Search

Backgroud: Schwannoma (SCH) and meningiomas (MEN) are the two most common primary spinal cord tumors. Differentiating between them preoperatively remains a clinical challenge due to the substantial overlap in their clinical presentation and imaging characteristics., Objective: The objective of this study is to facilitate early diagnosis of patients and reduce clinician stress by constructing a deep learning-based classification model for automatic diagnosis of schwannoma and meningiomas using magnetic resonance images (MRI)., Methods: We retrospectively collected MRI images of 74 patients with pathologically confirmed schwannoma and meningiomas from 2015 to 2020 at a local hosipital, and constructed a CNN model based on the PyTorch's deep learning framework for the discrimination between the two. First, a modified feature fusion CNN model (ResNet34-SKConv) was trained by introducing a selective convolutional kernel module into the original CNN model. The introduction of the selective convolutional kernel module enhances the network's focus on tumor features and effectively improves the network's performance. Finally, the trained model was used to process all the MRI image slices to achieve the classification of SCH and MEN patients by the voting prediction method., Results: Using the 5-fold cross-validation method, this new ResNet34-SKConv model achieves a classification accuracy of 92.32%, a specificity of 95.87%, and a F1-score of 93.54, respectively., Conclusion: This study demonstrated that a classification model using a deep learning network can be effective in achieving differential diagnosis of SCH and MEN. Thus, the new method has great potential for developing new computer-aided diagnosis and applications with future clinical practice., Competing Interests: Declaration of conflicting interestsThe authors declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.

Background: Pancreatic cancer is a highly lethal disease. The preoperative distinction between pancreatic serous cystic neoplasm (SCN) and mucinous cystic neoplasm (MCN) remains a clinical challenge., Objective: The goal of this study is to provide clinicians with supportive advice and avoid overtreatment by constructing a convolutional neural network (CNN) classifier to automatically identify pancreatic cancer using computed tomography (CT) images., Methods: We construct a CNN model using a dataset of 6,173 CT images obtained from 107 pathologically confirmed pancreatic cancer patients at Shanghai Changhai Hospital from January 2017 to February 2022. We divide CT slices into three categories namely, SCN, MCN, and no tumor, to train the DenseNet201-based CNN model with multi-head spatial attention mechanism (MSAM-DenseNet201). The attention module enhances the network's attention to local features and effectively improves the network performance. The trained model is applied to process all CT image slices and finally realize the two categories classification of MCN and SCN patients through a joint voting strategy., Results: Using a 10-fold cross validation method, this new MSAM-DenseNet201 model achieves a classification accuracy of 92.52%, a precision of 92.16%, a sensitivity of 92.16%, and a specificity of 92.86%, respectively., Conclusions: This study demonstrates the feasibility of using a deep learning network or classification model to help diagnose MCN and SCN cases. This, the new method has great potential for developing new computer-aided diagnosis systems and applying in future clinical practice.

Background: Liver metastases is a pivotal factor of death in patients with colorectal cancer. The longitudinal data of colorectal liver metastases (CRLM) during treatment can monitor and reflect treatment efficacy and outcomes., Objective: The objective of this study is to establish a radiomic model based on longitudinal magnetic resonance imaging (MRI) to predict chemotherapy response in patients with CRLM., Methods: This study retrospectively enrolled longitudinal MRI data of five modalities on 100 patients. According to Response Evaluation Criteria in Solid Tumors (RECIST 1.1), 42 and 58 patients were identified as responders and non-responders, respectively. First, radiomic features were computed from different modalities of image data acquired pre-treatment and early-treatment, as well as their differences (Δ). Next, the features were screened by a two-sample t-test, max-relevance and min-redundancy (mRMR), and least absolute shrinkage and selection operator (LASSO). Then, several ensemble radiomic models that integrate support vector machine (SVM), k-nearest neighbor (KNN), gradient boost decision tree (GBDT) and multi-layer perceptron (MLP) were established based on voting method to predict chemotherapy response. Data samples were divided into training and verification queues using a ratio of 8:2. Finally, we used the area under ROC curve (AUC) to evaluate model performance., Results: Using the ensemble model developed using featue differences (Δ) computed from the longitudinal apparent diffusion coefficient (ADC) images, AUC is 0.9007±0.0436 for the training cohort. Applying to the testing cohort, AUC is 0.8958 and overall accuracy is 0.9., Conclusions: Study results demonstrate advantages and high performance of the ensemble radiomic model based on the radiomics feature difference of the longitudinal ADC images in predicting chemotherapy response, which has potential to assist treatment decision-making and improve clinical outcome.

Background: Automatic segmentation of the pancreas and its tumor region is a prerequisite for computer-aided diagnosis., Objective: In this study, we focus on the segmentation of pancreatic cysts in abdominal computed tomography (CT) scan, which is challenging and has the clinical auxiliary diagnostic significance due to the variability of location and shape of pancreatic cysts., Methods: We propose a convolutional neural network architecture for segmentation of pancreatic cysts, which is called pyramid attention and pooling on convolutional neural network (PAPNet). In PAPNet, we propose a new atrous pyramid attention module to extract high-level features at different scales, and a spatial pyramid pooling module to fuse contextual spatial information, which effectively improves the segmentation performance., Results: The model was trained and tested using 1,346 CT slice images obtained from 107 patients with the pathologically confirmed pancreatic cancer. The mean dice similarity coefficient (DSC) and mean Jaccard index (JI) achieved using the 5-fold cross-validation method are 84.53% and 75.81%, respectively., Conclusions: The experimental results demonstrate that the proposed new method in this study enables to achieve effective results of pancreatic cyst segmentation.

Purpose: To investigate the value of a CT-based radiomics model in identification of Crohn's disease (CD) active phase and remission phase., Methods: CT images of 101 patients diagnosed with CD were retrospectively collected, which included 60 patients in active phase and 41 patients in remission phase. These patients were randomly divided into training group and test group at a ratio of 7 : 3. First, the lesion areas were manually delineated by the physician. Meanwhile, radiomics features were extracted from each lesion. Next, the features were selected by t-test and the least absolute shrinkage and selection operator regression algorithm. Then, several machine learning models including random forest (RF), extreme gradient boosting (XGBoost), support vector machine (SVM), logistic regression (LR) and K-nearest neighbor (KNN) algorithms were used to construct CD activity classification models respectively. Finally, the soft-voting mechanism was used to integrate algorithms with better effects to perform two classifications of data, and the receiver operating characteristic curves were applied to evaluate the diagnostic value of the models., Results: Both on the training set and the test set, AUC of the five machine learning classification models reached 0.85 or more. The ensemble soft-voting classifier obtained by using the combination of SVM, LR and KNN could better distinguish active CD from CD remission. For the test set, AUC was 0.938, and accuracy, sensitivity, and specificity were 0.903, 0.911, and 0.892, respectively., Conclusion: This study demonstrated that the established radiomics model could objectively and effectively diagnose CD activity. The integrated approach has better diagnostic performance.

Background: Effective detection of Alzheimer's disease (AD) is still difficult in clinical practice. Therefore, establishment of AD detection model by means of machine learning is of great significance to assist AD diagnosis., Objective: To investigate and test a new detection model aiming to help doctors diagnose AD more accurately., Methods: Diffusion tensor images and the corresponding T1w images acquired from subjects (AD = 98, normal control (NC) = 100) are used to construct brain networks. Then, 9 types features (198×90×9 in total) are extracted from the 3D brain networks by a graph theory method. Features with low correction in both groups are selected through the Pearson correlation analysis. Finally, the selected features (198×33, 198×26, 198×30, 198×42, 198×36, 198×23, 198×29, 198×14, 198×25) are separately used into train 3 machine learning classifier based detection models in which 60% of study subjects are used for training, 20% for validation and 20% for testing., Results: The best detection accuracy levels of 3 models are 90%, 98% and 90% with the corresponding sensitivity of 92%, 96%, and 72% and specificity of 88%, 100% and 94% when using a random forest classifier trained with the Shortest Path Length (SPL) features (198×14), a support vector machine trained with the Degree Centrality features (198×33), and a convolution neural network trained with SPL features, respectively., Conclusions: This study demonstrates that the new method and models not only improve the accuracy of detecting AD, but also avoid bias caused by the method of direct dimensionality reduction from high dimensional data.

Background: The corpus callosum in the midsagittal plane plays a crucial role in the early diagnosis of diseases. When the anisotropy of the diffusion tensor in the midsagittal plane is calculated, the anisotropy of corpus callosum is close to that of the fornix, which leads to blurred boundary of the segmentation region., Objective: To apply a fuzzy clustering algorithm combined with new spatial information to achieve accurate segmentation of the corpus callosum in the midsagittal plane in diffusion tensor images., Methods: In this algorithm, a fixed region of interest is selected from the midsagittal plane, and the anisotropic filtering algorithm based on tensor is implemented by replacing the gradient direction of the structural tensor with an eigenvector, thus filtering the diffusion tensor of region of interest. Then, the iterative clustering center based on K-means clustering is used as the initial clustering center of tensor fuzzy clustering algorithm. Taking filtered diffusion tensor as input data and different metrics as similarity measures, the neighborhood diffusion tensor voxel calculation method of Log Euclidean framework is introduced in the membership function calculation, and tensor fuzzy clustering algorithm is proposed. In this study, MGH35 data from the Human Connectome Project (HCP) are tested and the variance, accuracy and specificity of the experimental results are discussed., Results: Segmentation results of three groups of subjects in MGH35 data are reported. The average segmentation accuracy is 97.34%, and the average specificity is 98.43%., Conclusions: When segmenting the corpus callosum of diffusion tensor imaging, our method cannot only effective denoise images, but also achieve high accuracy and specificity.

Background: Multi-modal medical image fusion plays a crucial role in many areas of modern medicine like diagnosis and therapy planning., Objective: Due to the factor that the structure tensor has the property of preserving the image geometry, we utilized it to construct the directional structure tensor and further proposed an improved 3-D medical image fusion method., Method: The local entropy metrics were used to construct the gradient weights of different source images, and the eigenvectors of traditional structure tensor were combined with the second-order derivatives of image to construct the directional structure tensor. In addition, the guided filtering was employed to obtain detail components of the source images and construct a fused gradient field with the enhanced detail. Finally, the fusion image was generated by solving the functional minimization problem., Results and Conclusion: Experimental results demonstrated that this new method is superior to the traditional structure tensor and multi-scale analysis in both visual effect and quantitative assessment.

Gradient based image fusion can more effectively incorporate edge details using structure tensor, which is successfully used in 2D image fusion. In this study, we generalized and applied this gradient based image fusion method into 3D for non-small cell lung cancer PET/CT image fusion. According the characteristic of lung PET/CT images, we proposed a novel 3D structure tensor based feature, which can be used to construct a weighted structure tensor containing important local detail of both PET and CT images. The fusion gradient domain is deduced from a rank one tensor, which is the closest approximation of the weighted structure tensor in geometry. Based on the fusion gradient domain, final PET/CT fusion image is obtained by solving a Poisson equation. Comparing with the wavelet transform based fusion result, the average information entropy and average gradient measure of proposed fusion method increase 13.5% and 42.3%, respectively. The experimental results show that the proposed fusion method enables to effectively preserve lung vessel structure and sphere-like lesion detail while produces clear, stable and well consistent fusion images.

Inspired by the compressed sensing (CS) theory, introducing priori information of sparse image into sparse-view reconstruction algorithm of computed tomography (CT) can improve image quality. In recent years, as a special case of CS, total variation (TV) reconstruction algorithm that uses both image sparsity and prior information of edge direction have attracted much research interest in sparse-view image reconstruction due to its ability to preserve image edges. In this paper, we propose a new adaptive-weighted total variation (NAWTV) algorithm for CT image reconstruction, which is derived by considering local gradient direction continuity and the anisotropic edge property. The anisotropic edge property is used to consolidate the image sparsity, where the associated weights are expressed as a combination of exponential and cosine function. The weights can also be adjusted adaptively according the local image intensity gradient. The NAWTV algorithm is numerically implemented with gradient descent method. The typical Shepp-Logan phantom and FORBILD head phantom are employed to perform image reconstruction simulation. To evaluate performance of NAWTV algorithm, we compared it with TV and AwTV reconstruction algorithms in experiments. Numerical experimental results verified the effectiveness and feasibility of the proposed algorithm. Comparison results also showed that the NAWTV algorithm achieved a satisfactory performance in suppressing artifacts and preserving the edge structure details information of the reconstructed image.