Pathological changes or technical artefacts? The problem of the heterogenous databases in COVID-19 CXR image analysis

Socha, Marek; Prażuch, Wojciech; Suwalska, Aleksandra; Foszner, Paweł; Tobiasz, Joanna; Jaroszewicz, Jerzy; Gruszczynska, Katarzyna; Sliwinska, Magdalena; Nowak, Mateusz; Gizycka, Barbara; Zapolska, Gabriela; Popiela, Tadeusz; Przybylski, Grzegorz; Fiedor, Piotr; Pawlowska, Malgorzata; Flisiak, Robert; Simon, Krzysztof; Walecki, Jerzy; Cieszanowski, Andrzej; Szurowska, Edyta; Marczyk, Michal; Polanska, Joanna

doi:10.1016/j.cmpb.2023.107684

Cited by 4 publications

(3 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This approach stands in contrast to some recent studies focusing on disease detection, in which datasets are composed of positive disease samples, and controls [ 34 , 35 , 38 , 52 ]. Some studies struggle with poor generalization when applied in real clinical settings [ 76 , 77 ]. The lack of representation of critical patients with possible differential diagnoses and the differences in inclusion criteria for datasets can be confounding factors that contribute to this disparity in performance.…”

Section: Discussionmentioning

confidence: 99%

Uncertainty-Aware Convolutional Neural Network for Identifying Bilateral Opacities on Chest X-rays: A Tool to Aid Diagnosis of Acute Respiratory Distress Syndrome

et al. 2023

View full text Add to dashboard Cite

Acute Respiratory Distress Syndrome (ARDS) is a severe lung injury with high mortality, primarily characterized by bilateral pulmonary opacities on chest radiographs and hypoxemia. In this work, we trained a convolutional neural network (CNN) model that can reliably identify bilateral opacities on routine chest X-ray images of critically ill patients. We propose this model as a tool to generate predictive alerts for possible ARDS cases, enabling early diagnosis. Our team created a unique dataset of 7800 single-view chest-X-ray images labeled for the presence of bilateral or unilateral pulmonary opacities, or ‘equivocal’ images, by three blinded clinicians. We used a novel training technique that enables the CNN to explicitly predict the ‘equivocal’ class using an uncertainty-aware label smoothing loss. We achieved an Area under the Receiver Operating Characteristic Curve (AUROC) of 0.82 (95% CI: 0.80, 0.85), a precision of 0.75 (95% CI: 0.73, 0.78), and a sensitivity of 0.76 (95% CI: 0.73, 0.78) on the internal test set while achieving an (AUROC) of 0.84 (95% CI: 0.81, 0.86), a precision of 0.73 (95% CI: 0.63, 0.69), and a sensitivity of 0.73 (95% CI: 0.70, 0.75) on an external validation set. Further, our results show that this approach improves the model calibration and diagnostic odds ratio of the hypothesized alert tool, making it ideal for clinical decision support systems.

show abstract

Section: Discussionmentioning

confidence: 99%

Uncertainty-Aware Convolutional Neural Network for Identifying Bilateral Opacities on Chest X-rays: A Tool to Aid Diagnosis of Acute Respiratory Distress Syndrome

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Another significant challenge lies in the technical quality of radiographs, as suboptimal positioning, variable imaging techniques, variations in image exposure, and the presence of artifacts can lead to inaccuracies in the model. One study by Socha et al [90] examining COVID-19 detection AI models described how poor image quality, artifacts, and data heterogeneity in the initial datasets collected during the pandemic contributed to poor performance in real-world clinical settings. In the context of osteoporosis, Hsieh et al [58] noted that bony pathologies such as fractures, implants, bony tumors, infections, Deep learning models trained on small datasets tend to have reduced generalizability and overfitting.…”

Section: Challenges: Radiograph Quality and Confounding Pathologiesmentioning

confidence: 99%

“…Variability in data formats, quality, and acquisition techniques across various healthcare systems can also hinder the performance of AI tools. The heterogeneous distribution of disease in various populations and different populations also further complicates matters and may necessitate the use of separate training sets in different populations [90]. Most of the reviewed studies demonstrate good diagnostic accuracy on internal or external datasets without the inclusion of an integrated clinical pathway.…”

Section: Challenges: Clinical Integrationmentioning

confidence: 99%

Application of Artificial Intelligence Methods on Osteoporosis Classification with Radiographs—A Systematic Review

Liu,

Ong,

Makmur

et al. 2024

Bioengineering

View full text Add to dashboard Cite

Osteoporosis is a complex endocrine disease characterized by a decline in bone mass and microstructural integrity. It constitutes a major global health problem. Recent progress in the field of artificial intelligence (AI) has opened new avenues for the effective diagnosis of osteoporosis via radiographs. This review investigates the application of AI classification of osteoporosis in radiographs. A comprehensive exploration of electronic repositories (ClinicalTrials.gov, Web of Science, PubMed, MEDLINE) was carried out in adherence to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses 2020 statement (PRISMA). A collection of 31 articles was extracted from these repositories and their significant outcomes were consolidated and outlined. This encompassed insights into anatomical regions, the specific machine learning methods employed, the effectiveness in predicting BMD, and categorizing osteoporosis. Through analyzing the respective studies, we evaluated the effectiveness and limitations of AI osteoporosis classification in radiographs. The pooled reported accuracy, sensitivity, and specificity of osteoporosis classification ranges from 66.1% to 97.9%, 67.4% to 100.0%, and 60.0% to 97.5% respectively. This review underscores the potential of AI osteoporosis classification and offers valuable insights for future research endeavors, which should focus on addressing the challenges in technical and clinical integration to facilitate practical implementation of this technology.

show abstract

Label correlation guided discriminative label feature learning for multi-label chest image classification

Zhang,

Liang,

Cao

et al. 2024

Computer Methods and Programs in Biomedicine

View full text Add to dashboard Cite

Pathological changes or technical artefacts? The problem of the heterogenous databases in COVID-19 CXR image analysis

Cited by 4 publications

References 48 publications

Uncertainty-Aware Convolutional Neural Network for Identifying Bilateral Opacities on Chest X-rays: A Tool to Aid Diagnosis of Acute Respiratory Distress Syndrome

Uncertainty-Aware Convolutional Neural Network for Identifying Bilateral Opacities on Chest X-rays: A Tool to Aid Diagnosis of Acute Respiratory Distress Syndrome

Application of Artificial Intelligence Methods on Osteoporosis Classification with Radiographs—A Systematic Review

Label correlation guided discriminative label feature learning for multi-label chest image classification

Contact Info

Product

Resources

About