PMID- 38108979 OWN - NLM STAT- MEDLINE DCOM- 20240221 LR - 20240221 IS - 1826-6983 (Electronic) IS - 0033-8362 (Linking) VI - 129 IP - 2 DP - 2024 Feb TI - LNAS: a clinically applicable deep-learning system for mediastinal enlarged lymph nodes segmentation and station mapping without regard to the pathogenesis using unenhanced CT images. PG - 229-238 LID - 10.1007/s11547-023-01747-x [doi] AB - BACKGROUND: The accurate identification and evaluation of lymph nodes by CT images is of great significance for disease diagnosis, treatment, and prognosis. PURPOSE: To assess the lymph nodes' segmentation, size, and station by artificial intelligence (AI) for unenhanced chest CT images and evaluate its value in clinical scenarios. MATERIAL AND METHODS: This retrospective study proposed an end-to-end Lymph Nodes Analysis System (LNAS) consisting of three models: the Lymph Node Segmentation model (LNS), the Mediastinal Organ Segmentation model (MOS), and the Lymph Node Station Registration model (LNR). We selected a healthy chest CT image as the template image and annotated 14 lymph node station masks according to the IASLC to build the lymph node station mapping template. The exact contours and stations of the lymph nodes were annotated by two junior radiologists and reviewed by a senior radiologist. Patients aged 18 and above, who had undergone unenhanced chest CT and had at least one suspicious enlarged mediastinal lymph node in imaging reports, were included. Exclusions were patients who had thoracic surgeries in the past 2 weeks or artifacts on CT images affecting lymph node observation by radiologists. The system was trained on 6725 consecutive chest CTs that from Tianjin Medical University General Hospital, among which 6249 patients had suspicious enlarged mediastinal lymph nodes. A total of 519 consecutive chest CTs from Qilu Hospital of Shandong University (Qingdao) were used for external validation. The gold standard for each CT was determined by two radiologists and reviewed by one senior radiologist. RESULTS: The patient-level sensitivity of the LNAS system reached of 93.94% and 92.89% in internal and external test dataset, respectively. And the lesion-level sensitivity (recall) reached 89.48% and 85.97% in internal and external test dataset. For man-machine comparison, AI significantly apparently shortened the average reading time (p < 0.001) and had better lesion-level and patient-level sensitivities. CONCLUSION: AI improved the sensitivity lymph node segmentation by radiologists with an advantage in reading time. CI - (c) 2023. Italian Society of Medical Radiology. FAU - Cao, Yang AU - Cao Y AD - Department of Radiology, Tianjin Medical University General Hospital, Tianjin, 300052, China. FAU - Feng, Jintang AU - Feng J AD - Department of Radiology, Tianjin Medical University General Hospital, Tianjin, 300052, China. AD - Department of Radiology, Tianjin Chest Hospital, Tianjin, China. FAU - Wang, Cheng AU - Wang C AD - Deepwise AI Lab, Beijing, China. FAU - Yang, Fan AU - Yang F AD - Department of Radiology, Tianjin Medical University General Hospital, Tianjin, 300052, China. FAU - Wang, Xiaomeng AU - Wang X AD - Department of Radiology, Tianjin Medical University General Hospital, Tianjin, 300052, China. FAU - Xu, Jingxu AU - Xu J AD - Deepwise AI Lab, Beijing, China. FAU - Huang, Chencui AU - Huang C AD - Deepwise AI Lab, Beijing, China. FAU - Zhang, Shu AU - Zhang S AD - Deepwise AI Lab, Beijing, China. FAU - Li, Zihao AU - Li Z AD - Deepwise AI Lab, Beijing, China. FAU - Mao, Li AU - Mao L AD - Deepwise AI Lab, Beijing, China. FAU - Zhang, Tianzhu AU - Zhang T AD - Department of Radiology, Tianjin Medical University General Hospital, Tianjin, 300052, China. FAU - Jia, Bingzhen AU - Jia B AD - Department of Radiology, Tianjin Medical University General Hospital, Tianjin, 300052, China. FAU - Li, Tongli AU - Li T AD - Department of Radiology, Tianjin Medical University General Hospital, Tianjin, 300052, China. FAU - Li, Hui AU - Li H AD - Department of Radiology, Qilu Hospital (Qingdao), Cheeloo College of Medicine, Shandong University, Jinan, Shandong, China. FAU - Zhang, Bingjin AU - Zhang B AD - Department of Radiology, Qilu Hospital (Qingdao), Cheeloo College of Medicine, Shandong University, Jinan, Shandong, China. FAU - Shi, Hongmei AU - Shi H AD - Department of Radiology, Qilu Hospital (Qingdao), Cheeloo College of Medicine, Shandong University, Jinan, Shandong, China. FAU - Li, Dong AU - Li D AD - Department of Radiology, Tianjin Medical University General Hospital, Tianjin, 300052, China. FAU - Zhang, Ningnannan AU - Zhang N AD - Department of Radiology, Tianjin Medical University General Hospital, Tianjin, 300052, China. FAU - Yu, Yizhou AU - Yu Y AD - Deepwise AI Lab, Beijing, China. AD - Department of Computer Science, The University of Hong Kong, Hong Kong, China. FAU - Meng, Xiangshui AU - Meng X AD - Department of Radiology, Qilu Hospital (Qingdao), Cheeloo College of Medicine, Shandong University, Jinan, Shandong, China. FAU - Zhang, Zhang AU - Zhang Z AD - Department of Radiology, Tianjin Medical University General Hospital, Tianjin, 300052, China. filea1249@sina.com. LA - eng GR - 82071907/National Natural Science Foundation of China/ GR - 82271937/National Natural Science Foundation of China/ GR - 82302139/National Natural Science Foundation of China/ GR - 18JCYBJC25100/Natural Science Foundation of Tianjin Municipal Science and Technology Commission/ GR - MS20022/Tianjin Municipal Transportation Commission Science and Technology Development Plan Project/ GR - 320.6750.2022-3-5/Wu Jieping Medical Foundation-special Fund for Clinical Research/ GR - Z-2014-07-2003-05/China International Medical Foundation Sky Imaging Research Fund/ GR - TJYXZDXK-001A/Tianjin Key Medical Discipline (Specialty) Construction Project/ GR - 20140115/Tianjin University of Science and Technology Development Projects Fund/ GR - 1921131H/Zhangjiakou City Self-financing Project of the 2019 Scientific Research Plan/ GR - 22JCZDJC00500/Natural Science Foundation of Tianjin/ PT - Journal Article DEP - 20231218 PL - Italy TA - Radiol Med JT - La Radiologia medica JID - 0177625 SB - IM MH - Humans MH - Retrospective Studies MH - *Artificial Intelligence MH - *Deep Learning MH - Lymph Nodes/diagnostic imaging/pathology MH - Tomography, X-Ray Computed/methods OTO - NOTNLM OT - AI OT - Lymph node OT - Segmentation OT - Station mapping OT - Unenhanced CT EDAT- 2023/12/18 12:42 MHDA- 2024/02/21 11:15 CRDT- 2023/12/18 11:10 PHST- 2023/05/10 00:00 [received] PHST- 2023/10/20 00:00 [accepted] PHST- 2024/02/21 11:15 [medline] PHST- 2023/12/18 12:42 [pubmed] PHST- 2023/12/18 11:10 [entrez] AID - 10.1007/s11547-023-01747-x [pii] AID - 10.1007/s11547-023-01747-x [doi] PST - ppublish SO - Radiol Med. 2024 Feb;129(2):229-238. doi: 10.1007/s11547-023-01747-x. Epub 2023 Dec 18.