Assessing muscle invasion in bladder cancer via virtual biopsy: a study on quantitative parameters and classical radiomics features from dual-energy CT imaging.

OBJECTIVE: To evaluate the prediction value of Dual-energy CT (DECT)-based quantitative parameters and radiomics model in preoperatively predicting muscle invasion in bladder cancer (BCa). MATERIALS AND METHODS: A retrospective study was performed on 126 patients with BCa who underwent DECT urography (DECTU) in our hospital. Patients were randomly divided into training and test cohorts with a ratio of 7:3. Quantitative parameters derived from DECTU were identified through univariate and multivariate logistic regression analysis to construct a DECT model. Radiomics features were extracted from the 40, 70, 100 keV and iodine-based material-decomposition (IMD) images in the venous phase to construct radiomics models from individual and combined images using a support vector machine classifier, and the optimal performing model was chosen as the final radiomics model. Subsequently, a fusion model combining the DECT parameters and the radiomics model was established. The diagnostic performances of all three models were evaluated through receiver operating characteristic (ROC) curves and the clinical usefulness was estimated using decision curve analysis (DCA). RESULTS: The normalized iodine concentration (NIC) in DECT was an independent factor in diagnosing muscle invasion of BCa. The optimal multi-image radiomics model had predictive performance with an area-under-the-curve (AUC) of 0.867 in the test cohort, better than the AUC = 0.704 with NIC. The fusion model showed an increased level of performance, although the difference in AUC (0.893) was not statistically significant. Additionally, it demonstrated superior performance in DCA. For lesions smaller than 3 cm, the fusion model showed a high predictive capability, achieving an AUC value of 0.911. There was a slight improvement in model performance, although the difference was not statistically significant. This improvement was observed when comparing the AUC values of the DECT and radiomics models, which were 0.726 and 0.884, respectively. CONCLUSION: The proposed fusion model combing NIC and the optimal multi-image radiomics model in DECT showed good diagnostic capability in predicting muscle invasiveness of BCa.

Individualized Scan Protocol Based on Body Mass Index in Dual-Energy Computed Tomography Pulmonary Angiography to Reduce Radiation and Contrast Doses with Improved Image Quality.

BACKGROUND We evaluated an individualized dual-energy computed tomography (DECT) scan protocol by combining optimal monochromatic images with an appropriate ASIR-V reconstruction strength in computed tomography pulmonary angiography (CTPA) to reduce radiation and iodine doses and superior vena cava (SVC) artifacts. MATERIAL AND METHODS A total of 127 patients who underwent CTPA were prospectively enrolled and randomly divided into a standard (n=63) and individualized group (n=64). The standard group used 120 kVp, 150 mAs, and 60 mL contrast media at an injection rate of 5 mL/s; the individualized group used DECT imaging mode with tube current selected according to patients' BMI (BMI ≤20 kg/m², 200 mA; 20< BMI ≤23 kg/m², 240 mA; 23< BMI ≤25 kg/m², 280 mA; BMI >25 kg/m², 320 mA). Contrast media intake was 130 mgI/kg with an injection time of 7 s. The data in the individualized group was reconstructed to 55-70 keV (5 keV interval) monochromatic images combined with 40-80% ASIR-V (10% interval). Radiation dose, contrast dose, and image quality were compared between the groups. RESULTS There were no significant differences in patient habitus. Compared with the standard group, the individualized group significantly decreased radiation dose by 33.93% (3.31±0.57 mSv vs 5.01±0.34 mSv) and contrast dose by 56.95% (9.04±1.40 gI vs 21.00±0.00 gI). The 60 keV image with 80%ASIR-V in the individualized group provided the best image quality and further reduced SVC beam-hardening artifacts. CONCLUSIONS The use of BMI-dependent DECT protocol in CTPA further reduces radiation dose, contrast agent dose, and SVC artifacts, with the 60 keV images reconstructed using 80%ASiR-V having the best image quality.

Evaluation of BMI-based tube voltage selection in CT colonography: A prospective comparison of low kV versus routine 120 kV protocol.

AIM: To explore the value of individualized kVp selection based on the patient's body mass index (BMI, kg/m2 ) in CT colonography (CTC). MATERIALS AND METHODS: Seventy-eight patients underwent two CTC scans: conventional 120 kVp in supine position (Group A) with 30% Adaptive statistical iteration algorithm (ASIR-V) and BMI-based lower kV p in prone position (Group B): tube voltage was suggested by an experienced investigator according to the patient's body mass index (BMI; calculated as weight divided by height squared; kg/m (2)).70 kV for BMI < 23 kg/m2 (Group B1, n = 27), 80 kV for 23 ≤ BMI ≤ 25 kg/m2 (Group B2, n = 21) and 100 kV for BMI > 25 kg/m2 (Group B3, n = 30). Group A, corresponding to the BMI value in Group B, was divided into A1, A2, and A3 subgroups for analysis. Groups B used ASIR-V of different weights (30%-90% ASIR-V). The Hounsfield Unit (HU) and SD values of the muscles and the intestinal cavity air were measured, and the signal-to-noise ratio (SNR) and the contrast-to-noise ratio (CNR) of images were calculated. Imaging quality was evaluated by two reviewers and statistically compared. RESULTS: The 120 kV scans were preferred more than 50% of the time. All images had excellent quality with good consistency between reviewers (Kappa > 0.75, p < 0.05). The radiation dose was reduced in groups B1, B2 and B3 by 63.62%, 44.63%, and 32.14%, respectively, compared with group A (p < 0.05). The SNR and CNR values between group A1/A2/A3 and B1/B2/B3 + 60%ASIR-V were not statistically significant (p < 0.05). There was no statistically significant difference between the subjective scores of group B combined with 60%ASIR-V and group A (p > 0.05). CONCLUSION: BMI-based individualized kV CTC imaging significantly reduces overall radiation dose while providing an equal image quality with the conventional 120 kV.

Automatic Osteoporosis Screening System Using Radiomics and Deep Learning from Low-Dose Chest CT Images.

OBJECTIVE: Develop two fully automatic osteoporosis screening systems using deep learning (DL) and radiomics (Rad) techniques based on low-dose chest CT (LDCT) images and evaluate their diagnostic effectiveness. METHODS: In total, 434 patients who underwent LDCT and bone mineral density (BMD) examination were retrospectively enrolled and divided into the development set (n = 333) and temporal validation set (n = 101). An automatic thoracic vertebra cancellous bone (TVCB) segmentation model was developed. The Dice similarity coefficient (DSC) was used to evaluate the segmentation performance. Furthermore, the three-class Rad and DL models were developed to distinguish osteoporosis, osteopenia, and normal bone mass. The diagnostic performance of these models was evaluated using the receiver operating characteristic (ROC) curve and decision curve analysis (DCA). RESULTS: The automatic segmentation model achieved excellent segmentation performance, with a mean DSC of 0.96 ± 0.02 in the temporal validation set. The Rad model was used to identify osteoporosis, osteopenia, and normal BMD in the temporal validation set, with respective area under the receiver operating characteristic curve (AUC) values of 0.943, 0.801, and 0.932. The DL model achieved higher AUC values of 0.983, 0.906, and 0.969 for the same categories in the same validation set. The Delong test affirmed that both models performed similarly in BMD assessment. However, the accuracy of the DL model is 81.2%, which is better than the 73.3% accuracy of the Rad model in the temporal validation set. Additionally, DCA indicated that the DL model provided a greater net benefit compared to the Rad model across the majority of the reasonable threshold probabilities Conclusions: The automated segmentation framework we developed can accurately segment cancellous bone on low-dose chest CT images. These predictive models, which are based on deep learning and radiomics, provided comparable diagnostic performance in automatic BMD assessment. Nevertheless, it is important to highlight that the DL model demonstrates higher accuracy and precision than the Rad model.

Fully automated deep learning system for osteoporosis screening using chest computed tomography images.

Background: Osteoporosis, a disease stemming from bone metabolism irregularities, affects approximately 200 million people worldwide. Timely detection of osteoporosis is pivotal in grappling with this public health challenge. Deep learning (DL), emerging as a promising methodology in the field of medical imaging, holds considerable potential for the assessment of bone mineral density (BMD). This study aimed to propose an automated DL framework for BMD assessment that integrates localization, segmentation, and ternary classification using various dominant convolutional neural networks (CNNs). Methods: In this retrospective study, a cohort of 2,274 patients underwent chest computed tomography (CT) was enrolled from January 2022 to June 2023 for the development of the integrated DL system. The study unfolded in 2 phases. Initially, 1,025 patients were selected based on specific criteria to develop an automated segmentation model, utilizing 2 VB-Net networks. Subsequently, a distinct cohort of 902 patients was employed for the development and testing of classification models for BMD assessment. Then, 3 distinct DL network architectures, specifically DenseNet, ResNet-18, and ResNet-50, were applied to formulate the 3-classification BMD assessment model. The performance of both phases was evaluated using an independent test set consisting of 347 individuals. Segmentation performance was evaluated using the Dice similarity coefficient; classification performance was appraised using the receiver operating characteristic (ROC) curve. Furthermore, metrics such as the area under the curve (AUC), accuracy, and precision were meticulously calculated. Results: In the first stage, the automatic segmentation model demonstrated excellent segmentation performance, with mean Dice surpassing 0.93 in the independent test set. In the second stage, both the DenseNet and ResNet-18 demonstrated excellent diagnostic performance in detecting bone status. For osteoporosis, and osteopenia, the AUCs were as follows: DenseNet achieved 0.94 [95% confidence interval (CI): 0.91-0.97], and 0.91 (95% CI: 0.87-0.94), respectively; ResNet-18 attained 0.96 (95% CI: 0.92-0.98), and 0.91 (95% CI: 0.87-0.94), respectively. However, the ResNet-50 model exhibited suboptimal diagnostic performance for osteopenia, with an AUC value of only 0.76 (95% CI: 0.69-0.80). Alterations in tube voltage had a more pronounced impact on the performance of the DenseNet. In the independent test set with tube voltage at 100 kVp images, the accuracy and precision of DenseNet decreased on average by approximately 14.29% and 18.82%, respectively, whereas the accuracy and precision of ResNet-18 decreased by about 8.33% and 7.14%, respectively. Conclusions: The state-of-the-art DL framework model offers an effective and efficient approach for opportunistic osteoporosis screening using chest CT, without incurring additional costs or radiation exposure.

Achieving sub-millisievert CT colonography for accurate colorectal tumor detection using smart examination protocols: a prospective self-controlled study.

PURPOSE: To assess the feasibility of combining Auto-kVp selection technique, higher preset ASIR-V and noise index (NI) to realize individualized sub-mSv CT colonography (CTC) for accurate colorectal tumor detection and localization. METHODS: Ninety patients with suspected colorectal cancer (CRC) were prospectively enrolled to undergo standard dose CTC (SDCTC) in the prone and ultra-low dose CTC (ULDCTC) in the supine position. SDCTC used 120 kVp, preset ASIR-V of 30%, SmartmA for a NI of 13; ULDCTC used Auto-kVp selection technique with 80 or 100 kVp, preset ASIR-V of 60%, SmartmA for a NI of 13 for 80 kVp, and NI of 15 for 100 kVp. The effective dose (ED), image quality [signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) of colorectal neoplasms] between the two protocols were compared and the accuracies of tumor locations were evaluated for CTC in comparison with the surgery results. RESULTS: The mean ED of the ULDCTC-80 kVp subgroup was 0.70 mSv, 71.43% lower than the 2.45 mSv for the 120 kVp group, while that of the ULDCTC-100 kVp subgroup was 0.98 mSv, 73.00% lower than the 3.63 mSv for the 120 kVp group (P < 0.001). The tumor SNR and CNR of the ULDCTC were higher than those of SDCTC (P < 0.05), while there was no difference in the subjective image quality between them with good inter-observer agreement (Kappa: 0.805-0.923). Both SDCTC and ULDCTC groups had high detection rate of colorectal tumors, along with good consistency in determining tumor location compared with surgery reports (Kappa: 0.718-0.989). CONCLUSION: The combination of Auto-kVp selection, higher preset ASIR-V and NI achieves individualized sub-mSv CTC with good performance in detecting and locating CRC with surgery and consistent results between SDCTC and ULDCTC.

Combining Deep Learning and Radiomics for Automated, Objective, Comprehensive Bone Mineral Density Assessment From Low-Dose Chest Computed Tomography.

RATIONALE AND OBJECTIVES: To develop an intelligent diagnostic model for osteoporosis screening based on low-dose chest computed tomography (LDCT). The model incorporates automatic deep-learning thoracic vertebrae of cancellous bone (TVCB) segmentation model and radiomics analysis. MATERIALS AND METHODS: A total of 442 participants who underwent both LDCT and quantitative computed tomography (QCT) examinations were enrolled and were randomly allocated to the training, internal testing, and external testing cohorts. The TVCB automatic segmentation model was trained using VB-Net. The accuracy of the segmentation was evaluated using the Dice coefficient. Predictive models for assessing bone mineral density (BMD) were constructed utilizing radiomics analysis based on automatic segmentation (ASeg model) and manual segmentation (MSeg model), respectively. The BMD predictive model based on ASeg and MSeg included the identification of normal and abnormal BMD (first-level model), and osteopenia and osteoporosis (second-level model). The diagnostic performance of the radiomics models were evaluated using the area under the curve (AUC), sensitivity and specificity. RESULTS: The Dice coefficients of the TVCB segmentation model in the internal and external testing cohorts were found to be 0.988 ± 0.014 and 0.939 ± 0.034, respectively. In the first-level model, the AUC of the ASeg model exhibited comparable performance to that of the MSeg model for both the internal (0.985 vs. 0.946, P = 0.080) and external (0.965 vs. 0.955, P = 0.724) testing cohorts. Similarly, in the second-level model, the AUC of the ASeg model was found to be comparable to that of the MSeg model for both the internal (0.933 vs. 0.920, P = 0.794) and external (0.907 vs. 0.892, P = 0.805) testing cohorts. CONCLUSION: A fully automated pipeline for TVCB segmentation and BMD assessment with radiomics analysis can be used for opportunistic BMD screening in chest LDCT.

Opportunistic screening for osteoporosis using enhanced images based on dual-energy computed tomography material decomposition: a comparison with quantitative computed tomography.

Background: Many patients with malignant tumors require chemotherapy and radiation therapy, which can result in a decline in physical function and potentially influence bone mineral density (BMD). Furthermore, these treatments necessitate enhanced computed tomography (CT) scans for determining disease staging or treatment outcomes, and opportunistic screening with available imaging data is beneficial for patients at high risk for osteoporosis if existing imaging data can be used. The study aimed to investigate the feasibility of opportunistic screening for osteoporosis using enhanced CT based on a dual-energy CT (DECT) material decomposition technique. Methods: We prospectively enrolled 346 consecutive patients who underwent abdominal unenhanced and triphasic contrast-enhanced CT (arterial, portal venous, and delayed phases) between June 2021 and June 2022. The BMD, and the density of hydroxyapatite (HAP) on HAP-iodine images and calcium (Ca) on Ca-iodine images were measured on the L1-L3 vertebral bodies. The iodine intake was recorded. Pearson analysis was conducted to assess the correlation between iodine intake and the density values in three phases and the correlation between BMD and the densities of HAP and Ca. Furthermore, linear regression was employed for quantitative evaluation. Bland-Altman analysis was used to evaluate the agreement between calculated BMD derived from DECT (BMD-DECT) and reference BMD derived from quantitative CT (BMD-QCT). Receiver operating characteristic (ROC) analysis was applied to assess the diagnostic efficacy. Results: The HAP and Ca density of the L1-L3 vertebral bodies did not differ significantly among the three phases of contrast-enhanced CT (F=0.001-0.049; P>0.05). Significant positive correlations were found between HAP, Ca densities, and BMD (HAP-BMD: r=0.9472, R2=0.8973; Ca-BMD: r=0.9470, R2=0.8968; all P<0.001). Bland-Altman plots showed high agreement between BMD-DECT and BMD-QCT. The area under the curve (AUC) using HAP and Ca measurements was 0.963 [95% confidence interval (CI): 0.937-0.980] and 0.964 (95% CI: 0.939-0.981), respectively, for diagnosing osteoporosis and was 0.951 (95% CI: 0.917-0.973) and 0.950 (95% CI: 0.916-0.973), respectively, for diagnosing osteopenia. Conclusions: The HAP and Ca density measurements generated through the material decomposition technique in DECT have good diagnostic performances in assessing BMD, which offers a new perspective for opportunistic screening of osteoporosis on contrast-enhanced CT.

Impact of multi-parameter images obtained from dual-energy CT on radiomics to predict pathological grading of bladder urothelial carcinoma.

OBJECTIVE: To investigate the effect of radiomics models obtained from dual-energy CT (DECT) material decomposition images and virtual monoenergetic images (VMIs) in predicting the pathological grading of bladder urothelial carcinoma (BUC). MATERIALS AND METHODS: A retrospective analysis of preoperative DECT examination was conducted on 112 patients diagnosed with BUC. This cohort included 76 cases of high-grade urothelial carcinoma and 36 cases of low-grade urothelial carcinoma. DECT can provide material decomposition images of venous phase Iodine maps and Water maps based on the differences in attenuation of substances, as well as VMIs at 40 to 140 keV (interval 10 keV). A total of 13 image sets were obtained, and radiomics features were extracted and analyzed from each set to achieve preoperative prediction of BUC. The best features related to BUC were identified by recursive feature elimination (RFE), the Minimum Redundancy Maximum Relevance (mRMR), and the Least Absolute Shrinkage and Selection Operator (LASSO) in order. A five-fold cross-validation method was used to divide the samples into training and testing sets, and models for pathological prediction of BUC grading were constructed by a random forest (RF) classifier. Receiver operating curves (ROC) were plotted to evaluate the performance of 13 models obtained from each image set. RESULTS: Despite the notable differences in the best radiomics features chosen from each image set, all the features selected from 40 to 100 keV VMIs included the Dependence Variance of the GLDM feature set. There were no statistically significant differences in the area under the curve (AUC) between the training set and the testing set for all 13 models. In the testing set, the AUCs of the models established through 40 keV to 140 keV (interval of 10 keV) image sets were 0.895, 0.874, 0.855, 0.889, 0.841, 0.868, 0.852, 0.847, 0.889, 0.887 and 0.863 respectively. The AUCs for the models established using the Iodine maps and Water maps image sets were 0.873 and 0.852, respectively. CONCLUSION: Despite the differences in the selected radiomic features from DECT multi-parameter images, the performance of radiomics models in predicting the pathological grading of BUC was not affected by the variations in the types of images used for model training.

Impact of virtual monochromatic images of different low-energy levels in dual-energy CT on radiomics models for predicting muscle invasion in bladder cancer.

OBJECTIVE: The purpose of this study was to investigate the impact of different low-energy virtual monochromatic images (VMIs) in dual-energy CT on the performance of radiomics models for predicting muscle invasive status in bladder cancer (BCa). MATERIALS AND METHODS: A total of 127 patients with pathologically proven muscle-invasive BCa (n = 49) and non-muscle-invasive BCa (n = 78) were randomly allocated into the training and test cohorts at a ratio of 7:3. Feature extraction was performed on the venous phase images reconstructed at 40, 50, 60 and 70-keV (single-energy analysis) or in combination (multi-energy analysis). Recursive feature elimination (RFE) and the least absolute shrinkage and selection operator (LASSO) were employed to select the most relevant features associated with BCa. Models were built using a support vector machine (SVM) classifier. Diagnostic performance was assessed through receiver operating characteristic curves, evaluating sensitivity, specificity, accuracy, precision, and the area-under-the curve (AUC) values. RESULTS: In the test cohort, the multi-energy model achieved the best diagnostic performance with AUC, sensitivity, specificity, accuracy, and precision of 0.917, 0.800, 0.833, 0.821, and 0.750, respectively. Conversely, the single-energy model exhibited lower AUC and sensitivity in predicting the muscle invasion status. CONCLUSIONS: By combining information from VMIs of various energies, the multi-energy model displays superior performance in preoperatively predicting the muscle invasion status of bladder cancer.

Effect of fully automatic classification model from different tube voltage images on bone density screening: A self-controlled study.

PURPOSE: To develop two bone status prediction models combining deep learning and radiomics based on standard-dose chest computed tomography (SDCT) and low-dose chest computed tomography (LDCT), and to evaluate the effect of tube voltage on reproducibility of radiomics features and predictive efficacy of these models. METHODS: A total of 1508 patients were enrolled in this retrospective study. LDCT was conducted using 80 kVp, tube current ranging from 100 to 475 mA. On the other hand, SDCT was performed using 120 kVp, tube current ranging from 100 to 520 mA. We developed an automatic thoracic vertebral cancellous bone (TVCB) segmentation model. Subsequently, 1184 features were extracted and two classifiers were developed based on LDCT and SDCT images. Based on the diagnostic results of quantitative computed tomography examination, the first-level classifier was initially developed to distinguish normal or abnormal BMD (including osteoporosis and osteopenia), while the second-level classifier was employed to identify osteoporosis or osteopenia. The Dice coefficient was used to evaluate the performance of the automated segmentation model. The Concordance Correlation Coefficients (CCC) of radiomics features were calculated between LDCT and SDCT, and the performance of these models was evaluated. RESULTS: Our automated segmentation model achieved a Dice coefficient of 0.98 ± 0.01 and 0.97 ± 0.02 in LDCT and SDCT, respectively. Alterations in tube voltage decreased the reproducibility of the extracted radiomic features, with 85.05 % of the radiomic features exhibiting low reproducibility (CCC < 0.75). The area under the curve (AUC) using LDCT-based and SDCT-based models was 0.97 ± 0.01 and 0.94 ± 0.02, respectively. Nonetheless, cross-validation with independent test sets of different tube voltage scans suggests that variations in tube voltage can impair the diagnostic efficacy of the model. Consequently, radiomics models are not universally applicable to images of varying tube voltages. In clinical settings, ensuring consistency between the tube voltage of the image used for model development and that of the acquired patient image is critical. CONCLUSIONS: Automatic bone status prediction models, utilizing either LDCT or SDCT images, enable accurate assessment of bone status. Tube voltage impacts reproducibility of features and predictive efficacy of models. It is necessary to account for tube voltage variation during the image acquisition.

Estimation of renal function using iodine maps in dual-energy spectral computed tomography urography: a feasibility and accuracy study.

PURPOSE: To explore the feasibility of measuring glomerular filtration rate (GFR) using iodine maps in dual-energy spectral computed tomography urography (DEsCTU) and correlate them with the estimated GFR (eGFR) based on the equation of creatinine-cystatin C. MATERIALS AND METHODS: One hundred and twenty-eight patients referred for DEsCTU were retrospectively enrolled. The DEsCTU protocol included non-contrast, nephrographic, and excretory phase imaging. The CT-derived GFR was calculated using the above 3-phase iodine maps (CT-GFRiodine) and 120 kVp-like images (CT-GFR120kvp) separately. CT-GFRiodine and CT-GFR120kvp were compared with eGFR using paired t-test, correlation analysis, and Bland-Altman plots. The receiver operating characteristic curves were used to test the renal function diagnostic performance with CT-GFR120kvp and CT-GFRiodine. RESULTS: The difference between eGFR (89.91 ± 18.45 ml·min-1·1.73 m-2) as reference standard and CT-GFRiodine (90.06 ± 20.89 ml·min-1·1.73 m-2) was not statistically significant, showing excellent correlation (r = 0.88, P < 0.001) and agreement (± 19.75 ml·min-1·1.73 m-2, P = 0.866). The correlation between eGFR and CT-GFR120kvp (66.13 ± 19.18 ml·min-1·1.73 m-2) was poor (r = 0.36, P < 0.001), and the agreement was poor (± 40.65 ml·min-1·1.73 m-2, P < 0.001). There were 62 patients with normal renal function and 66 patients with decreased renal function based on eGFR. The CT-GFRiodine had the largest area under the curve (AUC) for distinguishing between normal and decreased renal function (AUC = 0.951). CONCLUSION: The GFR can be calculated accurately using iodine maps in DEsCTU. DEsCTU could be a non-invasive and reliable one-stop-shop imaging technique for evaluating both the urinary tract morphology and renal function.

Diagnostic Accuracy of Dual-Energy CT Material Decomposition Technique for Assessing Bone Status Compared with Quantitative Computed Tomography.

PURPOSE: The purpose of this study was to evaluate the diagnostic accuracy when using various base material pairs (BMPs) in dual-energy computed tomography (DECT), and to establish corresponding diagnostic standards for assessing bone status through comparison with quantitative computed tomography (QCT). METHODS: This prospective study enrolled a total of 469 patients who underwent both non-enhanced chest CT scans under conventional kVp and abdominal DECT. The bone densities of hydroxyapatite (water), hydroxyapatite (fat), hydroxyapatite (blood), calcium (water), and calcium (fat) (DHAP (water), DHAP (fat), DHAP (blood), DCa (water), and DCa (fat)) in the trabecular bone of vertebral bodies (T11-L1) were measured, along with bone mineral density (BMD) via QCT. Intraclass correlation coefficient (ICC) analysis was used to assess the agreement of the measurements. Spearman's correlation test was performed to analyze the relationship between the DECT- and QCT-derived BMD. Receiver operator characteristic (ROC) curves were generated to determine the optimal diagnostic thresholds of various BMPs for diagnosing osteopenia and osteoporosis. RESULTS: A total of 1371 vertebral bodies were measured, and QCT identified 393 with osteoporosis and 442 with osteopenia. Strong correlations were observed between DHAP (water), DHAP (fat), DHAP (blood), DCa (water), and DCa (fat) and the QCT-derived BMD. DHAP (water) showed the best predictive capability for osteopenia and osteoporosis. The area under the ROC curve, sensitivity, and specificity for identifying osteopenia were 0.956, 86.88%, and 88.91% with DHAP (water) ≤ 107.4 mg/cm3, respectively. The corresponding values for identifying osteoporosis were 0.999, 99.24%, and 99.53% with DHAP (water) ≤ 89.62 mg/cm3, respectively. CONCLUSIONS: Bone density measurement using various BMPs in DECT enables the quantification of vertebral BMD and the diagnosis of osteoporosis, with DHAP (water) having the highest diagnostic accuracy.

Virtual unenhanced images derived from dual-energy computed tomography for assessing bone mineral density and detecting osteoporosis.

Background: The early detection and treatment of osteoporosis can help prevent osteoporosis-related fractures, especially in patients who undergo enhanced computed tomography (CT) scans for disease diagnosis or evaluation of treatment outcomes. Although Hounsfield unit (HU) measurement of the vertebral body has been shown to have a strong positive correlation with bone mineral density (BMD), the contrast media will impact the CT value of the vertebral body and decrease the accuracy. This study is aimed to examine the distinctions in vertebral body CT attenuation measurement on true unenhanced (TUE) and virtual unenhanced (VUE) images generated from triphasic enhanced dual-energy CT (DECT) scans and to determine the feasibility of assessing BMD and detecting osteoporosis on VUE images as compared to quantitative CT (QCT). Methods: A total of 235 patients underwent abdominal CT examinations that included unenhanced (with 120 kVp and Smart mA) and triphasic enhanced DECT scans. The BMD and CT attenuation values of the L1-L2 vertebrae were measured on TUE and VUE images reconstructed from the triphasic enhanced CT. The differences and associations between TUE and VUE generated from triphasic enhanced CT were analyzed. The diagnostic performances of HU measurements obtained from TUE and VUE images were evaluated using receiver operating characteristic curve. Results: The BMD and HU measurements of the vertebrae showed good interobserver repeatability on both TUE and VUE images (all intercorrelation coefficients >0.92). The CT attenuation values of L1 and L2 and their average value showed no statistically significant difference among the triphasic VUE images (F=0.121, F=0.061, F=0.090; all P values >0.05) but were significantly lower than those obtained from the TUE images. HU measurements in both the TUE and triphasic VUE images, along with the reference BMD derived from QCT, demonstrated a strong positive correlation (rTUE =0.981, rVUEa =0.966, rVUEv =0.962, rVUEd =0.964; all P values <0.05), with excellent diagnostic performance for the diagnoses of osteoporosis and osteopenia (all areas under curve >0.95). The Bland-Altman scatter plot exhibited good agreement, as the deviations between the reference BMD and the calculated BMD were evenly distributed around 0. Conclusions: Although the attenuation values of the vertebrae on the VUE images were underestimated compared to those on the TUE images, the HU measurement on VUE image was effective in assessing BMD and detecting osteoporosis and osteopenia with good diagnostic performance.

Implementation of Individualized Low-Dose Computed Tomography-Guided Hook Wire Localization of Pulmonary Nodules: Feasibility and Safety in the Clinical Setting.

Background: CT-guided hook-wire localization is an essential step in the management of small pulmonary nodules. Few studies, however, have focused on reducing radiation exposure during the procedure. Purpose: This study aims to explore the feasibility of implementing a low-dose computed tomography (CT)-guided hook wire localization using tailored kVp based on patients' body size. Materials and Methods: A total of 151 patients with small pulmonary nodules were prospectively enrolled for CT-guided hook wire localization using individualized low-dose CT (LDCT) vs. standard-dose CT (SDCT) protocols. Radiation dose, image quality, characteristics of target nodules and procedure-related variables were compared. All variables were analyzed using Chi-Square and Student's t-test. Results: The mean CTDIvol was significantly reduced for LDCT (for BMI ≤ 21 kg/m2, 0.56 ± 0.00 mGy and for BMI > 21 kg/m2, 1.48 ± 0.00 mGy) when compared with SDCT (for BMI ≤ 21 kg/m2, 5.24 ± 0.95 mGy and for BMI > 21 kg/m2, 6.69 ± 1.47 mGy). Accordingly, the DLP of LDCT was significantly reduced as compared with that of SDCT (for BMI ≤ 21 kg/m2, 56.86 ± 4.73 vs. 533.58 ± 122.06 mGy.cm, and for BMI > 21 kg/m2, 167.02 ± 38.76 vs. 746.01 ± 230.91 mGy.cm). In comparison with SDCT, the effective dose (ED) of LDCT decreased by an average of 89.42% (for BMI ≤ 21 kg/m2) and 77.68% (for BMI > 21 kg/m2), respectively. Although the images acquired with the LDCT protocol yielded inferior quality to those acquired with the SDCT protocol, they were clinically acceptable for hook wire localization. Conclusions: LDCT-guided localization can provide safety and nodule detection performance comparable to SDCT-guided localization, benefiting radiation dose reduction dramatically, especially for patients with small body mass indexes.

Development and multi-center validation of machine learning model for early detection of fungal keratitis.

BACKGROUND: Fungal keratitis (FK) is a leading cause of corneal blindness in developing countries due to poor clinical recognition and laboratory identification. Here, we aimed to identify the distinct clinical signature of FK and develop a diagnostic model to differentiate FK from other types of infectious keratitis. METHODS: We reviewed the electronic health records (EHRs) of all patients with suspected infectious keratitis in Beijing Tongren Hospital from January 2011 to December 2021. Twelve clinical signs of slit-lamp images were assessed by Lasso regression analysis and collinear variables were excluded. Three models based on binary logistic regression, random forest classification, and decision tree classification were trained for FK diagnosis and employed for internal validation. Independent external validation of the models was performed in a cohort of 420 patients from seven different ophthalmic centers to evaluate the accuracy, specificity, and sensitivity in real world. FINDINGS: Three diagnostic models of FK based on binary logistic regression, random forest classification, and decision tree classification were established and internal validation were achieved with the mean AUC of 0.916, 0.920, and 0.859, respectively. The models were well-calibrated by external validation using a prospective cohort including 210 FK and 210 non-FK patients from seven eye centers across China. The diagnostic model with the binary logistic regression algorithm classified the external validation dataset with a sensitivity of 0.907 (0.774, 1.000), specificity 0.899 (0.750, 1.000), accuracy 0.905 (0.805, 1.000), and AUC 0.903 (0.808, 0.998). INTERPRETATION: Our model enables rapid identification of FK, which will help ophthalmologists to establish a preliminary diagnosis and to improve the diagnostic accuracy in clinic. FUNDING: The Open Research Fund from the National Key Research and Development Program of China (2021YFC2301000) and the Open Research Fund from Beijing Advanced Innovation Center for Big Data-Based Precision Medicine, Beijing Tongren Hospital, Beihang University &Capital Medical University (BHTR-KFJJ-202001) supported this study.

Deep learning-based classification of infectious keratitis on slit-lamp images.

Background: Infectious keratitis (IK) is an ocular emergency caused by a variety of microorganisms, including bacteria, fungi, viruses, and parasites. Culture-based methods were the gold standard for diagnosing IK, but difficult biopsy, delaying report, and low positive rate limited their clinical application. Objectives: This study aims to construct a deep-learning-based auxiliary diagnostic model for early IK diagnosis. Design: A retrospective study. Methods: IK patients with pathological diagnosis were enrolled and their slit-lamp photos were collected. Image augmentation, normalization, and histogram equalization were applied, and five image classification networks were implemented and compared. Model blending technique was used to combine the advantages of single model. The performance of combined model was validated by 10-fold cross-validation, receiver operating characteristic curves (ROC), confusion matrix, Gradient-wright class activation mapping (Grad-CAM) visualization, and t-distributed Stochastic Neighbor Embedding (t-SNE). Three experienced cornea specialists were invited and competed with the combined model on making clinical decisions. Results: Overall, 4830 slit-lamp images were collected from patients diagnosed with IK between June 2010 and May 2021, including 1490 (30.8%) bacterial keratitis (BK), 1670 (34.6%) fungal keratitis (FK), 600 (12.4%) herpes simplex keratitis (HSK), and 1070 (22.2%) Acanthamoeba keratitis (AK). KeratitisNet, the combination of ResNext101_32x16d and DenseNet169, reached the highest accuracy 77.08%. The accuracy of KeratitisNet for diagnosing BK, FK, AK, and HSK was 70.27%, 77.71%, 83.81%, and 79.31%, and AUC was 0.86, 0.91, 0.96, and 0.98, respectively. KeratitisNet was mainly confused in distinguishing BK and FK. There were 20% of BK cases mispredicted into FK and 16% of FK cases mispredicted into BK. In diagnosing each type of IK, the accuracy of model was significantly higher than that of human ophthalmologists (p < 0.001). Conclusion: KeratitisNet demonstrates a good performance on clinical IK diagnosis and classification. Deep learning could provide an auxiliary diagnostic method to help clinicians suspect IK using different corneal manifestations.