Deep learning and medical diagnosis

Liu, Yuliang; Liu, Guohua; Zhang, Quan

doi:10.1016/s0140-6736(19)32501-2

Cited by 21 publications

(25 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, compared to the needs of the patients, the number of radiologists is quite small, especially in Hubei province, China, which could greatly delay the diagnosis and isolation of patients, affect patient's treatment and prognosis, and ultimately, affect the overall control of COVID-19 epidemic. Deep learning, a technology has shown great performance on extracting tiny features in radiology data, may hold the promise to alleviate this problem 11 . Recently, Ardila D, et al achieved end-to-end lung cancer screening on low-dose chest CT with an AUC of 94.4% 29 .…”

Section: Discussionmentioning

confidence: 99%

“…Deep learning, an important breakthrough in the domain of AI in the past decade, has huge potential at extracting tiny features by the basic unit of DCNN's sampling kernel in image analysis 11 . Our group also succeeded in recruiting this technique in minor lesion detection and real-time assistance to doctors in gastrointestinal endoscopy [12][13][14][15][16] .…”

mentioning

confidence: 99%

See 1 more Smart Citation

Deep learning-based model for detecting 2019 novel coronavirus pneumonia on high-resolution computed tomography

Chen

Zhang

et al. 2020

Sci Rep

348

229

View full text Add to dashboard Cite

Computed tomography (CT) is the preferred imaging method for diagnosing 2019 novel coronavirus (COVID19) pneumonia. We aimed to construct a system based on deep learning for detecting COVID-19 pneumonia on high resolution CT. For model development and validation, 46,096 anonymous images from 106 admitted patients, including 51 patients of laboratory confirmed COVID-19 pneumonia and 55 control patients of other diseases in Renmin Hospital of Wuhan University were retrospectively collected. Twenty-seven prospective consecutive patients in Renmin Hospital of Wuhan University were collected to evaluate the efficiency of radiologists against 2019-CoV pneumonia with that of the model. An external test was conducted in Qianjiang Central Hospital to estimate the system’s robustness. The model achieved a per-patient accuracy of 95.24% and a per-image accuracy of 98.85% in internal retrospective dataset. For 27 internal prospective patients, the system achieved a comparable performance to that of expert radiologist. In external dataset, it achieved an accuracy of 96%. With the assistance of the model, the reading time of radiologists was greatly decreased by 65%. The deep learning model showed a comparable performance with expert radiologist, and greatly improved the efficiency of radiologists in clinical practice.

show abstract

Section: Discussionmentioning

confidence: 99%

mentioning

confidence: 99%

Deep learning-based model for detecting 2019 novel coronavirus pneumonia on high-resolution computed tomography

Chen

Zhang

et al. 2020

Sci Rep

348

229

View full text Add to dashboard Cite

show abstract

“…Increasing the explanatory power of the model can effectively increase the research on biomarkers. 34 The future work is still around to improve the performance of the auxiliary diagnostic system. In order to further improve the accuracy of the model, we will consider how to input more types of data into the model, such as patient history, etc.…”

Section: Resultsmentioning

confidence: 99%

“…Increasing the interpretability of the model will further improve the diagnostic level of the disease. 34 In addition, a method that can automatically process a large number of samples and provide biomarkers can speed up the study of disease mechanism. In conclusion, the combination of deep learning technology and medical diagnostic technology is of great significance for disease research.…”

Section: Introductionmentioning

confidence: 99%

<p>Deep Learning-Based Method of Diagnosing Hyperlipidemia and Providing Diagnostic Markers Automatically</p>

Liu¹,

Zhang²,

Zhao³

et al. 2020

DMSO

Self Cite

View full text Add to dashboard Cite

Introduction: The research of auxiliary diagnosis has always been one of the hotspots in the world. The implementation of auxiliary diagnosis support algorithm for medical text data faces challenges with interpretability and creditability. The improvement of clinical diagnostic techniques means not only the improvement of diagnostic accuracy but also the further study of diagnostic basis. Traditional research methods for diagnostic markers often require a large amount of time and economic costs. Research objects are often dozens of samples, and it is, therefore, difficult to synthesize large amounts of data. Therefore, the comprehensiveness and reliability of traditional methods have yet to be improved. Therefore, the establishment of a model that can automatically diagnose diseases and automatically provide a diagnostic basis at the same time has a positive effect on the improvement of medical diagnostic techniques. Methods: Here, we established an auxiliary diagnostic tool based on attention deep learning algorithm to diagnostic hyperlipemia and automatically predict the corresponding diagnostic markers using hematological parameters. In this paper, we not only demonstrated the ability of the proposed model to automatically diagnose diseases using text-based medical data, such as physiological parameters, but also demonstrated its ability to forecast disease diagnostic markers. Human physiological parameters are used as input to the model, and the doctor's diagnosis results as an output. Through the attention layer, the degree of attention of the model to different physiological parameters can be obtained, that is, the model provides a diagnostic basis. Results: It achieved 94% ACC, 97.48% AUC, 96% sensitivity and 92% specificity with the test dataset. All the above samples are drawn from clinical practice. Moreover, the model predicted the diagnostic markers of hyperlipidemia by the attention mechanism, and the results were fully agreeable to the golden criteria. Discussion: The auxiliary diagnosis system proposed in this paper not only achieves the accurate and robust performance, and can be used for the preliminary diagnosis of patients, but also showing its great potential to discover new diagnostic markers. Therefore, it not only can improve the efficiency of clinical diagnosis but also shorten the research period of researching a diagnosis basis to an extent. It has a positive significance to the development of the medical diagnosis level.

show abstract

“…In recent years, the application of deep learning to lesion detection in medical imaging has become a popular topic due to its high processing efficiency and analysis speed. [20] Some studies have accurately detected AIS lesions using fully supervised methods. The accurate annotation of AIS lesions from a large number of images requires tremendous time.…”

Section: Discussionmentioning

confidence: 99%

Suitability of Deep Weakly Supervised Learning to detect Acute Ischemic Stroke and Hemorrhagic Infarction Lesions Using Diffusion-weighted Imaging

Cao

Liu

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Objectives: The automatic detection of acute ischemic stroke (AIS) and hemorrhagic infarction (HI) based on deep learning could avoid missed diagnosis. The fully supervised learning requires the amount of time and the expertise to manually outline lesions, which limits its applicability. The weakly supervised learning has the potential to reduce the labeling workload. The purpose of this study was to evaluate a weakly supervised method in detection of AIS and HI location using DWI. Methods: We proposed to adopt weakly supervised learning to spatially-locate AIS lesions by residual neural network (ResNet) and visual geometry group (VGG) network. On an AIS dataset, the area under the receiver operating characteristic (ROC) curve (AUC), sensitivity and precision were calculated. Next, ResNet, which presented superior performance on the AIS dataset, was further applied to an HI dataset. Results: In the AIS dataset, the AUCs of ResNet and VGG on identifying image slices with AIS were 0.97 and 0.94, respectively. On spatially-locating the AIS lesions, ResNet provided higher sensitivity and a lower missed diagnosis rate than VGG, especially for pontine AIS lesions. In the HI dataset, the sensitivity of ResNet was 87.73% for AIS detection, and 86.20% for HI detection, respectively. Conclusions: Weakly supervised learning can effectively detect the location of AIS and HI lesions in DWI, which is of paramount importance in avoiding misdiagnosis in clinical scenario.

show abstract

Deep learning and medical diagnosis

Cited by 21 publications

References 2 publications

Deep learning-based model for detecting 2019 novel coronavirus pneumonia on high-resolution computed tomography

Deep learning-based model for detecting 2019 novel coronavirus pneumonia on high-resolution computed tomography

<p>Deep Learning-Based Method of Diagnosing Hyperlipidemia and Providing Diagnostic Markers Automatically</p>

Suitability of Deep Weakly Supervised Learning to detect Acute Ischemic Stroke and Hemorrhagic Infarction Lesions Using Diffusion-weighted Imaging

Contact Info

Product

Resources

About