Computed tomography-based radiomics predicts the fibroblast-related gene EZH2 expression level and survival of hepatocellular carcinoma.

BACKGROUND: Hepatocellular carcinoma (HCC) is the most common subtype of liver cancer. The primary treatment strategies for HCC currently include liver transplantation and surgical resection. However, these methods often yield unsatisfactory outcomes, leading to a poor prognosis for many patients. This underscores the urgent need to identify and evaluate novel therapeutic targets that can improve the prognosis and survival rate of HCC patients. AIM: To construct a radiomics model that can accurately predict the EZH2 expression in HCC. METHODS: Gene expression, clinical parameters, HCC-related radiomics, and fibroblast-related genes were acquired from public databases. A gene model was developed, and its clinical efficacy was assessed statistically. Drug sensitivity analysis was conducted with identified hub genes. Radiomics features were extracted and machine learning algorithms were employed to generate a radiomics model related to the hub genes. A nomogram was used to illustrate the prognostic significance of the computed Radscore and the hub genes in the context of HCC patient outcomes. RESULTS: EZH2 and NRAS were independent predictors for prognosis of HCC and were utilized to construct a predictive gene model. This model demonstrated robust performance in diagnosing HCC and predicted an unfavorable prognosis. A negative correlation was observed between EZH2 expression and drug sensitivity. Elevated EZH2 expression was linked to poorer prognosis, and its diagnostic value in HCC surpassed that of the risk model. A radiomics model, developed using a logistic algorithm, also showed superior efficiency in predicting EZH2 expression. The Radscore was higher in the group with high EZH2 expression. A nomogram was constructed to visually demonstrate the significant roles of the radiomics model and EZH2 expression in predicting the overall survival of HCC patients. CONCLUSION: EZH2 plays significant roles in diagnosing HCC and therapeutic efficacy. A radiomics model, developed using a logistic algorithm, efficiently predicted EZH2 expression and exhibited strong correlation with HCC prognosis.

Added value of spectral parameters in diagnosing metastatic lymph nodes of pT1-2 rectal cancer.

PURPOSE: To investigate the added value of spectral parameters derived from dual-layer spectral detector CT (SDCT) in diagnosing metastatic lymph nodes (LNs) of pT1-2 (stage 1-2 determined by pathology) rectal cancer. METHODS: A total of 80 LNs (57 non-metastatic LNs and 23 metastatic LNs) from 42 patients with pT1-T2 rectal cancer were retrospectively analyzed. The short-axis diameter of LNs was measured, then its border and enhancement homogeneity were evaluated. All spectral parameters, including iodine concentration (IC), effective atomic number (Zeff), normalized IC (nIC), normalized Zeff (nZeff), and slope of the attenuation curve (λ), were measured or calculated. The chi-square test, Fisher's exact test, independent-samples t-test, or Mann-Whitney U test was used to compare the differences of each parameter between the non-metastatic group and the metastatic group. Multivariable logistic regression analyses were used to determine the independent factors for predicting LN metastasis. Diagnostic performances were assessed by ROC curve analysis and compared with the DeLong test. RESULTS: The short-axis diameter, border, enhancement homogeneity, and each spectral parameter of LNs showed significant differences between the two groups (P < 0.05). The nZeff and short-axis diameter were independent predictors of metastatic LNs (P < 0.05), with areas under the curve (AUC) of 0.870 and 0.772, sensitivity of 82.5% and 73.9%, and specificity of 82.6% and 78.9%. After combining nZeff and the short-axis diameter, the AUC (0.966) was the highest with sensitivity of 100% and specificity of 87.7%. CONCLUSION: The spectral parameters derived from SDCT might help us to improve the diagnostic accuracy of metastatic LNs in patients with pT1-2 rectal cancer, the highest diagnostic performance can be achieved after combining nZeff with the short-axis diameter of LNs.

Transformer-Based Deep Learning Network for Tooth Segmentation on Panoramic Radiographs.

Panoramic radiographs can assist dentist to quickly evaluate patients' overall oral health status. The accurate detection and localization of tooth tissue on panoramic radiographs is the first step to identify pathology, and also plays a key role in an automatic diagnosis system. However, the evaluation of panoramic radiographs depends on the clinical experience and knowledge of dentist, while the interpretation of panoramic radiographs might lead misdiagnosis. Therefore, it is of great significance to use artificial intelligence to segment teeth on panoramic radiographs. In this study, SWin-Unet, the transformer-based Ushaped encoder-decoder architecture with skip-connections, is introduced to perform panoramic radiograph segmentation. To well evaluate the tooth segmentation performance of SWin-Unet, the PLAGH-BH dataset is introduced for the research purpose. The performance is evaluated by F1 score, mean intersection and Union (IoU) and Acc, Compared with U-Net, Link-Net and FPN baselines, SWin-Unet performs much better in PLAGH-BH tooth segmentation dataset. These results indicate that SWin-Unet is more feasible on panoramic radiograph segmentation, and is valuable for the potential clinical application.

Quantitative parameters of magnetic resonance imaging cannot predict human epidermal growth factor receptor 2 (HER2) status in rectal cancer.

PURPOSE: To retrospectively investigate whether magnetic resonance imaging (MRI) quantitative parameters can differentiate human epidermal growth factor receptor 2 (HER2) status in rectal cancer. MATERIALS AND METHODS: This study included 89 patients with surgically confirmed rectal cancer who underwent preoperative MRI from June 2014 to May 2019. Patients were divided into three groups: HER2 negative (HER2-Neg); HER2-low expression (HER2-L); and HER2 positive (HER2-Pos). Quantitative perfusion parameters derived from dynamic contrast-enhanced MRI (DCE-MRI) Tofts model (pharmacokinetic blood dual compartment model) were listed as follows: volume transfer constant (Ktrans), rate constant (Kep), and extracellular volume ratio (Ve). The mean, minimum, and maximum apparent diffusion coefficient (ADC) values at standard (800 s/mm2) b-values were obtained with diffusion-weighted imaging (DWI). Clinicopathologic characteristics and quantitative parameters were compared by Fisher's exact test and one-way analysis of variance (ANOVA), respectively. RESULTS: The 89 patients included 52 (58.4%) with HER2-Neg, 31 (34.8%) with HER2-L, and 6 (6.8%) with HER2-Pos states. Fisher's exact test showed that clinicopathologic characteristics among the three groups were not significantly different (p = 0.281 to 1.000). Likewise, there were no associations between HER2 status and any quantitative parameters, including Ktrans (p = 0.296), Kep (p = 0.290), Ve (p = 0.184), ADCmean (p = 0.181), ADCmin (p = 0.143), or ADCmax (p = 0.058). CONCLUSION: Quantitative perfusion parameters (Ktrans, Kep, Ve) and ADC values were not able to discriminate HER2 status in patients with rectal cancer or evaluate treatment response in real time.

Intramammary edema of invasive breast cancers on MRI T2-weighted fat suppression sequence: Correlation with molecular subtypes and clinical-pathologic prognostic factors.

OBJECTIVE: To investigate the associations between different patterns of intramammary edema on preoperative 3.0 T magnetic resonance imaging (MRI) T2-weighted fat suppression sequence and invasive breast cancer molecular subtypes and clinical-pathologic prognostic factors. METHODS: Between May 2014 and December 2020, 191 patients with invasive breast cancer who had undergone preoperative MRI and mastectomy or breast-conserving surgery were retrospectively enrolled. The relationships between different patterns of intramammary edema and invasive breast cancer molecular subtypes and clinical-pathologic features were evaluated using the Student's t-test or Mann-Whitney U test and the χ2 test or Fisher's exact test. RESULTS: Patients with luminal B (HER2 positive), HER2-enriched and triple negative breast cancers respectively had different patterns of intramammary edema (P < 0.001). There was a significant association between intramammary edema and clinical-pathologic factors, including larger tumor size, higher Ki-67 index, lymph node metastasis and lymphovascular invasion (all P < 0.001). CONCLUSIONS: Intramammary edema may provide added values of predicting molecular subtypes and clinical-pathologic prognosis, enhancing the ability to individualize the treatment of patients with invasive breast cancer.

Increased internal cerebral vein diameter is associated with age.

OBJECTIVE: A recent study described the relationship between cerebral venous diameter and white matter hyperintensity (WMH) volume. However, the adults were not further grouped; therefore, we aimed to compare across age groups and use susceptibility-weighted imaging (SWI) to explore whether there is also a relationship between a larger cerebral draining venous diameter and age, which could provide evidence of a temporal relationship. METHODS: We retrospectively analysed data collected from 405 subjects (90 youths, 166 middle-aged participants, and 149 elderly subjects) and respectively used T2-weighted fluid-attenuated inversion recovery (FLAIR) and SWI to assess WMHs and venous diameter. RESULTS: An increased internal cerebral vein (ICV) diameter was associated with age in different WMH groups (F = 3.453, 10.437, 11.746, and 21.723, respectively, all p < 0.001; multiple comparisons all p < 0.05), whereas the effect of the anterior septal vein (ASV) was opposite (F = 1.046, 1.210, 0.530, and 0.078, respectively, p > 0.05). There was a positive correlation between the ICV diameter and age with increasing WMH severity (R = 0.727, 0.709, 0.754, and 0.830, respectively, all p < 0.001). A statistically significant relationship between the thalamostriate vein (TSV) diameter and age was observed only in the moderate and severe WMH groups (F = 4.070 and 3.427, respectively, all p < 0.05; multiple comparisons all p < 0.05). CONCLUSIONS: Our study demonstrates that increased TSV and ICV diameters are associated with age with increasing WMH severity, especially the ICV diameter using SWI.

Correlations of Mean and Mimimum Apparent Diffusion Coefficient Values With the Clinicopathological Features in Rectal Cancer.

RATIONALE AND OBJECTIVE: The study aimed to investigate the possible correlation between mean (MeanADC) and minimum (MinADC) apparent diffusion coefficient values with the clinicopathological features and evaluate the diagnostic potential of MinADC values and MeanADC values in predicting the behavior of rectal cancer. MATERIALS AND METHODS: In total, 148 pathologically verified lesions that were subjected to conventional MR imaging and diffusion weighted imaging prior to operation were included. The MeanADC values and MinADC values were calculated and their correlation with clinicopathological characteristics were investigated. RESULTS: Both MeanADC values and MinADC values correlated with T classification (MeanADC: t = 2.841, p = 0.005; MinADC: t = 2.356, p = 0.020), N classification (MeanADC: t = 3.468, p = 0.001; MinADC: t = 3.072, p = 0.003), tumor histological grade (MeanADC: F = 8.175, p = 0.000; MinADC: F = 22.038, p = 0.000), perineural invasion (MeanADC: t = 2.547, p = 0.012; MinADC: t = 3.081, p = 0.002), and extramural venous invasion (MeanADC: t = 2.157, p = 0.033; MinADC: t = 2.635, p = 0.009) in rectal cancer, but no significant correlation with gender, age, and tumor location (p > 0.05). The MinADC values showed a higher diagnostic efficacy in discriminating the well or poor differentiation of rectal cancer compared to MeanADC values, with a threshold value of ≥0.929 × 10-3 mm2/s (sensitivity, 80%; specificity, 88.1%) or ≤0.752 × 10-3 mm2/s (sensitivity, 94.1%; specificity, 74%). CONCLUSION: Both MeanADC values and MinADC values might be used as a quantitative parameter to evaluate the aggressiveness of rectal cancer. The MinADC values could be as the better predictor in identifying tumor differentiation compared to the MeanADC values.

Relationship between quantitative parameters of lumbar vertebral perfusion and bone mineral density (BMD) in postmenopausal women.

BACKGROUND: Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is a noninvasive method to evaluate the microcirculation of bone marrow in local tissue, which will be a new tool for the diagnosis of osteoporosis. OBJECTIVES: To investigate the relationship between quantitative perfusion parameters (Ktrans, Kep and Ve) and bone mineral density (BMD) in postmenopausal women. MATERIAL AND METHODS: The subjects were divided into 3 groups according to T value: normal bone mass group (T value ≥-1.0); bone loss group (-2.5 < T <-1.0); and osteoporosis group (T ≤-2.5). Ktrans, Kep and Ve of the lumbar spine were measured using quantitative DCE-MRI. The relationship between these parameters and age was analyzed. RESULTS: Bone mineral density of the lumbar spine and femoral neck gradually decreased with age. The values of Ktrans, Kep and Ve significantly decreased with age. The values of Ktrans, Kep and Ve of the lumbar vertebrae in the osteoporosis group were lower than those in the bone loss and normal bone mass group. Bone mineral density was positively correlated with the Ktrans and Ve of the lumbar vertebrae. CONCLUSIONS: The incidences of bone loss and osteoporosis increased with age. The measurement of BMD was conducive to early diagnosis of osteoporosis. Ktrans, Kep and Ve values of the lumbar vertebra decreased with age, and have a positive correlation with lumbar BMD. The value of DCE-MRI may play a role in the diagnostic algorithm of osteoporosis.

[99mTc]cFLFLF for Early Diagnosis and Therapeutic Evaluation in a Rat Model of Acute Osteomyelitis.

PURPOSE: Early diagnosis and therapeutic monitoring of acute osteomyelitis (AO) is challenging. Here, we use a polyethylene glycol (PEG)ylated chemotactic peptide cinnamoyl-F-(D)L-F-(D)L-F (cFLFLF) conjugated with hydrazinonicotinamide (HYNIC) and labeled with Tc-99m ([(99m)Tc]cFLFLF) to image AO in a rat model and to validate its efficacy in early diagnosis and therapeutic evaluation of AO. PROCEDURES: Forty rats were divided into eight groups of five each. Groups A, B, C, G, and H were AO models, and D, E, and F were sham controls. Groups A and D underwent [(99m)Tc]cFLFLF scintigraphy, groups B and E underwent [(99m)Tc]methylene diphosphonate ([(99m)Tc]MDP) bone scan, and groups C and F underwent 2-deoxy-2-[(18)F]fluoro-D-glucose ([(18)F]FDG) positron emission tomography (PET)/computed tomography (CT) scan. [(99m)Tc]cFLFLF biodistribution was assessed in group G. The response to antibiotic therapy was evaluated using [(99m)Tc]cFLFLF scintigraphy in group H. Conventional radiographs were obtained following scintigraphy. Ratios of infected or sham-operated tibia to the opposite tibia (T/B) were calculated. Immediately after the imaging studies, infected tibias were excised and underwent histopathological analysis and immunohistochemistry staining. RESULTS: AO was present in all rats of groups A, B, C, G, and H. Total histological scores were not significantly different among groups A, B, and C (F = 0.34, p = 0.71). The biodistribution results revealed significant uptake and excellent retention of [(99m)Tc]cFLFLF in the infected tibia. [(99m)Tc]cFLFLF scintigraphy and [(99m)Tc]MDP bone scan both detected AO. The mean T/B ratio of [(99m)Tc]cFLFLF scintigraphy 1 h postinjection was 2.09-fold higher than that of [(99m)Tc]MDP bone scan (t = 13.81, p <0.001). The mean T/B ratio of [(18)F]FDG PET/CT scan was not significantly different from the control group F (t = 2.17, p = 0.062). [(99m)Tc]cFLFLF scintigraphy revealed a significant attenuation of inflammation in group H following a 3-week antibiotic treatment, which was verified by histopathological analysis and immunohistochemistry staining. CONCLUSION: Our results suggest that the specificity and image quality of [(99m)Tc]cFLFLF are superior to those of the [(99m)Tc]MDP and [(18)F]DFG imaging probes currently used for early diagnosis of AO. Furthermore, [(99m)Tc]cFLFLF was able to effectively evaluate the therapeutic response to antibiotic treatment of AO. Our data suggest that [(99m)Tc]cFLFLF is a promising imaging agent for detection of infectious diseases.