A ensemble methodology for automatic classification of chest X-rays using deep learning

• Published in: Computers in biology and medicine Vol. 145; p. 105442
• Main Authors: Vogado, Luis, Araújo, Flávio, Neto, Pedro Santos, Almeida, João, Tavares, João Manuel R.S., Veras, Rodrigo
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01-06-2022; Elsevier Limited
• Subjects: Accuracy; Artificial neural networks; Chest; Classification; Computer aided diagnosis; COVID-19; Datasets; Deep Learning; Hospitals; Humans; Image analysis; Image classification; Machine learning; Medical diagnosis; Medical research; Methods; Neural networks; Neural Networks, Computer; Patients; Radiography; X-Rays; 99-00; Image analysis; Computer aided diagnosis; 00-01; Machine learning; Image classification
• ISSN: 0010-4825; 1879-0534
• DOI: 10.1016/j.compbiomed.2022.105442

Chest radiographies, or chest X-rays, are the most standard imaging exams used in daily hospitals. Responsible for assisting in detecting numerous pathologies and findings that directly interfere in the patient's life, this exam is therefore crucial in screening patients. This work proposes a methodology based on a Convolutional Neural Networks (CNNs) ensemble to aid the diagnosis of chest X-ray exams by screening them with a high probability of being normal or abnormal. In the development of this study, a private dataset with frontal and lateral projections X-ray images was used. To build the ensemble model, VGG-16, ResNet50 and DenseNet121 architectures, which are commonly used in the classification of Chest X-rays, were evaluated. A Confidence Threshold (CTR) was used to define the predictions into High Confidence Normal (HCn), Borderline classification (BC), or High Confidence Abnormal (HCa). In the tests performed, very promising results were achieved: 54.63% of the exams were classified with high confidence; of the normal exams, 32% were classified as HCn with an false discovery rate (FDR) of 1.68%; and as to the abnormal exams, 23% were classified as HCa with 4.91% false omission rate (FOR).
•Evaluation in a heterogeneous dataset with abnormalities not present in literature.•New ensemble methodology using different CNNs architectures and different projections.•New evaluation methodology considering the probability of CNNs and confidence factors.•An automatic solution that can be easily implemented in different hospitals.