机构：[1]Department of Pathology, Beijing Tongren Hospital, Capital Medical University, Beijing, China.医技科室病理科首都医科大学附属北京同仁医院首都医科大学附属同仁医院[2]Beijing Key Laboratory of Head and Neck Molecular Pathological Diagnosis, Beijing Tongren Hospital, Capital Medical University, Beijing, China.首都医科大学附属北京同仁医院首都医科大学附属同仁医院[3]Department of Otolaryngology Head and Neck Surgery, Beijing Tongren Hospital, Capital Medical University, Beijing, China.临床科室耳鼻咽喉-头颈外科首都医科大学附属北京同仁医院首都医科大学附属同仁医院[4]Department of Center for Translational Medicine, Keymed Biosciences Inc, Chengdu, Sichuan, China.
This study aimed to establish a convenient and accurate chronic rhinosinusitis evaluation platform CRSAI 1.0 according to four phenotypes of nasal polyps.Tissue sections of a training (n = 54) and test cohort (n = 13) were sourced from the Tongren Hospital, and those for a validation cohort (n = 55) from external hospitals. Redundant tissues were automatically removed by the semantic segmentation algorithm of Unet++ with Efficientnet-B4 as backbone. After independent analysis by two pathologists, four types of inflammatory cells were detected and used to train the CRSAI 1.0. Dataset from Tongren Hospital were used for training and testing, and validation tests used the multicentre dataset.The mean average precision (mAP) in the training and test cohorts for tissue eosinophil%, neutrophil%, lymphocyte%, and plasma cell% was 0.924, 0.743, 0.854, 0.911 and 0.94, 0.74, 0.839, and 0.881, respectively. The mAP in the validation dataset was consistent with that of the test cohort. The four phenotypes of nasal polyps varied significantly according to the occurrence of asthma or recurrence.CRSAI 1.0 can accurately identify various types of inflammatory cells in CRSwNP from multicentre data, which could enable rapid diagnosis and personalized treatment.
基金：
national key R&D program of
China (2022YFC2504100), the program for the Changjiang scholars and
innovative research team (IRT13082), CAMS innovation fund for medical
sciences (2019-I2M-5-022) and the Capital’s Funds for Health Improvement
and Research (2022-2-2054)
第一作者机构：[1]Department of Pathology, Beijing Tongren Hospital, Capital Medical University, Beijing, China.[2]Beijing Key Laboratory of Head and Neck Molecular Pathological Diagnosis, Beijing Tongren Hospital, Capital Medical University, Beijing, China.
共同第一作者：
通讯作者：
通讯机构：[1]Department of Pathology, Beijing Tongren Hospital, Capital Medical University, Beijing, China.[2]Beijing Key Laboratory of Head and Neck Molecular Pathological Diagnosis, Beijing Tongren Hospital, Capital Medical University, Beijing, China.[3]Department of Otolaryngology Head and Neck Surgery, Beijing Tongren Hospital, Capital Medical University, Beijing, China.[*1]Department of Pathology, Beijing Tongren Hospital, Capital Medical University, No. 1, Dong Jiao Min Xiang, Beijing, Dongcheng 100005, China[*2]Department of Otolaryngology Head and Neck Surgery, Beijing Tongren Hospital, Capital Medical University, No. 1, Dong Jiao Min Xiang, Beijing, Dongcheng 100005, China
推荐引用方式(GB/T 7714)：
Ding Jing,Yue Changli,Wang Chengshuo,et al.Machine learning method for the cellular phenotyping of nasal polyps from multicentre tissue scans[J].EXPERT REVIEW OF CLINICAL IMMUNOLOGY.2023,19(8):1023-1028.doi:10.1080/1744666X.2023.2207824.
APA：
Ding Jing,Yue Changli,Wang Chengshuo,Liu Wei,Zhang Libo...&Zhang Luo.(2023).Machine learning method for the cellular phenotyping of nasal polyps from multicentre tissue scans.EXPERT REVIEW OF CLINICAL IMMUNOLOGY,19,(8)
MLA：
Ding Jing,et al."Machine learning method for the cellular phenotyping of nasal polyps from multicentre tissue scans".EXPERT REVIEW OF CLINICAL IMMUNOLOGY 19..8(2023):1023-1028
：