Endoscopic Rectal Ultrasound-Based Radiomics Analysis for the Prediction of Synchronous Liver Metastasis in Patients With Primary Rectal Cancer.

OBJECTIVES: To develop and validate an ultrasound-based radiomics model to predict synchronous liver metastases (SLM) in rectal cancer (RC) patients preoperatively. METHODS: Two hundred and thirty-nine RC patients were included in this study and randomly divided into training and validation cohorts. A total of 5936 radiomics features were calculated on the basis of ultrasound images to build a radiomic model and obtain a radiomics score (Rad-score) using logistic regression. Meanwhile, clinical characteristics were collected to construct a clinical model. The radiomics-clinical model was developed and validated by integrating the radiomics features with the selected clinical characteristics. The performances of three models were evaluated and compared through their discrimination, calibration, and clinical usefulness. RESULTS: The radiomics model was developed based on 13 radiomic features. The radiomics-clinical model, which incorporated Rad-score, CEA, and CA199, exhibited favorable discrimination and calibration with areas under the receiver operating characteristic curve (AUC) of 0.920 (95% CI: 0.874-0.965) in the training cohorts and 0.855 (95% CI: 0.759-0.951) in the validation cohorts. And the AUC of the radiomics-clinical model was 0.849 (95% CI: 0.771-0.927) for the training cohorts and 0.780 (95% CI: 0.655-0.905) for the validation cohorts, the clinical model was 0.811 (95% CI: 0.718-0.905) for the training cohorts and 0.805 (95% CI: 0.645-0.965) for the validation cohorts. Moreover, decision curve analysis (DCA) further confirmed the clinical utility of the radiomics-clinical model. CONCLUSIONS: The radiomics-clinical model performed satisfactory predictive performance, which can help improve clinical diagnosis performance and outcome prediction for SLM in RC patients.

A novel imaging scoring method for identifying facial canal dehiscence: an ultra-high-resolution CT study.

OBJECTIVES: Facial canal dehiscence (FCD), typically found in the tympanic segment, is a risk factor for facial nerve injury. An imaging scoring method was proposed to identify FCD based on ultra-high-resolution CT. METHODS: Forty patients (21 females and 19 males, mean age 44.3 ± 17.4 years), whose tympanic facial canal (FC) was examined during otological surgery, were divided into the FCD group (n = 29) and the control group (n = 11) based on surgical findings. Imaging appearance of tympanic FC was scored 0-3: 0 = no evident bony covering, 1 = discontinuous bony covering with linear deficiency, 2 = discontinuous bony covering with dotted deficiency, and 3 = continuous bony covering. Both lateral and inferior walls were assigned a score as LFCD and IFCD, respectively. An FCD score was calculated as LFCD + IFCD. The diagnostic value of the FCD score was tested using the ROC curve. RESULTS: The inter-observer agreement was moderate for the lateral wall (Cohen's κ coefficient 0.416, 95% CI 0.193-0.639), and good for the inferior wall (Cohen's κ coefficient 0.702, 95% CI 0.516-0.888). In the FCD group, the most common appearance for both walls was discontinuous bony covering with linear deficiency (LFCD = 1, 22/29, 75.9%; IFCD = 1, 15/29, 51.7%). An FCD score of less than 4 was associated with high sensitivity (0.82) and specificity (0.93) for identifying FCD, with an AUC of 0.928. CONCLUSIONS: Using the proposed scoring method, FCD score < 4 could identify FCD of the tympanic segment with high concordance with surgical findings. KEY POINTS: • Imaging appearance of the tympanic facial canal (FC) is divided into four types based on ultra-high-resolution CT images. • The most common appearance of FC with facial canal dehiscence (FCD) is discontinuous bony covering with linear deficiency. • An FCD score, consisting of scores of the lateral and inferior walls, less than 4 is highly indicative of FCD.

Assessment of cumulative cancer risk attributable to diagnostic X-ray radiation: a large cohort study.

OBJECTIVE: To assess the risk of cancer induced by diagnostic X-ray exposure in multiple radiological examinations and to explore the relevant influences to provide a reference for rational usage of X-ray examinations. METHODS: Data for all adult patients who underwent X-ray examinations from August 2004 to April 2020 in a general hospital was collected, including sex, age, primary diagnosis, and X-ray examination. Based on the Biological Effects of Ionizing Radiations report, age and sex and effective dose for a single X-ray examination were used to calculate the lifetime attributable risk (LAR). Patients whose cancer LAR values were in the top 5% were considered to have a high cancer risk; the factors influencing this status were explored by using multivariate logistic regression analyses. RESULTS: In total, 1,143,413 patients with 3,301,286 X-ray examinations were included. LARs of cancer incidence and death were < 0.2% and < 0.13% among 95% of patients and they were > 1% among 0.21% and 0.07% of patients. High risks of incidence and death were significantly associated with corrected exposure frequency (odds ratio [OR], 1.080 and 1.080), sex (OR, male vs. female, 0.421 and 0.372), and year of birth (OR, 1.088 and 1.054), with all p values < 0.001. Among 20 disease categories, congenital disease (OR, 3.792 and 4.024), genitourinary disease (OR, 3.608 and 3.202), digestive disease (OR, 3.247 and 3.272), and tumor disease (OR, 2.706 and 2.767) had the strongest associations with high risks of incidence and death (all p values < 0.001). CONCLUSIONS: Cancer risk induced by diagnostic X-ray examinations can be considered acceptable clinically. Patients having certain diseases are potentially at a relative higher risk due to recurrent examinations. KEY POINTS: • It was the first large-scale investigation of cumulative X-ray exposure in China, involving more than 3.3 million X-ray scans of all types of diagnostic X-ray examinations for about 1.1 million patients during the past 16 years. • The study revealed that the incidence risk of cancer induced by X-ray-related examinations was 0.01% on average, which was substantially lower than that of cancer induced by non-X-ray radiation. The risk could be considered acceptable clinically. • Patients having certain diseases were potentially at a relatively higher cancer risk due to recurrent X-ray examinations. The cumulative effect of X-ray exposure could not be ignored and was worthy of attention.

Clinical Feasibility of Automated Brain Tissue and Myelin Volumetry of Normal Brian Using Synthetic Magnetic Resonance Imaging With Fast Imaging Protocol: A Single-Center Pilot Study.

OBJECTIVE: This study aimed to investigate the clinical feasibility of synthetic magnetic resonance imaging (MRI) with fast imaging protocol for automated brain tissue and myelin volumetry in healthy volunteers at 3.0-T MRI. METHODS: Thirty-four healthy volunteers were scanned using synthetic MRI with 3 sets of scan parameters: groups Fast (FAS; 2 minutes, 29 seconds), Routine (ROU; 4 minutes, 7 seconds), and Research (RES; 7 minutes, 46 seconds). White matter (WM), gray matter (GM), cerebrospinal fluid (CSF), non-WM/GM/CSF (NoN), brain parenchymal volume (BPV), intracranial volume (ICV), and myelin volume (MYV) were compared between 3 groups. Linear correlation analysis was performed for measured volumes of groups FAS and ROU versus group RES. RESULTS: Significant differences were found in all the measured brain tissue volumes between groups FAS and ROU (P < 0.001), FAS and RES (P < 0.05), and ROU and RES (P < 0.05), except for NoN between groups ROU and RES (P = 0.0673), ICV between groups FAS and ROU (P = 0.2552), and ICV between groups FAS and RES (P = 0.4898). The intergroup coefficients of variation were 4.36% for WM, 6.39% for GM, 10.14% for CSF, 67.5% for NoN, 1.21% for BPV, 0.08% for ICV, and 5.88% for MYV. Strong linear correlation was demonstrated for WM, GM, CSF, BPV, ICV, and MYV (R = 0.9230-1.131) between FAS versus RES, and ROU versus RES. CONCLUSIONS: Using synthetic MRI with fast imaging protocol can change the measured brain tissue volumes of volunteers. It is necessary to use consistent acquisition protocols for comparing or following up cases quantitatively.

Chronic stress and turnover intention of resident physicians after experiencing COVID-19.

BACKGROUND: Previous studies have explored the stress and turnover intention of healthcare workers, but as important backup talents in the healthcare system, resident physicians have received little attention from researchers, especially after experiencing COVID-19. Therefore, this study aims to evaluate the chronic stress and turnover intention of resident physicians after experiencing COVID-19. METHODS: From June to August 2022, we conducted a questionnaire survey on resident physicians in the Children's Hospital of Hebei Province through the online platform (Wenjuanxing) to evaluate their chronic stress and turnover intention after experiencing COVID-19. For the collected data, we used frequency and percentage to make the statistical description, the Chi-square test to make a univariate analysis on the scores of chronic stress and turnover intention scale, and binary logistic regression analysis to explore the influencing factors of turnover intention. RESULTS: Out of 143 respondents, we finally received 127 questionnaires, with a response rate of 88.81%. Among 127 respondents, 80.31% of resident physicians experienced varying degrees of chronic stress (mild: 36.22%, moderate: 35.43%, severe: 8.66%), and 74.80% of resident physicians showed varying degrees of turnover intention (mild: 23.62%, moderate: 37.79%, severe: 13.39%). Moreover, age (OR = 0.772, P = 0.042), identity (OR = 8.648, P = 0.021), and chronic stress levels (mild: OR = 6.938, P = 0.003; moderate: OR = 44.049, P < 0.003; severe: OR = 46.141, P = 0.004) can significantly affect turnover intention. CONCLUSION: In this study, we reported a relatively high proportion of resident physicians with high chronic stress and high turnover intention after experiencing COVID-19. We suggest that the relevant departments should pay more attention to the resident physicians' group and formulate corresponding measures to solve the problems faced by the resident physicians and ensure the stability of the health human resources.

Potential of ultra-high-resolution CT in detecting osseous changes of temporomandibular joint: experiences in temporomandibular disorders.

BACKGROUND: Osseous changes of the temporomandibular joint (TMJ) are related to the progression of temporomandibular disorders (TMD), and computed tomography (CT) plays a vital role in disease evaluation. OBJECTIVE: The aims of this study were to evaluate the image quality and diagnostic value of ultra-high-resolution CT (U-HRCT) in TMD compared to cone-beam CT (CBCT). METHODS: TMD patients who underwent both CBCT and U-HRCT between November 2021 and September 2022 were retrospectively included. Image quality scores were assigned for four osseous structures (the cortical and trabecular bones of the condyle, articular eminence, and glenoid fossa) by two independent observers from Score 1 (unacceptable) to Score 5 (excellent). Diagnostic classification of TMD was categorized as follows: Class A (no evident lesion), Class B (indeterminate condition) and Class C (definitive lesion). Image quality scores and diagnostic classifications were compared between CBCT and U-HRCT. The Cohen's Kappa test, Wilcoxon signed-rank test, Chi-square test and Fisher's exact test were conducted for statistical analysis. RESULTS: Thirty TMD patients (median age, 30 years; interquartile range, 26-43 years; 25 females) with 60 TMJs were enrolled. Image quality scores were higher for U-HRCT than for CBCT by both observers (all Ps < 0.001). Definitive diagnoses (Class A and C) were achieved in more cases with U-HRCT than with CBCT (93.3% vs. 65.0%, Fisher's exact value = 7.959, P = 0.012). Among the 21 cases which were ambiguously diagnosed (Class B) by CBCT, definitive diagnosis was achieved for 17 cases (81.0%) using U-HRCT. CONCLUSIONS: U-HRCT can identify osseous changes in TMD, providing improved image quality and a more definitive diagnosis, which makes it a feasible diagnostic imaging method for TMD.

Morphological Neuroimaging Biomarkers for Tinnitus: Evidence Obtained by Applying Machine Learning.

According to previous studies, many neuroanatomical alterations have been detected in patients with tinnitus. However, the results of these studies have been inconsistent. The objective of this study was to explore the cortical/subcortical morphological neuroimaging biomarkers that may characterize idiopathic tinnitus using machine learning methods. Forty-six patients with idiopathic tinnitus and fifty-six healthy subjects were included in this study. For each subject, the gray matter volume of 61 brain regions was extracted as an original feature pool. From this feature pool, a hybrid feature selection algorithm combining the F-score and sequential forward floating selection (SFFS) methods was performed to select features. Then, the selected features were used to train a support vector machine (SVM) model. The area under the curve (AUC) and accuracy were used to assess the performance of the classification model. As a result, a combination of 13 cortical/subcortical brain regions was found to have the highest classification accuracy for effectively differentiating patients with tinnitus from healthy subjects. These brain regions include the bilateral hypothalamus, right insula, bilateral superior temporal gyrus, left rostral middle frontal gyrus, bilateral inferior temporal gyrus, right inferior parietal lobule, right transverse temporal gyrus, right middle temporal gyrus, right cingulate gyrus, and left superior frontal gyrus. The accuracy in the training and test datasets was 80.49% and 80.00%, respectively, and the AUC was 0.8586. To the best of our knowledge, this is the first study to elucidate brain morphological changes in patients with tinnitus by applying an SVM classifier. This study provides validated cortical/subcortical morphological neuroimaging biomarkers to differentiate patients with tinnitus from healthy subjects and contributes to the understanding of neuroanatomical alterations in patients with tinnitus.

Imaging re-evaluation of the tympanic segment of the facial nerve canal using cone-beam computed tomography compared with multi-slice computed tomography.

PURPOSE: This study aims to evaluate the imaging findings of cone-beam computed tomography (CBCT) in displaying subtle structures of the tympanic segment of the facial nerve canal in human cadaver heads compared with multi-slice computed tomography (MSCT). METHODS: Between January 2017 and July 2017, images of the tympanic segment of the facial nerve canal acquired from 73 human cadaver ears by both CBCT and MSCT were prospectively studied. Then, images of the lateral and inferior walls of the tympanic segment were scored using standard imaging slices through a four-point rating scale. Subsequently, the detailed findings of these two imaging modalities were recorded and compared, including interruptions of the bony walls, thread-like bony tubes connected with the walls, and separations in the cavity. The Wilcoxon signed-rank test was used to investigate the differences between scores derived by CBCT and MSCT. RESULTS: The mean score in the inferior and lateral walls by CBCT were significantly higher than that by MSCT (P = 0.000-0.005), which ranged from 2.0 (1.5, 2.5) to 3.5 (3.0, 4.0), and from 1.5 (1.0, 2.0) to 3.5 (2.5, 4.0), respectively. The interruption of the walls was most common at the anterior part of the inferior wall (38/73 cases). Furthermore, thread-like bony tubes were evident in 18 ears, which connected with the anterior part of the inferior wall (18/73 cases). Moreover, separation was found in 22 ears in the posterior part (22/73 cases). CONCLUSIONS: CBCT can readily demonstrate subtle imaging findings of the tympanic segment of the facial nerve canal.

Odd-Even Effect in Synthesis of Mesoporous Silica Using Long-Chain Acyl-L-Alanine Sodium Salt Templating.

In this research, hexagonal and cubic mesoporous silica with ordered parallel pore channels was synthesized using odd chain-length N-undecanoyl-L-alanine sodium salt and even chain-length N-lauroyl-L-alanine sodium salt as template respectively. Aminopropylsiloxane was used as the co-structure-directing agents (CSDA). The ordered mesostructure was characterized by infrared spectroscopy, small X-ray diffraction patterns (XRD), scanning electron microscope (SEM), trasmission electron microscope (TEM), and nitrogen sorption analysis. The results indicated that mesoporous silica which was prepared by asymmetric odd chain-length surfactants presented a looser strucuture with large volume than mesoporous silica prepared by the even chain-length surfactant. It led to the transformation from 2D hexagonal (p6mm) phase to cubic (Ia¯3d) mesophase.

Optic Perineuritis in Behçet Disease.

BACKGROUND: Optic perineuritis (OPN), an uncommon optic neuropathy, has previously not been described in patients with Behçet disease (BD). We conducted this study to describe the clinical features, response to treatment, and outcome of OPN due to BD, with particular emphasis on those features that might distinguish this from the idiopathic variety. METHODS: This is a retrospective, case series review of all patients with a diagnosis of OPN seen in a hospital-based neurology department from 2008 to 2014 who also met the international criteria for the diagnosis of BD. RESULTS: Twenty-one patients with OPN were identified, of whom 10 (12 eyes) met the criteria for BD. OPN developed 2-10 years (mean, 4 years) after onset of BD, but the diagnosis of BD was made only after onset of OPN in 6. Nine of 12 eyes (75%) had severe visual loss (≤20/200), and 80% of patients progressed over several days from onset. After high-dose corticosteroid treatment, all patients experienced relief of pain, and 5 patients (50%) showed improved visual acuity. At last follow-up (mean, 25 months) 7 of 11 (64%) of affected eyes had good visual outcome (≥14/20), and no patient experienced a subsequent neurological event. CONCLUSIONS: OPN may occur as a manifestation of BD and, in non-Western countries, this may be more common than the idiopathic variety. In contrast to idiopathic cases, OPN in BD is more likely to demonstrate initial rapid progression of visual loss and more severe loss at presentation. Patients show less recovery of vision in response to corticosteroids but carry a lower rate of subsequent relapse. Patients with OPN should be specifically questioned regarding symptoms of BD.

Superiority of spleen stiffness on two-dimensional magnetic resonance elastography over liver stiffness and serum tests in assessing portal hypertension in chronic liver disease.

Background: The value of magnetic resonance elastography (MRE) in portal hypertension (PH) has yet to be determined in the context of chronic liver disease (CLD). This study examined the value of MRE for the prediction of hepatic venous pressure gradient (HVPG) and high-risk esophageal varices (EVs) in a CLD cohort with a generally high HVPG. Methods: Patients with CLD who underwent both HVPG measurement and two-dimensional MRE examination at Beijing Friendship Hospital between April 2018 and March 2022 were prospectively included. Two-dimensional MRE was performed within the liver and spleen. Endoscopy results and laboratory parameters were collected. Some selected published serum markers were calculated, including fibrosis 4, aspartate aminotransferase-to-platelet ratio index, and King's score. The efficacy of the parameters for assessing PH was analyzed by using the Pearson correlation coefficient, linear and logistic regression, and receiver operating characteristic curve analyses. Results: A total of 48 patients were included. The mean HVPG was 16.8±5.8 mmHg. Among these patients, 47 patients had PH (HVPG >5 mmHg), and 43 patients had clinically significant PH (HVPG ≥10 mmHg). Among the parameters associated with HVPG, the strongest correlation was found for spleen stiffness (SS) (R=0.638; P<0.001). In multiple regression analyses, SS was independently associated with an elevated HVPG and high-risk EVs. The areas under the receiver operating characteristic curve of SS for identifying patients with an HVPG ≥16 mmHg, HVPG ≥20 mmHg, and high-risk EVs were 0.790, 0.822, and 0.886, respectively, which were higher than those of liver stiffness (LS) and serum markers but slightly inferior to that of fibrosis 4 (area under the receiver operating characteristic curve =0.844) in identifying an HVPG ≥16 mmHg. SS cutoff values of 9.5, 10.05, and 9.9 kPa were selected to rule out the presence of an HVPG ≥16 mmHg, HVPG ≥20 mmHg, and high-risk EVs (sensitivity: 100%, 100%, and 100%, respectively; specificity: 45.5%, 50%, and 60%, respectively). Conclusions: In patients with generally high HVPG, SS measured by two-dimensional MRE may be a better predictor of HVPG values and high-risk EVs than LS and serum markers.

Comparative study on the magnetic properties of Fe-substituted Co2Sn1-xFexO4 spinel oxides and its exchange bias effect.

A series of Fe-substituted Co2Sn1-xFexO4 (0 ≤ x ≤ 0.4) inverse spinel's oxides was synthesized using the solid-state reaction method. X-ray analysis reveals a single-phase cubic structure with the space group Fd3m. The transition temperature is shown to increase with a higher Fe concentration in the Co2Sn1-xFexO4 spinel oxide. The ac susceptibility at different frequencies also confirms a spin-glassy state at lower temperatures. The sample with Fe substitution (x = 0.2) exhibits a significant exchange bias effect when subjected to a constant temperature of ~10 K. The susceptibility at high temperatures, as calculated using Curie-Wise fitting, suggests that the system undergoes a shift from antiferromagnetic exchange (x < 0.2) to ferromagnetic exchange (x > 0.2).

Evaluating age-and gender-related changes in brain volumes in normal adult using synthetic magnetic resonance imaging.

OBJECTIVE: Normal aging is associated with brain volume change, and brain segmentation can be performed within an acceptable scan time using synthetic magnetic resonance imaging (MRI). This study aimed to investigate the brain volume changes in healthy adult according to age and gender, and provide age- and gender-specific reference values using synthetic MRI. METHODS: A total of 300 healthy adults (141 males, median age 48; 159 females, median age 50) were underwent synthetic MRI on 3.0 T. Brain parenchymal volume (BPV), gray matter volume (GMV), white matter volume (WMV), myelin volume (MYV), and cerebrospinal fluid volume (CSFV) were calculated using synthetic MRI software. These volumes were normalized by intracranial volume to normalized GMV (nGMV), normalized WMV (nWMV), normalized MYV (nMYV), normalized BPV (nBPV), and normalized CSFV (nCSFV). The normalized brain volumes were plotted against age in both males and females, and a curve fitting model that best explained the age dependence of brain volume was identified. The normalized brain volumes were compared between different age and gender groups. RESULTS: The approximate curves of nGMV, nWMV, nCSFV, nBPV, and nMYV were best fitted by quadratic curves. The nBPV decreased monotonously through all ages in both males and females, while the changes of nCSFV showed the opposite trend. The nWMV and nMYV in both males and females increased gradually and then decrease with age. In early adulthood (20s), nWMV and nMYV in males were lower and peaked later than that in females (p < .005). The nGMV in both males and females decreased in the early adulthood until the 30s and then remains stable. A significant decline in nWMV, nBPV, and nMYV was noted in the 60s (Turkey test, p < .05). CONCLUSIONS: Our study provides age- and gender-specific reference values of brain volumes using synthetic MRI, which could be objective tools for discriminating brain disorders from healthy brains.

Preparation and Performance of Micro-Arc Oxidation Coatings for Corrosion Protection of LaFe11.6Si1.4 Alloy.

The microstructure, corrosion resistance, and phase-transition process of micro-arc oxidation (MAO) coatings prepared on LaFe11.6Si1.4 alloy surfaces in different electrolyte systems were systematically investigated. Research has demonstrated that various electrolyte systems do not alter the main components of the coatings. However, the synergistic action of Na2CO3 and Na2B4O7 more effectively modulated the ionization and chemical reactions of the MAO process and accelerated the formation of α-Al2O3. Moreover, the addition of Na2CO3 and Na2B4O7 improved the micromorphology of the coating, resulting in a uniform coating thickness and good bonding with the LaFe11.6Si1.4 substrate. The dynamic potential polarization analysis was performed in a three-electrode system consisting of a LaFe11.6Si1.4 working electrode, a saturated calomel reference electrode, and a platinum auxiliary electrode. The results showed that the self-corrosion potential of the LaFe11.6Si1.4 alloy without surface treatment was -0.68 V, with a current density of 8.96 × 10-6 A/cm2. In contrast, the presence of a micro-arc electrolytic oxidation coating significantly improved the corrosion resistance of the LaFe11.6Si1.4 substrate, where the minimum corrosion current density was 1.32 × 10-7 A/cm2 and the corrosion potential was -0.50 V. Similarly, after optimizing the MAO electrolyte with Na2CO3 and Na2B4O7, the corrosion resistance of the material further improved. Simultaneously, the effect of the coatings on the order of the phase transition, latent heat, and temperature is negligible. Therefore, micro-arc oxidation technology based on the in situ growth coating of the material surface effectively improves the working life and stability of La(Fe, Si)13 materials in the refrigeration cycle, which is an excellent alternative as a protection technology to promote the practical process of magnetic refrigeration technology.

Utility of machine learning for identifying stapes fixation on ultra-high-resolution CT.

PURPOSE: Imaging diagnosis of stapes fixation (SF) is challenging owing to a lack of definite evidence. We developed a comprehensive machine learning (ML) model to identify SF on ultra-high-resolution CT. MATERIALS AND METHODS: We retrospectively enrolled 109 participants (143 ears) and divided them into the training set (115 ears) and test set (28 ears). Stapes mobility (SF or non-SF) was determined by surgical inspection. In the ML analysis, rectangular regions of interest were placed on consecutive axial slices in the training set. Radiomic features were extracted and fed into the training session. The test set was analyzed using 7 ML models (support vector machine, k nearest neighbor, decision tree, random forest, extra trees, eXtreme Gradient Boosting, and Light Gradient Boosting Machine) and by 2 dedicated neuroradiologists. Diagnostic performance (sensitivity, specificity and accuracy, with surgical findings as the reference) was compared between the radiologists and the optimal ML model by using the McNemar test. RESULTS: The mean age of the participants was 42.3 ± 17.5 years. The Light Gradient Boosting Machine (LightGBM) model showed the highest sensitivity (0.83), specificity (0.81), accuracy (0.82) and area under the curve (0.88) for detecting SF among the 7 ML models. The neuroradiologists achieved good sensitivities (0.75 and 0.67), moderate-to-good specificities (0.63 and 0.56) and good accuracies (0.68 and 0.61). This model showed no statistical differences with the neuroradiologists (P values 0.289-1.000). CONCLUSIONS: Compared to the neuroradiologists, the LightGBM model achieved competitive diagnostic performance in identifying SF, and has the potential to be a supportive tool in clinical practice.

Grating-based x-ray dark-field CT for lung cancer diagnosis in mice.

BACKGROUND: The low absorption of x-rays in lung tissue and the poor resolution of conventional computed tomography (CT) limits its use to detect lung disease. However, x-ray dark-field imaging can sense the scattered x-rays deflected by the structures being imaged. This technique can facilitate the detection of small alveolar lesions that would be difficult to detect with conventional CT. Therefore, it may provide an alternative imaging modality to diagnose lung disease at an early stage. METHODS: Eight mice were inoculated with lung cancers simultaneously. Each time two mice were scanned using a grating-based dark-field CT on days 4, 8, 12, and 16 after the introduction of the cancer cells. The detectability index was calculated between nodules and healthy parenchyma for both attenuation and dark-field modalities. High-resolution micro-CT and pathological examinations were used to crosscheck and validate our results. Paired t-test was used for comparing the ability of dark-field and attenuation modalities in pulmonary nodule detection. RESULTS: The nodules were shown as a signal decrease in the dark-field modality and a signal increase in the attenuation modality. The number of nodules increased from day 8 to day 16, indicating disease progression. The detectability indices of dark-field modality were higher than those of attenuation modality (p = 0.025). CONCLUSIONS: Compared with the standard attenuation CT, the dark-field CT improved the detection of lung nodules. RELEVANCE STATEMENT: Dark-field CT has a higher detectability index than conventional attenuation CT in lung nodule detection. This technique could improve the early diagnosis of lung cancer. KEY POINTS: • Lung cancer progression was observed using x-ray dark-field CT. • Dark-field modality complements with attenuation modality in lung nodule detection. • Dark-field modality showed a detectability index higher than that attenuation in nodule detection.

Sub-features orthogonal decoupling: Detecting bone wall absence via a small number of abnormal examples for temporal CT images.

The absence of bone wall located in the jugular bulb and sigmoid sinus of the temporal bone is one of the important reasons for pulsatile tinnitus. Automatic and accurate detection of these abnormal singes in CT slices has important theoretical significance and clinical value. Due to the shortage of abnormal samples, imbalanced samples, small inter-class differences, and low interpretability, existing deep-learning methods are greatly challenged. In this paper, we proposed a sub-features orthogonal decoupling model, which can effectively disentangle the representation features into class-specific sub-features and class-independent sub-features in a latent space. The former contains the discriminative information, while, the latter preserves information for image reconstruction. In addition, the proposed method can generate image samples using category conversion by combining the different class-specific sub-features and the class-independent sub-features, achieving corresponding mapping between deep features and images of specific classes. The proposed model improves the interpretability of the deep model and provides image synthesis methods for downstream tasks. The effectiveness of the method was verified in the detection of bone wall absence in the temporal bone jugular bulb and sigmoid sinus.

Deep learning-based arterial subtraction images improve the detection of LR-TR algorithm for viable HCC on extracellular agents-enhanced MRI.

PURPOSE: To determine the role of deep learning-based arterial subtraction images in viability assessment on extracellular agents-enhanced MRI using LR-TR algorithm. METHODS: Patients diagnosed with HCC who underwent locoregional therapy were retrospectively collected. We constructed a deep learning-based subtraction model and automatically generated arterial subtraction images. Two radiologists evaluated LR-TR category on ordinary images and then evaluated again on ordinary images plus arterial subtraction images after a 2-month washout period. The reference standard for viability was tumor stain on the digital subtraction hepatic angiography within 1 month after MRI. RESULTS: 286 observations of 105 patients were ultimately enrolled. 157 observations were viable and 129 observations were nonviable according to the reference standard. The sensitivity and accuracy of LR-TR algorithm for detecting viable HCC significantly increased with the application of arterial subtraction images (87.9% vs. 67.5%, p < 0.001; 86.4% vs. 75.9%, p < 0.001). And the specificity slightly decreased without significant difference when the arterial subtraction images were added (84.5% vs. 86.0%, p = 0.687). The AUC of LR-TR algorithm significantly increased with the addition of arterial subtraction images (0.862 vs. 0.768, p < 0.001). The arterial subtraction images also improved inter-reader agreement (0.857 vs. 0.727). CONCLUSION: Extended application of deep learning-based arterial subtraction images on extracellular agents-enhanced MRI can increase the sensitivity of LR-TR algorithm for detecting viable HCC without significant change in specificity.

TP-Net: Two-Path Network for Retinal Vessel Segmentation.

Refined and automatic retinal vessel segmentation is crucial for computer-aided early diagnosis of retinopathy. However, existing methods often suffer from mis-segmentation when dealing with thin and low-contrast vessels. In this paper, a two-path retinal vessel segmentation network is proposed, namely TP-Net, which consists of three core parts, i.e. main-path, sub-path, and multi-scale feature aggregation module (MFAM). Main-path is to detect the trunk area of the retinal vessels, and the sub-path to effectively capture edge information of the retinal vessels. The prediction results of the two paths are combined by MFAM, obtaining refined segmentation of retinal vessels. In the main-path, a three-layer lightweight backbone network is elaborately designed according to the characteristics of retinal vessels, and then a global feature selection mechanism (GFSM) is proposed, which can autonomously select features that are more important for the segmentation task from the features at different layers of the network, thereby, enhancing the segmentation capability for low-contrast vessels. In the sub-path, an edge feature extraction method and an edge loss function are proposed, which can enhance the ability of the network to capture edge information and reduce the mis-segmentation of thin vessels. Finally, MFAM is proposed to fuse the prediction results of main-path and sub-path, which can remove background noises while preserving edge details, and thus, obtaining refined segmentation of retinal vessels. The proposed TP-Net has been evaluated on three public retinal vessel datasets, namely DRIVE, STARE, and CHASE DB1. The experimental results show that the TP-Net achieved a superior performance and generalization ability with fewer model parameters compared with the state-of-the-art methods.