Large Language Model-Assisted cTNM Annotation From Chinese PSMA PET/CT Reports (PSMA-LLM-cTNM)
Large Language Model-Assisted Imaging cTNM Staging Annotation and Uncertainty Recognition for Prostate Cancer Based on Chinese PSMA PET/CT Reports
This observational study will develop and validate a large language model-assisted workflow for imaging cTNM staging annotation and uncertainty recognition in prostate cancer using Chinese PSMA PET/CT report texts generated during routine clinical care. The study will use de-identified report texts and necessary baseline clinical information only. No additional imaging examination, blood test, treatment, or follow-up visit will be assigned for this study.
The main objective is to evaluate whether a locally or institutionally controlled large language model can identify report-derived imaging cT, cN, and cM categories, extract supporting evidence from the original report, and recognize uncertainty expressions. Model performance will be assessed using an internal independent validation set, external validation reports from two collaborating hospitals, and a prospective validation set of 100 consecutive routine PSMA PET/CT reports. A human-AI comparison will also be performed using physicians from urology and imaging-related specialties with different seniority levels.
調査の概要
詳細な説明
This is a multicenter observational diagnostic accuracy validation study based on Chinese PSMA PET/CT report texts from patients with prostate cancer or suspected prostate cancer. The study is not designed to evaluate a drug, device, surgical procedure, or imaging intervention. PSMA PET/CT examinations will be performed as part of routine clinical care, and the study will only analyze de-identified report texts and necessary baseline information after the reports have been finalized.
The study consists of retrospective and prospective components. Retrospectively, approximately 4,000 PSMA PET/CT reports from the First Affiliated Hospital of Wenzhou Medical University will be systematically annotated to construct a research database. An internal independent validation set of 300 reports, not used for model development or prompt optimization, will be used to evaluate the performance of the large language model. The reference standard for this 300-report validation set will be established by two experienced urologists through joint annotation, with adjudication by a nuclear medicine expert when needed. External validation will be performed using 110 de-identified reports from the First Affiliated Hospital of Ningbo University and 102 de-identified reports from Liuzhou People's Hospital. In addition, after ethics approval, 100 consecutive routine PSMA PET/CT reports from the First Affiliated Hospital of Wenzhou Medical University will be prospectively included to evaluate the accuracy and operational stability of the frozen model and prompt versions.
The large language model workflow will be deployed locally or in an institutionally controlled environment. The model will be instructed to generate structured JSON outputs, including cT_report, cN_report, cM_report, cT_uncertain, cN_uncertain, cM_uncertain, evidence_T, evidence_N, and evidence_M. The target task is report-derived imaging cTNM staging annotation, not pathological TNM staging or overall AJCC stage grouping. The model output will be used only for research evaluation and methodological analysis and will not be used for clinical diagnosis, treatment decision-making, or patient notification.
A human-AI comparison will be conducted on the 300-report internal validation set. Eight human evaluators from urology and imaging-related specialties, including trainees, residents, attending physicians, and associate chief physicians, will independently annotate the reports before and after learning the annotation manual. Annotation time will be recorded for each round. The performance of human evaluators and the large language model will be compared against the expert consensus reference standard.
The main outcome will be the accuracy of the large language model in identifying cT, cN, and cM categories from Chinese PSMA PET/CT reports. Secondary outcomes will include precision, recall, F1-score, macro-F1, micro-F1, complete cTNM triplet matching rate, uncertainty recognition performance, evidence extraction quality, human-AI comparison results, annotation time, external validation performance, prospective validation performance, and error type distribution. Error analysis will focus on local tumor extent, regional versus non-regional lymph node boundaries, bone and visceral metastasis recognition, equivocal wording, treatment-related context, benign or inflammatory alternatives, and lesions not attributable to prostate cancer.
研究の種類
入学 (推定)
連絡先と場所
研究連絡先
- 名前：Qi Lin
- 電話番号：+86 15205771010
- メール：devillynch@126.com
研究連絡先のバックアップ
- 名前：Yikai Chen
- 電話番号：+86 13857730804
- メール：chenyikai@wzhospital.cn
研究場所
-
-
Zhejiang
-
Wenzhou、Zhejiang、中国
- The First Affiliated Hospital of Wenzhou Medical University
-
コンタクト：
- Qi Lin
- 電話番号：+86 15205771010
- メール：devillynch@126.com
-
コンタクト：
- Yikai Chen
- 電話番号：+86 13857730804
- メール：chenyikai@wzhospital.cn
-
-
参加基準
適格基準
就学可能な年齢
- 大人
- 高齢者
健康ボランティアの受け入れ
サンプリング方法
調査対象母集団
説明
Inclusion Criteria:
- Male patients aged 18 years or older.
- Patients with clinically diagnosed, pathologically diagnosed, or clinically suspected prostate cancer.
- Patients who underwent PSMA PET/CT for initial staging, recurrence assessment, treatment response evaluation, metastatic assessment, or other clinical purposes during routine care.
- Complete or basically complete Chinese PSMA PET/CT report text is available, including imaging findings and/or diagnostic impression.
- The report text contains information that can be used to evaluate at least one target field, such as local prostate lesion, regional lymph nodes, non-regional lymph nodes, bone metastasis, visceral metastasis, or uncertainty expressions.
- The research data can be de-identified and replaced by a study identification number before analysis.
Exclusion Criteria:
- PSMA PET/CT reports unrelated to prostate cancer, or reports clearly irrelevant to the research task.
- Reports with severely missing, unreadable, or unavailable main text, imaging findings, or diagnostic impression.
- Reports that cannot be adequately de-identified or contain residual direct personal identifiers that cannot be safely removed.
- Duplicate records, repeated exports of the same examination, or records for which the unique report version cannot be confirmed.
- Reports judged by the research team to be of insufficient quality for manual annotation, model evaluation, or statistical analysis.
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
コホートと介入
グループ/コホート |
介入・治療 |
|---|---|
|
PSMA PET/CT Report Text Validation Cohort
Patients with prostate cancer or suspected prostate cancer who underwent PSMA PET/CT as part of routine clinical care.
De-identified Chinese PSMA PET/CT report texts and necessary baseline information will be used for manual annotation, large language model-assisted imaging cTNM staging annotation, uncertainty recognition, internal validation, external validation, prospective validation, and human-AI comparison.
No additional examination, treatment, or follow-up will be assigned for this study.
|
A locally or institutionally controlled large language model workflow will analyze de-identified Chinese PSMA PET/CT report texts and generate structured outputs for report-derived imaging cTNM staging annotation, uncertainty recognition, and supporting evidence extraction.
This workflow is used only for research evaluation and methodological analysis.
It will not assign any examination, treatment, medication, procedure, or follow-up to participants, and it will not guide clinical diagnosis or treatment decisions.
|
この研究は何を測定していますか？
主要な結果の測定
結果測定 |
メジャーの説明 |
時間枠 |
|---|---|---|
|
Accuracy of LLM-Assisted Imaging cTNM Staging Annotation
時間枠：After freezing the model and prompt versions, through completion of internal, external, and prospective validation, up to 18 months
|
The primary outcome is the accuracy of the large language model in identifying report-derived imaging cT, cN, and cM categories from de-identified Chinese PSMA PET/CT report texts.
The LLM-generated cT_report, cN_report, and cM_report will be compared with the expert consensus reference standard.
Accuracy, precision, recall, F1-score, macro-F1, micro-F1, complete cTNM triplet matching rate, and confusion matrices will be calculated in the internal 300-report validation set, external validation sets, and prospective 100-report validation set.
|
After freezing the model and prompt versions, through completion of internal, external, and prospective validation, up to 18 months
|
二次結果の測定
結果測定 |
メジャーの説明 |
時間枠 |
|---|---|---|
|
Component-Level Accuracy of LLM-Based Uncertainty Recognition
時間枠：After freezing the model and prompt versions, through completion of all validation analyses, up to 18 months.
|
This outcome measures the component-level accuracy of the large language model in recognizing uncertainty labels for report-derived imaging cTNM staging. The LLM-generated cT_uncertain, cN_uncertain, and cM_uncertain labels will be compared with the expert consensus reference standard. Accuracy will be calculated as the number of correctly classified uncertainty labels divided by the total number of component-level uncertainty labels across all reports. The three uncertainty components will be aggregated into one percentage value. 中文对应 |
After freezing the model and prompt versions, through completion of all validation analyses, up to 18 months.
|
|
Complete cTNM Triplet Matching Rate for Human Evaluators and the LLM
時間枠：During pre-training and post-training human annotation rounds and LLM batch inference, up to 18 months.
|
This outcome measures the proportion of reports for which the complete report-derived imaging cTNM triplet assigned by human evaluators and by the large language model exactly matches the expert consensus reference standard.
A report will be counted as correct only when all three components, cT_report, cN_report, and cM_report, are correct.
The result will be reported as the percentage of reports with complete cTNM triplet agreement.
Results will be summarized separately for pre-training human annotation, post-training human annotation, and LLM batch inference.
|
During pre-training and post-training human annotation rounds and LLM batch inference, up to 18 months.
|
|
Annotation Time per Report for Human Evaluators and the LLM
時間枠：During pre-training and post-training human annotation rounds and LLM batch inference, up to 18 months.
|
This outcome measures the mean time required to complete report-derived imaging cTNM annotation per report.
For human evaluators, annotation time will be recorded during the annotation rounds and divided by the number of annotated reports.
For the LLM workflow, batch inference time will be divided by the number of processed reports.
Results will be reported separately for pre-training human annotation, post-training human annotation, and LLM batch inference.
|
During pre-training and post-training human annotation rounds and LLM batch inference, up to 18 months.
|
協力者と研究者
研究記録日
主要日程の研究
研究開始 (推定)
一次修了 (推定)
研究の完了 (推定)
試験登録日
最初に提出
QC基準を満たした最初の提出物
最初の投稿 (実際)
学習記録の更新
投稿された最後の更新 (実際)
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
詳しくは
本研究に関する用語
その他の研究ID番号
- KY2026-278
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
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。
前立腺がんの臨床試験
-
Novartis Pharmaceuticals終了しましたメラノーマ | 高度なEGFR変異体非小さな細胞肺cancer（NSCLC） | KRAS G12変異NSCLC | 食道扁平上皮がん（SCC） | ヘッド/ネックSCC | 進行した胃腸間質腫瘍（GIST） | 進行したNRAS/BRAFT WT皮膚黒色腫アメリカ, 台湾, オランダ, カナダ, スペイン, シンガポール, イタリア, 日本, 韓国
-
Jonsson Comprehensive Cancer CenterNational Cancer Institute (NCI); Highlight Therapeutics積極的、募集していない平滑筋肉腫 | 悪性末梢神経鞘腫瘍 | 滑膜肉腫 | 未分化多形肉腫 | 骨の未分化高悪性度多形肉腫 | 粘液線維肉腫 | II期の体幹および四肢の軟部肉腫 AJCC v8 | III期の体幹および四肢の軟部肉腫 AJCC v8 | IIIA 期の体幹および四肢の軟部肉腫 AJCC v8 | IIIB 期の体幹および四肢の軟部肉腫 AJCC v8 | 切除可能な軟部肉腫 | 多形性横紋筋肉腫 | 切除可能な脱分化型脂肪肉腫 | 切除可能な未分化多形肉腫 | 軟部組織線維肉腫 | 紡錘細胞肉腫 | ステージ I 後腹膜肉腫 AJCC (American Joint Committee on Cancer) v8 | 体幹および四肢の I 期軟部肉腫 AJCC v8 | ステージ... およびその他の条件アメリカ