Rethinking annotation granularity for overcoming shortcuts in deep learning–based radiograph diagnosis: A multicenter study

L Luo, H Chen, Y Xiao, Y Zhou, X Wang… - Radiology: Artificial …, 2022 - pubs.rsna.org
Purpose To evaluate the ability of fine-grained annotations to overcome shortcut learning in
deep learning (DL)–based diagnosis using chest radiographs. Materials and Methods Two …

[HTML][HTML] Better performance of deep learning pulmonary nodule detection using chest radiography with pixel level labels in reference to computed tomography: data …

JY Kim, WS Ryu, D Kim, EY Kim - Scientific Reports, 2024 - nature.com
Labeling errors can significantly impact the performance of deep learning models used for
screening chest radiographs. The deep learning model for detecting pulmonary nodules is …

[HTML][HTML] Performance of a deep-learning algorithm for referable thoracic abnormalities on chest radiographs: A multicenter study of a health screening cohort

EY Kim, YJ Kim, WJ Choi, GP Lee, YR Choi, KN Jin… - PloS one, 2021 - journals.plos.org
Purpose This study evaluated the performance of a commercially available deep-learning
algorithm (DLA)(Insight CXR, Lunit, Seoul, South Korea) for referable thoracic abnormalities …

[HTML][HTML] Deep learning for chest radiograph diagnosis: A retrospective comparison of the CheXNeXt algorithm to practicing radiologists

P Rajpurkar, J Irvin, RL Ball, K Zhu, B Yang… - PLoS …, 2018 - journals.plos.org
Background Chest radiograph interpretation is critical for the detection of thoracic diseases,
including tuberculosis and lung cancer, which affect millions of people worldwide each year …

Chest radiograph interpretation with deep learning models: assessment with radiologist-adjudicated reference standards and population-adjusted evaluation

A Majkowska, S Mittal, DF Steiner, JJ Reicher… - Radiology, 2020 - pubs.rsna.org
Background Deep learning has the potential to augment the use of chest radiography in
clinical radiology, but challenges include poor generalizability, spectrum bias, and difficulty …

Development and validation of a deep learning algorithm detecting 10 common abnormalities on chest radiographs

JG Nam, M Kim, J Park, EJ Hwang… - European …, 2021 - Eur Respiratory Soc
We aimed to develop a deep learning algorithm detecting 10 common abnormalities (DLAD-
10) on chest radiographs, and to evaluate its impact in diagnostic accuracy, timeliness of …

Generalizable inter-institutional classification of abnormal chest radiographs using efficient convolutional neural networks

I Pan, S Agarwal, D Merck - Journal of digital imaging, 2019 - Springer
Our objective is to evaluate the effectiveness of efficient convolutional neural networks
(CNNs) for abnormality detection in chest radiographs and investigate the generalizability of …

Performance and usability of code-free deep learning for chest radiograph classification, object detection, and segmentation

SM Santomartino, N Hafezi-Nejad… - Radiology: Artificial …, 2023 - pubs.rsna.org
Purpose To evaluate the performance and usability of code-free deep learning (CFDL)
platforms in creating DL models for disease classification, object detection, and …

[HTML][HTML] Validation of a deep learning model for detecting chest pathologies from digital chest radiographs

P Ajmera, P Onkar, S Desai, R Pant, J Seth, T Gupte… - Diagnostics, 2023 - mdpi.com
Purpose: Manual interpretation of chest radiographs is a challenging task and is prone to
errors. An automated system capable of categorizing chest radiographs based on the …

[HTML][HTML] Enhancing multi-disease diagnosis of chest X-rays with advanced deep-learning networks in real-world data

Y Chen, Y Wan, F Pan - Journal of Digital Imaging, 2023 - Springer
The current artificial intelligence (AI) models are still insufficient in multi-disease diagnosis
for real-world data, which always present a long-tail distribution. To tackle this issue, a long …