Value of deep learning reconstruction of chest low-dose CT for image quality improvement and lung parenchyma assessment on lung window.

OBJECTIVES: To explore the performance of low-dose computed tomography (LDCT) with deep learning reconstruction (DLR) for the improvement of image quality and assessment of lung parenchyma. METHODS: Sixty patients underwent chest regular-dose CT (RDCT) followed by LDCT during the same examination. RDCT images were reconstructed with hybrid iterative reconstruction (HIR) and LDCT images were reconstructed with HIR and DLR, both using lung algorithm. Radiation exposure was recorded. Image noise, signal-to-noise ratio, and subjective image quality of normal and abnormal CT features were evaluated and compared using the Kruskal-Wallis test with Bonferroni correction. RESULTS: The effective radiation dose of LDCT was significantly lower than that of RDCT (0.29 ± 0.03 vs 2.05 ± 0.65 mSv, p < 0.001). The mean image noise ± standard deviation was 33.9 ± 4.7, 39.6 ± 4.3, and 31.1 ± 3.2 HU in RDCT, LDCT HIR-Strong, and LDCT DLR-Strong, respectively (p < 0.001). The overall image quality of LDCT DLR-Strong was significantly better than that of LDCT HIR-Strong (p < 0.001) and comparable to that of RDCT (p > 0.05). LDCT DLR-Strong was comparable to RDCT in evaluating solid nodules, increased attenuation, linear opacity, and airway lesions (all p > 0.05). The visualization of subsolid nodules and decreased attenuation was better with DLR than with HIR in LDCT but inferior to RDCT (all p < 0.05). CONCLUSION: LDCT DLR can effectively reduce image noise and improve image quality. LDCT DLR provides good performance for evaluating pulmonary lesions, except for subsolid nodules and decreased lung attenuation, compared to RDCT-HIR. CLINICAL RELEVANCE STATEMENT: The study prospectively evaluated the contribution of DLR applied to chest low-dose CT for image quality improvement and lung parenchyma assessment. DLR can be used to reduce radiation dose and keep image quality for several indications. KEY POINTS: • DLR enables LDCT maintaining image quality even with very low radiation doses. • Chest LDCT with DLR can be used to evaluate lung parenchymal lesions except for subsolid nodules and decreased lung attenuation. • Diagnosis of pulmonary emphysema or subsolid nodules may require higher radiation doses.

Significance of Ultra-Radical Surgery in Extensive Metastatic Ovarian Growing Teratoma Syndrome.

INTRODUCTION: The aim of the study was to evaluate the perioperative risks and outcomes of ultra-radical surgery in patients with extensive metastatic ovarian growing teratoma syndrome (GTS). METHODS: We conducted a retrospective study of patients with extensive metastatic ovarian GTS treated in our hospital between 2000 and 2022. Patients' clinical characteristics, surgical treatment, and outcomes were evaluated. RESULTS: Overall, 13 patients were identified, and the median age at diagnosis of ovarian immature teratoma (IT) was 24 years (range: 5-37). The median interval between IT diagnosis and presenting GTS was 8 months (range: 2-60), with a median surgery delay of 5 months (range: 3-300). Peritoneum and liver were the most commonly affected sites (100%), followed by bowel (12 patients, 92.3%), diaphragm (12 patients, 92.3%), adnexa (9 patients, 69.2%), omentum (8 patients, 61.5%), uterus (7 patients, 53.8%), in the descending order. The mean operation time was 316 min (range: 180-625), and the mean blood loss volume was 992 mL (range: 200-5,000). Peritoneal metastasectomy (13 patients, 100%), diaphragmatic metastasectomy (12 patients, 92.3%), metastasis removal from the bowel (8 patients, 61.5%), partial hepatectomy (4 patients, 30.8%), bowel excision and anastomosis (1 patient, 7.7%) were also applied to achieve optimal debulking. R0 was achieved in 9 (69.2%) patients. A high rate of intraoperative blood transfusion (8 patients, 61.5%) and admission to the intensive care unit (9 patients, 69.2%) were observed, and the median postoperative hospitalization time was 8 days (range: 4-22). After a median follow-up of 3.3 years, 9 patients were free of disease, and 4 were alive with stable residual diseases. CONCLUSION: The survival outcomes in extensive metastatic ovarian GTS were satisfactory after ultra-radical surgery, while a proper therapeutic plan should be established due to the high perioperative risks.

Can deep learning improve image quality of low-dose CT: a prospective study in interstitial lung disease.

OBJECTIVES: To investigate whether deep learning reconstruction (DLR) could keep image quality and reduce radiation dose in interstitial lung disease (ILD) patients compared with HRCT reconstructed with hybrid iterative reconstruction (hybrid-IR). METHODS: Seventy ILD patients were prospectively enrolled and underwent HRCT (120 kVp, automatic tube current) and LDCT (120 kVp, 30 mAs) scans. HRCT images were reconstructed with hybrid-IR (Adaptive Iterative Dose Reduction 3-Dimensional [AIDR3D], standard-setting); LDCT images were reconstructed with DLR (Advanced Intelligence Clear-IQ Engine [AiCE], lung/bone, mild/standard/strong setting). Image noise, streak artifact, overall image quality, and visualization of normal and abnormal features of ILD were evaluated. RESULTS: The mean radiation dose of LDCT was 38% of HRCT. Objective image noise of reconstructed LDCT images was 33.6 to 111.3% of HRCT, and signal-to-noise ratio (SNR) was 0.9 to 3.1 times of the latter (p < 0.001). LDCT-AiCE was not significantly different from or even better than HRCT in overall image quality and visualization of normal lung structures. LDCT-AiCE (lung, mild/standard/strong) showed progressively better recognition of ground glass opacity than HRCT-AIDR3D (p < 0.05, p < 0.01, p < 0.001), and LDCT-AiCE (lung, mild/standard/strong; bone, mild) was superior to HRCT-AIDR3D in visualization of architectural distortion (p < 0.01, p < 0.01, p < 0.01; p < 0.05). LDCT-AiCE (bone, strong) was better than HRCT-AIDR3D in the assessment of bronchiectasis and/or bronchiolectasis (p < 0.05). LDCT-AiCE (bone, mild/standard/strong) was significantly better at the visualization of honeycombing than HRCT-AIDR3D (p < 0.05, p < 0.05, p < 0.01). CONCLUSION: Deep learning reconstruction could effectively reduce radiation dose and keep image quality in ILD patients compared to HRCT with hybrid-IR. KEY POINTS: • Deep learning reconstruction was a novel image reconstruction algorithm based on deep convolutional neural networks. It was applied in chest CT studies and received auspicious results. • HRCT plays an essential role in the whole process of diagnosis, treatment efficacy evaluation, and follow-ups for interstitial lung disease patients. However, cumulative radiation exposure could increase the risks of cancer. • Deep learning reconstruction method could effectively reduce the radiation dose and keep the image quality compared with HRCT reconstructed with hybrid iterative reconstruction in patients with interstitial lung disease.

Hybrid Clinical-Radiomics Model for Precisely Predicting the Invasiveness of Lung Adenocarcinoma Manifesting as Pure Ground-Glass Nodule.

RATIONALE AND OBJECTIVES: To identify whether the radiomics features of computed tomography (CT) allowed for the preoperative discrimination of the invasiveness of lung adenocarcinomas manifesting as pure ground-glass nodules (pGGNs) and further to develop and compare different predictive models. MATERIALS AND METHODS: We retrospectively included 187 lung adenocarcinomas presenting as pGGNs (66 preinvasive lesions and 121 invasive lesions), which were randomly divided into the training and test sets (8:2). Radiomics features were extracted from non-enhanced CT images. Clinical features, including patient's demographic characteristics, smoking status, and conventional CT features that reflect tumor's morphology and surrounding information were also collected. Intraclass correlation coefficient and ℓ2.1-norm minimization were used to identify influential feature subset which was then used to build three predictive models (clinical, radiomics, and clinical-radiomics models) with the gradient boosting regression tree classifier. The performances of the predictive models were evaluated using the area under the curve (AUC). RESULTS: Of the 1409 radiomics features and 27 clinical feature subtypes, 102 features were selected to construct the hybrid clinical-radiomics model, which achieved the best discriminative power (AUC = 0.934 and 0.929 in training and test set). The radiomics model showed comparable predictive performance (AUC = 0.911 and 0.901 in training and test set) compared to the clinical model (AUC = 0.911 and 0.894 in training and test set). CONCLUSION: The radiomics model showed good predictive performance in discriminating invasive lesions from preinvasive lesions for lung adenocarcinomas presenting as pGGNs. Its performance can be further improved by adding clinical features.

Individualized nomogram for predicting ALK rearrangement status in lung adenocarcinoma patients.

OBJECTIVES: To develop a nomogram to identify anaplastic lymphoma kinase (ALK) mutations in lung adenocarcinoma patients using clinical, CT, PET/CT, and histopathological features. METHODS: This retrospective study included 399 lung adenocarcinoma patients (129 ALK-rearranged patients and 270 ALK-negative patients) that were randomly divided into a training cohort and an internal validation cohort (4:1 ratio). Clinical factors, radiologist-defined CT features, maximum standard uptake values (SUVmax), and histopathological features were used to construct predictive models with stepwise backward-selection multivariate logistic regression (MLR). The models were then evaluated using the AUC. The integrated model was compared to the clinico-radiological model using the DeLong test to evaluate the role of histopathological features. An associated individualized nomogram was established. RESULTS: The integrated model reached an AUC of 0.918 (95% CI, 0.886-0.950), sensitivity of 0.774, and specificity of 0.934 in the training cohort and an AUC of 0.857 (95% CI, 0.777-0.937), sensitivity of 0.739, and specificity of 0.810 in the validation cohort. The MLR analysis showed that younger age, never smoker, lymph node enlargement, the presence of cavity, high SUVmax, solid or micropapillary predominant histology subtype, and local invasiveness were strong and independent predictors of ALK rearrangements. The nomogram calculated the risk of harboring ALK mutation for lung adenocarcinoma patients and exhibited a good generalization ability. CONCLUSION: Our study demonstrates that histopathological features added value to the imaging characteristics-based model. The nomogram with clinical, imaging, and histopathological features can serve as a supplementary non-invasive tool to evaluate the probability of ALK rearrangement in lung adenocarcinoma. KEY POINTS: • The developed nomogram can accurately predict the probability of lung adenocarcinoma harboring ALK-fused gene. • Pathological analysis is important to predict ALK rearrangement in lung adenocarcinoma. • Lung adenocarcinoma with lepidic predominant growth pattern and TTF-1 negativity is unlikely to have ALK rearrangement.

Distinctive Clinical Characteristics and Outcome of ILD-Onset Rheumatoid Arthritis and ACPA-Positive ILD: a Longitudinal Cohort of 282 Cases.

The aim of this study is to investigate the clinical features and outcome of interstitial lung disease (ILD)-onset rheumatoid arthritis (RA) and anti-citrullinated protein antibody (ACPA)-positive ILD-only patients. Arthritis-onset and ILD-onset RA-ILD and ACPA-positive ILD-only patients consecutively admitted to Peking Union Medical College Hospital from January 2008 to December 2017 were enrolled and followed-up. Their demographic, clinical, and laboratory features as well as outcome were collected and analyzed. Compared with arthritis-onset RA-ILD (n = 166, median arthritis-to-ILD interval: 60 months), the ILD-onset RA-ILD (n = 75, median ILD-to-arthritis interval: 2 months) had less rheumatoid nodules and higher titer of ACPA, and manifested more stable ILD (median estimated progression-free survival: 120 vs. 100 months, p = 0.019). Elder age (≥ 65 years) at ILD diagnosis and UIP pattern were associated with ILD progression by both univariate and Cox hazards modeling analysis (p < 0.05). In ACPA-positive ILD-only patients (n = 41), arthritis developed in 7 (17.1%) female patients after a median interval of 24 months. ACPA-positive ILD who subsequently developed arthritis exhibited higher frequency of rheumatoid factor (RF), higher titer of ACPA, and higher levels of ESR and CRP (p < 0.05). Multivariate regression analysis showed that positive RF (OR 12.55, 95% CI 1.31 to 120.48) was the independent risk factor for arthritis development in ACPA-positive ILD-only patients. ILD-onset RA-ILD had more stable ILD compared with arthritis-onset RA-ILD. ACPA-positive ILD patients with positive RF are at increased risk of developing RA.

[Chest High-resolution Computed Tomography Imaging Features of Lung Involvement in Rheumatoid Arthritis].

Objective To explore the chest high-resolution computed tomography (HRCT) features in patients with rheumatoid arthritis (RA) complicated with pulmonary involvement. Methods Totally 161 patients with RA with lung involvement were collected from June 2014 to May 2018. The chest HRCT findings were retrospectively analyzed. According to the imaging features as well as the results of history taking,pulmonary function test,pathology,and bronchoalveolar lavage fluid test,RA-related lung diseases (RA-LD) were classified and their clinical characteristics were compared. Results These 161 RA-LD patients (56 males and 105 females) whose mean age at diagnosis was (60.7±12.8) years (14-85 years) included 87 cases of usual interstitial pneumonia (UIP) (including 16 cases of possible UIP),44 cases of non-specific interstitial pneumonia (NSIP),10 cases of organizing pneumonia,7 cases of lymphocytic interstitial pneumonia,9 cases of small airway disease (SAD) (including 8 cases of bronchiolitis obliterans and 1 case of follicular bronchiolitis),and 4 other lung manifestations (including 3 cases of diffuse alveolar hemorrhage and 1 case of rheumatoid nodules). The UIP group had the oldest average age [(63.3±12.1) years old] and the highest smoking rate (41.4%). The SAD group had the youngest average age [(54.7±15.1) years old] and there was no smoking history. There were significant differences between these two groups (P=0.020,P<0.001). Seventy patients (43.5%) with RA-LD were complicated with pleural lesions. Conclusions RA involving the lung is common and has varied imaging manifestations,with interstitial lung diseases (mainly UIP and NSIP) being the most important manifestations. RA patients should undergo lung HRCT as early as possible to identify the lung involvement and related types.

Clinical, Conventional CT and Radiomic Feature-Based Machine Learning Models for Predicting ALK Rearrangement Status in Lung Adenocarcinoma Patients.

Objectives: To predict the anaplastic lymphoma kinase (ALK) mutations in lung adenocarcinoma patients non-invasively with machine learning models that combine clinical, conventional CT and radiomic features. Methods: This retrospective study included 335 lung adenocarcinoma patients who were randomly divided into a primary cohort (268 patients; 90 ALK-rearranged; and 178 ALK wild-type) and a test cohort (67 patients; 22 ALK-rearranged; and 45 ALK wild-type). One thousand two hundred and eighteen quantitative radiomic features were extracted from the semi-automatically delineated volume of interest (VOI) of the entire tumor using both the original and the pre-processed non-enhanced CT images. Twelve conventional CT features and seven clinical features were also collected. Normalized features were selected using a sequential of the F-test-based method, the density-based spatial clustering of applications with noise (DBSCAN) method, and the recursive feature elimination (RFE) method. Selected features were then used to build three predictive models (radiomic, radiological, and integrated models) for the ALK-rearranged phenotype by a soft voting classifier. Models were evaluated in the test cohort using the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity, and the performances of three models were compared using the DeLong test. Results: Our results showed that the addition of clinical information and conventional CT features significantly enhanced the validation performance of the radiomic model in the primary cohort (AUC = 0.83-0.88, P = 0.01), but not in the test cohort (AUC = 0.80-0.88, P = 0.29). The majority of radiomic features associated with ALK mutations reflected information around and within the high-intensity voxels of lesions. The presence of the cavity and left lower lobe location were new imaging phenotypic patterns in association with ALK-rearranged tumors. Current smoking was strongly correlated with non-ALK-mutated lung adenocarcinoma. Conclusions: Our study demonstrates that radiomics-derived machine learning models can potentially serve as a non-invasive tool to identify ALK mutation of lung adenocarcinoma.

Programmable optical pulse repetition rate multiplication via spectral phase manipulation.

Flexible phase patterns for optical pulse repetition rate multiplication (PRRM) are proposed and experimentally demonstrated via spectral phase-only manipulation. We introduce formulas of the phase condition for power lossless PPRM with arbitrary multiplication factors and undistorted temporal pulse profiles. For some multiplication factors the solution extends PRRM phase patterns from reported phase conditions to more flexible phase patterns, inspiring potentials of further devices available for PRRM. This flexibility also benefits PRRM when we use the reported devices. As a proof of concept, we numerically and experimentally demonstrate PRRM with multiplication factors up to eight by programming the spectral phase using an optical wave-shaper (OWS), involving different phase patterns. In practice, manipulation of the spectral phase induces spectral amplitude variations due to the intrinsic property limitation of the OWS. We quantitatively characterize this limitation and select a suitable phase pattern from our new solution to achieve a uniform temporal pulse train but with no spectral amplitude trimming.

High sensitivity microwave phase noise analyzer based on a phase locked optoelectronic oscillator.

Phase noise is a key parameter to evaluate the short-term stability of a microwave oscillator. This metric is of major concern for many applications. A phase locked loop (PLL) is widely used to extract the phase noise. However, due to the limitation of the phase noise of the reference, it is still a technical challenge to precisely characterize the phase noise of a high frequency carrier. To address this issue, we propose a high sensitivity microwave phase noise analyzer by using a photonic-based reference. By combining an optoelectronic oscillator (OEO) and a direct digital synthesizer, we achieve a 9 GHz to 11 GHz frequency tunable reference with phase noise of -140 dBc/Hz at 10 kHz offset, side-mode suppression ratio of 128 dB, and frequency switching time of 176 ns. Thanks to this low phase noise reference, we attain an X-band phase noise analyzer with an excellent sensitivity of -139 dBc/Hz at 10 kHz offset without cross-correlation. This is the first time to realize a PLL-based phase noise analyzer utilizing an OEO. We thoroughly present a theoretical analysis of our proposed system. Benefiting from the OEO's phase noise independent of frequency, the operation frequency of our proposed system can be extended to the millimeter-wave range while maintaining high sensitivity.

Wideband tunable optoelectronic oscillator based on the deamplification of stimulated Brillouin scattering.

A wideband tunable optoelectronic oscillator (OEO) based on the deamplification of stimulated Brillouin scattering (SBS) is proposed and experimentally demonstrated. A tunable single passband microwave photonic filter (MPF) utilizing phase modulation and SBS deamplification is used to realize the tunability of the OEO. Theoretical analysis of the MPF and phase noise performance of the OEO are presented. The frequency response of the MPF is determined by the + 1st sideband attenuation due to SBS deamplification and phase shift difference between the two sidebands due to chromatic dispersion and SBS. The close-in (< 1 MHz) phase noise of the proposed OEO is shown to be dominated by the laser frequency noise via phase shift of SBS. The conversion of the laser frequency noise to the close-in phase noise of the proposed OEO is effectively reduced compared with the OEO based on amplification by SBS. Tunable 7 to 40 GHz signals are experimentally obtained. The single-sideband (SSB) phase noise at 10 kHz offset is -128 dBc/Hz for 10.30 GHz signal. Compared with the OEO based on SBS amplification, the proposed OEO can achieve a phase noise performance improvement beyond 20 dB at 10 kHz offset. The maximum frequency and power drifts at 10.69 GHz are within 1 ppm and 1.4 dB during 1000 seconds, respectively. To achieve better close-in phase noise performance, lower frequency noise laser and higher pump power are preferred. The experimental results agree well with the theoretical models.