Deep Learning-Based Multiparametric MRI Model for Preoperative T-Stage in Rectal Cancer.

BACKGROUND: Conventional MRI staging can be challenging in the preoperative assessment of rectal cancer. Deep learning methods based on MRI have shown promise in cancer diagnosis and prognostication. However, the value of deep learning in rectal cancer T-staging is unclear. PURPOSE: To develop a deep learning model based on preoperative multiparametric MRI for evaluation of rectal cancer and to investigate its potential to improve T-staging accuracy. STUDY TYPE: Retrospective. POPULATION: After cross-validation, 260 patients (123 with T-stage T1-2 and 134 with T-stage T3-4) with histopathologically confirmed rectal cancer were randomly divided to the training (N = 208) and test sets (N = 52). FIELD STRENGTH/SEQUENCE: 3.0 T/Dynamic contrast enhanced (DCE), T2-weighted imaging (T2W), and diffusion-weighted imaging (DWI). ASSESSMENT: The deep learning (DL) model of multiparametric (DCE, T2W, and DWI) convolutional neural network were constructed for evaluating preoperative diagnosis. The pathological findings served as the reference standard for T-stage. For comparison, the single parameter DL-model, a logistic regression model composed of clinical features and subjective assessment of radiologists were used. STATISTICAL TESTS: The receiver operating characteristic curve (ROC) was used to evaluate the models, the Fleiss' kappa for the intercorrelation coefficients, and DeLong test for compare the diagnostic performance of ROCs. P-values less than 0.05 were considered statistically significant. RESULTS: The Area Under Curve (AUC) of the multiparametric DL-model was 0.854, which was significantly higher than the radiologist's assessment (AUC = 0.678), clinical model (AUC = 0.747), and the single parameter DL-models including T2W-model (AUC = 0.735), DWI-model (AUC = 0.759), and DCE-model (AUC = 0.789). DATA CONCLUSION: In the evaluation of rectal cancer patients, the proposed multiparametric DL-model outperformed the radiologist's assessment, the clinical model as well as the single parameter models. The multiparametric DL-model has the potential to assist clinicians by providing more reliable and precise preoperative T staging diagnosis. EVIDENCE LEVEL: 3 TECHNICAL EFFICACY: Stage 2.

Deep learning prediction of esophageal squamous cell carcinoma invasion depth from arterial phase enhanced CT images: a binary classification approach.

BACKGROUND: Precise prediction of esophageal squamous cell carcinoma (ESCC) invasion depth is crucial not only for optimizing treatment plans but also for reducing the need for invasive procedures, consequently lowering complications and costs. Despite this, current techniques, which can be invasive and costly, struggle with achieving the necessary precision, highlighting a pressing need for more effective, non-invasive alternatives. METHOD: We developed ResoLSTM-Depth, a deep learning model to distinguish ESCC stages T1-T2 from T3-T4. It integrates ResNet-18 and Long Short-Term Memory (LSTM) networks, leveraging their strengths in spatial and sequential data processing. This method uses arterial phase CT scans from ESCC patients. The dataset was meticulously segmented by an experienced radiologist for effective training and validation. RESULTS: Upon performing five-fold cross-validation, the ResoLSTM-Depth model exhibited commendable performance with an accuracy of 0.857, an AUC of 0.901, a sensitivity of 0.884, and a specificity of 0.828. These results were superior to the ResNet-18 model alone, where the average accuracy is 0.824 and the AUC is 0.879. Attention maps further highlighted influential features for depth prediction, enhancing model interpretability. CONCLUSION: ResoLSTM-Depth is a promising tool for ESCC invasion depth prediction. It offers potential for improvement in the staging and therapeutic planning of ESCC.

Low blood flow ratio is associated with hemorrhagic transformation secondary to mechanical thrombectomy in patients with acute ischemic stroke.

BACKGROUND AND PURPOSE: A significant decrease of cerebral blood flow (CBF) is a risk factor for hemorrhagic transformation (HT) in acute ischemic stroke (AIS). This study aimed to ascertain whether the ratio of different CBF thresholds derived from computed tomography perfusion (CTP) is an independent risk factor for HT after mechanical thrombectomy (MT). METHODS: A retrospective single center cohort study was conducted on patients with AIS undergoing MT at the First Affiliated Hospital of Wenzhou Medical University from August 2018 to December 2023. The perfusion parameters before thrombectomy were obtained according to CTP automatic processing software. The low blood flow ratio (LFR) was defined as the ratio of brain volume with relative CBF <20 % over volume with relative CBF <30 %. HT was evaluated on the follow-up CT images. Binary logistic regression was used to analyze the correlation between parameters that differ between the two groups with regards to HT occurrence. The predictive efficacy was assessed utilizing the receiver operating characteristic curve. RESULTS: In total, 243 patients met the inclusion criteria. During the follow-up, 46.5 % of the patients (113/243) developed HT. Compared with the Non-HT group, the HT group had a higher LFR (0.47 (0.34-0.65) vs. 0.32 (0.07-0.56); P < 0.001). According to the binary logistic regression analysis, the LFR (aOR: 6.737; 95 % CI: 1.994-22.758; P = 0.002), Hypertension history (aOR: 2.231; 95 % CI: 1.201-4.142; P = 0.011), plasma FIB levels before MT (aOR: 0.641; 95 % CI: 0.456-0.902; P = 0.011), and the mismatch ratio (aOR: 0.990; 95 % CI: 0.980-0.999; P = 0.030) were independently associated with HT secondary to MT. The area under the curve of the regression model for predicting HT was 0.741. CONCLUSION: LFR, a ratio quantified via CTP, demonstrates potential as an independent risk factor of HT secondary to MT.

Molecular Mechanism Exploration of Pancreatitis Based on miRNA Expression Profile.

BACKGROUND: Pancreatitis is a popular disease around the world, and can also lead to pancreatic cancer. Pancreatitis can be distinguished into two types, acute pancreatitis (AP) and chronic pancreatitis (CP). Every year, AP leads to approximately 275,000 new cases and is the most frequent gastrointestinal disease in American. METHODS: The miRNA expression profile of pancreatic cancer and pancreatitis was downloaded from GEO with accession id GSE24279. First, the differentially expressed miRNAs with |fold change| ≥ 2 and p-value ≤ 0.05 and then the target genes of significantly differentially expressed miRNAs in pancreatitis were identified and the interaction network was constructed. Also the biological functions of the target genes were explored based on GO and KEGG enrichment. Finally, the expression values of hsa-miR-373-5p and hsa-miR-374a-5p were validated using RT-PCR. RESULTS: A total of 40 and 13 differentially expressed miRNAs were screened out for pancreatic and pancreatitis, respectively. Two miRNAs, hsa-miR-373-5p and hsa-miR-374a-5p, had significantly down-regulated expression in pancreatitis. Target gene analysis showed that hsa-miR-373-5p probably participates in the development of pancreatitis by regulating MBL2, MAT2B, and BCL10. In addition, has-miR-374a-5p can regulate the expression of NCK1, MMP14. Those genes are involved in nuclear factor kappa B and p38 signaling in the early stage of pancreatitis. Also, NCK1 can regulate pancreatic ß-cell proinsulin content and participate in the progression of pancreatic cancer development. CONCLUSIONS: In summary, the findings in this study deciphered the potential miRNA regulation mechanism in pancreatitis, and identified valuable biomarkers for the diagnosis of pancreatitis.

Quantitative assessment on blood-brain barrier permeability of acute spontaneous intracerebral hemorrhage in basal ganglia: a CT perfusion study.

PURPOSE: Blood-brain barrier (BBB) damage aggravates perihematomal edema, and edema volume predicts prognosis independently. But the BBB permeability at the late stage of acute intracerebral hemorrhage (ICH) patients is uncertain. We aimed to assess the BBB permeability of spontaneous basal ganglia ICH using computed tomographic perfusion (CTP) and investigates its relationship with hematoma and perihematomal edema volume. METHODS: We performed CTP on 54 consecutive ICH patients within 24 to 72 h after symptom onset. Permeability-surface area product (PS) derived from CTP imaging was measured in hematoma, "high-PS spot," perihematoma, normal-appearing, hemispheric, and contralateral regions. Hematoma and edema volumes were calculated from non-contrast CT. RESULTS: "High-PS spot" and perihematoma regions had higher PS than the contralateral regions (p < 0.001). Hematoma PS was lower than that in the contralateral regions (p < 0.001). Perihematoma PS of the large-hematoma group was higher than that of the small-hematoma group (p = 0.011). Perihematomal edema volume correlated positively with hematoma volume (ß = 0.864, p < 0.001) and perihematoma PS (ß = 0.478, p < 0.001). Perihematoma PS correlated positively with hematoma volume (ß = 0.373, p = 0.005). CONCLUSIONS: Locally elevated perihematoma PS was found in most spontaneous basal ganglia ICH patients within 24 to 72 h after symptom onset. Perihematoma PS was higher in larger hematomas and was associated with larger edema volume. At this period, BBB leakage is likely to be an important factor in edema formation.

Effect of alprazolam on rat serum metabolic profiles.

We developed a serum metabolomic method by gas chromatography-mass spectrometry (GC-MS) to evaluate the effect of alprazolam in rats. The GC-MS with HP-5MS (0.25 µm × 30 m × 0.25 mm) mass was conducted in electron impact ionization (EI) mode with electron energy of 70 eV, and full-scan mode with m/z 50-550. The rats were randomly divided to four groups, three alprazolam-treated groups and a control group. The alprazolam-treated rats were given 5, 10 or 20 mg/kg (low, medium, high) of alprazolam by intragastric administration each day for 14 days. The serum samples were corrected on the seventh and fourteenth days for metabolomic study. The blood was collected for biochemical tests. Then liver and brain were rapidly isolated and immersed for pathological study. Compared with the control group, on the seventh and fourteen days, the levels of d-glucose, 9,12-octadecadienoic acid, butanoic acid, l-proline, d-mannose and malic acid had changed, indicating that alprazolam induced energy metabolism, fatty acid metabolism and amino acid metabolism perturbations in rats. There was no significant difference for alanine aminotransferase, aspartate aminotransferase, alkaline phosphatase, urea and uric acid between controls and alprazolam groups. According to the pathological results, alprazolam is not hepatotoxic. Metabolomics could distinguish different alprazolam doses in rats.

[Optimizing scan protocol in whole-brain vessel one-stop examination with 640-multislice computed tomography].

OBJECTIVE: To explore the feasibility of optimized scan protocol in whole-brain vessel one-stop examination with 640-multislice computed tomography (640-MSCT) scanner. METHODS: A total of 28 patients undergoing whole-brain vessel examination but showing no obvious cerebral disease with 640-MSCT scanner between September 2012 and May 2013 were collected and divided into two groups of A (n = 14) and B (n = 14) . The recommended scan protocol (protocol 1: collecting 19 volumes) was applied in A group while the optimized scan protocol (protocol 2: collecting 15 volumes) formulated by reducing scanning phases reasonably and changing collection intervals in B group. The dose length product (DLP) was recorded automatically and effective dose (E) measured. The CT perfusion (CTP) values and computed tomographic angiography (CTA) images were analyzed for both groups. The regions of interest (ROI) of CTP images with area (20 ± 2) mm² were located in bilateral frontal white matter, parietal white matter, centrum semiovate, basal ganglia, occipital lobe and cerebellum. The image quality of CTA was evaluated by two experienced radiologists using double-blind method. The results were analyzed by statistics. RESULTS: Dose length product (DLP) in B group decreased 19.23% versus A group (3 419.40 vs 4 233.50 mGy·cm) .Every relative perfusion value of both sides from both groups were not statistically significant (P > 0.05) .Every relative perfusion parameter from individual territory in both groups showed no significant differences (P > 0.05) . The quality of CTA images between groups A and B were not statistically significant (P > 0.05) . CONCLUSION: On the premise that the accuracy of perfusion parameters and the quality of CTA images, the optimized scan protocol in whole-brain vessel one-stop examination can obviously reduce radiation dose and it has important clinical significance.

Histone 3 lysine 9 acetylation-specific reprogramming regulates esophageal squamous cell carcinoma progression and metastasis.

Dysregulation of histone acetylation is widely implicated in tumorigenesis, yet its specific roles in the progression and metastasis of esophageal squamous cell carcinoma (ESCC) remain unclear. Here, we profiled the genome-wide landscapes of H3K9ac for paired adjacent normal (Nor), primary ESCC (EC) and metastatic lymph node (LNC) esophageal tissues from three ESCC patients. Compared to H3K27ac, we identified a distinct epigenetic reprogramming specific to H3K9ac in EC and LNC samples relative to Nor samples. This H3K9ac-related reprogramming contributed to the transcriptomic aberration of targeting genes, which were functionally associated with tumorigenesis and metastasis. Notably, genes with gained H3K9ac signals in both primary and metastatic lymph node samples (common-gained gene) were significantly enriched in oncogenes. Single-cell RNA-seq analysis further revealed that the corresponding top 15 common-gained genes preferred to be enriched in mesenchymal cells with high metastatic potential. Additionally, in vitro experiment demonstrated that the removal of H3K9ac from the common-gained gene MSI1 significantly downregulated its transcription, resulting in deficiencies in ESCC cell proliferation and migration. Together, our findings revealed the distinct characteristics of H3K9ac in esophageal squamous cell carcinogenesis and metastasis, and highlighted the potential therapeutic avenue for intervening ESCC through epigenetic modulation via H3K9ac.

Characterization of local white matter microstructural alterations in Alzheimer's disease: A reproducible study.

Alzheimer's disease (AD) is a neurodegenerative disease with a close association with microstructural alterations in white matter (WM). Current studies lack the characterization and further validation of specific regions in WM fiber tracts in AD. This study subdivided fiber tracts into multiple fiber clusters on the basis of automated fiber clustering and performed quantitative analysis along the fiber clusters to identify local WM microstructural alterations in AD. Diffusion tensor imaging data from a public dataset (53 patients with AD and 70 healthy controls [HCs]) and a clinical dataset (27 patients with AD and 19 HCs) were included for mutual validation. Whole-brain tractograms were automatically subdivided into 800 clusters through the automatic fiber clustering approach. Then, 100 segments were divided along the clusters, and the diffusion properties of each segment were calculated. Results showed that patients with AD had significantly lower fraction anisotropy (FA) and significantly higher mean diffusivity (MD) in some regions of the fiber clusters in the cingulum bundle, uncinate fasciculus, external capsule, and corpus callosum than HCs. Importantly, these changes were reproducible across the two datasets. Correlation analysis revealed a positive correlation between FA and Mini-Mental State Examination (MMSE) scores and a negative correlation between MD and MMSE in these clusters. The accuracy of the constructed classifier reached 89.76% with an area under the curve of 0.93. This finding indicates that this study can effectively identify local WM microstructural changes in AD and provides new insight into the analysis and diagnosis of WM abnormalities in patients with AD.

Enhanced Prediction of Malignant Cerebral Edema in Large Vessel Occlusion with Successful Recanalization Through Automated Weighted Net Water Uptake.

BACKGROUND: Malignant cerebral edema (MCE) is associated with both net water uptake (NWU) and infarct volume. We hypothesized that NWU weighted by the affected Alberta Stroke Program Early Computed Tomography Score (ASPECTS) regions could serve as a quantitative imaging biomarker of aggravated edema development in acute ischemic stroke with large vessel occlusion (LVO). The aim of this study was to evaluate the performance of weighted NWU (wNWU) to predict MCE in patients with mechanical thrombectomy (MT). METHODS: We retrospectively analyzed consecutive patients who underwent MT due to LVO. NWU was computed from nonenhanced computed tomography scans upon admission using automated ASPECTS software. wNWU was derived by multiplying NWU with the number of affected ASPECTS regions in the ischemic hemisphere. Predictors of MCE were assessed through multivariate logistic regression analysis and receiver operating characteristic curves. RESULTS: NWU and wNWU were significantly higher in MCE patients than in non-MCE patients. Vessel recanalization status influenced the performance of wNWU in predicting MCE. In patients with successful recanalization, wNWU was an independent predictor of MCE (adjusted odds ratio 1.61; 95% confidence interval [CI] 1.24-2.09; P < 0.001). The model integrating wNWU, National Institutes of Health Stroke Scale, and collateral score exhibited an excellent performance in predicting MCE (area under the curve 0.80; 95% CI 0.75-0.84). Among patients with unsuccessful recanalization, wNWU did not influence the development of MCE (adjusted odds ratio 0.99; 95% CI 0.60-1.62; P = 0.953). CONCLUSIONS: This study revealed that wNWU at admission can serve as a quantitative predictor of MCE in LVO with successful recanalization after MT and may contribute to the decision for early intervention.

Radiation pneumonitis prediction with dual-radiomics for esophageal cancer underwent radiotherapy.

BACKGROUND: To integrate radiomics and dosiomics features from multiple regions in the radiation pneumonia (RP grade ≥ 2) prediction for esophageal cancer (EC) patients underwent radiotherapy (RT). METHODS: Total of 143 EC patients in the authors' hospital (training and internal validation: 70%:30%) and 32 EC patients from another hospital (external validation) underwent RT from 2015 to 2022 were retrospectively reviewed and analyzed. Patients were dichotomized as positive (RP+) or negative (RP-) according to CTCAE V5.0. Models with radiomics and dosiomics features extracted from single region of interest (ROI), multiple ROIs and combined models were constructed and evaluated. A nomogram integrating radiomics score (Rad_score), dosiomics score (Dos_score), clinical factors, dose-volume histogram (DVH) factors, and mean lung dose (MLD) was also constructed and validated. RESULTS: Models with Rad_score_Lung&Overlap and Dos_score_Lung&Overlap achieved a better area under curve (AUC) of 0.818 and 0.844 in the external validation in comparison with radiomics and dosiomics models with features extracted from single ROI. Combining four radiomics and dosiomics models using support vector machine (SVM) improved the AUC to 0.854 in the external validation. Nomogram integrating Rad_score, and Dos_score with clinical factors, DVH factors, and MLD further improved the RP prediction AUC to 0.937 and 0.912 in the internal and external validation, respectively. CONCLUSION: CT-based RP prediction model integrating radiomics and dosiomics features from multiple ROIs outperformed those with features from a single ROI with increased reliability for EC patients who underwent RT.

Effect of low tube voltage on image quality, radiation dose, and low-contrast detectability at abdominal multidetector CT: phantom study.

PURPOSE: To investigate the effect of low tube voltage (80 kV) on image quality, radiation dose, and low-contrast detectability (LCD) at abdominal computed tomography (CT). MATERIALS AND METHODS: A phantom containing low-contrast objects was scanned with a CT scanner at 80 and 120 kV, with tube current-time product settings at 150-650 mAs. The differences between image noise, contrast-to-noise ratio (CNR), and scores of LCD obtained with 80 kV at 150-650 mAs and those obtained with 120 kV at 300 mAs were compared respectively. RESULTS: The image noise substantially increased with low tube voltage. However, with identical dose, use of 80 kV resulted in higher CNR compared with CNR at 120 kV. There were no statistically significant difference in CNR and scores of LCD between 120 kV at 300 mAs and 80 kV at 550-650 mAs (P > 0.05). The relative dose delivered at 80 kV ranged from 58% at 550 mAs to 68% at 650 mAs. CONCLUSION: With a reduction of the tube voltage from 120 kV to 80 kV at abdominal CT, the radiation dose can be reduced by 32% to 42% without degradation of CNR and LCD.

Brain network connectivity feature extraction using deep learning for Alzheimer's disease classification.

Early diagnosis and therapeutic intervention for Alzheimer's disease (AD) is currently the only viable option for improving clinical outcomes. Combining structural magnetic resonance imaging (sMRI) and resting-state functional magnetic resonance imaging (rs-fMRI) to diagnose AD has yielded promising results. Most studies assume fixed time lags when constructing functional networks. Since the propagation delays between brain signals are constantly changing, these methods cannot reflect more detailed relationships between brain regions. In this work, we use a deep learning-based Granger causality estimator for brain connectivity construction. It exploits the strength of long short-term memory in ever-changing time series processing. This research involves data analysis from sMRI and rs-fMRI. We use sMRI to analyze the cerebral cortex properties and use rs-fMRI to analyze the graph metrics of functional networks. We extract a small subset of optimal features from both types of data. A support vector machine (SVM) is trained and tested to classify AD (n = 27) from healthy controls (n = 20) using rs-fMRI and sMRI features. Using a subset of optimal features in SVM, we achieve a classification accuracy of 87.23% for sMRI, 78.72% for rs-fMRI, and 91.49% for combined sMRI with rs-fMRI. The results show the potential to identify AD from healthy controls by integrating rs-fMRI and sMRI. The integration of sMRI and rs-fMRI modalities can provide supplemental information to improve the diagnosis of AD relative to either the sMRI or fMRI modalities alone.

Integrative Analysis of 5-Hydroxymethylcytosine and Transcriptional Profiling Identified 5hmC-Modified lncRNA Panel as Non-Invasive Biomarkers for Diagnosis and Prognosis of Pancreatic Cancer.

Pancreatic adenocarcinoma (PAAD) is the fourth leading cause of cancer-related deaths worldwide. 5-Hydroxymethylcytosine (5hmC)-mediated epigenetic regulation has been reported to be involved in cancer pathobiology and has emerged to be promising biomarkers for cancer diagnosis and prognosis. However, 5hmC alterations at long non-coding RNA (lncRNA) genes and their clinical significance remained unknown. In this study, we performed the genome-wide investigation of lncRNA-associated plasma cfDNA 5hmC changes in PAAD by plotting 5hmC reads against lncRNA genes, and identified six PAAD-specific lncRNAs with abnormal 5hmC modifications compared with healthy individuals. Then we applied machine-learning and Cox regression approaches to develop predictive diagnostic (5hLRS) and prognostic (5hLPS) models using the 5hmC-modified lncRNAs. The 5hLRS demonstrated excellent performance in discriminating PAAD from healthy controls with an area under the curve (AUC) of 0.833 in the training cohort and 0.719 in the independent testing cohort. The 5hLPS also effectively divides PAAD patients into high-risk and low-risk groups with significantly different clinical outcomes in the training cohort (log-rank test p = 0.04) and independent testing cohort (log-rank test p = 0.0035). Functional analysis based on competitive endogenous RNA (ceRNA) and enrichment analysis suggested that these differentially regulated 5hmC modified lncRNAs were associated with angiogenesis, circulatory system process, leukocyte differentiation and metal ion homeostasis that are known important events in the development and progression of PAAD. In conclusion, our study indicated the potential clinical utility of 5hmC profiles at lncRNA loci as valuable biomarkers for non-invasive diagnosis and prognostication of cancers.

Differentiating Primary Tumors for Brain Metastasis with Integrated Radiomics from Multiple Imaging Modalities.

Objectives: To differentiate the primary site of brain metastases (BMs) is of high clinical value for the successful management of patients with BM. The purpose of this study is to investigate a combined radiomics model with computer tomography (CT) and magnetic resonance imaging (MRI) images in differentiating BMs originated from lung and breast cancer. Methods: Pretreatment cerebral contrast enhanced CT and T1-weighted MRI images of 78 patients with 179 BMs from primary lung and breast cancer were retrospectively analyzed. Radiomic features were extracted from contoured BM lesions and selected using the Mann-Whitney U test and the least absolute shrinkage and selection operator (LASSO) logistic regression. Binary logistic regression (BLR) and support vector machine (SVM) models were built and evaluated based on selected radiomic features from CT alone, MRI alone, and combined images to differentiate BMs originated from lung and breast cancer. Results: A total of 10 and 6 optimal radiomic features were screened out of 1288 CT and 1197 MRI features, respectively. The mean area under the curves (AUCs) of the BLR and SVM models using fivefolds cross-validation were 0.703 vs. 0.751, 0.718 vs. 0.754, and 0.781 vs. 0.803 in the training dataset and 0.708 vs. 0.763, 0.715 vs. 0.717, and 0.771 vs. 0.805 in the testing dataset for models with CT alone, MRI alone, and combined CT and MRI radiomic features, respectively. Conclusions: Radiomics model based on combined CT and MRI features is feasible and accurate in the differentiation of the primary site of BMs from lung and breast cancer.

Image Quality Control in Lumbar Spine Radiography Using Enhanced U-Net Neural Networks.

Purpose: To standardize the radiography imaging procedure, an image quality control framework using the deep learning technique was developed to segment and evaluate lumbar spine x-ray images according to a defined quality control standard. Materials and Methods: A dataset comprising anteroposterior, lateral, and oblique position lumbar spine x-ray images from 1,389 patients was analyzed in this study. The training set consisted of digital radiography images of 1,070 patients (800, 798, and 623 images of the anteroposterior, lateral, and oblique position, respectively) and the validation set included 319 patients (200, 205, and 156 images of the anteroposterior, lateral, and oblique position, respectively). The quality control standard for lumbar spine x-ray radiography in this study was defined using textbook guidelines of as a reference. An enhanced encoder-decoder fully convolutional network with U-net as the backbone was implemented to segment the anatomical structures in the x-ray images. The segmentations were used to build an automatic assessment method to detect unqualified images. The dice similarity coefficient was used to evaluate segmentation performance. Results: The dice similarity coefficient of the anteroposterior position images ranged from 0.82 to 0.96 (mean 0.91 ± 0.06); the dice similarity coefficient of the lateral position images ranged from 0.71 to 0.95 (mean 0.87 ± 0.10); the dice similarity coefficient of the oblique position images ranged from 0.66 to 0.93 (mean 0.80 ± 0.14). The accuracy, sensitivity, and specificity of the assessment method on the validation set were 0.971-0.990 (mean 0.98 ± 0.10), 0.714-0.933 (mean 0.86 ± 0.13), and 0.995-1.000 (mean 0.99 ± 0.12) for the three positions, respectively. Conclusion: This deep learning-based algorithm achieves accurate segmentation of lumbar spine x-ray images. It provides a reliable and efficient method to identify the shape of the lumbar spine while automatically determining the radiographic image quality.

Dynamic change of COVID-19 lung infection evaluated using co-registration of serial chest CT images.

Purpose: To evaluate the volumetric change of COVID-19 lesions in the lung of patients receiving serial CT imaging for monitoring the evolution of the disease and the response to treatment. Materials and methods: A total of 48 patients, 28 males and 20 females, who were confirmed to have COVID-19 infection and received chest CT examination, were identified. The age range was 21-93 years old, with a mean of 54 ± 18 years. Of them, 33 patients received the first follow-up (F/U) scan, 29 patients received the second F/U scan, and 11 patients received the third F/U scan. The lesion region of interest (ROI) was manually outlined. A two-step registration method, first using the Affine alignment, followed by the non-rigid Demons algorithm, was developed to match the lung areas on the baseline and F/U images. The baseline lesion ROI was mapped to the F/U images using the obtained geometric transformation matrix, and the radiologist outlined the lesion ROI on F/U CT again. Results: The median (interquartile range) lesion volume (cm3) was 30.9 (83.1) at baseline CT exam, 18.3 (43.9) at first F/U, 7.6 (18.9) at second F/U, and 0.6 (19.1) at third F/U, which showed a significant trend of decrease with time. The two-step registration could significantly decrease the mean squared error (MSE) between baseline and F/U images with p < 0.001. The method could match the lung areas and the large vessels inside the lung. When using the mapped baseline ROIs as references, the second-look ROI drawing showed a significantly increased volume, p < 0.05, presumably due to the consideration of all the infected areas at baseline. Conclusion: The results suggest that the registration method can be applied to assist in the evaluation of longitudinal changes of COVID-19 lesions on chest CT.

Diagnosis of architectural distortion on digital breast tomosynthesis using radiomics and deep learning.

Purpose: To implement two Artificial Intelligence (AI) methods, radiomics and deep learning, to build diagnostic models for patients presenting with architectural distortion on Digital Breast Tomosynthesis (DBT) images. Materials and Methods: A total of 298 patients were identified from a retrospective review, and all of them had confirmed pathological diagnoses, 175 malignant and 123 benign. The BI-RADS scores of DBT were obtained from the radiology reports, classified into 2, 3, 4A, 4B, 4C, and 5. The architectural distortion areas on craniocaudal (CC) and mediolateral oblique (MLO) views were manually outlined as the region of interest (ROI) for the radiomics analysis. Features were extracted using PyRadiomics, and then the support vector machine (SVM) was applied to select important features and build the classification model. Deep learning was performed using the ResNet50 algorithm, with the binary output of malignancy and benignity. The Gradient-weighted Class Activation Mapping (Grad-CAM) method was utilized to localize the suspicious areas. The predicted malignancy probability was used to construct the ROC curves, compared by the DeLong test. The binary diagnosis was made using the threshold of ≥ 0.5 as malignant. Results: The majority of malignant lesions had BI-RADS scores of 4B, 4C, and 5 (148/175 = 84.6%). In the benign group, a substantial number of patients also had high BI-RADS ≥ 4B (56/123 = 45.5%), and the majority had BI-RADS ≥ 4A (102/123 = 82.9%). The radiomics model built using the combined CC+MLO features yielded an area under curve (AUC) of 0.82, the sensitivity of 0.78, specificity of 0.68, and accuracy of 0.74. If only features from CC were used, the AUC was 0.77, and if only features from MLO were used, the AUC was 0.72. The deep-learning model yielded an AUC of 0.61, significantly lower than all radiomics models (p<0.01), which was presumably due to the use of the entire image as input. The Grad-CAM could localize the architectural distortion areas. Conclusion: The radiomics model can achieve a satisfactory diagnostic accuracy, and the high specificity in the benign group can be used to avoid unnecessary biopsies. Deep learning can be used to localize the architectural distortion areas, which may provide an automatic method for ROI delineation to facilitate the development of a fully-automatic computer-aided diagnosis system using combined AI strategies.

Multi-modality radiomics nomogram based on DCE-MRI and ultrasound images for benign and malignant breast lesion classification.

Objective: To develop a multi-modality radiomics nomogram based on DCE-MRI, B-mode ultrasound (BMUS) and strain elastography (SE) images for classifying benign and malignant breast lesions. Material and Methods: In this retrospective study, 345 breast lesions from 305 patients who underwent DCE-MRI, BMUS and SE examinations were randomly divided into training (n = 241) and testing (n = 104) datasets. Radiomics features were extracted from manually contoured images. The inter-class correlation coefficient (ICC), Mann-Whitney U test and the least absolute shrinkage and selection operator (LASSO) regression were applied for feature selection and radiomics signature building. Multivariable logistic regression was used to develop a radiomics nomogram incorporating radiomics signature and clinical factors. The performance of the radiomics nomogram was evaluated by its discrimination, calibration, and clinical usefulness and was compared with BI-RADS classification evaluated by a senior breast radiologist. Results: The All-Combination radiomics signature derived from the combination of DCE-MRI, BMUS and SE images showed better diagnostic performance than signatures derived from single modality alone, with area under the curves (AUCs) of 0.953 and 0.941 in training and testing datasets, respectively. The multi-modality radiomics nomogram incorporating the All-Combination radiomics signature and age showed excellent discrimination with the highest AUCs of 0.964 and 0.951 in two datasets, respectively, which outperformed all single modality radiomics signatures and BI-RADS classification. Furthermore, the specificity of radiomics nomogram was significantly higher than BI-RADS classification (both p < 0.04) with the same sensitivity in both datasets. Conclusion: The proposed multi-modality radiomics nomogram based on DCE-MRI and ultrasound images has the potential to serve as a non-invasive tool for classifying benign and malignant breast lesions and reduce unnecessary biopsy.

Reduced artifacts and improved diagnostic value of 640-slice computed tomography in patients with cardiac pacemakers.

OBJECTIVE: The aim of this study was to compare the feasibility of 640-slice with 64-slice computed tomography (CT) coronary angiography for diagnosing coronary lesions in patients with pacemakers. METHODS: Forty-five and 50 patients with pacemakers and with suspected or known coronary artery disease underwent 64-slice (64 group) and 640-slice (640 group) CT scans, respectively. All segments of the vessels were evaluated according to the 15-segment model recommended by the American Heart Association. RESULTS: The incidence of moderate or severe artifacts was significantly lower (7.27% vs. 32.17%) and the diagnosable rate for coronary lesions was higher (98.91% vs. 94.19%) in the 640 compared with the 64 group. In the 64 group, the incidence of artifacts in patients with a heart rate >65 bpm (20.98%) was higher than in those with a heart rate <65 bpm (15.67%), although the difference was not significant, while the incidence of artifacts was significantly higher in patients with heart arrhythmia (21.40%) compared with in those with normal heart rhythm (15.09%). CONCLUSIONS: Among patients with pacemakers and a higher heart rate or heart arrhythmia, 640-slice CT may be more effective than 64-slice CT for diagnosing coronary lesions, by reducing moderate and severe artifacts.