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

• Type: Article in International Scientific Journal
• Date: 2022-06

Authors

Luis Vogado (Author) Other; Flávio Araújo (Author) Other; Pedro Santos Neto (Author) Other; João Almeida (Author) Other; João Manuel R. S. Tavares (Author) FEUP; Rodrigo Veras (Author) Other

Journal

Title: Computers in Biology and Medicine

Vol. 145 No. 105442

Pages: 1-15

ISSN: 0010-4825

Publisher: Elsevier

Indexing

ISI Web of Knowledge - 0 Citations

ISI Web of Science

Clarivate Analytics

Scientific classification

CORDIS: Technological sciences

FOS: Medical and Health sciences

Other information

Authenticus ID: P-00W-R6S

DOI: 10.1016/j.compbiomed.2022.105442

Abstract (EN): 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).

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 15