Search

ObjectiveAutomated speech recognition (ASR) systems have become increasingly sophisticated, accurate, and deployable on many digital devices, including on a smartphone. This pilot study aims to examine the speech recognition performance of ASR apps using audiological speech tests. In addition, we compare ASR speech recognition performance to normal hearing and hearing impaired listeners and evaluate if standard clinical audiological tests are a meaningful and quick measure of the performance of ASR apps.MethodsFour apps have been tested on a smartphone, respectively AVA, Earfy, Live Transcribe, and Speechy. The Dutch audiological speech tests performed were speech audiometry in quiet (Dutch CNC-test), Digits-in-Noise (DIN)-test with steady-state speech-shaped noise, sentences in quiet and in averaged long-term speech-shaped spectrum noise (Plomp-test). For comparison, the app's ability to transcribe a spoken dialogue (Dutch and English) was tested.ResultsAll apps scored at least 50% phonemes correct on the Dutch CNC-test for a conversational speech intensity level (65 dB SPL) and achieved 90–100% phoneme recognition at higher intensity levels. On the DIN-test, AVA and Live Transcribe had the lowest (best) signal-to-noise ratio +8 dB. The lowest signal-to-noise measured with the Plomp-test was +8 to 9 dB for Earfy (Android) and Live Transcribe (Android). Overall, the word error rate for the dialogue in English (19–34%) was lower (better) than for the Dutch dialogue (25–66%).ConclusionThe performance of the apps was limited on audiological tests that provide little linguistic context or use low signal to noise levels. For Dutch audiological speech tests in quiet, ASR apps performed similarly to a person with a moderate hearing loss. In noise, the ASR apps performed more poorly than most profoundly deaf people using a hearing aid or cochlear implant. Adding new performance metrics including the semantic difference as a function of SNR and reverberation time could help to monitor and further improve ASR performance.

Purpose The purpose of this study was to assess, using an anthropomorphic digital phantom, the accuracy of algorithms in registering precontrast and contrast‐enhanced computed tomography (CT) chest images for generation of iodine maps of the pulmonary parenchyma via temporal subtraction. Materials and methods The XCAT phantom, with enhanced airway and pulmonary vessel structures, was used to simulate precontrast and contrast‐enhanced chest images at various inspiration levels and added CT simulation for realistic system noise. Differences in diaphragm position were varied between 0 and 20 mm, with the maximum chosen to exceed the 95th percentile found in a dataset of 100 clinical subtraction CTs. In addition, the influence of whole body movement, degree of iodine enhancement, beam hardening artifacts, presence of nodules and perfusion defects in the pulmonary parenchyma, and variation in noise on the registration were also investigated. Registration was performed using three lung registration algorithms - a commercial (algorithm A) and a prototype (algorithm B) version from Canon Medical Systems and an algorithm from the MEVIS Fraunhofer institute (algorithm C). For each algorithm, we calculated the voxel‐by‐voxel difference between the true deformation and the algorithm‐estimated deformation in the lungs. Results The median absolute residual error for all three algorithms was smaller than the voxel size (1.0 × 1.0 × 1.0 mm3) for up to an 8 mm diaphragm difference, which is the average difference in diaphragm levels found clinically, and increased with increasing difference in diaphragm position. At 20 mm diaphragm displacement, the median absolute residual error after registration was 0.85 mm (interquartile range, 0.51-1.47 mm) for algorithm A, 0.82 mm (0.50-1.40 mm) for algorithm B, and 0.91 mm (0.54-1.52 mm) for algorithm C. The largest errors were seen in the paracardiac regions and close to the diaphragm. The impact of all other evaluated conditions on the residual error varied, resulting in an increase in the median residual error lower than 0.1 mm for all algorithms, except in the case of whole body displacements for algorithm B, and with increased noise for algorithm C. Conclusion Motion correction software can compensate for respiratory and cardiac motion with a median residual error below 1 mm, which was smaller than the voxel size, with small differences among the tested registration algorithms for different conditions. Perfusion defects above 50 mm will be visible with the commercially available subtraction CT software, even in poorly registered areas, where the median residual error in that area was 7.7 mm.

The objective of this study was to compare the image quality of iodine maps derived from subtraction CT and from dual-energy CT (DECT) in patients with suspected pulmonary embolism (PE).In this prospective study conducted between July 2016 and April 2017, consecutive patients with suspected PE underwent unenhanced CT at 100 kV and dual-energy pulmonary CT angiography at 100 and 140 kV on a dual-source scanner. The scanner was set to generate subtraction and DECT iodine maps at similar radiation doses. In 55 patients (30 women, 25 men; mean age ± SD, 63.4 ± 11.9 years old), various subjective image quality criteria including diagnostic acceptability were rated on a 5-point scale by four radiologists and a radiology resident. In 29 patients (17 women, 12 men; mean age, 62.4 ± 11.7 years old) with confirmed perfusion defects, the signal-difference-to-noise ratio (SDNR) between perfusion defects and adjacent normally perfused parenchyma was measured in corresponding ROIs on subtraction and DECT iodine maps. McNemar and Wilcoxon signed-rank tests were used for statistical comparisons.Diagnostic acceptability was rated excellent or good in a mean of 67% (range, 31-80%) of subtraction CT studies and 36% (5-69%) of DECT studies (p0.05 for four of the five radiologists), mainly because of fewer artifacts on subtraction CT. Mean SDNR was marginally higher for subtraction CT than for DECT (18.6 vs 17.1, p = 0.06) and was significantly higher in the upper lobes (21.8 vs 17.9, p0.05).Radiologist-judged image quality of pulmonary iodine maps was higher for subtraction CT than for DECT with similar to higher SDNR. Subtraction CT is a software-only solution, so it may be an attractive alternative to DECT for depicting perfusion defects.

Contains fulltext : 229492.pdf (Publisher’s version ) (Open Access) OBJECTIVE: To compare nodule enhancement on subtraction CT iodine maps to that on dual-energy CT iodine maps using CT datasets acquired simultaneously. METHODS: A previously-acquired set of lung subtraction and dual-energy CT maps consisting of thirty patients with 95solid pulmonary nodules (>/=4mm diameter) was used. Nodules were annotated and segmented on CT angiography, and mean nodule enhancement in the iodine maps calculated. Three radiologists scored nodule visibility with both techniques on a 4-point scale. RESULTS: Mean nodule enhancement was higher (p

Background Dual-energy CT iodine maps are used to detect pulmonary embolism (PE) with CT angiography but require dedicated hardware. Subtraction CT, a software-only solution, results in iodine maps with high contrast-to-noise ratios. Purpose To compare the use of subtraction CT versus dual-energy CT iodine maps to CT angiography for PE detection. Materials and Methods In this prospective study ( https://clinicaltrials.gov , NCT02890706), 274 participants suspected of having PE underwent precontrast CT followed by contrast material-enhanced dual-energy CT angiography between July 2016 and April 2017. Iodine maps from dual-energy CT were derived. Subtraction maps (contrast-enhanced CT minus precontrast CT) were calculated after motion correction. Truth was established by expert consensus. A total of 75 randomly selected participants with and without PE (1:1 ratio) were evaluated by three radiologists and six radiology residents (blinded to final diagnosis) for the presence of PE using three types of CT: CT angiography alone, dual-energy CT, and subtraction CT. The partial area under the receiver operating characteristic curve (AUC) for the clinically relevant specificity region (maximum partial AUC, 0.11) was compared by using multireader multicase variance. A P value less than or equal to .025 was considered indicative of a significant difference due to multiple comparisons. Results There were 35 men and 40 women in the reader study (mean age, 63 years ± 12 [standard deviation]). The pooled sensitivities were not different (P ≥ .31 among techniques) (95% confidence intervals [CIs]: 67%, 89% for CT angiography; 72%, 91% for dual-energy CT; 70%, 91% for subtraction CT). However, pooled specificity was higher for subtraction CT (95% CI: 100%, 100%) than for CT angiography (95% CI: 89%, 97%) or dual-energy CT (95% CI: 89%, 98%) (P < .001). Partial AUCs for the average observer improved equally when adding iodine maps (subtraction CT [0.093] vs CT angiography [0.088], P = .03; dual-energy CT [0.094] vs CT angiography, P = .01; dual-energy CT vs subtraction CT, P = .68). Average reading times were equivalent (range, 97-101 seconds; P ≥ .41) among techniques. Conclusion Subtraction CT iodine maps had greater specificity than CT angiography alone in pulmonary embolism detection. Subtraction CT had comparable diagnostic performance to that of dual-energy CT, without the need for dedicated hardware. © RSNA, 2019 Online supplemental material is available for this article.

Purpose To determine the accuracy of registration algorithms, using an anthropomorphic digital phantom, in registering unenhanced and enhanced computed tomography (CT) chest images. Methods Lung subtraction CT generates pulmonary iodine maps by subtracting an unenhanced scan from an enhanced scan after image registration. This technique can be useful for detection of pulmonary embolism, characterization of nodule or mass perfusion, or for evaluation of pulmonary lesion growth at follow-up. The LUMIC challenge is aimed at comparing the performance of algorithms in registering simulated enhanced and unenhanced CT images of the XCAT anthropomorphic digital phantom (Duke University, Durham, North Carolina, U.S.A.). The simulated scans are available with two voxel sizes (anisotropic, 0.6 × 0.6 × 1.0 mm3, and isotropic, 1.0 × 1.0 × 1.0 mm3), and with varying differences in diaphragm levels between the CT scans: 3 mm (small difference), 8 mm (average clinical difference), and 20 mm (large difference), all without pulmonary pathology. Since the voxel-by-voxel true displacement between the unenhanced and enhanced phantom realizations is known, the residual error between the estimated displacement field and the known truth can be determined for all lung voxels. Results The results submitted in response to this challenge will be calculated as the median, 25th and 75th percentile of the residual values. Besides these values, whole residual error images will be generated, which will provide position-specific information on the performance of each algorithm. Three algorithms have already been evaluated, resulting in the following residual errors for the large diaphragm-position difference [median (25th – 75th percentile)]: 0.93 mm (0.52 mm – 1.58 mm), 0.92 mm (0.51 mm – 1.57 mm), and 0.93 mm (0.52 mm – 1.60 mm). For all three algorithms, the largest errors were seen in the paracardiac regions and close to the diaphragm. Conclusions This challenge, based on the use of a digital anthropomorphic phantom, is a useful way to not only determine the current performance level of registration algorithms world-wide, but also to directly compare their performance. In addition, given the availability of the resulting error location information, the participants will be able to identify problematic areas for their registration algorithms that might need further improvement. The challenge is available on https://lumic.grand-challenge.org .

Purpose To determine the impact of patient and acquisition parameters on the quantification of the enhancement of pulmonary parenchyma in subtraction computed tomography pulmonary angiography (CTPA) imaging in patients without pulmonary pathology. Methods 2515 patients underwent clinical CTPA with subtraction imaging on a 320-multidetector row CT scanner (Aquilion ONE VISION or GENESIS, Canon Medical Systems Corporation, Japan) between January 2013 and August 2017 for suspicion of pulmonary embolism. In subtraction CT, an unenhanced chest CT is subtracted from an enhanced CT after motion correction, resulting in an iodine map representing pulmonary perfusion. After examination of patient records and images, 74 patients (2.9 %) without any apparent pulmonary or systemic pathology were selected. The mean enhancement in circular regions of interest (ROI) in all lung lobes of the iodine maps, placed to avoid vessels depicted in the CTPA images, were calculated. Patient age, sex, BMI, and smoking habits, as well as CT scan time, diaphragm position and lung volume changes between the unenhanced and enhanced CT, type and volume of contrast, and enhancement in the aortic arch, pulmonary trunk and left atrium were collected. Linear regression analysis was used to evaluate the correlation between the parameters and the measured enhancement. Results The mean enhancement of the ROIs throughout the whole lung was 32.2 ± 21.6 HU. The enhancement in the lower lobes (39.4 ± 24.3 HU) was significantly higher than in the upper lobes (31.7 ± 22.3 HU, p r 2 = 0.54 p 0.001 ) , and with lung volume changes ( r 2 = 0.73 p 0.001 ) between the scans. No correlation was found between the mean enhancement and all other variables studied. Conclusions The enhancement of the pulmonary parenchyma on subtraction CT imaging in patients without pulmonary pathology varies widely. However, normal enhancement values correlate strongly with changes in diaphragm position and in pulmonary volume between scans. This implies that normalization of lung enhancement based on lung volume changes could improve clinical interpretation and would be the first step towards quantification of enhancement in subtraction CT imaging.