Neoplasms

All Conditions

Respiratory Tract (Lung and Bronchial) Diseases

Rare Diseases

Adenocarcinoma

Adenocarcinoma of Lung

Carcinoma

Neoplasms, Glandular and Epithelial

Neoplasms by Histologic Type

Lung Neoplasms

Respiratory Tract Neoplasms

Thoracic Neoplasms

Lung Adenocarcinoma

Deep Learning Signature Based on Whole Slide Image for Predicting the Novel Grading System In Resected Lung Adenocarcinoma

Whole Slide Image based Deep Learning Signature

Yongxiang Song, Dr

Bentong Yu, Dr

Minglei Yang, Dr

The purpose of this study is to evaluate the performance of a whole slide image based deep learning signature for predicting the novel grading system in resected lung adenocarcinoma based on a multicenter prospective cohort.

Whole Slide Image for Predicting the Novel Grading System of Resected Lung Adenocarcinoma

Deep Learning Signature Based on Whole Slide Images for Predicting the Novel Grading System of Resected Lung Adenocarcinoma

The specificity of the deep learning model based on whole slide imge in predicting the novel grading system of resected lung adenocarcinoma. The novel grading system of lung adenocarcinoma includes grade I, grade II, and grade III. And the model will output the predictive values (grade I/grade II/grade III) of the grade for each patient with resected lung adenocarcinoma.

The positive predictive value of the deep learning model based on whole slide imge in predicting the novel grading system of resected lung adenocarcinoma. The novel grading system of lung adenocarcinoma includes grade I, grade II, and grade III. And the model will output the predictive values (grade I/grade II/grade III) of the grade for each patient with resected lung adenocarcinoma.

The negative predictive value of the deep learning model based on whole slide imge in predicting the novel grading system of resected lung adenocarcinoma. The novel grading system of lung adenocarcinoma includes grade I, grade II, and grade III. And the model will output the predictive values (grade I/grade II/grade III) of the grade for each patient with resected lung adenocarcinoma.

The accuracy of the deep learning model based on whole slide imge in predicting the novel grading system of resected lung adenocarcinoma. The novel grading system of lung adenocarcinoma includes grade I, grade II, and grade III. And the model will output the predictive values (grade I/grade II/grade III) of the grade for each patient with resected lung adenocarcinoma.

The area under the receiver operating characteristic curve of the deep learning model based on whole slide imge in predicting the novel grading system of resected lung adenocarcinoma. The novel grading system of lung adenocarcinoma includes grade I, grade II, and grade III. And the model will output the predictive values (grade I/grade II/grade III) of the grade for each patient with resected lung adenocarcinoma.

The sensitivity of the deep learning model based on whole slide imge in predicting the novel grading system of resected lung adenocarcinoma. The novel grading system of lung adenocarcinoma includes grade I, grade II, and grade III. And the model will output the predictive values (grade I/grade II/grade III) of the grade for each patient with resected lung adenocarcinoma.

Ningbo No.2 Hospital

Zunyi Medical College

The First Affiliated Hospital of Nanchang University

Shanghai Pulmonary Hospital, Shanghai, China

Professor

Urinary Tract, Sexual Organs, and Pregnancy Conditions

Symptoms and General Pathology

Prostatic Neoplasms

Neoplasm Metastasis

Lymphatic Metastasis

Genital Neoplasms, Male

Urogenital Neoplasms

Genital Diseases

Genital Diseases, Male

Urogenital Diseases

Prostatic Diseases

Male Urogenital Diseases

Neoplastic Processes

Patients (will) undergo radical prostatectomy and pelvic lymph node dissection

Collect pathological slides of resected lymph nodes of the enrolled patients. Digitise these slides into whole-slide images (WSIs). Analyze the WSIs using the AI model to generate diagnostic results (with or without lymphatic metastasis). No intervention to patients would be performed in this diagnostic test study.

Artificial intelligence (AI)-based diagnostic model (developed)

Tianxin Lin, Ph.D

Shaoxu Wu, MD

Cuimei Yao

The goal of this diagnostic test is to prospectively test the performance of pre-developed artificial intelligence (AI) diagnostic model for detecting pathological lymph node metastasis (LNM) of prostate cancer. Investigators had developed this AI model based on deep learning algorithms in preliminary research, and it performed well in retrospective tests.

Investigators will compare the diagnostic performance (sensitivity, specificity, etc.) of the AI model and routine pathological report issued by pathologists, to see if the AI model can improve the clinical workflow of pathological evaluation of LNM in prostate cancer in the real world.

Lymph node metastasis (LNM) is a common mode of metastasis in prostate cancer, and accurate postoperative pathological lymph node staging is of great significance for further treatment and prognosis assessment. However, the current pathological evaluation of lymph nodes relies on manual examination by pathologists, which has a relatively low diagnostic efficiency and is prone to missed-diagnosis for micro metastatic lesions. Therefore, investigators developed an AI diagnostic model for detecting pathological lymph node metastasis of prostate cancer based on deep learning algorithms in preliminary research, and it performed well in retrospective tests.

This study is a diagnostic test with no intervention measures, planning to collect pathological slides of formalin-fixed, paraffin-embedded lymph nodes resected from the enrolled patients and digitise them into whole-slide images (WSIs). The AI model will analyse the WSIs and generate pixel-level heatmaps and slide-level diagnostic results (with or without LNM). The routine pathological examination will be performed as usual. These two processes will not interfere with each other. And if there are inconsistency in slide-level classification between AI and routine pathological examination, investigators would convene senior pathologists for discussion to make the final decision (immunohistochemistry would be performed if necessary). The final result will be presented to the patient in the form of a pathological report.

Histopathological slides of formalin-fixed, paraffin-embedded lymph nodes resected from patients with prostate cancer undergoing radical prostatectomy and pelvic lymph node dissection.

Prospective Validation of Pathology-based Artificial Intelligence Diagnostic Model for Lymph Node Metastasis in Prostate Cancer

To protect patient privacy, pathological slide images and other patient-related data are not publicly accessible.

the number of correctly diagnosed positive slides (with lymphatic metastasis), to be divided by the number of positive slides in total

the number of correctly diagnosed negative slides (without lymphatic metastasis), to be divided by the number of negative slides in total

Study title	NCT ID	Conditions	Interventions	Eligibility	Organization
Whole Slide Image for Predicting the Novel Grading System of Resected Lung Adenocarcinoma	NCT05925764	Lung Adenocarci... Whole Slide Ima... Novel Grading S...	Whole Slide Ima...	20 Years - 75 Years	Shanghai Pulmonary Hospital, Shanghai, China
Whole Slide Image for Predicting the Novel Grading System of Resected Lung Adenocarcinoma	NCT05925764	Lung Adenocarci... Whole Slide Ima... Novel Grading S...	Whole Slide Ima...	20 Years - 75 Years	Shanghai Pulmonary Hospital, Shanghai, China
Whole Slide Image for Predicting the Novel Grading System of Resected Lung Adenocarcinoma	NCT05925764	Lung Adenocarci... Whole Slide Ima... Novel Grading S...	Whole Slide Ima...	20 Years - 75 Years	Shanghai Pulmonary Hospital, Shanghai, China
Prospective Validation of Pathology-based Artificial Intelligence Diagnostic Model for Lymph Node Metastasis in Prostate Cancer	NCT06253065	Prostatic Neopl... Lymphatic Metas...	Artificial inte...	-	Sun Yat-Sen Memorial Hospital of Sun Yat-Sen University

Spots Global Cancer Trial Database for whole slide image