Dataset Information

Deep-Learning-Based Hemoglobin Concentration Prediction and Anemia Screening Using Ultra-Wide Field Fundus Images.

ABSTRACT: Background: Anemia is the most common hematological disorder. The purpose of this study was to establish and validate a deep-learning model to predict Hgb concentrations and screen anemia using ultra-wide-field (UWF) fundus images. Methods: The study was conducted at Peking Union Medical College Hospital. Optos color images taken between January 2017 and June 2021 were screened for building the dataset. ASModel_UWF using UWF images was developed. Mean absolute error (MAE) and area under the receiver operating characteristics curve (AUC) were used to evaluate its performance. Saliency maps were generated to make the visual explanation of the model. Results: ASModel_UWF acquired the MAE of the prediction task of 0.83 g/dl (95%CI: 0.81-0.85 g/dl) and the AUC of the screening task of 0.93 (95%CI: 0.92-0.95). Compared with other screening approaches, it achieved the best performance of AUC and sensitivity when the test dataset size was larger than 1000. The model tended to focus on the area around the optic disc, retinal vessels, and some regions located at the peripheral area of the retina, which were undetected by non-UWF imaging. Conclusion: The deep-learning model ASModel_UWF could both predict Hgb concentration and screen anemia in a non-invasive and accurate way with high efficiency.

SUBMITTER: Zhao X

PROVIDER: S-EPMC9160874 | biostudies-literature | 2022

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Deep-Learning-Based Hemoglobin Concentration Prediction and Anemia Screening Using Ultra-Wide Field Fundus Images.

Zhao Xinyu X Meng Lihui L Su Hao H Lv Bin B Lv Chuanfeng C Xie Guotong G Chen Youxin Y

Frontiers in cell and developmental biology 20220519

<b>Background:</b> Anemia is the most common hematological disorder. The purpose of this study was to establish and validate a deep-learning model to predict Hgb concentrations and screen anemia using ultra-wide-field (UWF) fundus images. <b>Methods:</b> The study was conducted at Peking Union Medical College Hospital. Optos color images taken between January 2017 and June 2021 were screened for building the dataset. ASModel_UWF using UWF images was developed. Mean absolute error (MAE) and area ...[more]

PMID: 35663399

Similar Datasets

Project description:BackgroundClinical application of artificial intelligence is limited due to the lack of interpretability and expandability in complex clinical settings. We aimed to develop an eye diseases screening system with improved interpretability and expandability based on a lesion-level dissection and tested the clinical expandability and auxiliary ability of the system.MethodsThe four-hierarchical interpretable eye diseases screening system (IEDSS) based on a novel structural pattern named lesion atlas was developed to identify 30 eye diseases and conditions using a total of 32,026 ultra-wide field images collected from the Second Affiliated Hospital of Zhejiang University, School of Medicine (SAHZU), the First Affiliated Hospital of University of Science and Technology of China (FAHUSTC), and the Affiliated People's Hospital of Ningbo University (APHNU) in China between November 1, 2016 to February 28, 2022. The performance of IEDSS was compared with ophthalmologists and classic models trained with image-level labels. We further evaluated IEDSS in two external datasets, and tested it in a real-world scenario and an extended dataset with new phenotypes beyond the training categories. The accuracy (ACC), F1 score and confusion matrix were calculated to assess the performance of IEDSS.FindingsIEDSS reached average ACCs (aACC) of 0·9781 (95%CI 0·9739-0·9824), 0·9660 (95%CI 0·9591-0·9730) and 0·9709 (95%CI 0·9655-0·9763), frequency-weighted average F1 scores of 0·9042 (95%CI 0·8957-0·9127), 0·8837 (95%CI 0·8714-0·8960) and 0·8874 (95%CI 0·8772-0·8972) in datasets of SAHZU, APHNU and FAHUSTC, respectively. IEDSS reached a higher aACC (0·9781, 95%CI 0·9739-0·9824) compared with a multi-class image-level model (0·9398, 95%CI 0·9329-0·9467), a classic multi-label image-level model (0·9278, 95%CI 0·9189-0·9366), a novel multi-label image-level model (0·9241, 95%CI 0·9151-0·9331) and a lesion-level model without Adaboost (0·9381, 95%CI 0·9299-0·9463). In the real-world scenario, the aACC of IEDSS (0·9872, 95%CI 0·9828-0·9915) was higher than that of the senior ophthalmologist (SO) (0·9413, 95%CI 0·9321-0·9504, p = 0·000) and the junior ophthalmologist (JO) (0·8846, 95%CI 0·8722-0·8971, p = 0·000). IEDSS remained strong performance (ACC = 0·8560, 95%CI 0·8252-0·8868) compared with JO (ACC = 0·784, 95%CI 0·7479-0·8201, p= 0·003) and SO (ACC = 0·8500, 95%CI 0·8187-0·8813, p = 0·789) in the extended dataset.InterpretationIEDSS showed excellent and stable performance in identifying common eye conditions and conditions beyond the training categories. The transparency and expandability of IEDSS could tremendously increase the clinical application range and the practical clinical value of it. It would enhance the efficiency and reliability of clinical practice, especially in remote areas with a lack of experienced specialists.FundingNational Natural Science Foundation Regional Innovation and Development Joint Fund (U20A20386), Key research and development program of Zhejiang Province (2019C03020), Clinical Medical Research Centre for Eye Diseases of Zhejiang Province (2021E50007).

Project description:PurposeTo compare the relative number of retinal pixels and retinal area imaged using the Optos P200DTx (Optos PLC) and Zeiss Clarus 500 (Carl Zeiss Meditec AG) ultra-widefield (UWF) fundus cameras.DesignSingle-center retrospective cross-sectional analysis.ParticipantsSeventy-eight eyes of 46 patients.MethodsEyes were imaged with Optos P200DTx, single-capture, and Zeiss Clarus 500, 2 capture montages when possible, UWF fundus cameras. Relative number of pixels encompassing all foveal-centered retinal quadrants were measured. Retinal area was measured with Zeiss Clarus 500 images that were registered to the Optos P200DTx images. Patients and technicians were asked for preferences between the machines. Imaging session times were recorded.Main outcome measuresRelative number of retinal pixels and retina area captured by each fundus camera.ResultsOptos P200DTx consistently captured more relative pixels compared with Zeiss Clarus 500: 510.4 versus 355.6 (P < 0.001) in total with a similarly statistically significant trend in all 4 quadrants (P < 0.001 for each). For area calculation, 70 of the 78 images achieved successful registration. Optos captured a larger total retinal area: 765.6 versus 566.5 mm2 (P < 0.001) with a similarly statistically significant trend in all 4 quadrants. In the subset of 52 of 70 registered and montaged Zeiss Clarus 500 images, similar results were found. For peripheral pathologic features, Optos P200DTx captured unique findings in 28 images, and Zeiss Clarus 500 captured unique findings 1 image (P < 0.001). Among the 48 imaging sessions in which technicians preferred Optos P200DTx for 28 sessions (58%) and Zeiss Clarus 500 for 20 (42%; P = 0.15). Among patients who responded with a preference, 24 preferred Optos P200DTx and 20 preferred Zeiss Clarus 500 (P = 0.52). Average imaging session time was 4.6 minutes (standard deviation, 3.0 minutes) for Optos P200DTx and 5.2 minutes (standard deviation, 3.0 minutes) for Zeiss Clarus 500 (P = 0.17).ConclusionsIn the current study, the Optos P200DTx captured statistically significantly more retinal area in all 4 quadrants compared with the Zeiss Clarus 500. No statistically significant difference was found in patient or technician preference or image acquisition time between devices.

Dataset Information

Deep-Learning-Based Hemoglobin Concentration Prediction and Anemia Screening Using Ultra-Wide Field Fundus Images.

Publications

Deep-Learning-Based Hemoglobin Concentration Prediction and Anemia Screening Using Ultra-Wide Field Fundus Images.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets