Xinling Li1, Fangfang Guo2, Zhen Zhou3, Fandong Zhang3, Qin Wang1, Zhijun Peng1, Datong Su1, Yaguang Fan4, Ying Wang1. 1. Department of Radiology, Tianjin Medical University General Hospital, Tianjin 300052, China. 2. Department of Radiology, the First Affiliated Hospital of XinXiang Medical College, Xinxiang 453100, China. 3. Deepwise Healthcare, Beijing 100080, China. 4. Tianjin Key Laboratory of Lung Cancer Metastasis and Tumor Microenvironment, Tianjin Lung Cancer Institute, Tianjin Medical University General Hospital, Tianjin 300052, China.
Abstract
BACKGROUND: The detection of pulmonary nodules is a key step to achieving the early diagnosis and therapy of lung cancer. Deep learning based Artificial intelligence (AI) presents as the state of the art in the area of nodule detection, however, a validation with clinical data is necessary for further application. Therefore, the aim of this study is to evaluate the performance of AI in the detection of malignant and non-calcified nodules in chest CT. METHODS: Two hundred chest computed tomography (CT) data were randomly selected from a self-built nodule database from Tianjin Medical University General Hospital. Both the pathology confirmed lung cancers and the nodules in the process of follow-up were included. All CTs were processed by AI and the results were compared with that of radiologists retrieved from the original medical reports. The ground truths were further determined by two experienced radiologists. The size and characteristics of the nodules were evaluated as well. The sensitivity and false positive rate were used to evaluate the effectiveness of AI and radiologists in detecting nodules. The McNemar test was used to determine whether there was a significant difference. RESULTS: A total of 889 non-calcified nodules were determined by experts on chest CT, including 133 lung cancers. Of them, 442 nodules were less than 5 mm. The cancer detection rates of AI and radiologists are 100%. The sensitivity of AI on nodule detection was significantly higher than that of radiologists (99.1% vs 43%, P<0.001). The false-positive rate of AI was 4.9 per CT and decreased to 1.5 when nodules less than 5 mm were excluded. CONCLUSIONS: AI achieves the detection of all malignancies and improve the sensitivity of pulmonary nodules detection beyond radiologists, with a low false positive rate after excluding small nodules.
BACKGROUND: The detection of pulmonary nodules is a key step to achieving the early diagnosis and therapy of lung cancer. Deep learning based Artificial intelligence (AI) presents as the state of the art in the area of nodule detection, however, a validation with clinical data is necessary for further application. Therefore, the aim of this study is to evaluate the performance of AI in the detection of malignant and non-calcified nodules in chest CT. METHODS: Two hundred chest computed tomography (CT) data were randomly selected from a self-built nodule database from Tianjin Medical University General Hospital. Both the pathology confirmed lung cancers and the nodules in the process of follow-up were included. All CTs were processed by AI and the results were compared with that of radiologists retrieved from the original medical reports. The ground truths were further determined by two experienced radiologists. The size and characteristics of the nodules were evaluated as well. The sensitivity and false positive rate were used to evaluate the effectiveness of AI and radiologists in detecting nodules. The McNemar test was used to determine whether there was a significant difference. RESULTS: A total of 889 non-calcified nodules were determined by experts on chest CT, including 133 lung cancers. Of them, 442 nodules were less than 5 mm. The cancer detection rates of AI and radiologists are 100%. The sensitivity of AI on nodule detection was significantly higher than that of radiologists (99.1% vs 43%, P<0.001). The false-positive rate of AI was 4.9 per CT and decreased to 1.5 when nodules less than 5 mm were excluded. CONCLUSIONS: AI achieves the detection of all malignancies and improve the sensitivity of pulmonary nodules detection beyond radiologists, with a low false positive rate after excluding small nodules.
Entities:
Keywords:
Artificial intelligence; Computed tomography; Deep learning; Detection; Lung nodules
A part-solid nodule located in right lower lobe, connected to the bronchioles, 10.7 mm in diameter, 43.3 mm far from the pleura, missed by radiologist, but detected by AI.
右肺下叶部分实性结节,与细支气管相连,直径10.7 mm,距胸膜43.3 mm,影像医师漏诊,AI实现检测。A part-solid nodule located in right lower lobe, connected to the bronchioles, 10.7 mm in diameter, 43.3 mm far from the pleura, missed by radiologist, but detected by AI.
Centrilobular nodules with a garland shape located in right upper lobe, false positive case by AI.
3
右肺下叶增厚、扩张的细支气管,AI假阳性。
Thickened, dilated bronchioles located in right lower lobe, false positive case by AI.
右肺上叶花环状小叶核心结构,AI假阳性。Centrilobular nodules with a garland shape located in right upper lobe, false positive case by AI.右肺下叶增厚、扩张的细支气管,AI假阳性。Thickened, dilated bronchioles located in right lower lobe, false positive case by AI.
Authors: Arnaud Arindra Adiyoso Setio; Alberto Traverso; Thomas de Bel; Moira S N Berens; Cas van den Bogaard; Piergiorgio Cerello; Hao Chen; Qi Dou; Maria Evelina Fantacci; Bram Geurts; Robbert van der Gugten; Pheng Ann Heng; Bart Jansen; Michael M J de Kaste; Valentin Kotov; Jack Yu-Hung Lin; Jeroen T M C Manders; Alexander Sóñora-Mengana; Juan Carlos García-Naranjo; Evgenia Papavasileiou; Mathias Prokop; Marco Saletta; Cornelia M Schaefer-Prokop; Ernst T Scholten; Luuk Scholten; Miranda M Snoeren; Ernesto Lopez Torres; Jef Vandemeulebroucke; Nicole Walasek; Guido C A Zuidhof; Bram van Ginneken; Colin Jacobs Journal: Med Image Anal Date: 2017-07-13 Impact factor: 8.545
Authors: Arnaud Arindra Adiyoso Setio; Francesco Ciompi; Geert Litjens; Paul Gerke; Colin Jacobs; Sarah J van Riel; Mathilde Marie Winkler Wille; Matiullah Naqibullah; Clara I Sanchez; Bram van Ginneken Journal: IEEE Trans Med Imaging Date: 2016-03-01 Impact factor: 10.048
Authors: Lindsey A Torre; Freddie Bray; Rebecca L Siegel; Jacques Ferlay; Joannie Lortet-Tieulent; Ahmedin Jemal Journal: CA Cancer J Clin Date: 2015-02-04 Impact factor: 508.702
Authors: Hyun Ju Lee; Jin Mo Goo; Chang Hyun Lee; Chul-Gyu Yoo; Young Tae Kim; Jung-Gi Im Journal: Korean J Radiol Date: 2007 Jan-Feb Impact factor: 3.500