Recalibration of deep learning models for abnormality detection in smartphone-captured chest radiograph

Kuo, Po-Chih; Tsai, Cheng Che; López, Diego M.; Karargyris, Alexandros; Pollard, Tom; Johnson, Alistair E. W.; Celi, Leo Anthony

doi:10.1038/s41746-021-00393-9

Cited by 18 publications

(14 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several previous study using the MIMIC-CXR database for modeling reported a DL model of CXR developed for accurately and automatically detecting pulmonary edema, atelectasis, consolidation, cardiomegaly, pneumothorax, and pleural effusion [43][44][45]. Compared with previously reported CXR scores or our CXR label models, the DL model of CXR has certain advantages and potential prospects for clinical application.…”

Section: Discussionmentioning

confidence: 94%

A deep learning model to identify fluid overload status in critically ill patients based on chest X-ray images

Qin¹,

Zhang²,

Xiang³

et al. 2023

Polish Archives of Internal Medicine

View full text Add to dashboard Cite

show abstract

Section: Discussionmentioning

confidence: 94%

A deep learning model to identify fluid overload status in critically ill patients based on chest X-ray images

Qin¹,

Zhang²,

Xiang³

et al. 2023

Polish Archives of Internal Medicine

View full text Add to dashboard Cite

show abstract

“…There is no agreement on whether the richness and representativeness of public databases are sufficient to develop cardiomegaly detection algorithms with comparable performance on internal and external data sources. Three studies have demonstrated the external and internal validation resulting in similar AUC values from 0.800 to 0.828 38 , 52 , 53 , while Cohen et al 6 observed a drastic drop from 0.945 AUC to 0.721 AUC. Rajpurkar et al 32 observed that cardiomegaly is one of the lung abnormalities where automated detection results are significantly lower than the inter-observer variability.…”

Section: Discussionmentioning

confidence: 96%

A 178-clinical-center experiment of integrating AI solutions for lung pathology diagnosis

Ibragimov

Arzamasov

Maksudov

et al. 2023

Sci Rep

View full text Add to dashboard Cite

In 2020, an experiment testing AI solutions for lung X-ray analysis on a multi-hospital network was conducted. The multi-hospital network linked 178 Moscow state healthcare centers, where all chest X-rays from the network were redirected to a research facility, analyzed with AI, and returned to the centers. The experiment was formulated as a public competition with monetary awards for participating industrial and research teams. The task was to perform the binary detection of abnormalities from chest X-rays. For the objective real-life evaluation, no training X-rays were provided to the participants. This paper presents one of the top-performing AI frameworks from this experiment. First, the framework used two EfficientNets, histograms of gradients, Haar feature ensembles, and local binary patterns to recognize whether an input image represents an acceptable lung X-ray sample, meaning the X-ray is not grayscale inverted, is a frontal chest X-ray, and completely captures both lung fields. Second, the framework extracted the region with lung fields and then passed them to a multi-head DenseNet, where the heads recognized the patient’s gender, age and the potential presence of abnormalities, and generated the heatmap with the abnormality regions highlighted. During one month of the experiment from 11.23.2020 to 12.25.2020, 17,888 cases have been analyzed by the framework with 11,902 cases having radiological reports with the reference diagnoses that were unequivocally parsed by the experiment organizers. The performance measured in terms of the area under receiving operator curve (AUC) was 0.77. The AUC for individual diseases ranged from 0.55 for herniation to 0.90 for pneumothorax.

show abstract

“…The Madrid CXR images are resized during training to the input size for each of the pre-trained models (320 × 320 vs. 224 × 224) to output the imaging features for classification. The last fully connected layer of both models, containing 14 outputs corresponding to the 14 radiologic CheXpert finding labels [ 35 ], was removed. Instead, linearized convolutional features from either the second (− 2) or the fourth (− 4) to the last layer were used for the mortality prediction classification task.…”

Section: Methodsmentioning

confidence: 99%

Developing and Validating Multi-Modal Models for Mortality Prediction in COVID-19 Patients: a Multi-center Retrospective Study

Hoz

Kuo

et al. 2022

J Digit Imaging

View full text Add to dashboard Cite

The unprecedented global crisis brought about by the COVID-19 pandemic has sparked numerous efforts to create predictive models for the detection and prognostication of SARS-CoV-2 infections with the goal of helping health systems allocate resources. Machine learning models, in particular, hold promise for their ability to leverage patient clinical information and medical images for prediction. However, most of the published COVID-19 prediction models thus far have little clinical utility due to methodological flaws and lack of appropriate validation. In this paper, we describe our methodology to develop and validate multi-modal models for COVID-19 mortality prediction using multi-center patient data. The models for COVID-19 mortality prediction were developed using retrospective data from Madrid, Spain (N = 2547) and were externally validated in patient cohorts from a community hospital in New Jersey, USA (N = 242) and an academic center in Seoul, Republic of Korea (N = 336). The models we developed performed differently across various clinical settings, underscoring the need for a guided strategy when employing machine learning for clinical decision-making. We demonstrated that using features from both the structured electronic health records and chest X-ray imaging data resulted in better 30-day mortality prediction performance across all three datasets (areas under the receiver operating characteristic curves: 0.85 (95% confidence interval: 0.83–0.87), 0.76 (0.70–0.82), and 0.95 (0.92–0.98)). We discuss the rationale for the decisions made at every step in developing the models and have made our code available to the research community. We employed the best machine learning practices for clinical model development. Our goal is to create a toolkit that would assist investigators and organizations in building multi-modal models for prediction, classification, and/or optimization.

show abstract

Recalibration of deep learning models for abnormality detection in smartphone-captured chest radiograph

Cited by 18 publications

References 31 publications

A deep learning model to identify fluid overload status in critically ill patients based on chest X-ray images

A deep learning model to identify fluid overload status in critically ill patients based on chest X-ray images

A 178-clinical-center experiment of integrating AI solutions for lung pathology diagnosis

Developing and Validating Multi-Modal Models for Mortality Prediction in COVID-19 Patients: a Multi-center Retrospective Study

Contact Info

Product

Resources

About