Computer-aided automatic measurement of leg length on full leg radiographs.

OBJECTIVES: To develop and evaluate a deep learning (DL)-based system for measuring leg length on full leg radiographs of diverse patients, including those with orthopedic hardware implanted for surgical treatment. METHODS: This study retrospectively assessed 2767 X-ray scanograms of 2767 patients who did or did not have orthopedic hardware implanted between January 2016 and December 2019. A cascaded DL model was developed to localize the relevant landmarks on the pelvis, knees, and ankles required for measuring leg length. Statistical analysis was performed using the correlation coefficient analysis and Bland-Altman plots to assess the agreement between the reference standard and DL-calculated lengths. RESULTS: Testing data comprised 400 radiographs from 400 patients. Of these radiographs, 100 were from patients with orthopedic hardware implanted in their pelvis, knees, or ankles. For all testing data, leg lengths derived from the DL-based measurement system, with or without internal fixation devices, showed excellent agreement with the reference standard (femoral length, r = 0.99 (P < .001); root mean square error (RMSE) = 0.17 cm; mean difference, - 0.01 ± 0.17 cm; 95% limit of agreement (LoA), - 0.35 to 0.34; tibial length, r = 0.99 (P < .001); RMSE = 0.17 cm; mean difference, - 0.02 ± 0.17 cm, 95% LoA, - 0.34 to 0.31; and full leg length, r = 1.0 (P < .001); RMSE = 0.19 cm; mean difference, 0.05 ± 0.18 cm; 95% LoA, - 0.31 to 0.40). The mean time for leg length measurement for each patient using the DL-based system was 8.68 ± 0.18 s. CONCLUSION: The DL-based leg length measurement system could provide similar performance to radiologists in terms of accuracy and reliability for a diverse group of patients.

Evaluation of the feasibility of explainable computer-aided detection of cardiomegaly on chest radiographs using deep learning.

We examined the feasibility of explainable computer-aided detection of cardiomegaly in routine clinical practice using segmentation-based methods. Overall, 793 retrospectively acquired posterior-anterior (PA) chest X-ray images (CXRs) of 793 patients were used to train deep learning (DL) models for lung and heart segmentation. The training dataset included PA CXRs from two public datasets and in-house PA CXRs. Two fully automated segmentation-based methods using state-of-the-art DL models for lung and heart segmentation were developed. The diagnostic performance was assessed and the reliability of the automatic cardiothoracic ratio (CTR) calculation was determined using the mean absolute error and paired t-test. The effects of thoracic pathological conditions on performance were assessed using subgroup analysis. One thousand PA CXRs of 1000 patients (480 men, 520 women; mean age 63 ± 23 years) were included. The CTR values derived from the DL models and diagnostic performance exhibited excellent agreement with reference standards for the whole test dataset. Performance of segmentation-based methods differed based on thoracic conditions. When tested using CXRs with lesions obscuring heart borders, the performance was lower than that for other thoracic pathological findings. Thus, segmentation-based methods using DL could detect cardiomegaly; however, the feasibility of computer-aided detection of cardiomegaly without human intervention was limited.

Determination of optimal imaging settings for urolithiasis CT using filtered back projection (FBP), statistical iterative reconstruction (IR) and knowledge-based iterative model reconstruction (IMR): a physical human phantom study.

OBJECTIVE: The purpose of this study was to compare CT image quality for evaluating urolithiasis using filtered back projection (FBP), statistical iterative reconstruction (IR) and knowledge-based iterative model reconstruction (IMR) according to various scan parameters and radiation doses. METHODS: A 5 × 5 × 5 mm(3) uric acid stone was placed in a physical human phantom at the level of the pelvis. 3 tube voltages (120, 100 and 80 kV) and 4 current-time products (100, 70, 30 and 15 mAs) were implemented in 12 scans. Each scan was reconstructed with FBP, statistical IR (Levels 5-7) and knowledge-based IMR (soft-tissue Levels 1-3). The radiation dose, objective image quality and signal-to-noise ratio (SNR) were evaluated, and subjective assessments were performed. RESULTS: The effective doses ranged from 0.095 to 2.621 mSv. Knowledge-based IMR showed better objective image noise and SNR than did FBP and statistical IR. The subjective image noise of FBP was worse than that of statistical IR and knowledge-based IMR. The subjective assessment scores deteriorated after a break point of 100 kV and 30 mAs. CONCLUSION: At the setting of 100 kV and 30 mAs, the radiation dose can be decreased by approximately 84% while keeping the subjective image assessment. ADVANCES IN KNOWLEDGE: Patients with urolithiasis can be evaluated with ultralow-dose non-enhanced CT using a knowledge-based IMR algorithm at a substantially reduced radiation dose with the imaging quality preserved, thereby minimizing the risks of radiation exposure while providing clinically relevant diagnostic benefits for patients.

The monetary value of the man-mSv for Korean NPP radiation workers assessed by the radiation aversion factor.

The monetary value of the man-mSv for operators of Korean nuclear power plants (NPPs) was calculated using a radiation aversion factor based on a survey of NPP workers. Initially, the life expectancy in the population is 79.4 y, the average age of cancer occurrence is 60 y, the average annual wage for an electric worker is 56 000 $ y(-1) and the nominal risk coefficient induced by radiation is 4.2E(-5) mSv were used to evaluate the basic monetary value (α(base)) resulting in 45.6 $ mSv(-1). To investigate the degree of radiation aversion, the subject of the investigation was selected as the working radiation workers in 10 NPPs in Korea (Kori 1-2, Yeonggwang 1-3, Ulchin 1-3 and Wolseong 1-2). In August 2010, with the cooperation of KHNP and partner companies, a total of 2500 survey questionnaires to 10 NPPs (or 250 surveys to each NPP) were distributed to currently employed radiation workers. From these, 2157 responses were obtained between August and October 2010. The assessed radiation aversion factor and the monetary value of the man-mSv from the calculated radiation aversion factor were 1.26 and ∼50 $ in the 0-1 mSv range, 1.38 and ∼200 $ in the 1-5 mSv range, 1.52 and ∼1000 $ in the 5-10 mSv range, 1.65 and ∼4000 $ in the 10-20 mSv range and 1.74 and ∼8500 $ >20 mSv.

Radiation dose distribution for workers in South Korean nuclear power plants.

A total of 33 680 nuclear power plants (NPPs) workers were monitored and recorded from 1990 to 2007. According to the record, the average individual radiation dose has been decreasing continually from 3.20 mSv man(-1) in 1990 to 1.12 mSv man(-1) at the end of 2007. After the International Commission on Radiological Protection 60 recommendation was generalised in South Korea, no NPP workers received >20 mSv radiation, and the numbers of relatively highly exposed workers have been decreasing continuously. The age distribution of radiation workers in NPPs was composed mainly of 20-30 y olds (83 %) for 1990-1994 and 30-40 y olds (75 %) for 2003-2007. The difference in individual average dose by age was not significant. Most (77 %) of the NPP radiation exposures from 1990 to 2007 occurred mostly during the refueling period. With regard to exposure type, the majority of exposures was external exposures, representing 95 % of the total exposures, whereas internal exposures represented only 5 %. External effective dose was affected mainly by gamma radiation exposure, with an insignificant amount of neutron exposure. As for internal effective dose, tritium in the pressurised heavy water reactor was the biggest cause of exposure.