Value of the virtual monoenergetic image from dual-layer dual-energy computed tomography enterography in the preoperative assessment of the internal penetrating complication of Crohn's disease.

BACKGROUND: To determine the utility of virtual-monoenergetic imaging (VMI) at low energy levels from contrast-enhanced dual-layer dual-energy (DLDE) computed tomography enterography (CTE) in the preoperative assessment of internal penetrating lesions of Crohn's disease (CD). MATERIALS AND METHODS: Thirty-eight patients with penetrating lesions of CD by surgery undergoing contrast-enhanced DLDE CTE were retrospectively included. Polyenergetic imaging (PEI) and VMIs at low energy levels [40-70 kiloelectron volts (keV)] with 10 keV intervals were reconstructed. The objective parameters of image quality [noise, signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR)] and the subjective parameter of image quality [diagnostic performance of lesions (DPL), overall image quality(OIQ)] of PEI and all VMIs at the low energy level were compared to determine the VMI on the optimal energy level. The lesion detection capability between PEI and the optimal VMI was compared. RESULTS: VMI40 was determined to be the optimal VMI among all VMIs at the low energy level for owning the best image quality. No significant difference was found in the detecting capability in penetrating lesions between VMI40 and PEI (p = 1.0), whereas a significant difference was found in the detecting capability in the bowel origin of the penetrating lesions (p = 0.004), the involved organ or structure by the fistula (p = 0.016) and the orifice of the fistula connected to the involved organ or structure ( p = 0.031) between them. CONCLUSIONS: Compared to conventional PEI, VMI40 improves the detection capability in anatomical details of penetrating lesions of CD, helping colorectal surgeons rationalizing preoperative plans of internal penetrating lesions of CD.

A clinical-radiomics model based on noncontrast computed tomography to predict hemorrhagic transformation after stroke by machine learning: a multicenter study.

OBJECTIVE: To build a clinical-radiomics model based on noncontrast computed tomography images to identify the risk of hemorrhagic transformation (HT) in patients with acute ischemic stroke (AIS) following intravenous thrombolysis (IVT). MATERIALS AND METHODS: A total of 517 consecutive patients with AIS were screened for inclusion. Datasets from six hospitals were randomly divided into a training cohort and an internal cohort with an 8:2 ratio. The dataset of the seventh hospital was used for an independent external verification. The best dimensionality reduction method to choose features and the best machine learning (ML) algorithm to develop a model were selected. Then, the clinical, radiomics and clinical-radiomics models were developed. Finally, the performance of the models was measured using the area under the receiver operating characteristic curve (AUC). RESULTS: Of 517 from seven hospitals, 249 (48%) had HT. The best method for choosing features was recursive feature elimination, and the best ML algorithm to build models was extreme gradient boosting. In distinguishing patients with HT, the AUC of the clinical model was 0.898 (95% CI 0.873-0.921) in the internal validation cohort, and 0.911 (95% CI 0.891-0.928) in the external validation cohort; the AUC of radiomics model was 0.922 (95% CI 0.896-0.941) and 0.883 (95% CI 0.851-0.902), while the AUC of clinical-radiomics model was 0.950 (95% CI 0.925-0.967) and 0.942 (95% CI 0.927-0.958) respectively. CONCLUSION: The proposed clinical-radiomics model is a dependable approach that could provide risk assessment of HT for patients who receive IVT after stroke.

A CT-based nomogram for differentiating invasive fungal disease of the lung from bacterial pneumonia.

BACKGROUND: There is an annual increase in the incidence of invasive fungal disease (IFD) of the lung worldwide, but it is always a challenge for physicians to make an early diagnosis of IFD of the lung. Computed tomography (CT) may play a certain role in the diagnosis of IFD of the lung, however, there are no specific imaging signs for differentiating IFD of lung from bacterial pneumonia (BP). METHODS: A total of 214 patients with IFD of the lung or clinically confirmed BP were retrospectively enrolled from two institutions (171 patients from one institution in the training set and 43 patients from another institution in the test set). The features of thoracic CT images of the 214 patients were analyzed on the picture archiving and communication system by two radiologists, and these CT images were imported into RadCloud to perform radiomics analysis. A clinical model from radiologic analysis, a radiomics model from radiomics analysis and a combined model from integrating radiologic and radiomics analysis were constructed in the training set, and a nomogram based on the combined model was further developed. The area under the ROC curve (AUC) of the receiver operating characteristic (ROC) curve was calculated to assess the diagnostic performance of the three models. Decision curve analysis (DCA) was conducted to evaluate the clinical utility of the three models by estimating the net benefit at a range of threshold probabilities. RESULTS: The AUCs of the clinical model for differentiating IFD of lung from BP in the training set and test sets were 0.820 and 0.827. The AUCs of the radiomics model in the training set and test sets were 0.895 and 0.857. The AUCs of the combined model in the training set and test setswere 0.944 and 0.911. The combined model for differentiating IFD of lung from BP obtained the greatest net benefit among the three models by DCA. CONCLUSION: Our proposed nomogram, based on a combined model integrating radiologic and radiomics analysis, has a powerful predictive capability for differentiating IFD from BP. A good clinical outcome could be obtained using our nomogram.

[Relationship of ADC histogram parameters with pathological grade and lymph node metastasis of prostate cancer].

OBJECTIVE: To investigate the relationship between the apparent diffusion coefficient (ADC) histogram parameters based on the whole tumor and the pathological grade and lymph node metastasis (LNM) of PCa. METHODS: This retrospective study included 82 cases of PCa confirmed pathologically and subjected to MRI preoperatively. We obtained a series of ADC histogram parameters, such as ADCmean, ADCmedian, ADC25%, ADC75%, entropy, and histogram width, by processing the ADC images via the Firevoxel Post-Processing and the SPSS24 software. We compared the parameters between the high-risk and low- or moderate-risk groups as well as between the LNM-positive and LNM-negative groups of the patients, and analyzed the diagnostic performance of the parameters with statistically significant differences. RESULTS: The high-risk group, compared with the low- or moderate-risk one, showed a significantly lower ADCmean (ï¼»590 ± 120ï¼½ vs ï¼»837 ± 142ï¼½ ×10－6 mm2/s, P < 0.01), ADCmedian (ï¼»560 ± 117ï¼½ vs ï¼»804 ± 139ï¼½ ×10－6 mm2/s, P < 0.01), ADC25% (ï¼»446.5 ± 98ï¼½ vs ï¼»717 ± 118ï¼½ ×10－6 mm2/, P < 0.01) and ADC75% (ï¼»667 ± 132ï¼½ vs ï¼»931 ± 167ï¼½ ×10－6 mm2/s, P < 0.01). The ADCmean manifested the highest diagnostic performance, with an AUC of 0.907, a sensitivity of 0.933 and a specificity of 0.796. No statistically significant difference was found between the high-risk and the low- or moderate-risk one in entropy (3.58 ± 0.39 vs 3.63 ± 0.42, P = 0.238) or the histogram width (ï¼»540 ± 73ï¼½ vs ï¼»520 ± 65ï¼½ ×10－6 mm2/s, P = 0.086). Both entropy and the histogram width were remarkably higher in the LNM-positive than in the LNM-negative group (3.95 ± 0.41 vs 3.12 ± 0.45, P < 0.01; ï¼»578 ± 59ï¼½ vs ï¼»455 ± 68ï¼½ ×10－6 mm2/s, P < 0.01), and the former had an even higher diagnostic performance, with an AUC of 0.836, a sensitivity of 0.887 and a specificity of 0.781. There were no statistically significant differences between the LNM-positive and LNM-negative groups in the ADCmean (ï¼»768 ± 135ï¼½ vs ï¼»790±128ï¼½ ×10－6 mm2/s, P = 0.402), ADCmedian (ï¼»759 ± 110ï¼½ vs ï¼»775 ± 121ï¼½ ×10－6 mm2/s, P = 0.225), ADC25% (ï¼»643 ± 91ï¼½ vs ï¼»657 ± 89ï¼½ ×10－6 mm2/s, P = 0.654) or ADC75% (ï¼»895 ± 127ï¼½ vs ï¼»872 ± 129ï¼½ ×10－6 mm2/s, P = 0.926). CONCLUSIONS: ADC histogram parameters are related to pathological grade and LNM of PCa, and the analysis of the ADC histogram based on the whole tumor has an important value for preoperative evaluation and prognostic estimation of the malignancy.