BMC Medical Imaging最新文献

Background: The P53-mutated Hepatocellular Carcinoma (HCC) is an aggressive variant associated with vascular endothelial growth factor (VEGF) overexpression and increased microvascular density. This study aimed to develop an MRI-based deep learning model for predicting P53-mutated HCC.

Methods: A total of 312 HCC patients who underwent gadolinium-enhanced MRI and were pathologically confirmed between January 2018 and December 2023 were retrospectively enrolled. Participants were randomly divided into training and test dataset at an 8:2 ratio. We developed an EfficientNetV2-based deep learning model, constructing arterial phase (AP) model, portal venous phase (VP), T2-weighted imaging (T2WI), hepatobiliary phase (HBP) single-sequence model, and combined models to predict P53 mutation status. Model performance was evaluated using the area under the curve (AUC), accuracy, sensitivity, specificity, precision, and F1 score as metrics. Differences in AUC values were compared using Delong's test.

Results: A total of 312 pathologically confirmed HCC patients (age: 56 ± 9 years; male = 240) were included, with a training dataset (n = 249) and test dataset (n = 63).Among single-sequence models, the HBP model demonstrated superior diagnostic performance (AUC = 0.715) compared to T2WI, AP, and VP models. The multiphase combined model (T2WI + AP + VP) significantly outperformed single-sequence models, achieving AUCs of 0.982 (95% CI: 0.959-1.000) in the training dataset and 0.914 (95% CI: 0.819-1.000) in the test dataset. However, incorporating the HBP sequence into the combined model (T2WI + AP + VP + HBP) did not further improve diagnostic performance (P > 0.05).

Advances in knowledge: The combined model incorporating AP, VP, T2WI, and HBP sequences demonstrated numerically highest performance in predicting P53-mutated HCC.

Background: When foreign bodies in the human body are not diagnosed (detected), it can cause various inflammatory reactions. Therefore, they should be detected and removed immediately. Taking a detailed patient history, performing a clinical examination, and selecting the appropriate imaging method are important for detection. The location, structure, and size of the foreign body affect the choice of radiography technique. This study aims to compare the detectability, measurement accuracy, and acoustic behaviors of various foreign bodies in the maxillofacial region using Cone Beam Computed Tomography (CBCT) and Ultrasonography (US) under ex vivo conditions.

Methods: Foreign bodies (wood, amalgam, glass, tooth, graphite, composite, plastic, and stone) and orthodontic materials (Elgiloy wire, TMA wire, stainless steel wire, stainless steel bracket, and ceramic bracket) with different sizes were placed on the mandibular cortical bone and in the tongue of a sheep's head. Foreign bodies' visibility and diameter measurements were made with CBCT and US. Data were statistically analyzed using the Wilcoxon rank-order test, the Friedman test, and the Pearson correlation coefficient.

Results: CBCT demonstrated superior inter- and intra-observer agreement, while the US exhibited higher sensitivity (95.4%) in detecting foreign bodies. CBCT failed to visualize plastic and wood, whereas the US successfully detected all materials. Larger foreign bodies could be detected more easily with both imaging methods. There was no statistically significant difference between the diameters of the foreign bodies measured on CBCT and US and their actual diameters (p > 0.05). Posterior acoustic enhancement was detected in glass, amalgam, stainless steel wire, and stainless steel brackets, while posterior acoustic shadowing was observed in teeth, composite, plastic, and stone.

Conclusions: CBCT is optimal for radiopaque foreign body detection, whereas the US excels in identifying radiolucent materials. All foreign bodies could be visualized with US, wood and plastic could not be observed with CBCT. As the size of the foreign body increased, it could be observed more clearly on both CBCT and US. The foreign body sensitivity of the US was higher than that of the CBCT. These findings suggest that CBCT is preferable for identifying metalic and dense radiopaque foreign bodies, while the US may be beneficial in detecting radiolucent materials such as wood and plastic.

Objective: To assess whether the pCASL technique and its radiomics features can enhance the differentiation between tumor recurrence (TR) and pseudoprogression (PsP) in postoperative glioma patients.

Methods: A retrospective study of 120 postoperative glioma patients (WHO Grade 2-4) from Tongji Hospital, Wuhan, was conducted. MRI data, including T₁WI, T₂WI, T₂FLAIR, contrast-enhanced T₁WI, and pCASL, were analyzed. Final diagnoses of TR or PsP were confirmed through pathology or follow-up. Among the patients, 65 had recurrence, and 55 had PsP. Process the pCASL images to generate the CBF parameter map, then perform N4 bias correction and Z- score standardization to obtain the standardized CBF parameter map for group analysis. The lesion areas were outlined, and mean values for ROI were calculated. Statistical analysis included the Mann-Whitney U test and ROC curve analysis. Radiomics features were extracted from the CBF maps. These features were then further selected and divided into training and testing sets. Machine learning models, including Support Vector Machine (SVM), logistic regression, random forest, and Gaussian Naive Bayes, were developed and subsequently validated.

Results: The Mann-Whitney U test showed a significant difference in mean CBF values between TR and PsP groups (p < 0.001). ROC analysis revealed an AUC of 0.879 (95% CI: 0.817-0.941), sensitivity of 0.846, specificity of 0.836, PPV of 0.859, and NPV of 0.821. After feature selection, seven radiomics features were retained. SVM yielded the best performance with an AUC of 0.971, sensitivity of 0.950, specificity of 0.813, PPV of 0.864, and NPV of 0.929.

Conclusion: The pCASL technique, combined with radiomics features, effectively differentiates TR from PsP in postoperative glioma patients. The pCASL provides reliable diagnostic information, with radiomics further improving classification accuracy. The SVM model demonstrated the best performance, highlighting the potential of combining pCASL and radiomics for accurate, non-invasive differentiation of TR and PsP. This approach could enhance clinical decision-making and patient management.

Aim: To determine the diagnostic value of high-frequency ultrasonography in the assessment of anterior talofibular ligament (ATFL) injury and concomitant lesions.

Methods: We retrospectively analyzed the data of 1005 patients with acute, unilateral ATFL injuries diagnosed using high-frequency ultrasonography in our hospital between January 2021 and December 2024. We analyzed ATFL and calcaneofibular ligament (CFL) thickness in patients with right vs. left ankle injuries and those with complete vs. incomplete ATFL rupture. We also analyzed the damage to other supporting structures of the ankle to provide an imaging basis for clinical diagnosis and treatment.

Results: In patients with incomplete ATFL injury with concomitant CFL injury, the thickness of the left and right CFL was 1.75 ± 0.47 mm and 1.90 ± 0.58 mm, respectively (P < 0.01). The CFL thickness was 1.83 ± 0.54 mm and 2.13 ± 0.54 mm in patients with incomplete and complete ATFL injury, respectively (P < 0.001). The incidence of concomitant CFL and superior extensor retinaculum (SER) injuries significantly differed between patients with incomplete and complete ATFL rupture (P < 0.05).

Conclusion: High-frequency ultrasonography is valuable for diagnosing acute ankle ligament injuries. CFL thickness was greater in patients with complete ATFL injury than in patients with incomplete ATFL injury. A trend toward increase CFL thickness on the right was noted, possibly due to right-sided dominance, though this requires further validation. ATFL injuries are frequently associated with concomitant CFL and SER injuries, and these structures should be carefully assessed during ultrasound examinations of acute ankle injuries.

Background: Plain radiography is a key diagnostic tool for trauma patients in emergency departments, often requiring immediate interpretation so that urgent care is not delayed. Due to difficulty in accessing timely radiologist reports and the demand for rapid decision-making, emergency department doctors, including junior doctors, have, over the years, been involved in the initial interpretation of plain trauma X-rays. However, concerns remain about the accuracy of these junior doctors, which may impact patient safety. Despite its significance, there's a notable gap in knowledge on the factors that influence their accuracy and strategies to improve their accuracy. This review explored these specific factors and strategies.

Method: A scoping review was conducted following the framework by Arksey and O'Malley as updated by Levac, Colquhoun, and O'Brien. Searches were performed in PubMed, SCOPUS, Embase, Cochrane Library, Google Scholar and through reference list search of eligible studies from a timeframe of 1985 to August 2025. A narrative approach was employed to describe findings after content analysis of eligible studies.

Results: Nine articles were ultimately included. The factors identified were emergency department clinical experience, anatomical site-specific interpretation, radiographic image-related factors, time and mechanism of traumatic injury. Further, plain trauma X-ray interpretation training, emergency department clinical experience with a teaching programme and collaboration with radiographers were identified as potential accuracy improvement strategies.

Conclusion: Junior doctors' plain trauma X-ray interpretation accuracy was influenced by several factors. Strategies like training, increased exposure to trauma X-rays in the emergency department with structured teaching programmes, and enhanced collaboration with radiographers can help mitigate the risk of misinterpretations among junior doctors. Future studies should not only validate these findings and investigate additional influencing factors and strategies, but also examine potential barriers to implementing such strategies.

Clinical trial number: Not applicable.