End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography

Ardila, Diego; Kiraly, Atilla P.; Bharadwaj, Sujeeth; Choi, Bokyung; Reicher, Joshua J.; Peng, Lily; Tse, Daniel; Etemadi, Mozziyar; Ye, Wenxing; Corrado, Greg S.; Naidich, David P.; Shetty, Shravya

doi:10.1038/s41591-019-0447-x

Cited by 1,397 publications

(994 citation statements)

References 41 publications

Supporting

Mentioning

879

Contrasting

Unclassified

Order By: Relevance

“…The deep learning-based COVID-19 diagnostic algorithm used in our study is effective compared to recent deep learning-based computer-aided diagnosis methods. On the task of predicting the risk of lung cancer [13], the deep learning model was trained on 42290 CT cases from 14851 patients and obtained 0.944 ROC AUC. On the task of critical findings from head CT [23], the deep learning model was trained on 310055 head CT scans and obtained ROC AUC of 0.920.…”

Section: Patient and Public Involvementmentioning

confidence: 99%

Deep Learning-based Detection for COVID-19 from Chest CT using Weak Label

Zheng

Deng

et al. 2020

Preprint

541

450

View full text Add to dashboard Cite

Accurate and rapid diagnosis of COVID-19 suspected cases plays a crucial role in timely quarantine and medical treatment. Developing a deep learning-based model for automatic COVID-19 detection on chest CT is helpful to counter the outbreak of SARS-CoV-2. A weakly-supervised deep learning-based software system was developed using 3D CT volumes to detect COVID-19. For each patient, the lung region was segmented using a pre-trained UNet; then the segmented 3D lung region was fed into a 3D deep neural network to predict the probability of COVID-19 infectious. 499 CT volumes collected from Dec. 13, 2019, to Jan. 23, 2020, were used for training and 131 CT volumes collected from Jan 24, 2020, to Feb 6, 2020, were used for testing. The deep learning algorithm obtained 0.959 ROC AUC and 0.976 PR AUC. There was an operating point with 0.907 sensitivity and 0.911 specificity in the ROC curve. When using a probability threshold of 0.5 to classify COVID-positive and COVID-negative, the algorithm obtained an accuracy of 0.901, a positive predictive value of 0.840 and a very high negative predictive value of 0.982. The algorithm took only 1.93 seconds to process a single patient's CT volume using a dedicated GPU. Our weaklysupervised deep learning model can accurately predict the COVID-19 infectious probability in chest CT volumes without the need for annotating the lesions for training. The easily-trained and highperformance deep learning algorithm provides a fast way to identify COVID-19 patients, which is beneficial to control the outbreak of SARS-CoV-2. The developed deep learning software is available at https://github.com/sydney0zq/covid-19-detection.

show abstract

Section: Patient and Public Involvementmentioning

confidence: 99%

Deep Learning-based Detection for COVID-19 from Chest CT using Weak Label

Zheng

Deng

et al. 2020

Preprint

541

450

View full text Add to dashboard Cite

show abstract

“…Powered by large labeled datasets [5] and modern GPUs, AI, especially deep learning technique [6], has achieved excellent performance in several computer vision tasks such as image classification [7] and object detection [8]. Recent research shows that AI algorithms can even achieve or exceed the performance of human experts in certain medical image diagnosis tasks [9][10][11][12][13]. The AI diagnosis algorithm also has the advantages of high efficiency, high repeatability and easy large-scale deployment.…”

Section: Introductionmentioning

confidence: 99%

Development and Evaluation of an AI System for COVID-19 Diagnosis

Cheng

Chen

Cao

et al. 2020

Preprint

152

125

View full text Add to dashboard Cite

Early detection of COVID-19 based on chest CT will enable timely treatment of patients and help control the spread of the disease. With rapid spreading of COVID-19 in many countries, however, CT volumes of suspicious patients are increasing at a speed much faster than the availability of human experts. Here, we propose an artificial intelligence (AI) system for fast COVID-19 diagnosis with an accuracy comparable to experienced radiologists. A large dataset was constructed by collecting 970 CT volumes of 496 patients with confirmed COVID-19 and 260 negative cases from three hospitals in Wuhan, China, and 1,125 negative cases from two publicly available chest CT datasets. Trained using only 312 cases, our diagnosis system, which is based on deep convolutional neural network, is able to achieve an accuracy of 94.98%, an area under the receiver operating characteristic curve (AUC) of 97.91%, a sensitivity of 94.06%, and a specificity of 95.47% on an independent external verification dataset of 1,255 cases. In a reader study involving five radiologists, only one radiologist is slightly more accurate than the AI system. The AI system is two orders of magnitude faster than radiologists and the code is available at https : //github.com

show abstract

“…This AI model was able to achieve a performance of 94.4% on accurately detecting lung cancer in more than 6,700 test cases [4]. In addition, when compared head-to-head with a radiologist, the AI produced 11% and 5% absolute reductions in false positives and false negatives, respectively, when no prior imaging was available [4]. The ability to teach and fine tune a machine to improve the detection ability of radiologists is another potential value AI brings to oncologic care.…”

Section: Diagnosismentioning

confidence: 99%