Digital radiography reject analysis: A comparison between two radiology departments in New Zealand

Bantas, Gabriela; Sweeney, Rhonda‐Joy; Mdletshe, Sibusiso

doi:10.1002/jmrs.654

Cited by 3 publications

(7 citation statements)

References 24 publications

(147 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To a large extent, the exposure-related issues of film-screen technology have now been replaced with patient positioning errors. These findings are supported in this edition of Journal of Medical Radiation Sciences (JMRS), where Bantas et al 2 conducted a multisite study of digital radiography reject rates and reject rationales in 2021 in two New Zealand radiology departments. They reported that patient positioning was found to be the most common rationale for image rejection and calculated overall reject rates of 7.86% and 5.91% for each site.…”

mentioning

confidence: 73%

“…Despite these reject rates being considerably lower than reported rates for film‐screen departments which have been documented to be between 10% and 15%, 3,4 these findings further support the need for reject analysis in the digital age. Additionally, Bantas et al 2 . highlighted that it would be beneficial to include a review of radiographic positioning technique within the reject analysis process.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Making the most of X‐ray reject analysis in the digital age

Neep

2023

J of Medical Radiation Sci

View full text Add to dashboard Cite

show abstract

mentioning

confidence: 73%

mentioning

confidence: 99%

Making the most of X‐ray reject analysis in the digital age

Neep

2023

J of Medical Radiation Sci

View full text Add to dashboard Cite

show abstract

“…In X-ray radiography, various factors can affect radiograph quality, such as positioning, exposure errors, and artifacts. [1][2][3] Low-quality radiographs can interfere with diagnoses, leading to image rejection and repeated exams. AAPM Report 151 indicates that 14% of patient exposure in projection radiography is due to repeated exams.…”

Section: Introductionmentioning

confidence: 99%

“…In X‐ray radiography, various factors can affect radiograph quality, such as positioning, exposure errors, and artifacts 1–3 . Low‐quality radiographs can interfere with diagnoses, leading to image rejection and repeated exams.…”

Section: Introductionmentioning

confidence: 99%

“…1 Currently, in some countries, the image rejection rate is above 5%. [2][3][4][5][6][7][8][9][10][11] To ensure the accuracy of diagnoses and reduce interference, it is necessary to conduct a quality evaluation of radiographs. However, manual sampling inspections, the current standard for quality evaluation, are time-consuming, laborious, and suffer from interobserver variability.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A semi‐supervised learning‐based quality evaluation system for digital chest radiographs

Wei,

Qiu,

et al. 2023

Medical Physics

View full text Add to dashboard Cite

BackgroundDigital radiography is the most commonly utilized medical imaging technique worldwide, and the quality of radiographs plays a crucial role in accurate disease diagnosis. Therefore, evaluating the quality of radiographs is an essential step in medical examinations. However, manual evaluation can be time‐consuming, labor‐intensive, and prone to interobserver differences, making it less reliable.PurposeTo alleviate the workload of radiographic technologists and enhance the efficiency of radiograph quality evaluation, it is crucial to develop rapid and reliable quality evaluation methods and establish a set of quantitative evaluation standards. To address this, we have proposed a quality evaluation system for digital radiographs that utilizes deep learning techniques to achieve fast and precise evaluation.MethodsThe evaluation of frontal chest radiograph quality involves assessing patient positioning through semantic segmentation and foreign body detection. For lung, scapula, and clavicle segmentation in digital chest radiographs, a residual connection‐based convolutional neural network π‐ResUNet, was proposed. Criteria for patient positioning evaluation were established based on the segmentation and manual evaluation results. A convolutional neural network, FasterRCNN, was utilized to detect and localize foreign bodies in digital chest radiographs. To enhance the performance of both neural networks, a semi‐supervised learning (SSL) strategy was implemented by incorporating a consistency loss that leverages a large number of unlabeled digital radiographs. We also trained the network using the fully supervised learning (FSL) strategy and compared their performance on the test set. The ChestXRay‐14 and object‐CXR datasets were used throughout the process.ResultsBy comparing with the manual annotation, the proposed network, trained using the SSL method, achieved a high Dice similarity coefficient (DSC) of 0.96, 0.88, and 0.88 for lung, scapula, and clavicle segmentation, respectively, outperforming the network trained with the FSL method. In addition, for foreign body detection, the proposed SSL method was superior to the FSL method, achieving an AUC (Area under receiver operating characteristic curve, Area under ROC curve) of 0.90 and an FROC (Free‐response ROC) of 0.77 on the test dataset.ConclusionsThe experimental results show that our proposed system is well‐suited for radiograph quality evaluation, with the semi‐supervised learning method further improving the network's performance. The proposed method can evaluate the quality of a chest radiograph from two aspects—patient positioning and foreign body detection—within 1 s, offering a promising tool in radiograph quality evaluation.

show abstract

Multi‐centre digital radiography reject analysis for different clinical room use types: The establishment of local reject reference levels for public hospital departments

Serra,

Neep,

Ryan

2024

J of Medical Radiation Sci

View full text Add to dashboard Cite

IntroductionReject analysis in digital radiography helps guide the training of staff to reduce patient radiation dose and improve department efficiency. The purpose of this study was to perform a multi‐centre, vendor agnostic reject analysis across different room usage types, and to provide benchmarks for comparison.MethodsRetrospective reject and exposure log data were collected via USB from fixed general X‐ray systems across multiple Australian sites, for collation and analysis. The overall reject rate, local reject reference level, absolute and relative reject rates for body part categories, reject rates by room usage types and the reject rate for each reason of rejection were calculated.ResultsData were collected from 44 X‐ray systems, across 11 hospitals. A total of 2,031,713 acquired images and 172,495 rejected images were included. The median reject rate was 9.1%. The local reject reference level (LRRL), set as the 75th percentile of all reject rates, was 10.6%. Median reject rates by room type were emergency (7.4%), inpatients + outpatients (9.6%), outpatients (9.2%), and hybrid (10.1%). The highest absolute reject rates by body part were chest (2.1%) and knee (1.4%). The highest relative rates by body part were knee (18.1%) and pelvis (17.2%). The most frequent reasons for image rejection were patient positioning (76%) and patient motion (7.5%).ConclusionsThe results compare well with previously published data. The range of reject rates highlights the need to analyse typical reject rates in different ways. With analysis feedback to participating sites and the implementation of standardised reject reasons, future analysis should monitor whether reject rates reduce.

show abstract

Digital radiography reject analysis: A comparison between two radiology departments in New Zealand

Cited by 3 publications

References 24 publications

Making the most of X‐ray reject analysis in the digital age

Making the most of X‐ray reject analysis in the digital age

A semi‐supervised learning‐based quality evaluation system for digital chest radiographs

Multi‐centre digital radiography reject analysis for different clinical room use types: The establishment of local reject reference levels for public hospital departments

Contact Info

Product

Resources

About