Label-free Femtosecond Laser Imaging Combined With the Fast Lung Artificial Intelligence Model for Rapid Intraoperative Diagnosis of Lung Surgical Specimens: A Multicentre, Prospective, Parallel-workflow, Non-inferiority Study.

This study aims to evaluate whether femtosecond laser imaging combined with FastLung AI model can provide intraoperative diagnostic performance that is non-inferior to standard frozen section diagnosis for pulmonary nodules or suspected pulmonary tumor lesions. Patients scheduled for lung surgery and requiring intraoperative pathological assessment will be prospectively enrolled. After tumor excision, the fresh tumor specimen will be bisected through the central plane. One half will be used for standard frozen section diagnosis, and the mirrored counterpart will be used for femtosecond laser imaging. Both diagnostic results will be compared with the final paraffin-embedded pathological diagnosis as the reference standard. The results of femtosecond laser imaging will not guide intraoperative clinical decision-making.

Study Overview

• Status: Not yet recruiting
• Conditions: Lung Cancer
• Intervention / Treatment: Diagnostic test: Femtosecond Laser Imaging; Diagnostic test: Frozen Section Diagnosis

Detailed Description

This is a prospective, multicenter, paired diagnostic accuracy study designed to evaluate the non-inferiority of femtosecond laser imaging compared with standard frozen section diagnosis for intraoperative assessment of pulmonary nodules or suspected pulmonary tumor lesions.

Eligible patients with pulmonary nodules, pulmonary space-occupying lesions, or suspected pulmonary tumor lesions who are scheduled to undergo surgical resection and require intraoperative pathological assessment will be prospectively enrolled from participating centers. After surgical excision of the tumor specimen, the fresh specimen will be bisected through the central plane. One half of the specimen will be submitted for routine frozen section diagnosis, while the mirrored counterpart will be used for femtosecond laser imaging. This paired design is intended to allow spatially corresponding comparison between the two diagnostic methods while preserving routine clinical workflow.

Frozen section diagnosis will be performed according to standard intraoperative pathological procedures and will continue to guide intraoperative clinical decision-making. Femtosecond laser imaging will be performed on fresh tissue specimens for research purposes. The imaging results will be recorded for diagnostic performance evaluation but will not be used to guide intraoperative surgical decisions.

The diagnostic results of femtosecond laser imaging and frozen section diagnosis will both be compared with the final paraffin-embedded pathological diagnosis, which will serve as the reference standard. The primary objective is to determine whether the diagnostic accuracy of femtosecond laser imaging is non-inferior to that of frozen section diagnosis. Secondary objectives may include comparisons of sensitivity, specificity, positive predictive value, negative predictive value, diagnostic concordance, and intraoperative assessment time between the two methods.

• Study Type: Observational
• Enrollment (Estimated): 294

Contacts and Locations

• Study Contact: Name: Xinghua Cheng, Dr. PhD.; Phone Number: 17701681215; Email: xinhuacheng@sjtu.edu.cn

Study Locations

• China
  • Shanghai Municipality
    • Shanghai, Shanghai Municipality, China, 200030
      • Shanghai Chest Hospital
      • Contact: Yin Li, Dr.; Phone Number: 8618758824569; Email: liy1398901568@163.com
    • Shanghai, Shanghai Municipality, China, 200030
      • Dongfang Hospital
      • Contact: Weigang Zhao, Dr.; Phone Number: 8618930170427; Email: zhaowg@163.com
    • Shanghai, Shanghai Municipality, China, 200030
      • Huadong Hospital
      • Contact: Huibiao Zhang, Dr.; Phone Number: 8613916804033; Email: huibiao_zhang@163.com
    • Shanghai, Shanghai Municipality, China, 200030
      • Tongji Hospital
      • Contact: wenli Wang, Dr.; Phone Number: 8613761295864; Email: anderson840913@163.com
    • Shanghai, Shanghai Municipality, China, 200030
      • Tongren Hospital
      • Contact: ning Wang, Dr.; Phone Number: 8618017337120; Email: WN3565@shtrhospital.com

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: No

• Sampling Method: Non-Probability Sample

Study Population

The study population will consist of patients with pulmonary nodules, pulmonary space-occupying lesions, or suspected pulmonary tumor lesions who are scheduled to undergo surgical resection at participating centers. Eligible patients will require intraoperative pathological assessment, and fresh lung tissue specimens must be available for both femtosecond laser imaging and standard frozen section diagnosis. All participants will be prospectively enrolled according to the predefined inclusion and exclusion criteria, and the diagnostic results will be compared with the final paraffin-embedded pathological diagnosis as the reference standard.

Description

Inclusion Criteria:

1. Preoperative imaging suggests a pulmonary nodule, pulmonary space-occupying lesion, or suspected pulmonary tumor lesion.
2. The participant is scheduled to undergo pulmonary wedge resection, segmentectomy, lobectomy, or other pulmonary surgery.
3. Fresh lung tissue specimens can be obtained intraoperatively for femtosecond laser imaging.
4. Intraoperative frozen section diagnosis is planned to assess the nature of the tumor lesion.
5. Corresponding postoperative paraffin-embedded pathological diagnosis can be obtained.
6. The participant or the participant's legally authorized representative has signed the written informed consent form.

Exclusion Criteria:

1. The intraoperative specimen is insufficient and cannot simultaneously meet the requirements for routine clinical pathological diagnosis and research-related testing.
2. The specimen shows severe carbonization, necrosis, compression, contamination, or improper preservation, and the investigator determines that effective imaging cannot be completed.
3. The femtosecond laser imaging specimen cannot be matched with the corresponding lesion assessed by final paraffin pathology.
4. Final paraffin-embedded pathological diagnosis cannot be obtained.
5. The participant withdraws informed consent.
6. Other conditions that, in the opinion of the investigator, make the participant unsuitable for this study.

Study Plan

How is the study designed?

Number of groups / cohorts

1

Cohorts and Interventions

Group / Cohort

Intervention / Treatment

Patients undergoing intraoperative pulmonary nodule diagnosis; Patients with pulmonary nodules who are scheduled for surgical resection and require intraoperative pathological assessment. All participants will undergo femtosecond laser imaging and standard frozen section diagnosis in parallel, and both results will be compared with final paraffin pathology as the reference standard.

Diagnostic test: Femtosecond Laser Imaging; Fresh surgical specimens will be examined intraoperatively using femtosecond laser imaging. The imaging results will be recorded for diagnostic performance evaluation and compared with final paraffin pathology. The results will not guide intraoperative clinical decision-making.; Diagnostic test: Frozen Section Diagnosis; Fresh tumor specimens will be evaluated intraoperatively by standard frozen section pathology. After the tumor is bisected through the central plane, one half of the specimen will be submitted for frozen section diagnosis, while the mirrored counterpart will be used for femtosecond laser imaging. Frozen section diagnosis will be used for routine intraoperative clinical decision-making and will also be compared with final paraffin pathology.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Non-inferiority performance threshold	To determine whether FLI combined with Fast Lung achieves the prespecified non-inferiority performance threshold for benign-malignant diagnosis of the patient-level primary target lesion, using final FFPE histopathology as the reference standard.	From intraoperative diagnosis to final paraffin pathology confirmation, up to 30 days after surgery.

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Workflow turnaround time	To compare workflow turnaround time for FLI + Fast Lung and routine frozen-section pathology.	From intraoperative diagnosis to final paraffin pathology confirmation, up to 30 days after surgery.
Accuracy for invasive versus non-invasive/minimally invasive adenocarcinoma-spectrum lesions.	To evaluate the accuracy of Fast Lung for invasive versus non-invasive/minimally invasive adenocarcinoma-spectrum lesions.	From intraoperative diagnosis to final paraffin pathology confirmation, up to 30 days after surgery.
Sensitivity	To estimate the sensitivity of Fast Lung for malignant lesions using FFPE histopathology as the reference standard.	From intraoperative diagnosis to final paraffin pathology confirmation, up to 30 days after surgery.
Specificity	To estimate the specificity of Fast Lung for benign lesions using FFPE histopathology as the reference standard.	From intraoperative diagnosis to final paraffin pathology confirmation, up to 30 days after surgery.

Other Outcome Measures

Outcome Measure	Measure Description	Time Frame
Diagnostic accuracy (ROC-AUC)	The area under the receiver operating characteristic curve (ROC-AUC) will be used to assess the overall diagnostic accuracy of FLI-FastLung model in etermination of the benign or malignant of surgical specimens compared with final paraffin pathology as the reference standard.	From intraoperative diagnosis to final paraffin pathology confirmation, up to 30 days after surgery.
Performance of histological subtype diagnostic	The performance of the FLI-FastLung model in distinguishing LUAD from LUSC will be evaluated using final paraffin pathology as the reference standard. Diagnostic performance will be quantified by area under the ROC curve (ROC-AUC), overall accuracy, sensitivity, and specificity.	From intraoperative diagnosis to final paraffin pathology confirmation, up to 30 days after surgery.
Performance in biopsy or small-tissue specimens	The performance of the FLI-FastLung model in biopsy or small tissue specimens will be assessed using final paraffin pathology as the reference standard. Diagnostic performance will be quantified by area under the ROC curve (ROC-AUC), overall accuracy, sensitivity, and specificity.	From intraoperative diagnosis to final paraffin pathology confirmation, up to 30 days after surgery.
Diagnostic Failure Rate	Diagnostic failure rate refers to the proportion of cases in which the FLI-FastLung system is unable to generate a valid histological classification result. A diagnostic failure is defined as the absence of a final output due to inadequate image quality, insufficient tissue input, or system processing failure.	From intraoperative diagnosis to final paraffin pathology confirmation, up to 30 days after surgery.
False Positive Rate	False positive rate will be calculated as the proportion of cases incorrectly classified as positive by the FLI-FastLung model when compared with final paraffin pathology as the reference standard. The result will be derived from a confusion matrix and expressed as a percentage (%).	From intraoperative diagnosis to final paraffin pathology confirmation, up to 30 days after surgery.
False Negative Rate	False negative rate will be calculated as the proportion of cases incorrectly classified as negative by the FLI-FastLung model when compared with final paraffin pathology as the reference standard. The result will be derived from a confusion matrix and expressed as a percentage (%).	From intraoperative diagnosis to final paraffin pathology confirmation, up to 30 days after surgery.
Heatmap-pathology concordance	Concordance between FastLung-generated heatmaps and corresponding pathological tumor regions will be evaluated using spatial overlap metrics. The primary measurement will be the Dice similarity coefficient (DSC) between model-generated heatmap regions and manually annotated pathological tumor areas. Results will be expressed as a continuous score ranging from 0 to 1.	From intraoperative diagnosis to final paraffin pathology confirmation, up to 30 days after surgery.

Collaborators and Investigators

• Sponsor: Shanghai Chest Hospital
• Collaborators: Femtosecond Applications and Research (Guangzhou)

Publications and helpful links

General Publications

• Xu X, Chung JH, Jheon S, Sung SW, Lee CT, Lee JH, Choe G. The accuracy of frozen section diagnosis of pulmonary nodules: evaluation of inflation method during intraoperative pathology consultation with cryosection. J Thorac Oncol. 2010 Jan;5(1):39-44. doi: 10.1097/JTO.0b013e3181c09f9c.
• Hollon TC, Pandian B, Adapa AR, Urias E, Save AV, Khalsa SSS, Eichberg DG, D'Amico RS, Farooq ZU, Lewis S, Petridis PD, Marie T, Shah AH, Garton HJL, Maher CO, Heth JA, McKean EL, Sullivan SE, Hervey-Jumper SL, Patil PG, Thompson BG, Sagher O, McKhann GM 2nd, Komotar RJ, Ivan ME, Snuderl M, Otten ML, Johnson TD, Sisti MB, Bruce JN, Muraszko KM, Trautman J, Freudiger CW, Canoll P, Lee H, Camelo-Piragua S, Orringer DA. Near real-time intraoperative brain tumor diagnosis using stimulated Raman histology and deep neural networks. Nat Med. 2020 Jan;26(1):52-58. doi: 10.1038/s41591-019-0715-9. Epub 2020 Jan 6.
• Lan C, Peng Y, Bai M, Zuo H, Li Y, Wu H, Zhang T, Zhu X, He J, Guo D, Chen X, Zhao H, Gao H. Fast multimodal imaging combined with machine learning identifying taurine as a potential marker for breast cancer margin assessment. NPJ Digit Med. 2025 Dec 17;9(1):32. doi: 10.1038/s41746-025-02202-z.

Study record dates

Study Major Dates

• Study Start (Estimated): June 30, 2026
• Primary Completion (Estimated): August 30, 2026
• Study Completion (Estimated): September 30, 2026

Study Registration Dates

• First Submitted: June 22, 2026
• First Submitted That Met QC Criteria: June 26, 2026
• First Posted (Actual): July 2, 2026

Study Record Updates

• Last Update Posted (Actual): July 2, 2026
• Last Update Submitted That Met QC Criteria: June 26, 2026
• Last Verified: June 1, 2026

More Information

Terms related to this study

• Keywords: lung cancer; artificial intelligence; Intraoperative diagnosis
• Additional Relevant MeSH Terms: Neoplasms by Site; Neoplasms; Respiratory Tract Diseases; Lung Diseases; Respiratory Tract Neoplasms; Thoracic Neoplasms; Lung Neoplasms; Investigative Techniques; Clinical Laboratory Techniques; Diagnostic Techniques and Procedures; Diagnosis; Cytological Techniques; Histological Techniques; Histocytological Preparation Techniques; Cryoultramicrotomy; Microtomy; Frozen Sections
• Other Study ID Numbers: FastLung; 2025SZ1002 (Other Grant/Funding Number: Foundation of Shanghai Key Laboratory of Thoracic Tumor Biotherapy)

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO
• IPD Plan Description: Individual participant data will not be publicly shared due to patient privacy considerations and institutional data-sharing restrictions. De-identified aggregate results may be made available in publications or upon reasonable request, in accordance with applicable regulations and institutional policies.

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No