Deep learning in chest radiography: Detection of findings and presence of change

Abstract

BackgroundDeep learning (DL) based solutions have been proposed for interpretation of several imaging modalities including radiography, CT, and MR. For chest radiographs, DL algorithms have found success in the evaluation of abnormalities such as lung nodules, pulmonary tuberculosis, cystic fibrosis, pneumoconiosis, and location of peripherally inserted central catheters. Chest radiography represents the most commonly performed radiological test for a multitude of non-emergent and emergent clinical indications. This study aims to assess accuracy of deep learning (DL) algorithm for detection of abnormalities on routine frontal chest radiographs (CXR), and assessment of stability or change in findings over serial radiographs.Methods and findingsWe processed 874 de-identified frontal CXR from 724 adult patients (> 18 years) with DL (Qure AI). Scores and prediction statistics from DL were generated and recorded for the presence of pulmonary opacities, pleural effusions, hilar prominence, and enlarged cardiac silhouette. To establish a standard of reference (SOR), two thoracic radiologists assessed all CXR for these abnormalities. Four other radiologists (test radiologists), unaware of SOR and DL findings, independently assessed the presence of radiographic abnormalities. A total 724 radiographs were assessed for detection of findings. A subset of 150 radiographs with follow up examinations was used to asses change over time. Data were analyzed with receiver operating characteristics analyses and post-hoc power analysis.ResultsAbout 42% (305/ 724) CXR had no findings according to SOR; single and multiple abnormalities were seen in 23% (168/724) and 35% (251/724) of CXR. There was no statistical difference between DL and SOR for all abnormalities (p = 0.2–0.8). The area under the curve (AUC) for DL and test radiologists ranged between 0.837–0.929 and 0.693–0.923, respectively. DL had lowest AUC (0.758) for assessing changes in pulmonary opacities over follow up CXR. Presence of chest wall implanted devices negatively affected the accuracy of DL algorithm for evaluation of pulmonary and hilar abnormalities.ConclusionsDL algorithm can aid in interpretation of CXR findings and their stability over follow up CXR. However, in its present version, it is unlikely to replace radiologists due to its limited specificity for categorizing specific findings.

Are All Deep Learning Architectures Alike for Point‐of‐Care Ultrasound?: Evidence From a Cardiac Image Classification Model Suggests Otherwise

“…As artificial intelligence and, more specifically, DL start to affect medical imaging, considerable focus has been placed on large–study volume cross‐sectional imaging modalities. New applications are being developed by well‐funded commercial entities, and most have focused on imaging modalities such as radiography, CT, and MRI . This is pragmatic, given the potential for larger revenue generation in CT and MRI markets, as well as engineering unfamiliarity with POCUS, a much newer and less well‐defined specialty.…”

“…Multiple uses have been described for artificial intelligence in medicine, and medical imaging is consistently noted as one of the greatest potential uses. To date, most examples of clinically useful DL image interpretation algorithms have focused on radiology‐based implementations such as interpretations of chest radiography, computed tomography (CT), and magnetic resonance imaging (MRI) . Ultrasound (US) examples of DL use for image analysis are relatively few and far between, with most being found in high‐end consultative imaging–type US machines …”

Computer-aided Assessment of Catheters and Tubes on Radiographs: How Good Is Artificial Intelligence for Assessment?

“…Ventilation, airway maintenance 5 cm above carina when the head is in neutral position or T3 or T4 if the carina is not visualized (in adults); mid trachea, approximately halfway between the inferior margin of the clavicles and the carina (in children); 1.5 cm above the carina (in neonates) (6,7,14) Bronchus, esophagus Trauma, infection, aspiration, altered oral development a such structures may potentially be a source of confusion for deep learning algorithms (8). Although the first CAD systems for evaluation of radiographs was proposed in the 1960s by Lodwick et al (9), it was not until 2007 that the first specialized system for catheter placement evaluation was published (10,11).…”

DIY AI, deep learning network development for automated image classification in a point‐of‐care ultrasound quality assurance program

“…Within medicine, deep learning algorithms have shown particular promise in the machine interpretation of diagnostic imaging techniques across various organ systems. For example, the application of deep learning techniques to the interpretation of chest x‐rays and computed tomography (CT) scans of the head and chest have all been shown to yield improved diagnostic accuracy when compared to radiologists 1‐4 . However, some of these studies and algorithms have come under justified criticism for inadequate validation in real world applications 5 …”