COMBINING HI-RESOLUTION SCAN MODE WITH DEEP LEARNING RECONSTRUCTION ALGORITHMS IN CARDIAC CT.

To investigate the impact of combining the high-resolution (Hi-res) scan mode with deep learning image reconstruction (DLIR) algorithm in CT. Two phantoms (Catphan600® and Lungman, small, medium, large size) were CT scanned using combinations of Hi-res/standard mode and high-definition (HD)/standard kernels. Images were reconstructed with ASiR-V and three levels of DLIR. Spatial resolution, noise and contrast-to-noise ratio (CNR) were assessed. The radiation dose was recorded. The spatial resolution increased using Hi-res & HD. Image noise in the Catphan600® (69%) and the Lungman (10-70%) significantly increased when Hi-res & HD was applied. DLIR reduced the mean noise (54%). The CNR was reduced (64%) for Hi-res & HD. The radiation dose increased for both small (+70%) and medium (+43%) Lungman phantoms but decreased slightly for the large ones (-3%) when Hi-res was applied. In conclusion, the Hi-res scan mode improved the spatial resolution. The HD kernel significantly increased the image noise. DLIR improved the image noise and CNR and did not affect the spatial resolution.

Agreement Between International Radiologists on the Appropriateness and Urgency in Lumbar Spine MRI Referrals.

Purpose: To determine how radiologists across health-care jurisdictions internationally assess the appropriateness and urgency levels of lumbar spine Magnetic Resonance Imaging MRI referrals. Patients and Methods: Clinical information was extracted from 203 lumbar spine MRI referrals. Texts were divided into 10 datasets and embedded into a software to facilitate the classification process. Participant radiologists were recruited at the Image Perception Lab, at the Radiological Society of North America Congress, 2019 and through the institution radiology network. Radiologists were asked if they use referral guidelines in their practices. Radiologists assigned appropriateness and urgency levels based on the referral text. Appropriateness level descriptors were: indicated, indicated but needs more information or not indicated. Urgency levels were categorized: urgent, semi-urgent, or not urgent. All cases containing neurological symptoms with/without red flags were extracted and exact agreement between radiologists' responses on the indication status was calculated. Results: Seventy radiologists from 25 countries participated; 42% of participants indicated non-use of referral guidelines. Poor-moderate radiology agreements were recorded for appropriateness and referral urgency level decisions. 79.6% of responses indicated that cases containing neurological symptoms with/without red flags were indicated for scanning. Conclusion: Despite referral guidelines promotion, nearly half of participants stated non-usage. Subsequently, a varied agreement levels were found in assigning the appropriateness of the referrals. Appropriateness of referrals with neurological symptoms (with/without red flags) recorded good agreement.

Automated vetting of radiology referrals: exploring natural language processing and traditional machine learning approaches.

BACKGROUND: With a significant increase in utilisation of computed tomography (CT), inappropriate imaging is a significant concern. Manual justification audits of radiology referrals are time-consuming and require financial resources. We aimed to retrospectively audit justification of brain CT referrals by applying natural language processing and traditional machine learning (ML) techniques to predict their justification based on the audit outcomes. METHODS: Two human experts retrospectively analysed justification of 375 adult brain CT referrals performed in a tertiary referral hospital during the 2019 calendar year, using a cloud-based platform for structured referring. Cohen's kappa was computed to measure inter-rater reliability. Referrals were represented as bag-of-words (BOW) and term frequency-inverse document frequency models. Text preprocessing techniques, including custom stop words (CSW) and spell correction (SC), were applied to the referral text. Logistic regression, random forest, and support vector machines (SVM) were used to predict the justification of referrals. A test set (300/75) was used to compute weighted accuracy, sensitivity, specificity, and the area under the curve (AUC). RESULTS: In total, 253 (67.5%) examinations were deemed justified, 75 (20.0%) as unjustified, and 47 (12.5%) as maybe justified. The agreement between the annotators was strong (κ = 0.835). The BOW + CSW + SC + SVM outperformed other binary models with a weighted accuracy of 92%, a sensitivity of 91%, a specificity of 93%, and an AUC of 0.948. CONCLUSIONS: Traditional ML models can accurately predict justification of unstructured brain CT referrals. This offers potential for automated justification analysis of CT referrals in clinical departments.

The impact of ASiR-V on abdominal CT radiation dose and image quality - A phantom study.

INTRODUCTION: To investigate how ASiR-V and kVp changes in Computed tomography (CT) affect radiation dose and image quality, when using automatic tube current modulation (ATCM) for different sized phantoms. METHODS: A liver-phantom with two different liver inserts (QRM, Moehrendorf, Germany), with extension rings, representing fat, were additionally applied to the phantom to simulate patients of different sizes (small: 30cm diameter, medium: 35cm and large: 40cm). Abdominal scans were performed on a 256 slice CT scanner (GE Healthcare, Milwaukee, WI, USA), with consistent pitch (0.992), rotation time (0.5s), slice thickness (0.625mm) and collimation (80mm), while other parameters were varied (kVp: 80/100/120/140; Noise Index: 13/22; mA interval 80-720, ASiR-V: 30/60/100%). CTDI and DLP was recorded for each scan and image quality was assessed using objective metrics in predefined anatomic areas (HU and noise). Radiation dose and image quality metrics were compared between protocols. RESULTS: CTDI decreased by 80% from ASIR-V 30% to ASiR-V 100% for prescribed NI 13, and by 79% for the prescribed NI of 22. For 100% ASiR-V and a prescribed NI of 22 the CTDI remained the same regardless of phantom size for the different kVp settings. Pairwise comparison revealed significant differences in CTDI (p < 0.0001) for all combinations of prescribed NI and ASIR-V levels, except the difference between ASIR-V levels of 30 and 60%, with a prescribed NI of 13 (p = 0.124). When data from the three phantom sizes were combined, increasing ASIR-V from 30-100%, resulted in noise decreases of 22% for NI of 13 and by 8% for NI of 22. Notably, image quality in the low contrast area of the liver insert was impaired when the large phantom was scanned with 100% ASiR-V and either 80/100kVp (NI 22), because of the large reduction in tube current applied (down to 80 mA). CONCLUSION: Substantial radiation dose reductions (up to 80%) resulted from increasing ASiR-V levels. However, image quality deteriorates when 100% ASiR-V is applied due to low applied tube current by the ATCM.

Optimization of region of interest luminances may enhance radiologists' light adaptation.

RATIONALE AND OBJECTIVES: Radiologic image details are best discriminated at luminance levels to which the eye is adapted. Recommendations that ambient light conditions are matched to overall monitor luminance to encourage appropriate adaptation are based on an assumption that clinically significant regions within the image match average monitor luminance. The current work examines this assumption. MATERIALS AND METHODS: Three image types were considered: posteroanterior (PA) chest; PA wrist; and computed tomography (CT) head. Luminance at clinically significant regions was measured at hilar region and peripheral lung (chest), distal radius (wrist), and supraventricular white matter (head). Average monitor luminances were calculated from measurements at 16 regions of the display face plate. Three ambient light levels-30, 100 and 400 lux-were employed. Thirty samples of each image type were used. RESULTS: Statistically significant differences were noted between average monitor luminances and clinically important regions of interest of up to a factor of 3.8, 2, and 6.3 for chest, wrist, and CT head images respectively (P < .0001). Values for the hilum of the chest and distal radius were higher than average monitor levels, whereas the reverse was observed for the peripheral lung and CT brain. Increasing ambient light had no impact on results. CONCLUSIONS: Clinically important radiologic information for common radiologic examinations is not being presented to observers in a way that facilitates optimized adaptation. This may have a significant impact on the ability of the observer to identify details with low contrast discriminability. The importance of image-processing algorithms focussing on clinically significant abnormalities rather than anatomic regions is highlighted.