Search

Objectives: Anaplastic lymphoma kinase (ALK) rearrangement status examination has been widely used in clinic for non-small cell lung cancer (NSCLC) patients in order to find patients that can be treated with targeted ALK inhibitors. This study intended to non-invasively predict the ALK rearrangement status in lung adenocarcinomas by developing a machine learning model that combines PET/CT radiomic features and clinical characteristics. Methods: Five hundred twenty-six patients of lung adenocarcinoma with PET/CT scan examination were enrolled, including 109 positive and 417 negative patients for ALK rearrangements from February 2016 to March 2019. The Artificial Intelligence Kit software was used to extract radiomic features of PET/CT images. The maximum relevance minimum redundancy (mRMR) and least absolute shrinkage and selection operator (LASSO) logistic regression were further employed to select the most distinguishable radiomic features to construct predictive models. The mRMR is a feature selection method, which selects the features with high correlation to the pathological results (maximum correlation), meanwhile retain the features with minimum correlation between them (minimum redundancy). LASSO is a statistical formula whose main purpose is the feature selection and regularization of data model. LASSO method regularizes model parameters by shrinking the regression coefficients, reducing some of them to zero. The feature selection phase occurs after the shrinkage, where every non-zero value is selected to be used in the model. Receiver operating characteristic (ROC) analysis was used to evaluate the performance of the models, and the performance of different models was compared by the DeLong test. Results: A total of 22 radiomic features were extracted from PET/CT images for constructing the PET/CT radiomic model, and majority of these features used were based on CT features (20 out of 22), only 2 PET features were included (PET percentile 10 and PET difference entropy). Moreover, three clinical features associated with ALK mutation (age, burr and pleural effusion) were also employed to construct a combined model of PET/CT and clinical model. We found that this combined model PET/CT-clinical model has a significant advantage to predict the ALK mutation status in the training group (AUC = 0.87) and the testing group (AUC = 0.88) compared with the clinical model alone in the training group (AUC = 0.76) and the testing group (AUC = 0.74) respectively. However, there is no significant difference between the combined model and PET/CT radiomic model. Conclusions: This study demonstrated that PET/CT radiomics-based machine learning model has potential to be used as a non-invasive diagnostic method to help diagnose ALK mutation status for lung adenocarcinoma patients in the clinic. [ABSTRACT FROM AUTHOR]

Ventricle segmentation is a challenging technique for the development of detection system of ischemic stroke in computed tomography (CT), as ischemic stroke regions are adjacent to the brain ventricle with similar intensity. To address this problem, we developed an objective segmentation system of brain ventricle in CT. The intensity distribution of the ventricle was estimated based on clustering technique, connectivity, and domain knowledge, and the initial ventricle segmentation results were then obtained. To exclude the stroke regions from initial segmentation, a combined segmentation strategy was proposed, which is composed of three different schemes: (1) the largest three-dimensional (3D) connected component was considered as the ventricular region; (2) the big stroke areas were removed by the image difference methods based on searching optimal threshold values; (3) the small stroke regions were excluded by the adaptive template algorithm. The proposed method was evaluated on 50 cases of patients with ischemic stroke. The mean Dice, sensitivity, specificity, and root mean squared error were 0.9447, 0.969, 0.998, and 0.219 mm, respectively. This system can offer a desirable performance. Therefore, the proposed system is expected to bring insights into clinic research and the development of detection system of ischemic stroke in CT. [ABSTRACT FROM AUTHOR]

Purpose: Spring-assisted surgery is an effective and minimally invasive treatment for sagittal craniosynostosis (CSO). The principal barrier to the advancement of spring-assisted surgery is the patient-specific spring selection. The selection of spring force depends on the suture involved, subtypes of sagittal CSO, and age of the infant, among other factors. Clinically, physicians manually judge the subtype of sagittal CSO patients based on their CT image data, which may cause bias from different clinicians. An objective system would be helpful to stratify the sagittal CSO patients and make spring choice less subjective. Methods: The authors developed a novel informatics system to automatically segment and characterize sutures and classify sagittal CSO. The proposed system is composed of three phases: preprocessing, sutures segmentation, and classification. First, the three-dimensional (3D) skull was extracted from the CT images and aligned with the symmetry of the cranial vault. Second, a "hemispherical projection" algorithm was developed to transform 3D surface of the skull to a polar two-dimensional plane. Through the transformation, an "effective" projected region can be obtained to enable easy segmentation of sutures. Then, the different types of sutures, such as coronal sutures, lambdoid sutures, sagittal suture, and metopic suture, obtained from the segmented sutures were further identified by a dual-projection technique of the midline of the sutures. Finally, 108 quantified features of sutures were extracted and selected by a proposed multiclass feature scoring system. The sagittal CSO patients were classified into four subtypes: anterior, central, posterior, and complex with the support vector machine approach. Fivefold cross validation (CV) was employed to evaluate the capability of selected features in discriminating the four subtypes in 33 sagittal CSO patients. Receiver operating characteristics (ROC) curves were used to assess the robustness of the developed system. Results: The segmentation results of the proposed method were clinically acceptable for the qualitative evaluation. For the quantitative evaluation, the fivefold CV accuracy of the classification for the four subtypes was 72.7%. This classification system was reliable with the area under curve (in ROC analysis) being greater than 0.8 for four two-class problems. Conclusions: The proposed hemispherical projection algorithm based on backtracking search can successfully segment sutures of the cranial vault. The classification system can also offer a desirable performance. As a result, the proposed segmentation and classification system is expected to bring insights into clinic research and the selection of the spring force to facilitate widespread application of this minimally invasive treatment. [ABSTRACT FROM AUTHOR]

Purpose: Cardiac computed tomography (CT) is widely used in clinical diagnosis of cardiovascular diseases. Whole heart segmentation (WHS) plays a vital role in developing new clinical applications of cardiac CT. However, the shape and appearance of the heart can vary greatly across different scans, making the automatic segmentation particularly challenging. The objective of this work is to develop and evaluate a multiatlas segmentation (MAS) scheme using a new atlas ranking and selection algorithm for automatic WHS of CT data. Research on different MAS strategies and their influence on WHS performance are limited. This work provides a detailed comparison study evaluating the impacts of label fusion, atlas ranking, and sizes of the atlas database on the segmentation performance. Methods: Atlases in a database were registered to the target image using a hierarchical registration scheme specifically designed for cardiac images. A subset of the atlases were selected for label fusion, according to the authors' proposed atlas ranking criterion which evaluated the performance of each atlas by computing the conditional entropy of the target image given the propagated atlas labeling. Joint label fusion was used to combine multiple label estimates to obtain the final segmentation. The authors used 30 clinical cardiac CT angiography (CTA) images to evaluate the proposed MAS scheme and to investigate different segmentation strategies. Results: The mean WHS Dice score of the proposed MAS method was 0.918±0.021, and the mean runtime for one case was 13.2 min on a workstation. This MAS scheme using joint label fusion generated significantly better Dice scores than the other label fusion strategies, including majority voting (0.901±0.276, p < 0.01), locally weighted voting (0.905±0.0247, p < 0.01), and probabilistic patch-based fusion (0.909±0.0249, p < 0.01). In the atlas ranking study, the proposed criterion based on conditional entropy yielded a performance curve with higher WHS Dice scores compared to the conventional schemes (p < 0.03). In the atlas database study, the authors showed that the MAS using larger atlas databases generated better performance curves than the MAS using smaller ones, indicating larger atlas databases could produce more accurate segmentation. Conclusions: The authors have developed a new MAS framework for automatic WHS of CTA and investigated alternative implementations of MAS. With the proposed atlas ranking algorithm and joint label fusion, the MAS scheme is able to generate accurate segmentation within practically acceptable computation time. This method can be useful for the development of new clinical applications of cardiac CT. [ABSTRACT FROM AUTHOR]

• A generalized method for effective early diagnosis of pancreatic cancer based on multiple instance learning. • A spatial transformation based on anatomical structures is proposed to reduce the background interference and enhance the detection stability for the learned features. • Instance-level contrastive learning is developed to aggregate different types of tumor features, maintain the tumor feature integrity, and enhance the diagnosis stability. • The method achieves remarkable generalization performance in unseen datasets and is sensitive to tumors smaller than 2 cm in diameter. Pancreatic cancer is a highly malignant cancer type with a high mortality rate. As no obvious symptoms are associated with this cancer type, most of the diagnoses are made when the patients are already in a late stage. In this work, we propose an automated method for effective early diagnosis of pancreatic cancer based on multiple instance learning with contrast-enhanced CT images. In this method, diagnosis stability and generalizability were improved through shape normalization based on anatomical structures as well as instance-level contrastive learning. Specifically, anatomically-guided shape normalization were developed to reconstruct the pancreatic regions of interest by spatial transformations, account for larger tumor parts in these regions, and hence enhance the extraction of pancreatic features. Moreover, instance-level contrastive learning was employed to aggregate different types of tumor features within the multiple instance learning framework. This learning approach can maintain the tumor feature integrity and enhance the diagnosis stability. Finally, a balance-adjustment strategy was designed to alleviate the class imbalance problem caused by the scarcity of tumor samples. Extensive experimental results demonstrated remarkable performance of our method when conducted cross-validation on an in-house dataset with 310 patients and independent test on two unseen datasets (a private test set with 316 and a publicly-available test set with 281). The proposed strategies also led to significant improvements in generalizability. Besides, the clinical significance of the proposed method was further verified through two independent test results in which tumors smaller than 2 cm in diameter were identified at accuracies of 80.9% and 90.1%, respectively. Overall, our method provides a potentially successful tool for early diagnosis of pancreatic cancer. Our source codes will be released at https://github.com/SJTUBME-QianLab/MIL_PAdiagnosis. [Display omitted] [ABSTRACT FROM AUTHOR]

Purpose: Cerebrospinal fluid (CSF) segmentation in computed tomography (CT) is a key step in computer-aided detection (CAD) of acute ischemic stroke. Because of image noise, low contrast and intensity inhomogeneity, CSF segmentation has been a challenging task. A region-based active contour model, which is insensitive to contour initialization and robust to intensity inhomogeneity, was developed for segmenting CSF in brain CT images. Methods: The energy function of the region-based active contour model is composed of a range domain kernel function, a space domain kernel function, and an edge indicator function. By minimizing the energy function, the region of edge elements of the target could be automatically identified in images with less dependence on initial contours. The energy function was optimized by means of the deepest descent method with a level set framework. An overlap rate between segmentation results and the reference standard was used to assess the segmentation accuracy. The authors evaluated the performance of the proposed method on both synthetic data and real brain CT images. They also compared the performance level of our method to those of region-scalable fitting (RSF) and global convex segment (GCS) models. Results: For the experiment of CSF segmentation in 67 brain CT images, their method achieved an average overlap rate of 66% compared to the average overlap rates of 16% and 46% from the RSF model and the GCS model, respectively. Conclusions: Their region-based active contour model has the ability to achieve accurate segmentation results in images with high noise level and intensity inhomogeneity. Therefore, their method has great potential in the segmentation of medical images and would be useful for developing CAD schemes for acute ischemic stroke in brain CT images. [ABSTRACT FROM AUTHOR]

• A causal intervention based automated method for generalized pancreatic cancer diagnosis. • A continuous image generation strategy and a pancreatic feature diversification method are proposed to simulate appearance potential variations on limited dataset and enrich the feature diversity. • A causal intervention strategy is developed for alleviating spurious correlations caused by appearance changes, enhance causal feature extraction, thereby solving the challenges of generalization. • Extensive experiments conducted on a multi-center dataset with more than 1000 subjects showed that the proposed method achieves remarkable generalization performance. Pancreatic cancer (PC) is a severely malignant cancer variant with high mortality. Since PC has no obvious symptoms, most PC patients are belatedly diagnosed at advanced disease stages. Recently, artificial intelligence (AI) approaches have demonstrated promising prospects for early diagnosis of pancreatic cancer. However, certain non-causal factors (such as intensity and texture appearance variations, also called confounders) tend to induce spurious correlation with PC diagnosis. This undermines the generalization performance and the clinical applicability of the AI-based PC diagnosis approaches. Therefore, we propose a causal intervention based automated method for pancreatic cancer diagnosis with contrast-enhanced computerized tomography (CT) images, where a confounding effects reduction scheme is developed for alleviating spurious correlations to achieve unbiased learning, thereby improving the generalization performance. Specifically, a continuous image generation strategy was developed to simulate wide variations of intensity differences caused by imaging heterogeneities, where Monte Carlo sampling is added to further enhance the continuity of simulated images. Then, to enhance the pancreatic texture variability, a texture diversification method was introduced in conjunction with gradient-based data augmentation. Finally, a causal intervention strategy was proposed to alleviate the adverse confounding effects by decoupling the causal and non-causal factors and combining them randomly. Extensive experiments showed remarkable diagnosis performance on a cross-validation dataset. Also, promising generalization performance with an average accuracy of 0.87 was attained on three independent test sets of a total of 782 subjects. Therefore, the proposed method shows high clinical feasibility and applicability for pancreatic cancer diagnosis. [Display omitted] [ABSTRACT FROM AUTHOR]

• A novel dual meta-learning framework based on idle multi-parametric MRIs is developed to enhance the segmentation performance of CT pancreatic cancer, one to explore commonalities in idle multi-parametric MRIs, and the other to obtain salient knowledge of CT images. • Intermediate modalities are used to smoothly fill the gap between different modalities, providing abundant intermediate representations to boost the performance of our meta-learning scheme. • This approach is an effective pancreatic cancer segmentation framework, which can be easily integrated into other segmentation networks. • This method is a potential paradigm for leveraging idle data to mitigate the challenge of data scarcity. Automated segmentation of pancreatic cancer is vital for clinical diagnosis and treatment. However, the small size and inconspicuous boundaries limit the segmentation performance, which is further exacerbated for deep learning techniques with the few training samples due to the high threshold of image acquisition and annotation. To alleviate this issue caused by the small-scale dataset, we collect idle multi-parametric MRIs of pancreatic cancer from different studies to construct a relatively large dataset for enhancing the CT pancreatic cancer segmentation. Therefore, we propose a deep learning segmentation model with the dual meta-learning framework for pancreatic cancer. It can integrate the common knowledge of tumors obtained from idle MRIs and salient knowledge from CT images, making high-level features more discriminative. Specifically, the random intermediate modalities between MRIs and CT are first generated to smoothly fill in the gaps in visual appearance and provide rich intermediate representations for ensuing meta-learning scheme. Subsequently, we employ intermediate modalities-based model-agnostic meta-learning to capture and transfer commonalities. At last, a meta-optimizer is utilized to adaptively learn the salient features within CT data, thus alleviating the interference due to internal differences. Comprehensive experimental results demonstrated our method achieved the promising segmentation performance, with a max Dice score of 64.94% on our private dataset, and outperformed state-of-the-art methods on a public pancreatic cancer CT dataset. The proposed method is an effective pancreatic cancer segmentation framework, which can be easily integrated into other segmentation networks and thus promises to be a potential paradigm for alleviating data scarcity challenges using idle data. [Display omitted] [ABSTRACT FROM AUTHOR]