Multi-sequence Magnetic Resonance Research Articles

Multicenter Integration of MR Radiomics, Deep Learning, and Clinical Indicators for Predicting Hepatocellular Carcinoma Recurrence After Thermal Ablation.

To develop and validate an innovative predictive model that integrates multisequence magnetic resonance (MR) radiomics, deep learning features, and clinical indicators to accurately predict the recurrence of hepatocellular carcinoma (HCC) after thermal ablation. This retrospective multicenter cohort study enrolled patients who were diagnosed with HCC and treated via thermal ablation. We extracted radiomic features from multisequence 3T MR images, analyzed these images using a 3D convolutional neural network (3D CNN), and incorporated clinical data into the model. Model performance was evaluated using the area under the curve (AUC) of the receiver operating characteristic (ROC) curve. The study included 535 patients from three hospitals, comprising 462 males and 43 females. The RDC model, which stands for the Radiomics-Deep Learning-Clinical data model, demonstrated high predictive accuracy, achieving AUCs of 0.794 in the training set, 0.777 in the validation set, and 0.787 in the test set. Statistical analysis confirmed the model's robustness and the significant contribution of the integrated features to its predictive capabilities. The RDC model effectively predicts HCC recurrence after thermal ablation by synergistically combining advanced imaging analysis and clinical parameters. This study highlights the potential of such integrative approaches to enhance prognostic assessments in HCC patients and offers a promising tool for clinical decision-making.

Automated segmentation of midbrain nuclei using deep learning and multisequence MRI: a longitudinal study on iron accumulation with age

Abstract Elevated levels of brain iron, particularly within the basal ganglia, have been associated with cognitive and motor impairment in normal aging and neurodegenerative conditions. The subthalamic nucleus (STN), substantia nigra (SN), and red nucleus (RN), despite their high iron content and contribution to motor and cognitive processes, are less frequently studied. This oversight can largely be attributed to the challenges posed by in-vivo assessments of these small, deep-seated midbrain structures. We developed and validated an automated tool for the segmentation of the STN, SN, and RN. Multi-sequence magnetic resonance imaging (MRI) data including T1-weighted, FLAIR, Quantitative Susceptibility Mapping (QSM) and R2* alongside manual delineation on QSM images of 40 individuals, was used to train segmentation models based on nnU-Net deep-learning framework. A combination of QSM and FLAIR sequences was found to be optimal for structure segmentation (mean Dice scores of 0.84, 0.91 and 0.94 for STN, SN and RN, respectively). We next applied the automated segmentation method to an independent 3-year longitudinal dataset including 175 healthy adults (age range at baseline: 20-79 years old). Structural equation modelling was used to assess iron accumulation over time using age, sex, baseline iron and regional volume as factors of interest. Cross-sectionally, older age was linearly associated with higher iron load in SN and STN; the association was non-linear in RN. Longitudinally, results indicated significant iron accumulation in the STN (Mean increase = 0.02, p = 0.005) and SN (Mean increase = 0.035, p = 0.001), but not in the RN (Mean increase = 0.015, p = 0.2). Our findings demonstrated high performance of nnU-Net in automated segmentation, and advanced our understanding of iron accumulation in midbrain nuclei in aging.

Clinical study on improving the diagnostic accuracy of adult elbow joint cartilage injury by multisequence magnetic resonance imaging.

Due to frequent and high-risk sports activities, the elbow joint is susceptible to injury, especially to cartilage tissue, which can cause pain, limited movement and even loss of joint function. To evaluate magnetic resonance imaging (MRI) multisequence imaging for improving the diagnostic accuracy of adult elbow cartilage injury. A total of 60 patients diagnosed with elbow cartilage injury in our hospital from January 2020 to December 2021 were enrolled in this retrospective study. We analyzed the accuracy of conventional MRI sequences (T1-weighted imaging, T2-weighted imaging, proton density weighted imaging, and T2 star weighted image) and Three-Dimensional Coronary Imaging by Spiral Scanning (3D-CISS) in the diagnosis of elbow cartilage injury. Arthroscopy was used as the gold standard to evaluate the diagnostic effect of single and combination sequences in different injury degrees and the consistency with arthroscopy. The diagnostic accuracy of 3D-CISS sequence was 89.34% ± 4.98%, the sensitivity was 90%, and the specificity was 88.33%, which showed the best performance among all sequences (P < 0.05). The combined application of the whole sequence had the highest accuracy in all sequence combinations, the accuracy of mild injury was 91.30%, the accuracy of moderate injury was 96.15%, and the accuracy of severe injury was 93.33% (P < 0.05). Compared with arthroscopy, the combination of all MRI sequences had the highest consistency of 91.67%, and the kappa value reached 0.890 (P < 0.001). Combination of 3D-CISS and each sequence had significant advantages in improving MRI diagnostic accuracy of elbow cartilage injuries in adults. Multisequence MRI is recommended to ensure the best diagnosis and treatment.

Learning co-plane attention across MRI sequences for diagnosing twelve types of knee abnormalities

Multi-sequence magnetic resonance imaging is crucial in accurately identifying knee abnormalities but requires substantial expertise from radiologists to interpret. Here, we introduce a deep learning model incorporating co-plane attention across image sequences to classify knee abnormalities. To assess the effectiveness of our model, we collected the largest multi-sequence knee magnetic resonance imaging dataset involving the most comprehensive range of abnormalities, comprising 1748 subjects and 12 types of abnormalities. Our model achieved an overall area under the receiver operating characteristic curve score of 0.812. It achieved an average accuracy of 0.78, outperforming junior radiologists (accuracy 0.65) and remains competitive with senior radiologists (accuracy 0.80). Notably, with the assistance of model output, the diagnosis accuracy of all radiologists was improved significantly (p < 0.001), elevating from 0.73 to 0.79 on average. The interpretability analysis demonstrated that the model decision-making process is consistent with the clinical knowledge, enhancing its credibility and reliability in clinical practice.

Artificial intelligence improves the diagnosis of human leukocyte antigen (HLA)-B27-negative axial spondyloarthritis based on multi-sequence magnetic resonance imaging and clinical features.

Axial spondyloarthritis (axSpA) is frequently diagnosed late, particularly in human leukocyte antigen (HLA)-B27-negative patients, resulting in a missed opportunity for optimal treatment. This study aimed to develop an artificial intelligence (AI) tool, termed NegSpA-AI, using sacroiliac joint (SIJ) magnetic resonance imaging (MRI) and clinical SpA features to improve the diagnosis of axSpA in HLA-B27-negative patients. We retrospectively included 454 HLA-B27-negative patients with rheumatologist-diagnosed axSpA or other diseases (non-axSpA) from the Third Affiliated Hospital of Southern Medical University and Nanhai Hospital between January 2010 and August 2021. They were divided into a training set (n=328) for 5-fold cross-validation, an internal test set (n=72), and an independent external test set (n=54). To construct a prospective test set, we further enrolled 87 patients between September 2021 and August 2023 from the Third Affiliated Hospital of Southern Medical University. MRI techniques employed included T1-weighted (T1W), T2-weighted (T2W), and fat-suppressed (FS) sequences. We developed NegSpA-AI using a deep learning (DL) network to differentiate between axSpA and non-axSpA at admission. Furthermore, we conducted a reader study involving 4 radiologists and 2 rheumatologists to evaluate and compare the performance of independent and AI-assisted clinicians. NegSpA-AI demonstrated superior performance compared to the independent junior rheumatologist (≤5 years of experience), achieving areas under the curve (AUCs) of 0.878 [95% confidence interval (CI): 0.786-0.971], 0.870 (95% CI: 0.771-0.970), and 0.815 (95% CI: 0.714-0.915) on the internal, external, and prospective test sets, respectively. The assistance of NegSpA-AI promoted discriminating accuracy, sensitivity, and specificity of independent junior radiologists by 7.4-11.5%, 1.0-13.3%, and 7.4-20.6% across the 3 test sets (all P<0.05). On the prospective test set, AI assistance also improved the diagnostic accuracy, sensitivity, and specificity of independent junior rheumatologists by 7.7%, 7.7%, and 6.9%, respectively (all P<0.01). The proposed NegSpA-AI effectively improves radiologists' interpretations of SIJ MRI and rheumatologists' diagnoses of HLA-B27-negative axSpA.

Prediction of glypican-3 expression in hepatocellular carcinoma using multisequence magnetic resonance imaging-based histology nomograms.

Hepatocellular carcinoma (HCC) is often associated with the overexpression of multiple proteins and genes. For instance, patients with HCC and a high expression of the glypican-3 (GPC3) gene have a poor prognosis, and noninvasive assessment of GPC3 expression before surgery is helpful for clinical decision-making. Therefore, our primary aim in this study was to develop and validate multisequence magnetic resonance imaging (MRI) radiomics nomograms for predicting the expression of GPC3 in individuals diagnosed with HCC. We conducted a retrospective analysis of 143 patients with HCC, including 123 cases from our hospital and 20 cases from The Cancer Genome Atlas (TCGA) or The Cancer Imaging Archive (TCIA) public databases. We used preoperative multisequence MRI images of the patients for the radiomics analysis. We extracted and screened the imaging histologic features using fivefold cross-validation, Pearson correlation coefficient, and the least absolute shrinkage and selection operator (LASSO) analysis method. We used logistic regression (LR) to construct a radiomics model, developed nomograms based on the radiomics scores and clinical parameters, and evaluated the predictive performance of the nomograms using receiver operating characteristic (ROC) curves, calibration curves, and decision curves. Our multivariate analysis results revealed that tumor morphology (P=0.015) and microvascular (P=0.007) infiltration could serve as independent predictors of GPC3 expression in patients with HCC. The nomograms integrating multisequence radiomics radiomics score, tumor morphology, and microvascular invasion had an area under the curve (AUC) value of 0.989. This approach was superior to both the radiomics model (AUC 0.979) and the clinical model (AUC 0.793). The sensitivity, specificity, and accuracy of 0.944, 0.800, and 0.913 for the test set, respectively, and the model's calibration curve demonstrated good consistency (Brier score =0.029). The decision curve analysis (DCA) indicated that the nomogram had a higher net clinical benefit for predicting the expression of GPC3. External validation of the model's prediction yielded an AUC value of 0.826. Our study findings highlight the close association of multisequence MRI imaging and radiomic features with GPC3 expression. Incorporating clinical parameters into nomograms can offer valuable preoperative insights into tailoring personalized treatment plans for patients diagnosed with HCC.

Synthetic CT generation based on multi-sequence MR using CycleGAN for head and neck MRI-only planning.

The purpose of this study is to investigate the influence of different magnetic resonance (MR) sequences on the accuracy of generating computed tomography (sCT) images for nasopharyngeal carcinoma based on CycleGAN. In this study, 143 patients' head and neck MR sequence (T1, T2, T1C, and T1DIXONC) and CT imaging data were acquired. The generator and discriminator of CycleGAN are improved to achieve the purpose of balance confrontation, and a cyclic consistent structure control domain is proposed in terms of loss function. Four different single-sequence MR images and one multi-sequence MR image were used to evaluate the accuracy of sCT. During the model testing phase, five testing scenarios were employed to further assess the mean absolute error, peak signal-to-noise ratio, structural similarity index, and root mean square error between the actual CT images and the sCT images generated by different models. T1 sequence-based sCT achieved better results in single-sequence MR-based sCT. Multi-sequence MR-based sCT achieved better results with T1 sequence-based sCT in terms of evaluation metrics. For metrological evaluation, the global gamma passage rate of sCT based on sequence MR was greater than 95% at 3%/3mm, except for sCT based on T2 sequence MR. We developed a CycleGAN method to synthesize CT using different MR sequences, this method shows encouraging potential for dosimetric evaluation.

Application value of artificial intelligence algorithm-based magnetic resonance multi-sequence imaging in staging diagnosis of cervical cancer.

The aim of this research is to explore the application value of Deep residual network model (DRN) for deep learning-based multi-sequence magnetic resonance imaging (MRI) in the staging diagnosis of cervical cancer (CC). This research included 90 patients diagnosed with CC between August 2019 and May 2021 at the hospital. After undergoing MRI examination, the clinical staging and surgical pathological staging of patients were conducted. The research then evaluated the results of clinical staging and MRI staging to assess their diagnostic accuracy and correlation. In the staging diagnosis of CC, the feature enhancement layer was added to the DRN model, and the MRI imaging features of CC were used to enhance the image information. The precision, specificity, and sensitivity of the constructed model were analyzed, and then the accuracy of clinical diagnosis staging and MRI staging were compared. As the model constructed DRN in this research was compared with convolutional neural network (CNN) and the classic deep neural network visual geometry group (VGG), the precision was 67.7, 84.9, and 93.6%, respectively. The sensitivity was 70.4, 82.5, and 91.2%, while the specificity was 68.5, 83.8, and 92.2%, respectively. The precision, sensitivity, and specificity of the model were remarkably higher than those of CNN and VGG models (P < 0.05). As the clinical staging and MRI staging of CC were compared, the diagnostic accuracy of MRI was 100%, while that of clinical diagnosis was 83.7%, showing a significant difference between them (P < 0.05). Multi-sequence MRI under intelligent algorithm had a high diagnostic rate for CC staging, deserving a good clinical application value.

MR radiomics and neoadjuvant chemo-responsiveness with insights into selective treatment de-intensification in HPV-positive oropharyngeal carcinoma.

6085 Background: In HPV-positive oropharyngeal squamous cell carcinoma (OPSCC), patients with good response to neoadjuvant chemotherapy (NAC) exhibit superior prognosis. Accurate prediction of NAC response allows for NAC candidate selection and personalized treatment de-intensification in HPV-positive OPSCC. In this study, we aimed to apply baseline magnetic resonance (MR) radiomic features to predict NAC response and prognosis. Methods: Pre-treatment MR images and clinical data of 131 patients with HPV-positive OPSCC were retrieved from Fudan University Shanghai Cancer Center. Radiomic features of both oropharyngeal lesions and metastatic nodes were extracted on T2WI and contrast-enhanced T1WI sequence. Patients were divided into training cohort (n=47), prospective validation cohort (n=49) and real-world validation cohort (n=35). Following radiomic feature selection, a linear support vector machine (SVM) model was built and validated for NAC response prediction. Nomograms that combined radiomics and clinical characteristics were then developed to predict survival outcomes. The performance of response models was assessed by the area under the curve (AUC), accuracy, sensitivity, specificity and prognostic models were measured by C-index. RNA-seq and proteomic data were further leveraged and compared to interpret the molecular features underlying radiomic signatures with differential NAC response. Results: For NAC response prediction, the fusion model with both oropharyngeal and nodal radiomic signatures on multi-sequence MR images achieved encouraging performance to predict good responders in the training cohort (AUC 0.89, 95% CI, 0.79-0.95) and prospective validation cohort (AUC 0.71, 95% CI, 0.59-0.83). For prognosis prediction, radiomics-based nomograms exhibited satisfactory discriminative ability between low-risk and high-risk patients in training cohort and two validation cohorts (PFS, C-index: 0.85, 0.76 and 0.83; OS, C-index: 0.79, 0.76 and 0.87). An exploratory analysis in the prospective validation cohort showed that de-intensified radiotherapy after NAC in low-risk patients yielded 100% in both PFS and OS. Furthermore, expression analysis unveiled distinct molecular phenotypes in relation to NAC response, where poor responders had predominantly enhanced keratinization while good responders were featured by stronger innate and adaptive immune response. Conclusions: The MR-based radiomic models and subsequent prognostic models efficiently discriminate among patients with different NAC response and survival risk. This study provides a new strategy for patient selection in HPV-positive OPSCC that are suitable for personalized de-intensification. Integration of radiomics in future trials is warranted.

Diagnostic significance of multisequence MRI radiomics models in distinguishing benign and malignant spinal fractures

PurposeTo investigate the diagnostic value of multi-sequence magnetic resonance imaging (MRI) in benign and malignant spinal fractures. Materials and methodsMRI data of patients with pathologically confirmed malignant vertebral fractures were retrospectively collected and compared with those with benign vertebral fractures. The image omics features of T1-weighted imaging (T1WI) and T2-weighted imaging (T2WI) were extracted respectively, and were randomly divided into training and test sets at 8:2. The training set adopted recursive feature elimination method and minimum absolute contraction and selection operator (LASSO) regression to screen the variables. Three image omics models, T1WI, T2WI and the combination of two sequences, were constructed by logistic regression, and the diagnostic efficiency of each model was verified by the test set. The receiver operating curve evaluated the diagnostic efficiency of the model. ResultsA total of 111 vertebrae with fracture were included in 97 patients, 55 with benign fracture and 56 with malignant fracture. In the training set, the AUC, sensitivity and specificity of the T1WI model were 0.892, 88.9% and 81.4%, respectively. In T2WI model, the results were 0.924, 82.2% and 95.3%, respectively. The combined models of the two sequences were 0.934, 90.0% and 87.5%, respectively. In the test set, the AUC, sensitivity and specificity of T1WI model were 0.877, 80.0% and 92.3%, respectively. In T2WI model, the results were 0.923, 90.0% and 92.3%, respectively. The combined models were 0.933, 100.0% and 87.5%, respectively. The diagnostic efficiency of the two-sequence combined image omics model was better than that of the radiologist. ConclusionThe combined model, incorporating T1WI and T2WI, outperformed single-sequence models in terms of diagnostic accuracy. The integration of multisequence radiomic features provided enhanced texture information, contributing to superior accuracy and efficiency in diagnosing malignant spinal fractures.

Machine learning based on optimal VOI of multi-sequence MR images to predict lymphovascular invasion in invasive breast cancer

ObjectivesLymphovascular invasion serves as a crucial prognostic indicator in invasive breast cancer, influencing treatment decisions. We aimed to develop a machine learning model utilizing optimal volumes of interest extracted from multisequence magnetic resonance images to predict lymphovascular invasion in patients with invasive breast cancer. Materials and methodsThis study comprised 191 patients postoperatively diagnosed with invasive breast cancer through multi-sequence magnetic resonance imaging. Independent predictors were identified through univariate and multivariate logistic regression analyses, culminating in the construction of a clinical model. Radiomic features were extracted from multi-sequence magnetic resonance imaging images across various volume of interest scales (−2 mm, entire, +2 mm, +4 mm, and +6 mm). Subsequently, various radiomic models were developed using machine learning model algorithms, including logistic regression, support vector machine, k-nearest neighbor, gradient boosting machine, classification and regression tree, and random forest. A hybrid model was then formulated, amalgamating optimal radiomic and clinical models. ResultsThe area under the curve of the clinical model was 0.757. Among the radiomic models, the most efficient diagnosis was achieved by the k-nearest neighbor-based radiomics-volume of interest (+2 mm), resulting in an area under the curve of 0.780. The hybrid model, integrating the k-nearest neighbor-based radiomics-volume of interest (+2 mm), and the clinical model surpassed the individual clinical and radiomics models, exhibiting a superior area under the curve of 0.864. ConclusionUtilizing a hybrid approach integrating clinical data and multi-sequence magnetic resonance imaging-derived radiomics models based on the multiscale tumor region volume of interest (+2 mm) proved effective in determining lymphovascular invasion status in patients with invasive breast cancer. This innovative methodology may offer valuable insights for treatment planning and disease management.

A New Automated Prognostic Prediction Method Based on Multi-Sequence Magnetic Resonance Imaging for Hepatic Resection of Colorectal Cancer Liver Metastases.

Colorectal cancer is a prevalent and life-threatening disease, where colorectal cancer liver metastasis (CRLM) exhibits the highest mortality rate. Currently, surgery stands as the most effective curative option for eligible patients. However, due to the insufficient performance of traditional methods and the lack of multi-modality MRI feature complementarity in existing deep learning methods, the prognosis of CRLM surgical resection has not been fully explored. This paper proposes a new method, multi-modal guided complementary network (MGCNet), which employs multi-sequence MRI to predict 1-year recurrence and recurrence-free survival in patients after CRLM resection. In light of the complexity and redundancy of features in the liver region, we designed the multi-modal guided local feature fusion module to utilize the tumor features to guide the dynamic fusion of prognostically relevant local features within the liver. On the other hand, to solve the loss of spatial information during multi-sequence MRI fusion, the cross-modal complementary external attention module designed an external mask branch to establish inter-layer correlation. The results show that the model has accuracy (ACC) of 0.79, the area under the curve (AUC) of 0.84, C-Index of 0.73, and hazard ratio (HR) of 4.0, which is a significant improvement over state-of-the-art methods. Additionally, MGCNet exhibits good interpretability.

Synthesis of gadolinium-enhanced glioma images on multisequence magnetic resonance images using contrastive learning.

Gadolinium-based contrast agents are commonly used in brain magnetic resonance imaging (MRI), however, they cannot be used by patients with allergic reactions or poor renal function. For long-term follow-up patients, gadolinium deposition in the body can cause nephrogenic systemic fibrosis and other potentialrisks. Developing a new method of enhanced image synthesis based on the advantages of multisequence MRI has important clinical value for these patients. In this paper, an end-to-end synthesis model structure similarity index measure (SSIM)-based Dual Constrastive Learning with Attention (SDACL) based on contrastive learning is proposed to synthesize contrast-enhanced T1 (T1ce) using three unenhanced MRI images of T1, T2, and Flair in patients withglioma. The model uses the attention-dilation generator to enlarge the receptive field by expanding the residual blocks and to strengthen the feature representation and context learning of multisequence MRI. To enhance the detail and texture performance of the imaged tumor area, a comprehensive loss function combining patch-level contrast loss and structural similarity loss is created, which can effectively suppress noise and ensure the consistency of synthesized images and real images. The normalized root-mean-square error (NRMSE), peak signal-to-noise ratio (PSNR), and SSIM of the model on the independent test set are 0.307 0.12, 23.337 3.21, and 0.881 0.05,respectively. Results show this method can be used for the multisequence synthesis of T1ce images, which can provide valuable information for clinical diagnosis.

CoNeS: Conditional neural fields with shift modulation for multi-sequence MRI translation

Multi-sequence magnetic resonance imaging (MRI) has found wide applications in both modern clinical studies and deep learning research. However, in clinical practice, it frequently occurs that one or more of the MRI sequences are missing due to different image acquisition protocols or contrast agent contraindications of patients, limiting the utilization of deep learning models trained on multi-sequence data. One promising approach is to leverage generative models to synthesize the missing sequences, which can serve as a surrogate acquisition. State-of-the-art methods tackling this problem are based on convolutional neural networks (CNN) which usually suffer from spectral biases, resulting in poor reconstruction of high-frequency fine details. In this paper, we propose Conditional Neural fields with Shift modulation (CoNeS), a model that takes voxel coordinates as input and learns a representation of the target images for multi-sequence MRI translation. The proposed model uses a multi-layer perceptron (MLP) instead of a CNN as the decoder for pixel-to-pixel mapping. Hence, each target image is represented as a neural field that is conditioned on the source image via shift modulation with a learned latent code. Experiments on BraTS 2018 and an in-house clinical dataset of vestibular schwannoma patients showed that the proposed method outperformed state-of-the-art methods for multi-sequence MRI translation both visually and quantitatively. Moreover, we conducted spectral analysis, showing that CoNeS was able to overcome the spectral bias issue common in conventional CNN models. To further evaluate the usage of synthesized images in clinical downstream tasks, we tested a segmentation network using the synthesized images at inference. The results showed that CoNeS improved the segmentation performance when some MRI sequences were missing and outperformed other synthesis models. We concluded that neural fields are a promising technique for multi-sequence MRI translation.

Radiomics of Preoperative Multi-Sequence Magnetic Resonance Imaging Can Improve the Predictive Performance of Microvascular Invasion in Hepatocellular Carcinoma.

The aim of the study is to demonstrate that radiomics of preoperative multi-sequence magnetic resonance imaging (MRI) can indeed improve the predictive performance of microvascular invasion (MVI) in hepatocellular carcinoma (HCC). A total of 206 patients with pathologically confirmed HCC who underwent preoperative enhanced MRI were retrospectively recruited. Univariate and multivariate logistic regression analysis identified the independent clinicoradiologic predictors of MVI present and constituted the clinicoradiologic model. Recursive feature elimination (RFE) was applied to select radiomics features (extracted from six sequence images) and constructed the radiomics model. Clinicoradiologic model plus radiomics model formed the clinicoradiomics model. Five-fold cross-validation was used to validate the three models. Discrimination, calibration, and clinical utility were used to evaluate the performance. Net reclassification improvement (NRI) and integrated discrimination improvement (IDI) were used to compare the prediction accuracy between models. The clinicoradiologic model contained alpha-fetoprotein (AFP)_lg10, radiological capsule enhancement, enhancement pattern and arterial peritumoral enhancement, which were independent risk factors of MVI. There were 18 radiomics features related to MVI constructed the radiomics model. The mean area under the receiver operating curve (AUC) of clinicoradiologic, radiomics and clinicoradiomics model were 0.849, 0.925 and 0.950 in the training cohort and 0.846, 0.907 and 0.933 in the validation cohort, respectively. The three models' calibration curves fitted well, and decision curve analysis (DCA) confirmed the clinical usefulness. Compared with the clinicoradiologic model, the NRI of radiomics and clinicoradiomics model increased significantly by 0.575 and 0.825, respectively, and the IDI increased significantly by 0.280 and 0.398, respectively. Radiomics of preoperative multi-sequence MRI can improve the predictive performance of MVI in HCC.

Application of machine learning-based multi-sequence MRI radiomics in diagnosing anterior cruciate ligament tears

ObjectiveTo compare the diagnostic power among various machine learning algorithms utilizing multi-sequence magnetic resonance imaging (MRI) radiomics in detecting anterior cruciate ligament (ACL) tears. Additionally, this research aimed to create and validate the optimal diagnostic model.MethodsIn this retrospective analysis, 526 patients were included, comprising 178 individuals with ACL tears and 348 with a normal ACL. Radiomics features were derived from multi-sequence MRI scans, encompassing T1-weighted imaging and proton density (PD)-weighted imaging. The process of selecting the most reliable radiomics features involved using interclass correlation coefficient (ICC) testing, t tests, and the least absolute shrinkage and selection operator (LASSO) technique. After the feature selection process, five machine learning classifiers were created. These classifiers comprised logistic regression (LR), support vector machine (SVM), K-nearest neighbors (KNN), light gradient boosting machine (LightGBM), and multilayer perceptron (MLP). A thorough performance evaluation was carried out, utilizing diverse metrics like the area under the receiver operating characteristic curve (ROC), specificity, accuracy, sensitivity positive predictive value, and negative predictive value. The classifier exhibiting the best performance was chosen. Subsequently, three models were developed: the PD model, the T1 model, and the combined model, all based on the optimal classifier. The diagnostic performance of these models was assessed by employing AUC values, calibration curves, and decision curve analysis.ResultsOut of 2032 features, 48 features were selected. The SVM-based multi-sequence radiomics outperformed all others, achieving AUC values of 0.973 and 0.927, sensitivities of 0.933 and 0.857, and specificities of 0.930 and 0.829, in the training and validation cohorts, respectively.ConclusionThe multi-sequence MRI radiomics model, which is based on machine learning, exhibits exceptional performance in diagnosing ACL tears. It provides valuable insights crucial for the diagnosis and treatment of knee joint injuries, serving as an accurate and objective supplementary diagnostic tool for clinical practitioners.

A deep convolutional neural network for the automatic segmentation of glioblastoma brain tumor: Joint spatial pyramid module and attention mechanism network

This study proposes a deep convolutional neural network for the automatic segmentation of glioblastoma brain tumors, aiming sat replacing the manual segmentation method that is both time-consuming and labor-intensive. There are many challenges for automatic segmentation to finely segment sub-regions from multi-sequence magnetic resonance images because of the complexity and variability of glioblastomas, such as the loss of boundary information, misclassified regions, and subregion size. To overcome these challenges, this study introduces a spatial pyramid module and attention mechanism to the automatic segmentation algorithm, which focuses on multi-scale spatial details and context information. The proposed method has been tested in the public benchmarks BraTS 2018, BraTS 2019, BraTS 2020 and BraTS 2021 datasets. The Dice score on the enhanced tumor, whole tumor, and tumor core were respectively 79.90 %, 89.63 %, and 85.89 % on the BraTS 2018 dataset, respectively 77.14 %, 89.58 %, and 83.33 % on the BraTS 2019 dataset, and respectively 77.80 %, 90.04 %, and 83.18 % on the BraTS 2020 dataset, and respectively 83.48 %, 90.70 %, and 88.94 % on the BraTS 2021 dataset offering performance on par with that of state-of-the-art methods with only 1.90 M parameters. In addition, our approach significantly reduced the requirements for experimental equipment, and the average time taken to segment one case was only 1.48 s; these two benefits rendered the proposed network intensely competitive for clinical practice.

A deep learning model integrating multisequence MRI to predict EGFR mutation subtype in brain metastases from non-small cell lung cancer.

To establish a predictive model based on multisequence magnetic resonance imaging (MRI) using deep learning to identify wild-type (WT) epidermal growth factor receptor (EGFR), EGFR exon 19 deletion (19Del), and EGFR exon 21-point mutation (21L858R) simultaneously. A total of 399 patients with proven brain metastases of non-small cell lung cancer (NSCLC) were retrospectively enrolled and divided into training (n = 306) and testing (n = 93) cohorts separately based on two timepoints. All patients underwent 3.0-T brain MRI including T2-weighted, T2-weighted fluid-attenuated inversion recovery, diffusion-weighted imaging, and contrast-enhanced T1-weighted sequences. Radiomics features were extracted from each lesion based on four sequences. An algorithm combining radiomics approach with graph convolutional networks architecture (Radio-GCN) was designed for the prediction of EGFR mutation status and subtype. The area under the curve (AUC) at receiver operating characteristic analysis was used to evaluate the predication capabilities of each model. We extracted 1,290 radiomics features from each MRI sequence. The AUCs of the Radio-GCN model for identifying EGFR 19Del, 21L858R, and WT for the lesion-wise analysis were 0.996 ± 0.004, 0.971 ± 0.013, and 1.000 ± 0.000 on the independent testing cohort separately. It also yielded AUCs of 1.000 ± 0.000, 0.991 ± 0.009, and 1.000 ± 0.000for predicting EGFR mutations respectively for the patient-wise analysis. The κ coefficients were 0.735 and 0.812, respectively. The constructed Radio-GCN model is a new potential tool to predict the EGFR mutation status and subtype in NSCLC patients with brain metastases. The study demonstrated that a deep learning approach based on multisequence MRI can help to predict the EGFR mutation status in NSCLC patients with brain metastases, which is beneficial to guide a personalized treatment. • This is the first study to predict the EGFR mutation subtype simultaneously. • The Radio-GCN model holds the potential to be used as a diagnostic tool. • This study provides an imaging surrogate for identifying the EGFR mutation subtype.

Preoperative Prediction of Microvascular Invasion in Hepatocellular Carcinoma from Multi-sequence Magnetic Resonance Imaging based on Deep Fusion Representation Learning.

Recent studies have identified microvascular invasion (MVI) as the most vital independent biomarker associated with early tumor recurrence. With advancements in medical technology, several computational methods have been developed to predict preoperative MVI using diverse medical images. These existing methods rely on human experience, attribute selection or clinical trial testing, which is often time-consuming and labor-intensive. Leveraging the advantages of deep learning, this study presents a novel end-to-end algorithm for predicting MVI prior to surgery. We devised a series of data preprocessing strategies to fully extract multi-view features from the data while preserving peritumoral information. Notably, a new multi-branch deep fused feature algorithm based on ResNet (DFFResNet) is introduced, which combines Magnetic Resonance Images (MRI) from different sequences to enhance information complementarity and integration. We conducted prediction experiments on a dataset from the Radiology Department of the First Hospital of Lanzhou University, comprising 117 individuals and seven MRI sequences. The model was trained on 80% of the data using 10-fold cross-validation, and the remaining 20% were used for testing. This evaluation was processed in two cases: CROI, containing samples with a complete region of interest (ROI), and PROI, containing samples with a partial ROI region. The robustness results from repeated experiments at both image and patient levels demonstrate the superior performance and improved generalization of the proposed method compared to alternative models. Our approach yields highly competitive prediction results even when the ROI region outline is incomplete, offering a novel and effective multi-sequence fused strategy for predicting preoperative MVI.

Radiomics model based on multi-sequence MRI for preoperative prediction of ki-67 expression levels in early endometrial cancer

To validate a radiomics model based on multi-sequence magnetic resonance imaging (MRI) in predicting the ki-67 expression levels in early-stage endometrial cancer, 131 patients with early endometrial cancer who had undergone pathological examination and preoperative MRI scan were retrospectively enrolled and divided into two groups based on the ki-67 expression levels. The radiomics features were extracted from the T2 weighted imaging (T2WI), dynamic contrast enhanced T1 weighted imaging (DCE-T1WI), and apparent diffusion coefficient (ADC) map and screened using the Pearson correlation coefficients (PCC). A multi-layer perceptual machine and fivefold cross-validation were used to construct the radiomics model. The receiver operating characteristic (ROC) curves analysis, calibration curves, and decision curve analysis (DCA) were used to assess the models. The combined multi-sequence radiomics model of T2WI, DCE-T1WI, and ADC map showed better discriminatory powers than those using only one sequence. The combined radiomics models with multi-sequence fusions achieved the highest area under the ROC curve (AUC). The AUC value of the validation set was 0.852, with an accuracy of 0.827, sensitivity of 0.844, specificity of 0.773, and precision of 0.799. In conclusion, the combined multi-sequence MRI based radiomics model enables preoperative noninvasive prediction of the ki-67 expression levels in early endometrial cancer. This provides an objective imaging basis for clinical diagnosis and treatment.