Quality Assurance Images //TOP\ Download

Purpose: Patient-specific quality assurance (QA) for intensity-modulated radiation therapy (IMRT) is a ubiquitous clinical procedure, but conventional methods have often been criticized as being insensitive to errors or less effective than other common physics checks. Recently, there has been interest in the application of radiomics, quantitative extraction of image features, to radiotherapy QA. In this work, we investigate a deep learning approach to classify the presence or absence of introduced radiotherapy treatment delivery errors from patient-specific QA.

Methods: Planar dose maps from 186 IMRT beams from 23 IMRT plans were evaluated. Each plan was transferred to a cylindrical phantom CT geometry. Three sets of planar doses were exported from each plan corresponding to (a) the error-free case, (b) a random multileaf collimator (MLC) error case, and (c) a systematic MLC error case. Each plan was delivered to the electronic portal imaging device (EPID), and planned and measured doses were used to calculate gamma images in an EPID dosimetry software package (for a total of 558 gamma images). Two radiomic approaches were used. In the first, a convolutional neural network with triplet learning was used to extract image features from the gamma images. In the second, a handcrafted approach using texture features was used. The resulting metrics from both approaches were input into four machine learning classifiers (support vector machines, multilayer perceptrons, decision trees, and k-nearest-neighbors) in order to determine whether images contained the introduced errors. Two experiments were considered: the two-class experiment classified images as error-free or containing any MLC error, and the three-class experiment classified images as error-free, containing a random MLC error, or containing a systematic MLC error. Additionally, threshold-based passing criteria were calculated for comparison.

Quality Assurance Images Download

Download File 🔥 https://ssurll.com/2y5SOj 🔥

Results: In total, 303 gamma images were used for model training and 255 images were used for model testing. The highest classification accuracy was achieved with the deep learning approach, with a maximum accuracy of 77.3% in the two-class experiment and 64.3% in the three-class experiment. The performance of the handcrafted approach with texture features was lower, with a maximum accuracy of 66.3% in the two-class experiment and 53.7% in the three-class experiment. Variability between the results of the four machine learning classifiers was lower for the deep learning approach vs the texture feature approach. Both radiomic approaches were superior to threshold-based passing criteria.

Conclusions: Deep learning with convolutional neural networks can be used to classify the presence or absence of introduced radiotherapy treatment delivery errors from patient-specific gamma images. The performance of the deep learning network was superior to a handcrafted approach with texture features, and both radiomic approaches were better than threshold-based passing criteria. The results suggest that radiomic QA is a promising direction for clinical radiotherapy.

Image quality can be defined as the attribute of the image that influences the clinician's certainty to perceive the appropriate diagnostic features from the image visually.[1][2] Quality assurance or quality improvement is defined as the proactive actions to enhance the quality of care and services and cost-effectively remove the waste. In this article, we will discuss the fundamental concepts of digital radiographic image quality assurance. The most common digital radiographic detectors are computed radiography (CR) and digital radiography (DR). The important components of the radiographic image quality include contrast, dynamic range, spatial resolution, noise, and artifacts.[3] We will discuss these components briefly.

By adjusting kVp, decreasing mAs, and decreasing focal spot size, one can obtain high-quality digital radiographs with a lower radiation dose. Although a higher radiation dose leads to less noise and better image quality, one should be very cautious about the radiation dose to the patient. The radiographic systems should be optimized to obtain image quality that provides diagnostic accuracy at least possible radiation dose. The selection of radiographic projection affects the radiation dose. For example, in chest radiographs, anterior-posterior (AP) orientation has a higher radiation dose compared to the posterior-anterior (PA) view due to greater radiation exposure of breasts. In pediatric patients, the use of as low as reasonably achievable (ALARA) principle is essential during radiographic studies since children are more susceptible to the effects of ionizing radiation than adults.[7][8] The radiographic detectors with higher DQE provide superior SNR performance that enables radiation dose reduction without significantly affecting image quality, particularly in pediatric patients.[3][6][7]

The appropriate use of effective collimation and anti-scatter grid reduces the scattered radiation and improves image quality by reducing noise and improvement of SNR. The anti-scatter grid is most useful when the amount of scattered radiation is high, especially if the patient's thickness is greater than 10 cm.[3] However anti-scatter grid is not useful in smaller or pediatric patients or for smaller body part imaging.

For the troubleshooting of poor-quality radiographic images, the first step should be adjusting the post-processing parameters to see if the image can be reproduced with better image quality. One should optimize image acquisition and processing protocols to avoid repeat examination of the patients and unnecessary radiation exposure.

The optimal imaging protocols should be developed and established with the help of a medical physicist to obtain consistently high image quality at minimum possible radiation dose. The images should be properly compressed for transmission and storage without loss of significant clinical data. The appropriate image post-processing should be used to improve the image display. The imaging systems should comply with appropriate state and federal regulations. The imaging systems should minimize the incidence of poor-quality images and maximize clinical efficiency and continuous quality improvement.[3]

A meticulous quality assurance program is essential for consistently maintaining high-quality performance. The image quality should be monitored by doing acceptance testing to assure safety and image quality, periodical checkups and maintenance assessment, and thorough annual inspections under the guidance of the medical physicist.[9]

In summary, we discussed important components of the radiographic image quality and various factors affecting image quality. This knowledge is useful to obtain high-quality digital radiographs with the lowest possible radiation dose to improve the clinician's diagnostic accuracy.

Background: When running large trials, histopathology services are used to assess the state of a tissue. However, in many clinics in low resource settings there are large variations in quality of such services, specifically in biopsy processing and histopathological interpretation/assessment of images. Quality assurance (QA) is needed, but it involves physically mailing slides to a remote clinic. A telemedicine solution can address this challenge.

Methods: A novel smartphone adapter for microscopes was developed, consisting of a 3D printed attachment and software integration for the image capture. The attachment is used to couple the eyepiece of a low end microscope to a smartphone (Samsung J530). Image capture was controlled through the EVA System app. The entire system was characterized optically using standard calibration targets. Additionally, images captured on the attachment were compared to the standard method of shipping and scanning slides in a high end slice scanner at a remote clinic.

One of the many advantages of working with MMI is our comprehensive quality assurance program, which provides our clients with additional confidence that their imaging outcomes are accurate and reliable. Prior to the start of each study, our expert physician reviewers are carefully selected and go through a rigorous training program to prepare for the trial reads. During the study, our Technical Services team continuously scrutinize the data with custom-developed anomaly detection tools, project-specific, pre-programmed QC checks (e.g. for implausible data beyond physiological ranges), and additional inspections for data inconsistencies. We monitor reviewer agreement statistics and trends over time to make sure that the reported imaging outcomes are fully supported by the source images.

In addition to our custom-developed quality assurance programs for clinical trials, MMI is an ISO 9001:2015-certified company and committed to continuous improvement and delivering the highest standard of quality and reliability in our industry. Read more about MMI.

A = Diagnostically acceptable. No errors or minimal errors in either patient preparation, exposure, positioning, image (receptor) processing or image reconstruction and of sufficient image quality to answer the clinical question.

Radiographs can be evaluated prospectively by rating according to the above criteria and recording the rating as they are being viewed, or retrospectively by drawing a suitably representative sample of radiographs from clinical records at regular intervals and rating the image quality as above.

It is recommended that the quality ratings of radiographs are regularly analysed to determine the percentage of the total images produced that are categorised as A or N (see Quality Assessment of Radiographic Images Sept 2022 template (Word)). Analysis should be carried out at least every six months and the sample size should include at least 100 images [1]. When using more than one type of radiograph e.g. intra oral and panoramic images, results should be reported separately. 17dc91bb1f