Calculating the target exposure index using a deep convolutional neural network and a rule base

Abstract

The objective of this study is to determine the quality of chest X-ray images using a deep convolutional neural network (DCNN) and a rule base without performing any visual assessment. A method is proposed for determining the minimum diagnosable exposure index (EI) and the target exposure index (EIt). Methods: The proposed method involves transfer learning to assess the lung fields, mediastinum, and spine using GoogLeNet, which is a type of DCNN that has been trained using conventional images. Three detectors were created, and the image quality of local regions was rated. Subsequently, the results were used to determine the overall quality of chest X-ray images using a rule-based technique that was in turn based on expert assessment. The minimum EI required for diagnosis was calculated based on the distribution of the EI values, which were classified as either suitable or non-suitable and then used to ascertain the EIt. Results: The accuracy rate using the DCNN and the rule base was 81%. The minimum EI required for diagnosis was 230, and the EIt was 288. Conclusion: The results indicated that the proposed method using the DCNN and the rule base could discriminate different image qualities without any visual assessment; moreover, it could determine both the minimum EI required for diagnosis and the EIt.

Proper Management of the Clinical Exposure Index Based on Body Thickness Using Dose Optimization Tools in Digital Chest Radiography: A Phantom Study

“…Park et al investigated the possibility of using it as a quality control tool by using displayed EI, as per IEC standards, and also revealed that the usefulness of clinical EI, EI T , and DI, which could be recorded in DICOM header tags for monitoring the ESD based on the national diagnostic reference levels (DRLs) [ 13 , 14 ]. In clinical situations, there are several trials that have introduced the clinical EI, EI T , and DI to optimize medical radiation use [ 15 , 16 , 17 ].…”

Deep Learning for Chest X-ray Analysis: A Survey

“…Some studies that make use of MIL are (Crosby et al, 2020c;Schwab et al, 2020). Other topics within the literature include model uncertainty (Ul Abideen et al, 2020;Ghesu et al, 2019), quality of the CXR (Moradi et al, 2020;McManigle et al, 2020;Moradi et al, 2019a;Takaki et al, 2020;McManigle et al, 2020) and defence against adversarial attack (Li and Zhu, 2020;Anand et al, 2020;Xue et al, 2019).…”

The EU medical device regulation: Implications for artificial intelligence-based medical device software in medical physics

“…Artificial intelligence is expected to soon play a key role in diagnostic imaging [1,2], radiation therapy [3,4] and medical physics in general. It has already been demonstrated to successfully improve image quality [1], decrease radiation dosage [5,6], assign label types and identify pathology locations [7][8][9][10][11][12][13], create and optimize protocols [14], accurately segment pathology areas and organs [15,16], and optimize technology utilization [17].…”