15 July 2021 in BMC Medical Imaging
Background: Lung region segmentation is an important stage of automated image-based approaches for the diagnosis of respiratory diseases. Manual methods executed by experts are considered the gold standard, but it is time consuming and the accuracy is dependent on radiologists’ experience. Automated methods are relatively fast and reproducible with potential to facilitate physician interpretation of images. However, these benefits are possible only after overcoming several challenges. The traditional methods that are formulated as a three-stage segmentation demonstrate promising results on normal CT data but perform poorly in the presence of pathological features and variations in image quality attributes. The implementation of deep learning methods that can demonstrate superior performance over traditional methods is dependent on the quantity, quality, cost and the time it takes to generate training data. Thus, efficient and clinically relevant automated segmentation method is desired for the diagnosis of respiratory diseases. Methods: We implement each of the three stages of traditional methods using deep learning methods trained on five different configurations of training data with ground truths obtained from the 3D Image Reconstruction for Comparison of Algorithm Database (3DIRCAD) and the Interstitial Lung Diseases (ILD) database. The data was augmented with the Lung Image Database Consortium (LIDC-IDRI) image collection and a realistic phantom. A convolutional neural network (CNN) at the preprocessing stage classifies the input into lung and none lung regions. The processing stage was implemented using a CNN-based U-net while the postprocessing stage utilize another U-net and CNN for contour refinement and filtering out false positives, respectively. Results: The performance of the proposed method was evaluated on 1230 and 1100 CT slices from the 3DIRCAD and ILD databases. We investigate the performance of the proposed method on five configurations of training data and three configurations of the segmentation system; three-stage segmentation and three-stage segmentation without a CNN classifier and contrast enhancement, respectively. The Dice-score recorded by the proposed method range from 0.76 to 0.95. Conclusion: The clinical relevance and segmentation accuracy of deep learning models can improve though deep learning-based three-stage segmentation, image quality evaluation and enhancement as well as augmenting the training data with large volume of cheap and quality training data. We propose a new and novel deep learning-based method of contour refinement.
17 April 2012 in Pediatric Radiology
1 May 2020 in Radiography
PAP.A. Blackburn Andersen
+7
1 May 2019 in Radiography
31 March 2017 in Radiography Open
LHLinn Therese Håkonsen Haug
Linn Therese Håkonsen Haug
Introduction: Radiographer´s usual role in the medical imaging chain is to acquire relevant and qualitatively good images that help the radiologist or physician to diagnose most accurately. After the image acquisition, the radiographer does a quality evaluation based on established imaging criteria to decide if the image is satisfactory, or otherwise reject it and subsequently take a new one. Contrary to expectations that the number of image rejects should decrease substantially with the introduction of digital imaging, a number of studies have shown that it has not, although the reasons for rejects has changed from exposure errors to positioning and centring errors. Very little research has been on examining how radiographers visually perceive and evaluate the X-ray images in this acceptance/rejection process.Purpose: Investigate how radiographers and radiography students visually perceives X-ray images in the process of accepting or rejecting them on basis of radiographic imaging criteria, and see if there are differences in strategies across experience levels.Materials and methods: Three radiography students and five radiographers with varying years of experience were given the task of accepting or rejecting shoulder and knee projection images based on positioning criteria. Using eye tracking, we measured the participants’ number and duration of gaze fixations within 1) the field of view defined by the monitor display, 2) the part of the monitor displaying the X-ray image only, and 3) the region within the X-ray images considered to be most relevant given the imaging criteria task. The quantitative eye-tracking measurements were followed-up by four qualitative questions.Results: Some differences in fixation patterns between the groups were found; the medium experienced radiographers spent statistically significant lesser number of fixations and lesser average single fixation durations than both the radiography students and the most experienced radiographers did, whereas the two latter groups scored almost equally. Conclusion: The study revealed that work experience might have some influence on how radiographers and radiography students assess X-ray images, but in subtler ways than expected. The study also revealed, however, quite large individual differences across experience.