Longitudinal Study on Pre- and Post-Operation CT Imaging for Predicting Pedicle Screw Loosening in Patients with Lumbar Degenerative Disease.

Purpose: We conducted a longitudinal study to examine the predictive role of risk factors in the occurrence of pedicle screw loosening, assessed through pre- and post-operative computed tomography (CT) scans. Methods: A total of 103 patients with degenerative lumbar disease who had undergone L4/5 pedicle screw fixation (involving 412 screws) were included in this study. They were subsequently categorized into two groups-the "loosening group" and the "non-loosening group". The axial and sagittal angles of the screw trajectory in pre- and post-operative CT images were measured, and the deviation angles were computed. Additionally, measurements were taken of the Hounsfield unit (HU) within the screw entry point area, the pedicle, and the vertebral body in preoperative CT images. Logistic regression analysis was employed to ascertain the risk factors influencing the occurrence of screw loosening. Results: Elderly patients who experienced screw loosening tended to have bilateral screw issues at the L5 level (p < 0.005). The HU of the pedicle (p < 0.001), age (p < 0.001), and the axial deviation angle (p = 0.014) were identified as independent factors predicting screw loosening. Additionally, when HU of the pedicle < 126.5 or age ≥ 53.5 years, the axial deviation angle was found to be smaller in the group experiencing screw loosening (p = 0.018 and p = 0.019). Conclusion: Loosening of screws positioned at L5 was found to be more prevalent in elderly patients, particularly exhibiting a bilateral occurrence. Independent predictors of this phenomenon included a low HU value in the pedicle, advanced age in patients, and a substantial axial deviation angle. In the case of elderly patients with a low HU value in the pedicle, a reduced axial surgical deflection was necessitated to prevent the occurrence of screw loosening.

Predicting pathological complete response to neoadjuvant chemotherapy in breast cancer patients: use of MRI radiomics data from three regions with multiple machine learning algorithms.

OBJECTIVE: To construct a multi-region MRI radiomics model for predicting pathological complete response (pCR) in breast cancer (BCa) patients who received neoadjuvant chemotherapy (NACT) and provide a theoretical basis for the peritumoral microenvironment affecting the efficacy of NACT. METHODS: A total of 133 BCa patients who received NACT, including 49 with confirmed pCR, were retrospectively analyzed. The radiomics features of the intratumoral region, peritumoral region, and background parenchymal enhancement (BPE) were extracted, and the most relevant features were obtained after dimensional reduction. Then, combining different areas, multivariate logistic regression analysis was used to select the optimal feature set, and six different machine learning models were used to predict pCR. The optimal model was selected, and its performance was evaluated using receiver operating characteristic (ROC) analysis. SHAP analysis was used to examine the relationship between the features of the model and pCR. RESULTS: For signatures constructed using three individual regions, BPE provided the best predictions of pCR, and the diagnostic performance of the intratumoral and peritumoral regions improved after adding the BPE signature. The radiomics signature from the combination of all the three regions with the XGBoost machine learning algorithm provided the best predictions of pCR based on AUC (training set: 0.891, validation set: 0.861), sensitivity (training set: 0.882, validation set: 0.800), and specificity (training set: 0.847, validation set: 0.84). SHAP analysis demonstrated that LZ_log.sigma.2.0.mm.3D_glcm_ClusterShade_T12 made the greatest contribution to the predictions of this model. CONCLUSION: The addition of the BPE MRI signature improved the prediction of pCR in BCa patients who received NACT. These results suggest that the features of the peritumoral microenvironment are related to the efficacy of NACT.

Multi-instance learning based lung nodule system for assessment of CT quality after small-field-of-view reconstruction.

Small-field-of-view reconstruction CT images (sFOV-CT) increase the pixel density across airway structures and reduce partial volume effects. Multi-instance learning (MIL) is proposed as a weakly supervised machine learning method, which can automatically assess the image quality. The aim of this study was to evaluate the disparities between conventional CT (c-CT) and sFOV-CT images using a lung nodule system based on MIL and assessments from radiologists. 112 patients who underwent chest CT were retrospectively enrolled in this study between July 2021 to March 2022. After undergoing c-CT examinations, sFOV-CT images with small-field-of-view were reconstructed. Two radiologists analyzed all c-CT and sFOV-CT images, including features such as location, nodule type, size, CT values, and shape signs. Then, an MIL-based lung nodule system objectively analyzed the c-CT (c-MIL) and sFOV-CT (sFOV-MIL) to explore their differences. The signal-to-noise ratio of lungs (SNR-lung) and contrast-to-noise ratio of nodules (CNR-nodule) were calculated to evaluate the quality of CT images from another perspective. The subjective evaluation by radiologists showed that feature of minimal CT value (p = 0.019) had statistical significance between c-CT and sFOV-CT. However, most features (all with p < 0.05), except for nodule type, location, volume, mean CT value, and vacuole sign (p = 0.056-1.000), had statistical differences between c-MIL and sFOV-MIL by MIL system. The SNR-lung between c-CT and sFOV-CT had no statistical significance, while the CNR-nodule showed statistical difference (p = 0.007), and the CNR of sFOV-CT was higher than that of c-CT. In detecting the difference between c-CT and sFOV-CT, features extracted by the MIL system had more statistical differences than those evaluated by radiologists. The image quality of those two CT images was different, and the CNR-nodule of sFOV-CT was higher than that of c-CT.

A multicenter clinical AI system study for detection and diagnosis of focal liver lesions.

Early and accurate diagnosis of focal liver lesions is crucial for effective treatment and prognosis. We developed and validated a fully automated diagnostic system named Liver Artificial Intelligence Diagnosis System (LiAIDS) based on a diverse sample of 12,610 patients from 18 hospitals, both retrospectively and prospectively. In this study, LiAIDS achieved an F1-score of 0.940 for benign and 0.692 for malignant lesions, outperforming junior radiologists (benign: 0.830-0.890, malignant: 0.230-0.360) and being on par with senior radiologists (benign: 0.920-0.950, malignant: 0.550-0.650). Furthermore, with the assistance of LiAIDS, the diagnostic accuracy of all radiologists improved. For benign and malignant lesions, junior radiologists' F1-scores improved to 0.936-0.946 and 0.667-0.680 respectively, while seniors improved to 0.950-0.961 and 0.679-0.753. Additionally, in a triage study of 13,192 consecutive patients, LiAIDS automatically classified 76.46% of patients as low risk with a high NPV of 99.0%. The evidence suggests that LiAIDS can serve as a routine diagnostic tool and enhance the diagnostic capabilities of radiologists for liver lesions.

Prediction of neoadjuvant chemotherapy pathological complete response for breast cancer based on radiomics nomogram of intratumoral and derived tissue.

BACKGROUND: Non-invasive identification of breast cancer (BCa) patients with pathological complete response (pCR) after neoadjuvant chemotherapy (NACT) is critical to determine appropriate surgical strategies and guide the resection range of tumor. This study aimed to examine the effectiveness of a nomogram created by combining radiomics signatures from both intratumoral and derived tissues with clinical characteristics for predicting pCR after NACT. METHODS: The clinical data of 133 BCa patients were analyzed retrospectively and divided into training and validation sets. The radiomics features for Intratumoral, peritumoral, and background parenchymal enhancement (BPE) in the training set were dimensionalized. Logistic regression analysis was used to select the optimal feature set, and a radiomics signature was constructed using a decision tree. The signature was combined with clinical features to build joint models and generate nomograms. The area under curve (AUC) value of receiver operating characteristic (ROC) curve was then used to assess the performance of the nomogram and independent predictors. RESULTS: Among single region, intratumoral had the best predictive value. The diagnostic performance of the intratumoral improved after adding the BPE features. The AUC values of the radiomics signature were 0.822 and 0.82 in the training and validation sets. Multivariate logistic regression analysis revealed that age, ER, PR, Ki-67, and radiomics signature were independent predictors of pCR in constructing a nomogram. The AUC of the nomogram in the training and validation sets were 0.947 and 0.933. The DeLong test showed that the nomogram had statistically significant differences compared to other independent predictors in both the training and validation sets (P < 0.05). CONCLUSION: BPE has value in predicting the efficacy of neoadjuvant chemotherapy, thereby revealing the potential impact of tumor growth environment on the efficacy of neoadjuvant chemotherapy.

Artificial Intelligence in the Differential Diagnosis of Cardiomyopathy Phenotypes.

Artificial intelligence (AI) is rapidly being applied to the medical field, especially in the cardiovascular domain. AI approaches have demonstrated their applicability in the detection, diagnosis, and management of several cardiovascular diseases, enhancing disease stratification and typing. Cardiomyopathies are a leading cause of heart failure and life-threatening ventricular arrhythmias. Identifying the etiologies is fundamental for the management and diagnostic pathway of these heart muscle diseases, requiring the integration of various data, including personal and family history, clinical examination, electrocardiography, and laboratory investigations, as well as multimodality imaging, making the clinical diagnosis challenging. In this scenario, AI has demonstrated its capability to capture subtle connections from a multitude of multiparametric datasets, enabling the discovery of hidden relationships in data and handling more complex tasks than traditional methods. This review aims to present a comprehensive overview of the main concepts related to AI and its subset. Additionally, we review the existing literature on AI-based models in the differential diagnosis of cardiomyopathy phenotypes, and we finally examine the advantages and limitations of these AI approaches.

Predicting progression of white matter hyperintensity using coronary artery calcium score based on coronary CT angiography-feasibility and accuracy.

Objective: Coronary artery disease (CAD) usually coexists with subclinical cerebrovascular diseases given the systematic nature of atherosclerosis. In this study, our objective was to predict the progression of white matter hyperintensity (WMH) and find its risk factors in CAD patients using the coronary artery calcium (CAC) score. We also investigated the relationship between the CAC score and the WMH volume in different brain regions. Methods: We evaluated 137 CAD patients with WMH who underwent coronary computed tomography angiography (CCTA) and two magnetic resonance imaging (MRI) scans from March 2018 to February 2023. Patients were categorized into progressive (n = 66) and nonprogressive groups (n = 71) by the change in WMH volume from the first to the second MRI. We collected demographic, clinical, and imaging data for analysis. Independent risk factors for WMH progression were identified using logistic regression. Three models predicting WMH progression were developed and assessed. Finally, patients were divided into groups based on their total CAC score (0 to <100, 100 to 400, and > 400) to compare their WMH changes in nine brain regions. Results: Alcohol abuse, maximum pericoronary fat attenuation index (pFAI), CT-fractional flow reserve (CT-FFR), and CAC risk grade independently predicted WMH progression (p < 0.05). The logistic regression model with all four variables performed best (training: AUC = 0.878, 95% CI: 0.790, 0.938; validation: AUC = 0.845, 95% CI: 0.734, 0.953). An increased CAC risk grade came with significantly higher WMH volume in the total brain, corpus callosum, and frontal, parietal and occipital lobes (p < 0.05). Conclusion: This study demonstrated the application of the CCTA-derived CAC score to predict WMH progression in elderly people (≥60 years) with CAD.

A novel CT-responsive hydrogel for the construction of an organ simulation phantom for the repeatability and stability study of radiomic features.

Radiomic features have demonstrated reliable outcomes in tumor grading and detecting precancerous lesions in medical imaging analysis. However, the repeatability and stability of these features have faced criticism. In this study, we aim to enhance the repeatability and stability of radiomic features by introducing a novel CT-responsive hydrogel material. The newly developed CT-responsive hydrogel, mineralized by in situ metal ions, exhibits exceptional repeatability, stability, and uniformity. Moreover, by adjusting the concentration of metal ions, it achieves remarkable CT similarity comparable to that of human organs on CT scans. To create a phantom, the hydrogel was molded into a universal model, displaying controllable CT values ranging from 53 HU to 58 HU, akin to human liver tissue. Subsequently, 1218 radiomic features were extracted from the CT-responsive hydrogel organ simulation phantom. Impressively, 85-97.2% of the extracted features exhibited good repeatability and stability during coefficient of variability analysis. This finding emphasizes the potential of CT-responsive hydrogel in consistently extracting the same features, providing a novel approach to address the issue of repeatability in radiomic features.

Retrolaminar migration as a complication of intraocular silicone oil injection detected on unenhanced CT.

AIM: To describe the clinical and radiologic features of retrolaminar migration silicone oil (SiO) and observe the dynamic position of ventricular oil accumulation in supine and prone. METHODS: For this retrospective study, 29 patients who had a history of SiO injection treatment and underwent unenhanced head computed tomography (CT) were included from January 2019 to October 2022. The patients were divided into migration-positive and negative groups. Clinical history and CT features were compared using Whitney U and Fisher's exact tests. The dynamic position of SiO was observed within the ventricular system in supine and prone. CT images were visually assessed for SiO migration along the retrolaminar involving pathways for vision (optic nerve, chiasm, and tract) and ventricular system. RESULTS: Intraocular SiO migration was found in 5 of the 29 patients (17.24%), with SiO at the optic nerve head (n=1), optic nerve (n=4), optic chiasm (n=1), optic tract (n=1), and within lateral ventricles (n=1). The time interval between SiO injection and CT examination of migration-positive cases was significantly higher than that of migration-negative patients (22.8±16.5mo vs 13.1±2.6mo, P<0.001). The hyperdense lesion located in the frontal horns of the right lateral ventricle migrated to the fourth ventricle when changing the position from supine to prone. CONCLUSION: Although SiO retrolaminar migration is unusual, the clinician and radiologist should be aware of migration routes. The supine combined with prone examination is the first-choice method to confirm the presence of SiO in the ventricular system.

Is coronary artery calcium an independent risk factor for white matter hyperintensity?

BACKGROUND: Cardiovascular diseases have been considered the primary cause of disability and death worldwide. Coronary artery calcium (CAC) is an important indicator of the severity of coronary atherosclerosis. This study is aimed to investigate the relationship between CAC and white matter hyperintensity (WMH) in the context of diagnostic utility. METHODS: A retrospective analysis was conducted on 342 patients with a diagnosis of WMH on magnetic resonance images (MRI) who also underwent chest computed tomography (CT) scans. WMH volumes were automatically measured using a lesion prediction algorithm. Subjects were divided into four groups based on the CAC score obtained from chest CT scans. A multilevel mixed-effects linear regression model considering conventional vascular risk factors assessed the association between total WMH volume and CAC score. RESULTS: Overall, participants with coronary artery calcium (CAC score > 0) had larger WMH volumes than those without calcium (CAC score = 0), and WMH volumes were statistically different between the four CAC score groups, with increasing CAC scores, the volume of WMH significantly increased. In the linear regression model 1 of the high CAC score group, for every 1% increase in CAC score, the WMH volume increases by 2.96%. After including other covariates in model 2 and model 3, the ß coefficient in the high CAC group remains higher than in the low and medium CAC score groups. CONCLUSION: In elderly adults, the presence and severity of CAC is related to an increase in WMH volume. Our findings suggest an association between two different vascular bed diseases in addition to traditional vascular risk factors, possibly indicating a comorbid mechanism.

Coronary computed tomography angiography imaging features combined with computed tomography-fractional flow reserve, pericoronary fat attenuation index, and radiomics for the prediction of myocardial ischemia.

BACKGROUND: This study aimed to predict myocardial ischemia (MIS) by constructing models with imaging features, CT-fractional flow reserve (CT-FFR), pericoronary fat attenuation index (pFAI), and radiomics based on coronary computed tomography angiography (CCTA). METHODS AND RESULTS: This study included 96 patients who underwent CCTA and single photon emission computed tomography-myocardial perfusion imaging (SPECT-MPI). According to SPECT-MPI results, there were 72 vessels with MIS in corresponding supply area and 105 vessels with no-MIS. The conventional model [lesion length (LL), MDS (maximum stenosis diameter × 100% / reference vessel diameter), MAS (maximum stenosis area × 100% / reference vessel area) and CT value], radiomics model (radiomics features), and multi-faceted model (all features) were constructed using support vector machine. Conventional and radiomics models showed similar predictive efficacy [AUC: 0.76, CI 0.62-0.90 vs. 0.74, CI 0.61-0.88; p > 0.05]. Adding pFAI to the conventional model showed better predictive efficacy than adding CT-FFR (AUC: 0.88, CI 0.79-0.97 vs. 0.80, CI 0.68-0.92; p < 0.05). Compared with conventional and radiomics model, the multi-faceted model showed the highest predictive efficacy (AUC: 0.92, CI 0.82-0.98, p < 0.05). CONCLUSION: pFAI is more effective for predicting MIS than CT-FFR. A multi-faceted model combining imaging features, CT-FFR, pFAI, and radiomics is a potential diagnostic tool for MIS.

Enhancing the Selectivity of Leucine Aminopeptidase Near-Infrared Fluorescent Probes for Assisting in Surgical Tumor Resection.

Selective fluorescence imaging of analytes is a challenge for monitoring diseases as homologues interfere with the imaging agents. Leucine aminopeptidase (LAP), a kind of protease, is related to tumor pathogenesis. The known LAP fluorescent probes based on leucine recognition have limited selectivity. Herein, a selective t-butyl-alanine recognition unit for LAP through the ligand regulation strategy is prepared as a new near-infrared (NIR) fluorescent probe (DCM-LAP) having a large Stokes shift of 214 nm and a high sensitivity with a detection limit of 168 mU/L. DCM-LAP has an enhanced response toward LAP with NIR fluorescence at 656 nm based on intramolecular charge transfer. The probe is selective without being interfered with by biological enzymes including the aminopeptidase N (APN). DCM-LAP can image LAP activity in living cells. It can also visualize the cell invasion and migration processes. DCM-LAP is employed in the real-time imaging of LAP in tumor-bearing nude mice and guides in the accurate resection of breast tumors. It also distinguishes tumor tissues from normal with a high tumor-to-normal ratio (9.8). The DCM-LAP probe can thus assist in the investigations of LAP-associated clinical disease.

Quercetin alleviates subarachnoid hemorrhage-induced early brain injury via inhibiting ferroptosis in the rat model.

Early brain injury (EBI) refers to a series of pathophysiological brain lesions that occur within 72 hr after subarachnoid hemorrhage (SAH), which is an extremely crucial factor in the poor prognosis of patients. In EBI, ferroptosis has been proven to cause neuronal death. Quercetin (QCT) is effective in deactivating reactive oxygen species (ROS), inhibiting lipid peroxidation, and even chelating iron, but its role in SAH remains unclear. In this study, the mortality rate, severity grade of SAH, brain water content (BWC), blood-brain barrier permeability, and neurological function of the rats were detected. Moreover, mitochondrial morphology in cortical neurons were observed and their sizes were subsequently quantified. The levels of lipid peroxidation on glutathione and malondialdehyde (MDA) and glutathione peroxidase (GSH-Px) were determined, whereas the protein expressions of glutathione peroxidase 4 (GPX4), SLC7A11 (xCT), transferrin receptor 1 (TfR1), and ferroportin-1 (FPN1) were analyzed by western immunoblotting. The neurodegeneration involved in EBI was investigated by fluoro-Jade C staining, while iron staining was utilized to measure iron content. Our results showed that inhibition of ferroptosis by QCT could suppress EBI and improve neurological function in SAH rats. QCT increased the expression levels of GPX4, xCT, and FPN1, while downregulated TfR1, and exerted protective effects on neurons as well as alleviated iron accumulation and lipid peroxidation in the cortex of SAH rats. In conclusion, our study revealed that QCT might alleviate the EBI by inhibiting ferroptosis in SAH rats.

Hybrid model of CT-fractional flow reserve, pericoronary fat attenuation index and radiomics for predicting the progression of WMH: a dual-center pilot study.

Objective: To develop and validate a hybrid model incorporating CT-fractional flow reserve (CT-FFR), pericoronary fat attenuation index (pFAI), and radiomics signatures for predicting progression of white matter hyperintensity (WMH). Methods: A total of 226 patients who received coronary computer tomography angiography (CCTA) and brain magnetic resonance imaging from two hospitals were divided into a training set (n = 116), an internal validation set (n = 30), and an external validation set (n = 80). Patients who experienced progression of WMH were identified from subsequent MRI results. We calculated CT-FFR and pFAI from CCTA images using semi-automated software, and segmented the pericoronary adipose tissue (PCAT) and myocardial ROI. A total of 1,073 features were extracted from each ROI, and were then refined by Elastic Net Regression. Firstly, different machine learning algorithms (Logistic Regression [LR], Support Vector Machine [SVM], Random Forest [RF], k-nearest neighbor [KNN] and eXtreme Gradient Gradient Boosting Machine [XGBoost]) were used to evaluate the effectiveness of radiomics signatures for predicting WMH progression. Then, the optimal machine learning algorithm was used to compare the predictive performance of individual and hybrid models based on independent risk factors of WMH progression. Receiver operating characteristic (ROC) curve analysis, calibration and decision curve analysis were used to evaluate predictive performance and clinical value of the different models. Results: CT-FFR, pFAI, and radiomics signatures were independent predictors of WMH progression. Based on the machine learning algorithms, the PCAT signatures led to slightly better predictions than the myocardial signatures and showed the highest AUC value in the XGBoost algorithm for predicting WMH progression (AUC: 0.731 [95% CI: 0.603-0.838] vs.0.711 [95% CI: 0.584-0.822]). In addition, pFAI provided better predictions than CT-FFR (AUC: 0.762 [95% CI: 0.651-0.863] vs. 0.682 [95% CI: 0.547-0.799]). A hybrid model that combined CT-FFR, pFAI, and two radiomics signatures provided the best predictions of WMH progression [AUC: 0.893 (95%CI: 0.815-0.956)]. Conclusion: pFAI was more effective than CT-FFR, and PCAT signatures were more effective than myocardial signatures in predicting WMH progression. A hybrid model that combines pFAI, CT-FFR, and two radiomics signatures has potential use for identifying WMH progression.

Sagittal intervertebral rotational motion: a deep learning-based measurement on flexion-neutral-extension cervical lateral radiographs.

BACKGROUND: The analysis of sagittal intervertebral rotational motion (SIRM) can provide important information for the evaluation of cervical diseases. Deep learning has been widely used in spinal parameter measurements, however, there are few investigations on spinal motion analysis. The purpose of this study is to develop a deep learning-based model for fully automated measurement of SIRM based on flexion-neutral-extension cervical lateral radiographs and to evaluate its applicability for the flexion-extension (F/E), flexion-neutral (F/N), and neutral-extension (N/E) motion analysis. METHODS: A total of 2796 flexion, neutral, and extension cervical lateral radiographs from 932 patients were analyzed. Radiographs from 100 patients were randomly selected as the test set, and those from the remaining 832 patients were used for training and validation. Landmarks were annotated for measuring SIRM at five segments from C2/3 to C6/7 on F/E, F/N, and N/E motion. High-Resolution Net (HRNet) was used as the main structure to train the landmark detection network. Landmark performance was assessed according to the percentage of correct key points (PCK) and mean of the percentage of correct key points (MPCK). Measurement performance was evaluated by intra-class correlation coefficient (ICC), Pearson correlation coefficient, mean absolute error (MAE), root mean square error (RMSE), and Bland-Altman plots. RESULTS: At a 2-mm distance threshold, the PCK for the model ranged from 94 to 100%. Compared with the reference standards, the model showed high accuracy for SIRM measurements for all segments on F/E and F/N motion. On N/E motion, the model provided reliable measurements from C3/4 to C6/7, but not C2/3. Compared with the radiologists' measurements, the model showed similar performance to the radiologists. CONCLUSIONS: The developed model can automatically measure SIRM on flexion-neutral-extension cervical lateral radiographs and showed comparable performance with radiologists. It may provide rapid, accurate, and comprehensive information for cervical motion analysis.

A novel computed tomography radiomic nomogram for early evaluation of small airway dysfunction development.

The common respiratory abnormality, small airway dysfunction (fSAD), is easily neglected. Its prognostic factors, prevalence, and risk factors are unclear. This study aimed to explore the early detection of fSAD using radiomic analysis of computed tomography (CT) images to predict fSAD progress. The patients were divided into fSAD and non-fSAD groups and divided randomly into a training group (n = 190) and a validation group (n = 82) at a 7:3 ratio. Lung kit software was used for automatic delineation of regions of interest (ROI) on chest CT images. The most valuable imaging features were selected and a radiomic score was established for risk assessment. Multivariate logistic regression analysis showed that age, radiomic score, smoking, and history of asthma were significant predictors of fSAD (P < 0.05). Results suggested that the radiomic nomogram model provides clinicians with useful data and could represent a reliable reference to form fSAD clinical treatment strategies.

CRAUNet: A cascaded residual attention U-Net for retinal vessel segmentation.

Retinal vessels play an important role in judging many eye-related diseases, so accurate segmentation of retinal vessels has become the key to auxiliary diagnosis. In this paper, we present a Cascaded Residual Attention U-Net (CRAUNet) that can be regarded as a set of U-Nets, that allows coarse-to-fine representations. In the CRAUNet, we introduce a DropBlock regularization similar to the frequently-used dropout, which greatly reduces the overfitting problem. In addition, we propose a multi-scale fusion channel attention (MFCA) module to explore helpful information, and then merge this information instead of using a direct skip-connection. Finally, to prove the effectiveness of our method, we conduct extensive experiments on DRIVE and CHASE_DB1 datasets. The proposed CRAUNet achieves area under the receiver operating characteristic curve (AUC) of 0.9830 and 0.9865, respectively, for the two datasets. Compared to other state-of-the-art methods, the experimental results demonstrate that the performance of the proposed method is superior to that of others.

Automated quality assessment of chest radiographs based on deep learning and linear regression cascade algorithms.

OBJECTIVES: Develop and evaluate the performance of deep learning and linear regression cascade algorithms for automated assessment of the image layout and position of chest radiographs. METHODS: This retrospective study used 10 quantitative indices to capture subjective perceptions of radiologists regarding image layout and position of chest radiographs, including the chest edges, field of view (FOV), clavicles, rotation, scapulae, and symmetry. An automated assessment system was developed using a training dataset consisting of 1025 adult posterior-anterior chest radiographs. The evaluation steps included: (i) use of a CNN framework based on ResNet - 34 to obtain measurement parameters for quantitative indices and (ii) analysis of quantitative indices using a multiple linear regression model to obtain predicted scores for the layout and position of chest radiograph. In the testing dataset (n = 100), the performance of the automated system was evaluated using the intraclass correlation coefficient (ICC), Pearson correlation coefficient (r), mean absolute difference (MAD), and mean absolute percentage error (MAPE). RESULTS: The stepwise regression showed a statistically significant relationship between the 10 quantitative indices and subjective scores (p < 0.05). The deep learning model showed high accuracy in predicting the quantitative indices (ICC = 0.82 to 0.99, r = 0.69 to 0.99, MAD = 0.01 to 2.75). The automatic system provided assessments similar to the mean opinion scores of radiologists regarding image layout (MAPE = 3.05%) and position (MAPE = 5.72%). CONCLUSIONS: Ten quantitative indices correlated well with the subjective perceptions of radiologists regarding the image layout and position of chest radiographs. The automated system provided high performance in measuring quantitative indices and assessing image quality. KEY POINTS: • Objective and reliable assessment for image quality of chest radiographs is important for improving image quality and diagnostic accuracy. • Deep learning can be used for automated measurements of quantitative indices from chest radiographs. • Linear regression can be used for interpretation-based quality assessment of chest radiographs.

Development of Deep Learning-based Automatic Scan Range Setting Model for Lung Cancer Screening Low-dose CT Imaging.

RATIONALE AND OBJECTIVES: To develop an automatic setting of a deep learning-based system for detecting low-dose computed tomography (CT) lung cancer screening scan range and compare its efficiency with the radiographer's performance. MATERIALS AND METHODS: This retrospective study was performed using 1984 lung cancer screening low-dose CT scans obtained between November 2019 and May 2020. Among 1984 CT scans, 600 CT scans were considered suitable for an observational study to explore the relationship between the scout landmarks and the actual lung boundaries. Further, 1144 CT scans data set was used for the development of a deep learning-based algorithm. This data set was split into an 8:2 ratio divided into a training set (80%, n = 915) and a validation set (20%, n = 229). The performance of the deep learning algorithm was evaluated in the test set (n = 240) using actual lung boundaries and radiographers' scan ranges. RESULTS: The mean differences between the upper and lower boundaries of the deep learning-based algorithm and the actual lung boundaries were 4.72 ± 3.15 mm and 16.50 ± 14.06 mm, respectively. The accuracy and over-scanning of the scan ranges generated by the system were 97.08% (233/240) and 0% (0/240) for the upper boundary, and 96.25% (231/240) and 29.58% (71/240) for the lower boundary. CONCLUSION: The developed deep learning-based algorithm system can effectively predict lung cancer screening low-dose CT scan range with high accuracy using only the frontal scout.

Engineering a Ratiometric Photoacoustic Probe with a Hepatocyte-Specific Targeting Ability for Liver Injury Imaging.

In situ imaging of biological indicators is imperative for pathological research by utilizing an activatable photoacoustic (PA) probe. However, precise imaging in actual applications is hampered by the inevitable poor accumulation and low sensitivity. Herein, an amphiphilic molecular probe (AP) was rationally constructed as proof of concept for in situ imaging of drug-induced liver injury, which consists of a hydrophilic target unit and a superoxide anion radical (O2•-)-sensitive small-molecule PA moiety. The probe AP successfully realizes the selectivity and sensitivity toward O2•- in vitro and in living cells. Notably, the amphiphilic probe AP can be selectively retained in the liver and activated toward endogenous O2•- through receptor-mediated endocytosis inside hepatocytes. By virtue of the highly efficient accumulation at the liver, AP was further applied to assess isoniazid-induced liver injury through desired ratiometric PA signals. In addition, based on the fluctuation of O2•-, the therapeutic efficacy of hepatoprotective medicines for hepatotoxicity was analyzed in vivo. Therefore, the O2•--specific probe could serve as a promising molecular tool for early diagnosis study of other liver diseases and analysis of new potential therapeutic agents.