Improving Low-Dose Pediatric Abdominal CT by Using Convolutional Neural Networks

How subjective CT image quality assessment becomes surprisingly reliable: pairwise comparisons instead of Likert scale

OBJECTIVES

The aim of this study is to improve the reliability of subjective IQ assessment using a pairwise comparison (PC) method instead of a Likert scale method in abdominal CT scans.

METHODS

Abdominal CT scans (single-center) were retrospectively selected between September 2019 and February 2020 in a prior study. Sample variance in IQ was obtained by adding artificial noise using dedicated reconstruction software, including reconstructions with filtered backprojection and varying iterative reconstruction strengths. Two datasets (each n = 50) were composed with either higher or lower IQ variation with the 25 original scans being part of both datasets. Using in-house developed software, six observers (five radiologists, one resident) rated both datasets via both the PC method (forcing observers to choose preferred scans out of pairs of scans resulting in a ranking) and a 5-point Likert scale. The PC method was optimized using a sorting algorithm to minimize necessary comparisons. The inter- and intraobserver agreements were assessed for both methods with the intraclass correlation coefficient (ICC).

RESULTS

Twenty-five patients (mean age 61 years ± 15.5; 56% men) were evaluated. The ICC for interobserver agreement for the high-variation dataset increased from 0.665 (95%CI 0.396-0.814) to 0.785 (95%CI 0.676-0.867) when the PC method was used instead of a Likert scale. For the low-variation dataset, the ICC increased from 0.276 (95%CI 0.034-0.500) to 0.562 (95%CI 0.337-0.729). Intraobserver agreement increased for four out of six observers.

CONCLUSION

The PC method is more reliable for subjective IQ assessment indicated by improved inter- and intraobserver agreement.

CLINICAL RELEVANCE STATEMENT

This study shows that the pairwise comparison method is a more reliable method for subjective image quality assessment. Improved reliability is of key importance for optimization studies, validation of automatic image quality assessment algorithms, and training of AI algorithms.

KEY POINTS

• Subjective assessment of diagnostic image quality via Likert scale has limited reliability. • A pairwise comparison method improves the inter- and intraobserver agreement. • The pairwise comparison method is more reliable for CT optimization studies.

Deep learning-based noise reduction for coronary CT angiography: using four-dimensional noise-reduction images as the ground truth

Background

To assess low-contrast areas such as plaque and coronary artery stenosis, coronary computed tomography angiography (CCTA) needs to provide images with lower noise without increasing radiation doses.

Purpose

To develop a deep learning-based noise-reduction method for CCTA using four-dimensional noise reduction (4DNR) as the ground truth for supervised learning.

Material and Methods

\We retrospectively collected 100 retrospective ECG-gated CCTAs. We created 4DNR images using non-rigid registration and weighted averaging three timeline CCTA volumetric data with intervals of 50 ms in the mid-diastolic phase. Our method set the original reconstructed image as the input and the 4DNR as the target image and obtained the noise-reduced image via residual learning. We evaluated the objective image quality of the original and deep learning-based noise-reduction (DLNR) images based on the image noise of the aorta and the contrast-to-noise ratio (CNR) of the coronary arteries. Further, a board-certified radiologist evaluated the blurring of several heart structures using a 5-point Likert scale subjectively and assigned a coronary artery disease reporting and data system (CAD-RADS) category independently.

Results

DLNR CCTAs showed 64.5% lower image noise ( P < 0.001) and achieved a 2.9 times higher CNR of coronary arteries than that in original images, without significant blurring in subjective comparison ( P > 0.1). The intra-observer agreement of CAD-RADS in the DLNR image was excellent (0.87, 95% confidence interval = 0.77–0.99) with original CCTAs.

Conclusion

Our DLNR method supervised by 4DNR significantly reduced the image noise of CCTAs without affecting the assessment of coronary stenosis.

The current and future roles of artificial intelligence in pediatric radiology

Artificial intelligence (AI) is a broad and complicated concept that has begun to affect many areas of medicine, perhaps none so much as radiology. While pediatric radiology has been less affected than other radiology subspecialties, there are some well-developed and some nascent applications within the field. This review focuses on the use of AI within pediatric radiology for image interpretation, with descriptive summaries of the literature to date. We highlight common features that enable successful application of the technology, along with some of the limitations that can inhibit the development of this field. We present some ideas for further research in this area and challenges that must be overcome, with an understanding that technology often advances in unpredictable ways.

The clinical performance of ultra-low-dose shoulder CT scans: The assessment on image and physical 3D printing models

Objectives

Evaluation of the clinical performance of ultra-low-dose computed tomography (CT) images of the shoulder joint on image-based diagnosis and three-dimensional (3D) printing surgical planning.

Materials and methods

A total of 93 patients with displaced shoulder fractures were randomly divided into standard-dose, low-dose, and ultra-low-dose groups. Three-dimensional printing models of all patients’ shoulder joints were fabricated. The subjective image quality and 3D-printing model were evaluated by two senior orthopedic surgeons who were blinded to any scanning setting. A 3-point scale system was used to quantitatively assess the image quality and 3D printing model, where more than 2 points meant adequate level for clinical application.

Results

Compared with the standard dose protocol, ultra-low-dose technique reduced the radiation dose by 99.29% without loss of key image quality of fracture pattern. Regarding the subjective image quality, the assessment scores for groups of standard, low, and ultra-low doses were 3.00, 2.76, 2.00 points on scapula and humerus, and 3.00, 2.73, 2.44 points on clavicle. Scores of the three groups for the assessment of 3D printing models were 3.00, 2.80, 1.34 on scapula and humerus, and 3.00, 2.90, 2.06 on clavicle. In the ultra-low-dose group, 24 out of 33 (72.7%) 3D printing models of scapula and humerus received lower than 2 points of the evaluation score, while nearly 94% of the clavicle models reached the adequate level.

Conclusion

An ultra-low-dose protocol is adequate for the diagnosis of either displaced or non-displaced fractures of the shoulder joint even though minor flaws of images are present. Three-dimensional printing models of shoulder joints created from ultra-low-dose CT scans can be used for surgical planning at specific bone like the clavicle but perform insufficiently in the overall surgical planning for shoulder injuries due to the significant geometric flaws.

Segmental strain for scar detection in acute myocardial infarcts and in follow-up exams using non-contrast CMR cine sequences

Background

The purpose of the study was to investigate feasibility of infarct detection in segmental strain derived from non-contrast cardiac magnetic resonance (CMR) cine sequences in patients with acute myocardial infarction (AMI) and in follow-up (FU) exams.

Methods

57 patients with AMI (mean age 61 ± 12 years, CMR 2.8 ± 2 days after infarction) were retrospectively included, FU exams were available in 32 patients (35 ± 14 days after first CMR). 43 patients with normal CMR (54 ± 11 years) served as controls. Dedicated software (Segment CMR, Medviso) was used to calculate global and segmental strain derived from cine sequences. Cine short axis stacks and segmental circumferential strain calculations of every patient and control were presented to two blinded readers in random order, who were advised to identify potentially infarcted segments, blinded to LGE and clinical information.

Results

Impaired global strain was measured in AMI patients compared to controls (global peak circumferential strain [GPCS] p = 0.01; global peak longitudinal strain [GPLS] p = 0.04; global peak radial strain [GPRS] p = 0.01). In both imaging time points, mean segmental peak circumferential strain [SPCS] was impaired in infarcted tissue compared to remote segments (AMI: p = 0.03, FU: p = 0.02). SPCS values in infarcted segments were similar between AMI and FU (p = 0.8). In SPCS calculations, 141 from 189 acutely infarcted segments were accurately detected (74.6%), visual evaluation of correlating cine images detected 43.4% infarcts. In FU, 80% infarcted segments (91/114 segments) were detected in SPCS and 51.8% by visual evaluation of correlating short axis cine images (p = 0.01).

Conclusion

Segmental circumferential strain derived from routinely acquired native cine sequences detects nearly 75% of acute infarcts and 80% of infarcts in subacute follow-up CMR, significantly more than visual evaluation of correlating cine images alone. Acute infarcts may display only subtle impairment of wall motion and no obvious wall thinning, thus SPCS calculation might be helpful for scar detection in patients with acute infarcts, when LGE images are not available.

Characteristics of Computed Tomography Images for Patients with Acute Liver Injury Caused by Sepsis under Deep Learning Algorithm

This study was aimed at exploring the application of image segmentation based on full convolutional neural network (FCN) in liver computed tomography (CT) image segmentation and analyzing the clinical features of acute liver injury caused by sepsis. The Sigmoid function, encoder-decoder, and weighted cross entropy loss function were introduced and optimized based on FCN. The Dice value, precision, recall rate, volume overlap error (VOE), relative volume difference (RVD), and root mean square error (RMSE) values of the optimized algorithms were compared and analyzed. 92 patients with sepsis were selected as the research objects, and they were divided into a nonacute liver injury group (50 cases) and acute liver injury group (42 cases) based on whether they had acute liver injury. The differences in the proportion of patients with different disease histories, the proportion of patients with different infection sites, the number of organ failure, and the time of admission to intensive care unit (ICU) were compared between the two groups. It was found that the optimized window CT image Dice value after preprocessing (0.704 ± 0.06) was significantly higher than the other two methods (P < 0.05). The Dice value, precision, and recall rate of the optimized-FCN algorithm were (0.826 ± 0.06), (0.91 ± 0.08), and (0.88 ± 0.09), respectively, which were significantly higher than other algorithms (P < 0.05). The VOE, RVD, and RMSE values were (21.19 ± 1.97), (10.45 ± 1.02), and (0.25 ± 0.02), respectively, which were significantly lower than other algorithms (P < 0.05). The proportion of patients with a history of drinking in the nonacute liver injury group was lower than that in the acute liver injury group (P < 0.05), and the proportion of patients with a history of hypotension was greatly higher than that in the nonacute liver injury group (P < 0.01). CT images of sepsis patients with acute liver injury showed that large areas of liver parenchyma mixed with high-density hematoma, the number of organ failures, and the length of stay in ICU were significantly higher than those in the nonacute liver injury group (P < 0.05). It showed that the optimization algorithm based on FCN greatly improved the performance of CT image segmentation. Long-term drinking, low blood pressure, number of organ failures, and length of stay in ICU were all related to sepsis and acute liver injury. Conclusion in this study could provide a reference basis for the diagnosis and prognosis of acute liver injury caused by sepsis.

Current and emerging artificial intelligence applications in chest imaging: a pediatric perspective

Artificial intelligence (AI) applications for chest radiography and chest CT are among the most developed applications in radiology. More than 40 certified AI products are available for chest radiography or chest CT. These AI products cover a wide range of abnormalities, including pneumonia, pneumothorax and lung cancer. Most applications are aimed at detecting disease, complemented by products that characterize or quantify tissue. At present, none of the thoracic AI products is specifically designed for the pediatric population. However, some products developed to detect tuberculosis in adults are also applicable to children. Software is under development to detect early changes of cystic fibrosis on chest CT, which could be an interesting application for pediatric radiology. In this review, we give an overview of current AI products in thoracic radiology and cover recent literature about AI in chest radiography, with a focus on pediatric radiology. We also discuss possible pediatric applications.

Artificial intelligence development in pediatric body magnetic resonance imaging: best ideas to adapt from adults

Emerging manifestations of artificial intelligence (AI) have featured prominently in virtually all industries and facets of our lives. Within the radiology literature, AI has shown great promise in improving and augmenting radiologist workflow. In pediatric imaging, while greatest AI inroads have been made in musculoskeletal radiographs, there are certainly opportunities within thoracoabdominal MRI for AI to add significant value. In this paper, we briefly review non-interpretive and interpretive data science, with emphasis on potential avenues for advancement in pediatric body MRI based on similar work in adults. The discussion focuses on MRI image optimization, abdominal organ segmentation, and osseous lesion detection encountered during body MRI in children.

Current status of deep learning in abdominal image reconstruction

Abdominal magnetic resonance imaging (MRI) and computed tomography (CT) are commonly used for disease screening, diagnosis, and treatment guidance. However, abdominal MRI has disadvantages including slow speed and vulnerability to motions, while CT suffers from problems of radiation. It has been reported that deep learning reconstruction can solve such problems while maintaining good image quality. Recently, deep learning-based image reconstruction has become a hot topic in the field of medical imaging. This study reviews the latest research on deep learning reconstruction in abdominal imaging, including the widely used convolutional neural network, generative adversarial network, and recurrent neural network.

Artificial intelligence in paediatric radiology: Future opportunities

Artificial intelligence (AI) has received widespread and growing interest in healthcare, as a method to save time, cost and improve efficiencies. The high-performance statistics and diagnostic accuracies reported by using AI algorithms (with respect to predefined reference standards), particularly from image pattern recognition studies, have resulted in extensive applications proposed for clinical radiology, especially for enhanced image interpretation. Whilst certain sub-speciality areas in radiology, such as those relating to cancer screening, have received wide-spread attention in the media and scientific community, children's imaging has been hitherto neglected.In this article, we discuss a variety of possible 'use cases' in paediatric radiology from a patient pathway perspective where AI has either been implemented or shown early-stage feasibility, while also taking inspiration from the adult literature to propose potential areas for future development. We aim to demonstrate how a 'future, enhanced paediatric radiology service' could operate and to stimulate further discussion with avenues for research.