BMC Medical Imaging最新文献

Background: Differentiated thyroid cancer (DTC) accounts for the majority of thyroid cancers. The preoperative diagnosis of extrathyroidal extension (ETE) in DTC patients is highly important. However, two-dimensional ultrasound (2D-US) has several limitations in diagnosing ETE. This study aimed to evaluate the efficiency of OmniView of three-dimensional ultrasound (3D-OmniView) in assessing the ETE of DTC patients compared with that of 2D-US.

Methods: Patients who underwent thyroid surgery for nodules adjacent to the thyroid capsule between February 2016 and January 2018 were prospectively enrolled in this study. Both 2D-US and 3D-OmniView were used to evaluate ETE of thyroid nodules. The definition for ETE in ultrasound images was capsule disruption, or capsule disruption and surrounding tissue invasion. Intraoperative and pathological findings of ETE were considered positive. The sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), accuracy, and area under the ROC curve (AUC) were calculated.

Results: A total of 176 DTC nodules from 137 patients were included in this study. ETE was identified in 67.0% of the nodules. The sensitivity, accuracy, NPV and AUC of 3D-OmniView for predicting ETE were significantly greater than those of 2D-US. The sensitivity and specificity of 2D-US and 3D-OmniView were 51.7% and 79.7%, respectively (P < 0.001), and 81.0% and 82.8%, respectively (P = 0.809). Both 2D-US and 3D-OmniView showed better efficacy in evaluating ETE in nodules > 1 cm than in evaluating ETE in nodules ≤ 1 cm.

Conclusion: 3D-OmniView was more precise in predicting ETE of DTC nodules than 2D-US. 3D-OmniView is recommended for further evaluation of all thyroid nodules adjacent to the thyroid capsule. ETE was easier to detect by ultrasound for nodules > 1 cm than for nodules ≤ 1 cm.

Objectives: This study aimed to investigate the diagnostic test accuracy of MRI-based radiomics studies for predicting EGFR mutation in brain metastasis originating from lung cancer.

Methods: This meta-analysis, conducted following PRISMA guidelines, involved a systematic search in PubMed, Embase, and Web of Science up to November 3, 2024. Eligibility criteria followed the PICO framework, assessing population, intervention, comparison, and outcome. The RQS and QUADAS-2 tools were employed for quality assessment. A Bayesian model determined summary estimates, and statistical analysis was conducted using R and STATA software.

Results: Eleven studies consisting of nine training and ten validation cohorts were included in the meta-analysis. In the training cohorts, MRI-based radiomics showed robust predictive performance for EGFR mutations in brain metastases, with an AUC of 0.90 (95% CI: 0.82-0.93), sensitivity of 0.84 (95% CI: 0.80-0.88), specificity of 0.86 (95% CI: 0.80-0.91), and a diagnostic odds ratio (DOR) of 34.17 (95% CI: 19.16-57.49). Validation cohorts confirmed strong performance, with an AUC of 0.91 (95% CI: 0.69-0.95), sensitivity of 0.79 (95% CI: 0.73-0.84), specificity of 0.88 (95% CI: 0.83-0.93), and a DOR of 31.33 (95% CI: 15.50-58.3). Subgroup analyses revealed notable trends: the T1C + T2WI sequences and 3.0 T scanners showed potential superiority, machine learning-based radiomics and manual segmentation exhibited higher diagnostic accuracy, and PyRadiomics emerged as the preferred feature extraction software.

Conclusion: This meta-analysis suggests that MRI-based radiomics holds promise for the non-invasive prediction of EGFR mutations in brain metastases of lung cancer.

Background: The prevalence and detection rates of adrenal incidentalomas have been on the rise globally, with more than 90% of these lesions pathologically classified as adrenocortical adenomas. Among these, approximately 30% of patients present with hormone-secreting adenomas, leading to the deterioration of their health, with some requiring surgical resection. The available methods for adrenal function evaluation are invasive and costly. Moreover, their accuracy is influenced by numerous factors. Therefore, it is imperative to develop non-invasive and simplified preoperative diagnostic approach.

Methods: A retrospective study was performed on 169 patients from two tertiary medical centers. Subsequently, radiomics features were extracted after tumor margins were delineated layer-by-layer using a semi-automatic contouring approach. Feature selection was achieved in two cycles, with the first round utilizing a support vector machine (SVM) and the second round using a LASSO-based recursive feature elimination algorithm. Finally, logistic regression models were constructed using the clinico-radiological, radiomics, and a combination of both.

Results: After a comprehensive evaluation of the predictive indicators, the logistic regression classifier model based on the combined clinico-radiological and radiomic features had an AUC of (0.945, 0.927, 0.856) for aldosterone-producing adenoma (APA), (0.963, 0.889, 0.887) for cortisol-producing adenoma (CPA), and (0.940, 0.765, 0.816) for non-functioning adrenal adenoma (NAA) in the training set, validation set, and external test set, respectively. This model exhibited superior predictive performance in differentiating between the three adrenal adenoma subtypes.

Conclusions: A logistic regression model was constructed using radiomics and clinico-radiological features derived from multi-phase enhanced CT images and conducted external validation. The combined model showed good overall performance, highlighting the feasibility of applying the model for preoperative differentiation and prediction of various types of ACA.

Background: To develop and validate a dual-phase contrast-enhanced computed tomography (CT)-based intratumoral and peritumoral radiomics for the prediction of lymphovascular invasion (LVI) in patients with gastric cancer.

Method: Three hundred and eighty-three patients with gastric cancer (training cohort, 269 patients; test cohort, 114 patients) were retrospectively enrolled between January 2017 and June 2023. Radiomics features were extracted from the intratumoral volume (ITV) and peritumoral volume (PTV) on CT images at arterial phase (AP) and venous phase (VP), and selected by the least absolute shrinkage and selection operator. Radiomics models were constructed by logistic regression. The clinical-radiomics combined model incorporating the most predictive radiomics signature and clinical risk factors were developed with multivariate analysis. Receiver operating characteristic (ROC) curves were used to evaluate the prediction performance of models.

Results: Clinical model comprised of three clinical risk factors including tumor differentiation, CT-reported lymph node metastasis status and CT-TNM staging showed good performance with an area under the ROC curve (AUC) of 0.804 and 0.825 in the training and test cohort, respectively. Compared with the other radiomics models, dual-phase (AP + VP) CT-based ITV + PTV radiomics model presented superior AUC of 0.844 and 0.835 in the training and test cohort, respectively. Clinical-radiomics combined model further improved the discriminatory performance (AUC, 0.903) in the training and test cohort (AUC, 0.901). Decision curve analysis confirmed the net benefit of clinical-radiomics combined model. Subgroup analyses showed that the clinical-radiomics nomogram showed the best performance with an AUC of 0.879 and 0.883 for predicting LVI in T1-T2 and T3-T4 gastric cancer compared with the clinical model and the ITV + PTV-AP + VP radiomics model, respectively.

Conclusions: Clinical-radiomics combined model integrating clinical risk factors and dual-phase contrast-enhanced CT-based intratumoral and peritumoral radiomics signatures provided favorable performance for predicting LVI in gastric cancer.

Background: Vertebral compression fractures (VCFs) are prevalent in the elderly, often caused by osteoporosis or trauma. Differentiating acute from chronic VCFs is vital for treatment planning, but MRI, the gold standard, is inaccessible for some. However, CT, a more accessible alternative, lacks precision. This study aimed to enhance CT's diagnostic accuracy for VCFs using deep transfer learning (DTL) and radiomics.

Methods: We retrospectively analyzed 218 VCF patients scanned with CT and MRI within 3 days from Oct 2022 to Feb 2024. MRI categorized VCFs. 3D regions of interest (ROIs) from CT scans underwent feature extraction and DTL modeling. Receiver operating characteristic (ROC) analysis evaluated models, with the best fused with radiomic features via LASSO. AUCs compared via Delong test, and clinical utility assessed by decision curve analysis (DCA).

Results: Patients were split into training (175) and test (43) sets. Traditional radiomics with LR yielded AUCs of 0.973 (training) and 0.869 (test). Optimal DTL modeling improved to 0.992 (training) and 0.941 (test). Feature fusion further boosted AUCs to 1.000 (training) and 0.964 (test). DCA validated its clinical significance.

Conclusion: The feature fusion model enhances the differential diagnosis of acute and chronic VCFs, outperforming single-model approaches and offering a valuable decision-support tool for patients unable to undergo spinal MRI.

Background: Long-term severe cholangitis can lead to dense adhesions and increased fragility of the bile duct, complicating surgical procedures and elevating operative risk in children with pancreaticobiliary maljunction (PBM). Consequently, preoperative diagnosis of moderate-to-severe chronic cholangitis is essential for guiding treatment strategies and surgical planning. This study aimed to develop and validate a deep learning radiomics nomogram (DLRN) based on contrast-enhanced CT images and clinical characteristics to preoperatively identify moderate-to-severe chronic cholangitis in children with PBM.

Methods: A total of 323 pediatric patients with PBM who underwent surgery were retrospectively enrolled from three centers, and divided into a training cohort (n = 153), an internal validation cohort (IVC, n = 67), and two external test cohorts (ETC1, n = 58; ETC2, n = 45). Chronic cholangitis severity was determined by postoperative pathology. Handcrafted radiomics features and deep learning (DL) radiomics features, extracted using transfer learning with the ResNet50 architecture, were obtained from portal venous-phase CT images. Multivariable logistic regression was used to establish the DLRN, integrating significant clinical factors with handcrafted and DL radiomics signatures. The diagnostic performances were evaluated in terms of discrimination, calibration, and clinical usefulness.

Results: Biliary stones and peribiliary fluid collection were selected as important clinical factors. 5 handcrafted and 5 DL features were retained to build the two radiomics signatures, respectively. The integrated DLRN achieved satisfactory performance, achieving area under the curve (AUC) values of 0.913 (95% CI, 0.834-0.993), 0.916 (95% CI, 0.845-0.987), and 0.895 (95% CI, 0.801-0.989) in the IVC, and two ETCs, respectively. In comparison, the clinical model, handcrafted signature, and DL signature had AUC ranges of 0.654-0.705, 0.823-0.857, and 0.840-0.872 across the same cohorts. The DLRN outperformed single-modality clinical, handcrafted radiomics, and DL radiomics models, with all integrated discrimination improvement values > 0 and P < 0.05. The Hosmer-Lemeshow test and calibration curves showed good consistency of the DLRN (P > 0.05), and the decision curve analysis and clinical impact curve further confirmed its clinical utility.

Conclusions: The integrated DLRN can be a useful and non-invasive tool for preoperatively identifying moderate-to-severe chronic cholangitis in children with PBM, potentially enhancing clinical decision-making and personalized management strategies.

Background: Blunt spleen injuries (BSI) present significant diagnostic and management challenges in trauma care. Current guidelines recommend arterial-phase contrast-enhanced multidetector computed tomography (CT) for a detailed assessment. However, the direct impact of add-on arterial phase CT on clinical outcomes remains unclear. This study investigated the impact of early arterial-phase imaging via multidetector CT on the clinical outcomes of patients with blunt splenic injuries.

Methods: A retrospective case-control study was conducted to analyze the data of adult patients with BSI treated at a single institution between 2019 and 2022. Patients were divided based on the CT phase performed: portal vein phase only or add-on arterial phase. Management methods were divided according to the initial treatment intent: nonoperative management observation (NOM-Obs), transarterial embolization (TAE), and splenectomy. NOM failure refers to either NOM-Obs or TAE failure leading to splenectomy. NOM-Obs failure refers to cases initially managed with observation only, but later requiring either TAE or splenectomy. Transarterial embolization (TAE) failure refers to cases initially treated with TAE, but subsequently requiring splenectomy. Inverse probability of treatment weighting (IPTW) was used to balance baseline differences and compare outcomes between the two groups.

Results: Of 170 patients assessed, 147 met the inclusion criteria and were divided into two groups: those receiving portal vein phasic-only CT (N = 104) and those receiving add-on arterial phasic CT (N = 43). The overall NOM failure rate was 3.0% (4/132), the NOM-OBS failure rate was 6.7% (4/60), and the TAE failure rate was 4.1% (3/73). After adjusting for covariates using inverse probability of treatment weighting (IPTW), the comparison between the add-on arterial phase and portal phase CT groups revealed similar overall NOM failure rates (3.0% vs. 2.2%, p = 0.721), NOM-OBS failure rates (3.8% vs. 6.2%, p = 0.703), and intra-abdominal bleeding-related mortality rates (4.8% vs. 2.1%, p = 0.335). Among the 43 patients who underwent add-on arterial CT, only one was diagnosed with a tiny pseudoaneurysm (0.7 cm) attributable to the inclusion of the arterial phase.

Conclusion: Dual-phase CT within 24 h of presentation offers no added value over single-phase CT in managing blunt splenic injuries in terms of clinical outcomes.

Background: Computed tomography attenuation correction (CTAC) is commonly used in cardiac SPECT imaging to reduce soft-tissue attenuation artifacts. However, CTAC is prone to inaccuracies due to CT artifacts and SPECT-CT mismatch, along with additional radiation exposure to patients. Thus, these limitations have led to increasing interest in CT-free AC, with deep learning (DL) offering promising solutions. We proposed a new DL-based CT-free AC methods for cardiac SPECT.

Methods: We developed a feature alignment attenuation correction network (FA-ACNet) based on the 3D U-Net framework to generate predicted DL-based AC SPECT (Deep AC). The network was trained on 167 cardiac SPECT/CT studies using 5-fold cross validation and tested in an independent testing set (n = 35), with CTAC serving as the reference. During training, multi-scale features from non-attenuation-corrected (NAC) SPECT and CT were processed separately and then aligned with the encoded features from NAC SPECT using adversarial learning and distance metric learning techniques. The performance of FA-ACNet was evaluated using mean square error (MSE), structural similarity index (SSIM) and peak signal-to-noise ratio (PSNR). Additionally, semi-quantitative evaluation of Deep AC images was performed and compared to CTAC using Bland-Altman plots.

Results: FA-ACNet achieved an MSE of 16.94 ± 2.03 × 10^- 6, SSIM of 0.9955 ± 0.0006 and PSNR of 43.73 ± 0.50 after 5-fold cross validation. Compared to U-Net, MSE and PSNR improved by aligning multi-scale features from NAC SPECT and CT with those from NAC SPECT. In the testing set, FA-ACNet achieved an MSE of 11.98 × 10^- 6, SSIM of 0.9976 and PSNR of 45.54. The 95% limits of agreement (LoAs) between the Deep AC and CTAC images for the summed stress/rest scores (SSS/SRS) were [- 2.3, 2.8] and [-1.9,2.1] in the training set and testing set respectively. Changes in perfusion categories were observed in 4.19% and 5.9% of studies assessed for global perfusion scores in the training set and testing set.

Conclusion: We propose a novel DL-based CT-free AC approach for cardiac SPECT, which can generate AC images without the need for a CT scan. By leveraging multi-scale features from both NAC SPECT and CT, the performance of CT-free AC is significantly enhanced, offering a promising alternative for future DL-based AC strategies.

Objectives: A predictive model was developed based on enhanced computed tomography (CT), laboratory test results, and pathological indicators to achieve the convenient and effective prediction of single lymph node metastasis (LNM) in gastric cancer.

Methods: Sixty-six consecutive patients (235 regional lymph nodes) with pathologically confirmed gastric cancer who underwent surgery at our hospital between December 2020 and November 2021 were retrospectively reviewed. They were randomly allocated to training (n = 38, number of lymph nodes = 119) and validation (n = 28, number of lymph nodes = 116) datasets. The clinical data, laboratory test results, enhanced CT characteristics, and pathological indicators from gastroscopy-guided needle biopsies were obtained. Multivariable logistic regression with generalised estimation equations (GEEs) was used to develop a predictive model for LNM in gastric cancer. The predictive performance of the model developed using the training and validation datasets was validated using receiver operating characteristic curves.

Results: Lymph node enhancement pattern, Ki67 level, and lymph node long-axis diameter were independent predictors of LNM in gastric cancer (p < 0.01). The GEE-logistic model was associated with LNM (p = 0.001). The area under the curve and accuracy of the model, with 95% confidence intervals, were 0.944 (0.890-0.998) and 0.897 (0.813-0.952), respectively, in the training dataset and 0.836 (0.751-0.921) and 0.798 (0.699-0.876), respectively, in the validation dataset.

Conclusion: The predictive model constructed based on lymph node enhancement pattern, Ki67 level, and lymph node long-axis diameter exhibited good performance in predicting LNM in gastric cancer and should aid the lymph node staging of gastric cancer and clinical decision-making.

Liver cancer detection is critically important in the discipline of biomedical image testing and diagnosis. Researchers have explored numerous machine learning (ML) techniques and deep learning (DL) approaches aimed at the automated recognition of liver disease by analysing computed tomography (CT) images. This study compares two frameworks, Deep Convolutional Neural Network (DCNN) and Hierarchical Fusion Convolutional Neural Networks (HFCNN), to assess their effectiveness in liver cancer segmentation. The contribution includes enhancing the edges and textures of CT images through filtering to achieve precise liver segmentation. Additionally, an existing DL framework was employed for liver cancer detection and segmentation. The strengths of this paper include a clear emphasis on the criticality of liver cancer detection in biomedical imaging and diagnostics. It also highlights the challenges associated with CT image detection and segmentation and provides a comprehensive summary of recent literature. However, certain difficulties arise during the detection process in CT images due to overlapping structures, such as bile ducts, blood vessels, image noise, textural changes, size and location variations, and inherent heterogeneity. These factors may lead to segmentation errors and subsequently different analyses. This research analysis compares two advanced methodologies, DCNN and HFCNN, for liver cancer detection. The evaluation of DCNN and HFCNN in liver cancer detection is conducted using multiple performance metrics, including precision, F1-score, recall, and accuracy. This comprehensive assessment provides a detailed evaluation of these models' effectiveness compared to other state-of-the-art methods in identifying liver cancer.