chongqing Medical University
-
コンタクト:
- QuanHao He, PHD
- 電話番号:800-555-5555
- メール:2020120460@stu.cqmu.edu.cn
-
コンタクト:
- Mingzhao Xiao, PHD
- 電話番号:023-89012557
- メール:2023140134@stu.cqmu.edu.cn
-
-
参加基準
適格基準
適格基準
就学可能な年齢
- 子
- 大人
- 高齢者
健康ボランティアの受け入れ
受講資格のある性別
サンプリング方法
調査対象母集団
We included patients who had surgery only or who had neoadjuvant chemotherapy before surgery. We excluded patients with a postoperative diagnosis of non-urothelial carcinoma.
説明
Inclusion Criteria:
- patients with bladder cancer who had surgery like radical cystectomy or transurethral resection of bladder tumour (TURBT)
- contrast-CT scan less than two weeks before surgery
- complete CT image data and clinical data
- complete whole slide image data
Exclusion Criteria:
- patients with a postoperative diagnosis of non-urothelial carcinoma
- poor quality of CT images
研究計画
研究はどのように設計されていますか?
デザインの詳細
- 観測モデル:COHORT
- 時間の展望:OTHER
グループ/コホートの数
コホートと介入
グループ/コホートグループ/コホート |
介入・治療介入・治療 |
|---|---|
|
Retrospective cohort
Patients with bladder cancer included in the retrospective phase of the study, using clinical records, CT images, and whole-slide images obtained during [2012-2024]. This cohort was used for model development and/or validation and was reported in our npj publications. |
develop and validate a deep learning system for prognostication prediction in bladder cancer based on CT radiomics and whole slide images. |
|
Prospective cohort of newly enrolled patients
Newly enrolled patients with bladder cancer recruited at four centers between 2024 and2026. Eligibility is assessed at enrollment, and participants are followed according to protocol version and date for the study outcomes. This cohort is distinct from the previously reported retrospective cohort. |
develop and validate a deep learning system for prognostication prediction in bladder cancer based on CT radiomics and whole slide images. |
この研究は何を測定していますか?
主要な結果の測定
主要な結果の測定
結果測定 |
メジャーの説明 |
時間枠 |
|---|---|---|
|
Overall survival
時間枠:up to 10 years
|
the time from the date of surgery to death from any cause or the date of last contact (censored observation) at the date of data cut-off. |
up to 10 years
|
二次結果の測定
二次結果の測定
結果測定 |
メジャーの説明 |
時間枠 |
|---|---|---|
|
Recurrence free survival
時間枠:up to 10 years
|
the time from the date of surgery to the date of first documented disease recurrence. Patients without recurrence at the time of analysis will be censored |
up to 10 years
|
|
progression-free survival
時間枠:up to 10 years
|
The length of time during and after the treatment of a disease, such as cancer, that a patient lives with the disease but it does not get worse. In a clinical trial, measuring the progression-free survival is one way to see how well a new treatment works. Also called PFS. |
up to 10 years
|
協力者と研究者
研究記録日
主要日程の研究
研究開始 (実際)
研究開始
一次修了 (推定)
一次修了
研究の完了 (推定)
研究の完了
試験登録日
最初に提出
最初に提出
QC基準を満たした最初の提出物
QC基準を満たした最初の提出物
最初の投稿 (実際)
最初の投稿
学習記録の更新
投稿された最後の更新 (実際)
投稿された最後の更新
QC基準を満たした最後の更新が送信されました
QC基準を満たした最後の更新が送信されました
最終確認日
最終確認日
詳しくは
本研究に関する用語
追加の関連 MeSH 用語
その他の研究ID番号
その他の研究ID番号
- BLCA_CMUFH
- K2024-187-01 (その他の識別子:The First Affiliated Hospital of Chongqing Medical University)
個々の参加者データ (IPD) の計画
個々の参加者データ (IPD) を共有する予定はありますか?
IPD プランの説明
The datasets analyzed during the current study are not publicly available due to the privacy of patients but are available from the corresponding author on reasonable request.
医薬品およびデバイス情報、研究文書
米国FDA規制医薬品の研究
米国FDA規制機器製品の研究
この情報は、Web サイト clinicaltrials.gov から変更なしで直接取得したものです。研究の詳細を変更、削除、または更新するリクエストがある場合は、register@clinicaltrials.gov。 までご連絡ください。 clinicaltrials.gov に変更が加えられるとすぐに、ウェブサイトでも自動的に更新されます。