AI-Assisted 3D Reconstruction for Lung Resection Planning
Prospective Validation of an Artificial Intelligence-Based 3D Reconstruction Model for Preoperative Planning of Lung Resection.
This prospective observational study aims to validate an artificial intelligence (AI)-based system for automated three-dimensional (3D) reconstruction of pulmonary anatomy from preoperative chest computed tomography (CT) scans in patients undergoing lung resection.
The AI system will automatically identify and reconstruct relevant pulmonary anatomical structures, including pulmonary arteries, veins, bronchi, lobes, and segments. AI-generated 3D reconstructions will be compared with expert manual 3D reconstructions and with anatomical findings documented during surgery.
The primary objective is to assess the anatomical accuracy of AI-generated 3D reconstructions in identifying surgically relevant bronchovascular anatomy and anatomical variants. Secondary objectives include evaluating accuracy for individual anatomical structures, discrepancies between automated and manual reconstructions, concordance with intraoperative findings, and the time required to generate and review the automated reconstruction.
The study is observational and will not modify the planned surgical procedure or standard patient care.
調査の概要
詳細な説明
Patients scheduled for anatomical lung resection who meet the study eligibility criteria will be prospectively enrolled. Preoperative contrast-enhanced chest CT images acquired as part of routine clinical care will be used for 3D reconstruction.
For each patient, an AI-based segmentation system will generate a 3D reconstruction of the relevant pulmonary anatomy, including pulmonary arterial, venous and bronchial structures, as well as lobar and segmental anatomy when applicable. The automated reconstruction will be reviewed without modifying the planned surgical treatment.
AI-generated reconstructions will be compared with expert manual 3D reconstructions and with anatomical findings documented intraoperatively. Particular attention will be given to the identification of surgically relevant bronchovascular branches and anatomical variants.
The primary analysis will assess the proportion of patients in whom the AI-generated reconstruction accurately represents all predefined surgically relevant anatomical structures for the planned resection, without clinically relevant omissions or incorrect structures.
Secondary analyses will assess performance at the individual anatomical-structure level, including arterial, venous and bronchial structures; characterize errors and discrepancies between automated and manual reconstruction; evaluate concordance with intraoperative anatomy; and assess the time required for automated reconstruction and expert review.
The study is a prospective, single-center observational validation study. All diagnostic and therapeutic decisions, including the indication and type of lung resection, will be made according to standard clinical practice independently of study participation.
研究の種類
入学 (推定)
連絡先と場所
研究場所
-
-
Lazio
-
Rome、Lazio、イタリア、00189
- Azienda Ospedaliera Universitaria Sant'Andrea
-
コンタクト：
- Giacomo Argento, MD
- 電話番号：+390633775773
- メール：giargento@ospedalesantandrea.it
-
-
参加基準
適格基準
就学可能な年齢
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
Adult patients undergoing anatomical lung resection at the Thoracic Surgery Unit of Sant'Andrea University Hospital who have a preoperative contrast-enhanced chest CT scan suitable for AI-based 3D reconstruction.
説明
Inclusion Criteria:
- Age ≥18 years
- Scheduled for anatomical lung resection (segmentectomy, lobectomy, bilobectomy, or pneumonectomy)
- Availability of a preoperative contrast-enhanced chest CT scan suitable for 3D reconstruction, with slice thickness ≤1.5 mm.
- Ability to provide informed consent.
Exclusion Criteria:
- Preoperative CT images of insufficient quality or technical characteristics for 3D reconstruction.
- Cancellation of the planned surgical procedure before surgery.
- Inability or unwillingness to provide informed consent.
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：PROSPECTIVE
コホートと介入
グループ/コホート |
介入・治療 |
|---|---|
|
Prospective Validation Cohort
Patients undergoing lung resection who are prospectively enrolled for validation of the AI-based 3D reconstruction system. Preoperative CT images will be processed by the AI system, and the resulting 3D reconstructions will be compared with expert manual reconstruction and intraoperative anatomical findings. |
Preoperative contrast-enhanced chest CT images will be processed using an artificial intelligence-based segmentation system to automatically generate three-dimensional reconstructions of pulmonary anatomy, including pulmonary arteries, veins, bronchi, lobes, and segments when applicable. The AI-generated reconstructions will be evaluated against expert manual 3D reconstruction and intraoperative anatomical findings. The AI output will not determine or modify the planned surgical treatment. |
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 |
|---|---|---|
|
Patient-Level Anatomical Accuracy of AI-Generated 3D Reconstruction
時間枠：From preoperative CT imaging through completion of the surgical procedure
|
Proportion of patients in whom the AI-generated 3D reconstruction correctly represents all predefined surgically relevant pulmonary arterial, venous, and bronchial structures and anatomical variants for the planned lung resection, without clinically relevant omissions or incorrectly represented structures. Accuracy will be assessed by comparison with expert manual 3D reconstruction and intraoperative anatomical findings. |
From preoperative CT imaging through completion of the surgical procedure
|
協力者と研究者
スポンサー
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
キーワード
その他の研究ID番号
- SANTANDREA-3D-LUNG-01
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。