Deep learning-based reconstruction for acceleration of lumbar spine MRI: a prospective comparison with standard MRI.

OBJECTIVE: To compare the image quality and diagnostic performance between standard turbo spin-echo MRI and accelerated MRI with deep learning (DL)-based image reconstruction for degenerative lumbar spine diseases. MATERIALS AND METHODS: Fifty patients who underwent both the standard and accelerated lumbar MRIs at a 1.5-T scanner for degenerative lumbar spine diseases were prospectively enrolled. DL reconstruction algorithm generated coarse (DL_coarse) and fine (DL_fine) images from the accelerated protocol. Image quality was quantitatively assessed in terms of signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) and qualitatively assessed using five-point visual scoring systems. The sensitivity and specificity of four radiologists for the diagnosis of degenerative diseases in both protocols were compared. RESULTS: The accelerated protocol reduced the average MRI acquisition time by 32.3% as compared to the standard protocol. As compared with standard images, DL_coarse and DL_fine showed significantly higher SNRs on T1-weighted images (T1WI; both p < .001) and T2-weighted images (T2WI; p = .002 and p < 0.001), higher CNRs on T1WI (both p < 0.001), and similar CNRs on T2WI (p = .49 and p = .27). The average radiologist assessment of overall image quality for DL_coarse and DL_fine was higher on sagittal T1WI (p = .04 and p < .001) and axial T2WI (p = .006 and p = .01) and similar on sagittal T2WI (p = .90 and p = .91). Both DL_coarse and DL_fine had better image quality of cauda equina and paraspinal muscles on axial T2WI (both p = .04 for cauda equina; p = .008 and p = .002 for paraspinal muscles). Differences in sensitivity and specificity for the detection of central canal stenosis and neural foraminal stenosis between standard and DL-reconstructed images were all statistically nonsignificant (p ≥ 0.05). CONCLUSION: DL-based protocol reduced MRI acquisition time without degrading image quality and diagnostic performance of readers for degenerative lumbar spine diseases. CLINICAL RELEVANCE STATEMENT: The deep learning (DL)-based reconstruction algorithm may be used to further accelerate spine MRI imaging to reduce patient discomfort and increase the cost efficiency of spine MRI imaging. KEY POINTS: • By using deep learning (DL)-based reconstruction algorithm in combination with the accelerated MRI protocol, the average acquisition time was reduced by 32.3% as compared with the standard protocol. • DL-reconstructed images had similar or better quantitative/qualitative overall image quality and similar or better image quality for the delineation of most individual anatomical structures. • The average radiologist's sensitivity and specificity for the detection of major degenerative lumbar spine diseases, including central canal stenosis, neural foraminal stenosis, and disc herniation, on standard and DL-reconstructed images, were similar.

Artificial Intelligence-Based Identification of Normal Chest Radiographs: A Simulation Study in a Multicenter Health Screening Cohort.

OBJECTIVE: This study aimed to investigate the feasibility of using artificial intelligence (AI) to identify normal chest radiography (CXR) from the worklist of radiologists in a health-screening environment. MATERIALS AND METHODS: This retrospective simulation study was conducted using the CXRs of 5887 adults (mean age ± standard deviation, 55.4 ± 11.8 years; male, 4329) from three health screening centers in South Korea using a commercial AI (Lunit INSIGHT CXR3, version 3.5.8.8). Three board-certified thoracic radiologists reviewed CXR images for referable thoracic abnormalities and grouped the images into those with visible referable abnormalities (identified as abnormal by at least one reader) and those with clearly visible referable abnormalities (identified as abnormal by at least two readers). With AI-based simulated exclusion of normal CXR images, the percentages of normal images sorted and abnormal images erroneously removed were analyzed. Additionally, in a random subsample of 480 patients, the ability to identify visible referable abnormalities was compared among AI-unassisted reading (i.e., all images read by human readers without AI), AI-assisted reading (i.e., all images read by human readers with AI assistance as concurrent readers), and reading with AI triage (i.e., human reading of only those rendered abnormal by AI). RESULTS: Of 5887 CXR images, 405 (6.9%) and 227 (3.9%) contained visible and clearly visible abnormalities, respectively. With AI-based triage, 42.9% (2354/5482) of normal CXR images were removed at the cost of erroneous removal of 3.5% (14/405) and 1.8% (4/227) of CXR images with visible and clearly visible abnormalities, respectively. In the diagnostic performance study, AI triage removed 41.6% (188/452) of normal images from the worklist without missing visible abnormalities and increased the specificity for some readers without decreasing sensitivity. CONCLUSION: This study suggests the feasibility of sorting and removing normal CXRs using AI with a tailored cut-off to increase efficiency and reduce the workload of radiologists.

AI-based improvement in lung cancer detection on chest radiographs: results of a multi-reader study in NLST dataset.

OBJECTIVE: Assess if deep learning-based artificial intelligence (AI) algorithm improves reader performance for lung cancer detection on chest X-rays (CXRs). METHODS: This reader study included 173 images from cancer-positive patients (n = 98) and 346 images from cancer-negative patients (n = 196) selected from National Lung Screening Trial (NLST). Eight readers, including three radiology residents, and five board-certified radiologists, participated in the observer performance test. AI algorithm provided image-level probability of pulmonary nodule or mass on CXRs and a heatmap of detected lesions. Reader performance was compared with AUC, sensitivity, specificity, false-positives per image (FPPI), and rates of chest CT recommendations. RESULTS: With AI, the average sensitivity of readers for the detection of visible lung cancer increased for residents, but was similar for radiologists compared to that without AI (0.61 [95% CI, 0.55-0.67] vs. 0.72 [95% CI, 0.66-0.77], p = 0.016 for residents, and 0.76 [95% CI, 0.72-0.81] vs. 0.76 [95% CI, 0.72-0.81, p = 1.00 for radiologists), while false-positive findings per image (FPPI) was similar for residents, but decreased for radiologists (0.15 [95% CI, 0.11-0.18] vs. 0.12 [95% CI, 0.09-0.16], p = 0.13 for residents, and 0.24 [95% CI, 0.20-0.29] vs. 0.17 [95% CI, 0.13-0.20], p < 0.001 for radiologists). With AI, the average rate of chest CT recommendation in patients positive for visible cancer increased for residents, but was similar for radiologists (54.7% [95% CI, 48.2-61.2%] vs. 70.2% [95% CI, 64.2-76.2%], p < 0.001 for residents and 72.5% [95% CI, 68.0-77.1%] vs. 73.9% [95% CI, 69.4-78.3%], p = 0.68 for radiologists), while that in cancer-negative patients was similar for residents, but decreased for radiologists (11.2% [95% CI, 9.6-13.1%] vs. 9.8% [95% CI, 8.0-11.6%], p = 0.32 for residents and 16.4% [95% CI, 14.7-18.2%] vs. 11.7% [95% CI, 10.2-13.3%], p < 0.001 for radiologists). CONCLUSIONS: AI algorithm can enhance the performance of readers for the detection of lung cancers on chest radiographs when used as second reader. KEY POINTS: • Reader study in the NLST dataset shows that AI algorithm had sensitivity benefit for residents and specificity benefit for radiologists for the detection of visible lung cancer. • With AI, radiology residents were able to recommend more chest CT examinations (54.7% vs 70.2%, p < 0.001) for patients with visible lung cancer. • With AI, radiologists recommended significantly less proportion of unnecessary chest CT examinations (16.4% vs. 11.7%, p < 0.001) in cancer-negative patients.

Validation of a Deep Learning Algorithm for the Detection of Malignant Pulmonary Nodules in Chest Radiographs.

Importance: The improvement of pulmonary nodule detection, which is a challenging task when using chest radiographs, may help to elevate the role of chest radiographs for the diagnosis of lung cancer. Objective: To assess the performance of a deep learning-based nodule detection algorithm for the detection of lung cancer on chest radiographs from participants in the National Lung Screening Trial (NLST). Design, Setting, and Participants: This diagnostic study used data from participants in the NLST ro assess the performance of a deep learning-based artificial intelligence (AI) algorithm for the detection of pulmonary nodules and lung cancer on chest radiographs using separate training (in-house) and validation (NLST) data sets. Baseline (T0) posteroanterior chest radiographs from 5485 participants (full T0 data set) were used to assess lung cancer detection performance, and a subset of 577 of these images (nodule data set) were used to assess nodule detection performance. Participants aged 55 to 74 years who currently or formerly (ie, quit within the past 15 years) smoked cigarettes for 30 pack-years or more were enrolled in the NLST at 23 US centers between August 2002 and April 2004. Information on lung cancer diagnoses was collected through December 31, 2009. Analyses were performed between August 20, 2019, and February 14, 2020. Exposures: Abnormality scores produced by the AI algorithm. Main Outcomes and Measures: The performance of an AI algorithm for the detection of lung nodules and lung cancer on radiographs, with lung cancer incidence and mortality as primary end points. Results: A total of 5485 participants (mean [SD] age, 61.7 [5.0] years; 3030 men [55.2%]) were included, with a median follow-up duration of 6.5 years (interquartile range, 6.1-6.9 years). For the nodule data set, the sensitivity and specificity of the AI algorithm for the detection of pulmonary nodules were 86.2% (95% CI, 77.8%-94.6%) and 85.0% (95% CI, 81.9%-88.1%), respectively. For the detection of all cancers, the sensitivity was 75.0% (95% CI, 62.8%-87.2%), the specificity was 83.3% (95% CI, 82.3%-84.3%), the positive predictive value was 3.8% (95% CI, 2.6%-5.0%), and the negative predictive value was 99.8% (95% CI, 99.6%-99.9%). For the detection of malignant pulmonary nodules in all images of the full T0 data set, the sensitivity was 94.1% (95% CI, 86.2%-100.0%), the specificity was 83.3% (95% CI, 82.3%-84.3%), the positive predictive value was 3.4% (95% CI, 2.2%-4.5%), and the negative predictive value was 100.0% (95% CI, 99.9%-100.0%). In digital radiographs of the nodule data set, the AI algorithm had higher sensitivity (96.0% [95% CI, 88.3%-100.0%] vs 88.0% [95% CI, 75.3%-100.0%]; P = .32) and higher specificity (93.2% [95% CI, 89.9%-96.5%] vs 82.8% [95% CI, 77.8%-87.8%]; P = .001) for nodule detection compared with the NLST radiologists. For malignant pulmonary nodule detection on digital radiographs of the full T0 data set, the sensitivity of the AI algorithm was higher (100.0% [95% CI, 100.0%-100.0%] vs 94.1% [95% CI, 82.9%-100.0%]; P = .32) compared with the NLST radiologists, and the specificity (90.9% [95% CI, 89.6%-92.1%] vs 91.0% [95% CI, 89.7%-92.2%]; P = .91), positive predictive value (8.2% [95% CI, 4.4%-11.9%] vs 7.8% [95% CI, 4.1%-11.5%]; P = .65), and negative predictive value (100.0% [95% CI, 100.0%-100.0%] vs 99.9% [95% CI, 99.8%-100.0%]; P = .32) were similar to those of NLST radiologists. Conclusions and Relevance: In this study, the AI algorithm performed better than NLST radiologists for the detection of pulmonary nodules on digital radiographs. When used as a second reader, the AI algorithm may help to detect lung cancer.

Effect of the Number of Pregnancies on Mortality Risk in HIV-Infected Women: a Prospective Cohort Study in Rural KwaZulu-Natal, South Africa.

We investigated whether mortality risk increases with the number of full-term pregnancies in HIV-infected women. Our study is based on data from the ACDIS cohort, collected in rural KwaZulu-Natal, South Africa. Mortality risk for different number of pregnancies in HIV-infected women was analyzed using Cox proportional hazards model. The risk of TB or AIDS mortality in HIV-uninfected women did not change with the number of full-term pregnancies, while the corresponding risk increased markedly in HIV-infected women. The risk of TB or AIDS mortality increased 1.48-fold (95% CI 1.25-1.75), 1.76-fold (95% CI 1.45-2.13), and 1.59-fold (95% CI 1.31-1.94) for one, two, and three or more full-term pregnancies compared to none, respectively. Finally, women who are young (age < 26) have greater risk of TB or AIDS mortality compared to women who are old (age ≥ 26), and women residing in rural areas have greater risk compared to women who reside in non-rural areas.

T2* Mapping from Multi-Echo Dixon Sequence on Gadoxetic Acid-Enhanced Magnetic Resonance Imaging for the Hepatic Fat Quantification: Can It Be Used for Hepatic Function Assessment?

OBJECTIVE: To evaluate the diagnostic value of T2* mapping using 3D multi-echo Dixon gradient echo acquisition on gadoxetic acid-enhanced liver magnetic resonance imaging (MRI) as a tool to evaluate hepatic function. MATERIALS AND METHODS: This retrospective study was approved by the IRB and the requirement of informed consent was waived. 242 patients who underwent liver MRIs, including 3D multi-echo Dixon fast gradient-recalled echo (GRE) sequence at 3T, before and after administration of gadoxetic acid, were included. Based on clinico-laboratory manifestation, the patients were classified as having normal liver function (NLF, n = 50), mild liver damage (MLD, n = 143), or severe liver damage (SLD, n = 30). The 3D multi-echo Dixon GRE sequence was obtained before, and 10 minutes after, gadoxetic acid administration. Pre- and post-contrast T2* values, as well as T2* reduction rates, were measured from T2* maps, and compared among the three groups. RESULTS: There was a significant difference in T2* reduction rates between the NLF and SLD groups (-0.2 ± 4.9% vs. 5.0 ± 6.9%, p = 0.002), and between the MLD and SLD groups (3.2 ± 6.0% vs. 5.0 ± 6.9%, p = 0.003). However, there was no significant difference in both the pre- and post-contrast T2* values among different liver function groups (p = 0.735 and 0.131, respectively). A receiver operating characteristic (ROC) curve analysis showed that the area under the ROC curve for using T2* reduction rates to differentiate the SLD group from the NLF group was 0.74 (95% confidence interval: 0.63-0.83). CONCLUSION: Incorporation of T2* mapping using 3D multi-echo Dixon GRE sequence in gadoxetic acid-enhanced liver MRI protocol may provide supplemental information for liver function deterioration in patients with SLD.

Prospective Comparison of Liver Stiffness Measurements between Two Point Shear Wave Elastography Methods: Virtual Touch Quantification and Elastography Point Quantification.

OBJECTIVE: To prospectively compare technical success rate and reliable measurements of virtual touch quantification (VTQ) elastography and elastography point quantification (ElastPQ), and to correlate liver stiffness (LS) measurements obtained by the two elastography techniques. MATERIALS AND METHODS: Our study included 85 patients, 80 of whom were previously diagnosed with chronic liver disease. The technical success rate and reliable measurements of the two kinds of point shear wave elastography (pSWE) techniques were compared by χ(2) analysis. LS values measured using the two techniques were compared and correlated via Wilcoxon signed-rank test, Spearman correlation coefficient, and 95% Bland-Altman limit of agreement. The intraobserver reproducibility of ElastPQ was determined by 95% Bland-Altman limit of agreement and intraclass correlation coefficient (ICC). RESULTS: The two pSWE techniques showed similar technical success rate (98.8% for VTQ vs. 95.3% for ElastPQ, p = 0.823) and reliable LS measurements (95.3% for VTQ vs. 90.6% for ElastPQ, p = 0.509). The mean LS measurements obtained by VTQ (1.71 ± 0.47 m/s) and ElastPQ (1.66 ± 0.41 m/s) were not significantly different (p = 0.209). The LS measurements obtained by the two techniques showed strong correlation (r = 0.820); in addition, the 95% limit of agreement of the two methods was 27.5% of the mean. Finally, the ICC of repeat ElastPQ measurements was 0.991. CONCLUSION: Virtual touch quantification and ElastPQ showed similar technical success rate and reliable measurements, with strongly correlated LS measurements. However, the two methods are not interchangeable due to the large limit of agreement.

Pt(IV) prodrugs designed to bind non-covalently to human serum albumin for drug delivery.

Albumin is the most abundant protein in human serum and drugs that are administered intravenously inevitably interact with it. We present here a series of platinum(IV) prodrugs designed specifically to enhance interaction with human serum albumin (HSA) for drug delivery. This goal is achieved by asymmetrically functionalizing the axial ligands of the prodrug so as to mimic the overall features of a fatty acid. Systematic variation of the length of the aliphatic tail tunes the cellular uptake and, consequently, the cytotoxicity of cis,cis,trans-[Pt(NH3)2Cl2(O2CCH2CH2COOH)(OCONHR)], 4, where R is a linear alkyl group. Investigation of an analogue bearing a fluorophore conjugated to the succinate ligand confirmed that these compounds are reduced by biological reductants with loss of the axial ligands. Intracellular release of cisplatin from 4 was further confirmed by observing the characteristic effects of cisplatin on the cell cycle and morphology following treatment with the prodrug. The most potent member of series 4, for which R is a hexadecyl chain, interacts with HSA in a 1:1 stoichiometry to form the platinum-protein complex 7. The interaction is non-covalent and extraction with octanol completely removes the prodrug from an aqueous solution of HSA. Construct 7 is robust and can be isolated following fast protein liquid chromatography. The nature of the tight interaction was investigated computationally, and these studies suggest that the prodrug is buried below the surface of the protein. Consequently, complexation to HSA is able to reduce the rate of reduction of the prodrug by ascorbate. The lead compound from series 4 also exhibited significant stability in whole human blood, attributed to its interaction with HSA. This favorable redox profile, in conjunction with the established nonimmunogenicity, biocompatibility, and enhanced tumor accumulation of HSA, produces a system that holds significant therapeutic potential.

Selective sterilization of Vibro parahaemolyticus from a bacterial mixture by low-amperage electric current.

The objective of this study was to investigate the possibility of using low-amperage electrical treatment (LAET) as a selective bacteriocide. Mixtures containing Escherichia coli, Staphylococcus aureus, and Vibrio parahaemolyticus were treated with different electric current intensities and for different times. The results showed that at 263 mA, treating bacteria for 100 ms eliminated all V. parahaemolyticus colonies. Although LAET reduced the populations of the three microorganisms, V. parahaemolyticus was more injured by LAET than S. aureus and E. coli when treated at the same processing conditions.