A deep learning and radiomics based Alberta stroke program early CT score method on CTA to evaluate acute ischemic stroke.

BACKGROUND: Alberta stroke program early CT score (ASPECTS) is a semi-quantitative evaluation method used to evaluate early ischemic changes in patients with acute ischemic stroke, which can guide physicians in treatment decisions and prognostic judgments. OBJECTIVE: We propose a method combining deep learning and radiomics to alleviate the problem of large inter-observer variance in ASPECTS faced by physicians and assist them to improve the accuracy and comprehensiveness of the ASPECTS. METHODS: Our study used a brain region segmentation method based on an improved encoding-decoding network. Through the deep convolutional neural network, 10 regions defined for ASPECTS will be obtained. Then, we used Pyradiomics to extract features associated with cerebral infarction and select those significantly associated with stroke to train machine learning classifiers to determine the presence of cerebral infarction in each scored brain region. RESULTS: The experimental results show that the Dice coefficient for brain region segmentation reaches 0.79. Three radioactive features are selected to identify cerebral infarction in brain regions, and the 5-fold cross-validation experiment proves that these 3 features are reliable. The classifier trained based on 3 features reaches prediction performance of AUC = 0.95. Moreover, the intraclass correlation coefficient of ASPECTS between those obtained by the automated ASPECTS method and physicians is 0.86 (95% confidence interval, 0.56-0.96). CONCLUSIONS: This study demonstrates advantages of using a deep learning network to replace the traditional template registration for brain region segmentation, which can determine the shape and location of each brain region more precisely. In addition, a new brain region classifier based on radiomics features has potential to assist physicians in clinical stroke detection and improve the consistency of ASPECTS.

A Novel Deep Learning Model Based on Multi-Scale and Multi-View for Detection of Pulmonary Nodules.

Lung cancer manifests as pulmonary nodules in the early stage. Thus, the early and accurate detection of these nodules is crucial for improving the survival rate of patients. We propose a novel two-stage model for lung nodule detection. In the candidate nodule detection stage, a deep learning model based on 3D context information roughly segments the nodules detects the preprocessed image and obtain candidate nodules. In this model, 3D image blocks are input into the constructed model, and it learns the contextual information between the various slices in the 3D image block. The parameters of our model are equivalent to those of a 2D convolutional neural network (CNN), but the model could effectively learn the 3D context information of the nodules. In the false-positive reduction stage, we propose a multi-scale shared convolutional structure model. Our lung detection model has no significant increase in parameters and computation in both stages of multi-scale and multi-view detection. The proposed model was evaluated by using 888 computed tomography (CT) scans from the LIDC-IDRI dataset and achieved a competition performance metric (CPM) score of 0.957. The average detection sensitivity per scan was 0.971/1.0 FP. Furthermore, an average detection sensitivity of 0.933/1.0 FP per scan was achieved based on data from Shanghai Pulmonary Hospital. Our model exhibited a higher detection sensitivity, a lower false-positive rate, and better generalization than current lung nodule detection methods. The method has fewer parameters and less computational complexity, which provides more possibilities for the clinical application of this method.

Weakly Supervised Breast Lesion Detection in Dynamic Contrast-Enhanced MRI.

Currently, obtaining accurate medical annotations requires high labor and time effort, which largely limits the development of supervised learning-based tumor detection tasks. In this work, we investigated a weakly supervised learning model for detecting breast lesions in dynamic contrast-enhanced MRI (DCE-MRI) with only image-level labels. Two hundred fifty-four normal and 398 abnormal cases with pathologically confirmed lesions were retrospectively enrolled into the breast dataset, which was divided into the training set (80%), validation set (10%), and testing set (10%) at the patient level. First, the second image series S2 after the injection of a contrast agent was acquired from the 3.0-T, T1-weighted dynamic enhanced MR imaging sequences. Second, a feature pyramid network (FPN) with convolutional block attention module (CBAM) was proposed to extract multi-scale feature maps of the modified classification network VGG16. Then, initial location information was obtained from the heatmaps generated using the layer class activation mapping algorithm (Layer-CAM). Finally, the detection results of breast lesion were refined by the conditional random field (CRF). Accuracy, sensitivity, specificity, and area under the receiver operating characteristic (ROC) curve (AUC) were utilized for evaluation of image-level classification. Average precision (AP) was estimated for breast lesion localization. Delong's test was used to compare the AUCs of different models for significance. The proposed model was effective with accuracy of 95.2%, sensitivity of 91.6%, specificity of 99.2%, and AUC of 0.986. The AP for breast lesion detection was 84.1% using weakly supervised learning. Weakly supervised learning based on FPN combined with Layer-CAM facilitated automatic detection of breast lesion.

Ischemic stroke subtyping method combining convolutional neural network and radiomics.

BACKGROUND: Cardiogenic embolism (CE) and large-artery atherosclerosis embolism (LAA) are the two most common ischemic stroke (IS) subtypes. OBJECTIVE: In order to assist doctors in the precise diagnosis and treatment of patients, this study proposed an IS subtyping method combining convolutional neural networks (CNN) and radiomics. METHODS: Firstly, brain embolism regions were segmented from the computed tomography angiography (CTA) images, and radiomics features were extracted; Secondly, the extracted radiomics features were optimized with the L2 norm, and the feature selection was performed by combining random forest; then, the CNN Cap-UNet was built to extract the deep learning features of the last layer of the network; Finally, combining the selected radiomics features and deep learning features, 9 small-sample classifiers were trained respectively to build and select the optimal IS subtyping classification model. RESULTS: The experimental data include CTA images of 82 IS patients diagnosed and treated in Shanghai Sixth People's Hospital. The AUC value and accuracy of the optimal subtyping model based on the Adaboost classifier are 0.9018 and 0.8929, respectively. CONCLUSION: The experimental results show that the proposed method can effectively predict the subtype of IS and has potential to assist doctors in making timely and accurate diagnoses of IS patients.

Accelerating image reconstruction for multi-contrast MRI based on Y-Net3.

BACKGROUND: As one of the significant preoperative imaging modalities in medical diagnosis, Magnetic resonance imaging (MRI) takes a long scanning time due to its special imaging principle. OBJECTIVE: We propose an innovative MRI reconstruction strategy and data consistency method based on deep learning to reconstruct high-quality brain MRIs from down-sampled data and accelerate the MR imaging process. METHODS: Sixteen healthy subjects undergoing T1-weighted spin-echo (SE) and T2-weighted fast spin-echo (FSE) sequences by a 1.5T MRI scanner were recruited. A Y-Net3+ network was used to facilitate the high-quality MRI reconstruction through context information. In addition, the existing data consistency fidelity method was improved. The difference between the reconstructed K-space and the original K-space was shorten by the linear regression algorithm. Therefore, the redundant artifacts derived from under-sampling were avoided. The Structural Similarity (SSIM) and Peak Signal to Noise Ratio (PSNR) were applied to quantitatively evaluate image reconstruction performance of different down-sampling patterns. RESULTS: Compared with the classical Y-Net, Y-Net3+ network improved SSIM and PSNR of MRI images from 0.9164±0.0178 and 33.2216±3.2919 to 0.9387±0.0363 and 35.1785±3.3105, respectively, under compressed sensing reconstruction with acceleration factor of 4. The improved network increases signal-to-noise ratio and adds more image texture information in the reconstructed images. Furthermore, in the process of data consistency, linear regression analysis was used to reduce the difference between the reconstructed K-space and the original K-space, so that the SSIM and PSNR were increased to 0.9808±0.0081 and 40.9254±1.1911, respectively. CONCLUSIONS: The improved Y-Net combined with data consistency fidelity method elucidates its potential in reconstructing high-quality T2-weighted images from the down-sampled data by fully exploring the T1-weighted information. With the advantage of avoiding down-sampled artifacts, the improved network exhibits remarkable clinical promise for fast MRI applications.

[Application of generative adversarial network in magnetic resonance image reconstruction].

Magnetic resonance imaging (MRI) is an important medical imaging method, whose major limitation is its long scan time due to the imaging mechanism, increasing patients' cost and waiting time for the examination. Currently, parallel imaging (PI) and compress sensing (CS) together with other reconstruction technologies have been proposed to accelerate image acquisition. However, the image quality of PI and CS depends on the image reconstruction algorithms, which is far from satisfying in respect to both the image quality and the reconstruction speed. In recent years, image reconstruction based on generative adversarial network (GAN) has become a research hotspot in the field of magnetic resonance imaging because of its excellent performance. In this review, we summarized the recent development of application of GAN in MRI reconstruction in both single- and multi-modality acceleration, hoping to provide a useful reference for interested researchers. In addition, we analyzed the characteristics and limitations of existing technologies and forecasted some development trends in this field.

Transfer Learning Strategy Based on Unsupervised Learning and Ensemble Learning for Breast Cancer Molecular Subtype Prediction Using Dynamic Contrast-Enhanced MRI.

BACKGROUND: Imaging-driven deep learning strategies focus on training from scratch and transfer learning. However, the performance of training from scratch is often impeded by the lack of large-scale labeled training data. Additionally, owing to the differences between source and target domains, analyzing medical image tasks satisfactorily via transfer learning based on ImageNet is difficult. PURPOSE: To investigate two transfer learning algorithms for breast cancer molecular subtype prediction (luminal and non-luminal) based on unsupervised pre-training and ensemble learning: M_EL and B_EL, using malignant and benign datasets as the source domain, respectively. STUDY TYPE: Retrospective. POPULATION: Eight hundred and thirty-three female patients with histologically confirmed breast lesions (567 benign and 266 malignant cases) were selected. In the 5-fold cross-validation, the malignant cohort was randomly divided into 5 subsets to form a training set (80%) and a validation set (20%). FIELD STRENGTH/SEQUENCE: 3.0 T, dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) using T1-weighted high-resolution isotropic volume examination. ASSESSMENT: First, three datasets acquired at different times post-contrast were preprocessed as unlabeled source domains. Second, three baseline networks corresponding to the different MRI post-contrast phases were built, optimized by a combination of mutual information maximization between high- and low-level representations and prior distribution constraints. Next, the pre-trained networks were fine-tuned on the labeled target domain. Finally, prediction results were integrated using weighted voting-based ensemble learning. STATISTICAL TESTS: Mean accuracy, precision, specificity, and area under receiver operating characteristic curve (AUC) were obtained with 5-fold cross-validation. P < 0.05 was considered to be statistically significant. RESULTS: Compared with a convolutional long short-term memory network, pre-trained VGG-16, VGG-19, and DenseNet-121 from ImageNet, M_EL and B_EL exhibited significantly more optimized prediction performance (specificity: 90.5% and 89.9%; accuracy: 82.6% and 81.1%; precision: 91.2% and 90.9%; AUC: 0.836 and 0.823, respectively). DATA CONCLUSION: Transfer learning based on unsupervised pre-training may facilitate automatic prediction of breast cancer molecular subtypes. LEVEL OF EVIDENCE: 3 TECHNICAL EFFICACY: Stage 2.

The influence of white matter hyperintensities severity on functional brain activity in cerebral small vessel disease: An rs-fMRI study.

OBJECTIVE: To investigate relationships between the severity of white matter hyperintensities (WMH), functional brain activity, and cognition in cerebral small vessel disease (CSVD) based on resting-state functional magnetic resonance imaging (rs-fMRI) data. METHODS: A total of 103 subjects with CSVD were included. The amplitude of low frequency fluctuations (ALFF), regional homogeneity (ReHo), functional connectivity (FC) and their graph properties were applied to explore the influence of WMH burden on functional brain activity. We also investigated whether there are correlations between different functional brain characteristics and cognitive assessments. Finally, we selected disease-related rs-fMRI features in combination with ensemble learning to classify CSVD patients with low WMH load and with high WMH load. RESULTS: The high WMH load group demonstrated significantly abnormal functional brain activity based on rs-MRI data, relative to the low WMH load group. ALFF and graph properties in specific brain regions were significantly correlated with patients' cognitive assessments in CSVD. Moreover, altered rs-fMRI signal can help predict the severity of WMH in CSVD patients with an overall accuracy of 92.23%. CONCLUSIONS: This study provided a comprehensive analysis and evidence for a pattern of altered functional brain activity under different WMH load in CSVD based on rs-fMRI data, enabling accurately individual prediction of status of WMH.

[Segmentation of ground glass pulmonary nodules using full convolution residual network based on atrous spatial pyramid pooling structure and attention mechanism].

Accurate segmentation of ground glass nodule (GGN) is important in clinical. But it is a tough work to segment the GGN, as the GGN in the computed tomography images show blur boundary, irregular shape, and uneven intensity. This paper aims to segment GGN by proposing a fully convolutional residual network, i.e., residual network based on atrous spatial pyramid pooling structure and attention mechanism (ResAANet). The network uses atrous spatial pyramid pooling (ASPP) structure to expand the feature map receptive field and extract more sufficient features, and utilizes attention mechanism, residual connection, long skip connection to fully retain sensitive features, which is extracted by the convolutional layer. First, we employ 565 GGN provided by Shanghai Chest Hospital to train and validate ResAANet, so as to obtain a stable model. Then, two groups of data selected from clinical examinations (84 GGN) and lung image database consortium (LIDC) dataset (145 GGN) were employed to validate and evaluate the performance of the proposed method. Finally, we apply the best threshold method to remove false positive regions and obtain optimized results. The average dice similarity coefficient (DSC) of the proposed algorithm on the clinical dataset and LIDC dataset reached 83.46%, 83.26% respectively, the average Jaccard index (IoU) reached 72.39%, 71.56% respectively, and the speed of segmentation reached 0.1 seconds per image. Comparing with other reported methods, our new method could segment GGN accurately, quickly and robustly. It could provide doctors with important information such as nodule size or density, which assist doctors in subsequent diagnosis and treatment.

A One-Dimensional U-Net-Based Calibration-Transfer Method for Low-Field Nuclear Magnetic Resonance Signals.

The reconstruction of the statistical analysis model of an instrument is a time-consuming and expensive process. Herein, the feasibility of spectral model calibration-transfer application to the same type of low-field nuclear magnetic resonance (LF-NMR) instrument was investigated using a one-dimensional U-net (1D U-net). Unlike conventional calibration-transfer algorithms such as direct standardization (DS), the 1D U-net network can reduce the error between the master and slave instruments through iterative cycles. The calibration-transfer ability was verified; three experiments that entailed the use of edible oil and copper sulfate (CuSO4) samples were implemented. The analysis of the spectral responses and feature analysis of the edible oil samples revealed that the signal of the slave instrument calibrated using the 1D U-net most resembled the signal of the master instrument, and its relative residual value was reduced to 0.0045. Further analysis of the CuSO4 concentration prediction showed that on the support vector regression (SVR) model constructed using the master instrument, the signal of the slave instrument calibrated by the 1D U-net was more similar to the response of the master instrument, and its root mean square error (RMSE) was only 0.01606 mmol/L. Thus, 1D U-net is a viable candidate for calibration-transfer applications to LF-NMR instruments.

Rapid screening for hazelnut oil and high-oleic sunflower oil in extra virgin olive oil using low-field nuclear magnetic resonance relaxometry and machine learning.

BACKGROUND: As extra virgin olive oil (EVOO) has high commercial value, it is routinely adulterated with other oils. The present study investigated the feasibility of rapidly identifying adulterated EVOO using low-field nuclear magnetic resonance (LF-NMR) relaxometry and machine learning approaches (decision tree, K-nearest neighbor, linear discriminant analysis, support vector machines and convolutional neural network (CNN)). RESULTS: LF-NMR spectroscopy effectively distinguished pure EVOO from that which was adulterated with hazelnut oil (HO) and high-oleic sunflower oil (HOSO). The applied CNN algorithm had an accuracy of 89.29%, a precision of 81.25% and a recall of 81.25%, and enabled the rapid (2 min) discrimination of pure EVOO that was adulterated with HO and HOSO in the volumetric ratio range of 10-100%. CONCLUSIONS: LF-NMR coupled with the CNN algorithm is a viable candidate for rapid EVOO authentication. © 2020 Society of Chemical Industry.

[Progress in computer-assisted Alberta stroke program early computer tomography score of acute ischemic stroke based on different modal images].

Clinically, non-contrastive computed tomography (NCCT) is used to quickly diagnose the type and area of ​​stroke, and the Alberta stroke program early computer tomography score (ASPECTS) is used to guide the next treatment. However, in the early stage of acute ischemic stroke (AIS), it's difficult to distinguish the mild cerebral infarction on NCCT with the naked eye, and there is no obvious boundary between brain regions, which makes clinical ASPECTS difficult to conduct. The method based on machine learning and deep learning can help physicians quickly and accurately identify cerebral infarction areas, segment brain areas, and operate ASPECTS quantitative scoring, which is of great significance for improving the inconsistency in clinical ASPECTS. This article describes current challenges in the field of AIS ASPECTS, and then summarizes the application of computer-aided technology in ASPECTS from two aspects including machine learning and deep learning. Finally, this article summarizes and prospects the research direction of AIS-assisted assessment, and proposes that the computer-aided system based on multi-modal images is of great value to improve the comprehensiveness and accuracy of AIS assessment, which has the potential to open up a new research field for AIS-assisted assessment.

A deep residual learning network for predicting lung adenocarcinoma manifesting as ground-glass nodule on CT images.

OBJECTIVE: To develop a deep learning-based artificial intelligence (AI) scheme for predicting the likelihood of the ground-glass nodule (GGN) detected on CT images being invasive adenocarcinoma (IA) and also compare the accuracy of this AI scheme with that of two radiologists. METHODS: First, we retrospectively collected 828 histopathologically confirmed GGNs of 644 patients from two centers. Among them, 209 GGNs are confirmed IA and 619 are non-IA, including 409 adenocarcinomas in situ and 210 minimally invasive adenocarcinomas. Second, we applied a series of pre-preprocessing techniques, such as image resampling, rescaling and cropping, and data augmentation, to process original CT images and generate new training and testing images. Third, we built an AI scheme based on a deep convolutional neural network by using a residual learning architecture and batch normalization technique. Finally, we conducted an observer study and compared the prediction performance of the AI scheme with that of two radiologists using an independent dataset with 102 GGNs. RESULTS: The new AI scheme yielded an area under the receiver operating characteristic curve (AUC) of 0.92 ± 0.03 in classifying between IA and non-IA GGNs, which is equivalent to the senior radiologist's performance (AUC 0.92 ± 0.03) and higher than the score of the junior radiologist (AUC 0.90 ± 0.03). The Kappa value of two sets of subjective prediction scores generated by two radiologists is 0.6. CONCLUSIONS: The study result demonstrates using an AI scheme to improve the performance in predicting IA, which can help improve the development of a more effective personalized cancer treatment paradigm. KEY POINTS: • The feasibility of using a deep learning method to predict the likelihood of the ground-glass nodule being invasive adenocarcinoma. • Residual learning-based CNN model improves the performance in classifying between IA and non-IA nodules. • Artificial intelligence (AI) scheme yields higher performance than radiologists in predicting invasive adenocarcinoma.

Correlation between White Matter Hyperintensities Related Gray Matter Volume and Cognition in Cerebral Small Vessel Disease.

BACKGROUND AND AIM: The relationship between severity of cerebral small vessel disease, as defined by white matter hyperintensities classification, and gray matter volume of different brain regions has not been well defined. This study aimed to investigate brain regions with significant differences in gray matter volume associated with different degrees of white matter hyperintensities in patients with cerebral small vessel disease. Meanwhile, we examined whether correlations existed between gray matter volume in different brain regions and cognitive ability. METHODS: 110 cerebral small vessel disease patients underwent 3.0T Magnetic resonance imaging scans and neuropsychological cognitive assessments. White matter hyperintensities of each subject was graded according to Fazekas grade scale and was divided into two groups: (A) White matter hyperintensities score of 1-2 points (n = 64), (B) White matter hyperintensities score of 3-6 points (n = 46). Gray matter volume was analyzed using voxel-based morphometry implemented in Statistical Parametric Mapping 12 software. RESULTS: Brain regions with significant differences in gray matter volume between groups were diffused throughout the brain. Patients with high white matter hyperintensities scores exhibited decreased gray matter volume in some subregions of the frontal lobes, the temporal lobes, the parahippocampal gyrus, hippocampus and thalamus (p < 0.05). Among them, gray matter volume in the ventrolateral area of right inferior temporal gyrus, together with the right posterior parietal and occipital thalamus were positively correlated with Montreal Cognitive Assessment scores (p < 0.05). Gray matter volume in the extreme ventrolateral area of right inferior temporal gyrus along with the entorhinal cortex of left parahippocampal gyrus were positively correlated with both Montreal Cognitive Assessment and Mini-Mental Status Examination scores (p < 0.05). CONCLUSIONS: Cerebral small vessel disease is considered as a whole brain disease and local white matter lesions can influence the gray matter in remote areas. Reducing the severity and progression of white matter hyperintensities may help to prevent secondary brain atrophy and cognitive impairment.

A quality improvement method for lung LDCT images.

BACKGROUND: Low dose computed tomography (LDCT) reduces radiation damage to patients. However, with the decrease of radiation dose, LDCT images of the lung often appear some serious problems such as poor contrast, noise and streak artifacts. OBJECTIVE: To improve the quality of lung LDCT images, this study proposed and investigated a new denoising method based on classification training structure combined dictionary for lung LDCT images. METHODS: First, top-hat transform and anisotropic diffusion with a shock filter (ADSF) algorithm are used to enhance the image contrast and image details. Second, an adaptive dictionary is trained and used for noise reduction. Third, more image details are extracted from the residual image by using the atom activity measurement. The final result is obtained by combining the dictionary denoising result with the extracted detail information. The proposed method is then validated by both simulated and clinical lung LDCT images. Four metrics including Contrast-to-Noise Ratio (CNR), Noise Suppression Index (NSI), Edge Preserving Index (EPI), and Blurring Index (BI) are computed to quantitatively evaluate image quality. RESULTS: The results showed that the CNR, NSI, EPI, and BI of our method reached 8.953, 0.9500, 0.7230 and 0.0170, respectively. Noise and streak artifacts can be removed from lung LDCT images while keeping and retaining more details. CONCLUSIONS: Comparing with the results of other methods tested using the same dataset, this study demonstrated that our new method significantly improved quality of the lung LDCT images.

Region growing algorithm combined with morphology and skeleton analysis for segmenting airway tree in CT images.

BACKGROUND: Automatic segmentation of pulmonary airway tree is a challenging task in many clinical applications, including developing computer-aided detection and diagnosis schemes of lung diseases. OBJECTIVE: To segment the pulmonary airway tree from the computed tomography (CT) chest images using a novel automatic method proposed in this study. METHODS: This method combines a two-pass region growing algorithm with gray-scale morphological reconstruction and leakage elimination. The first-pass region growing is implemented to obtain a rough airway tree. The second-pass region growing and gray-scale morphological reconstruction are used to detect the distal airways. Finally, leakage detection is performed to remove leakage and refine the airway tree. RESULTS: Our methods were compared with the gold standards. Forty-five clinical CT lung image scan cases were used in the experiments. Statistics on tree division order, branch number, and airway length were adopted for evaluation. The proposed method detected up to 12 generations of bronchi. On average, 148.85 branches were extracted with a false positive rate of 0.75%. CONCLUSIONS: The results show that our method is accurate for pulmonary airway tree segmentation. The strategy of separating the leakage detection from the segmenting process is feasible and promising for ensuring a high branch detected rate with a low leakage volume.

[Research progress on genetic effects of the asymmetry of human brain structure revealed by magnetic resonance imaging].

Hemispheric asymmetry is a fundamental organizing principle of the human brain. Answering the genetic effects of the asymmetry is a prerequisite for elucidating developmental mechanisms of brain asymmetries. Multi-modal magnetic resonance imaging (MRI) has provided an important tool for comprehensively interpreting human brain asymmetry and its genetic mechanism. By combining MRI data, individual differences in brain structural asymmetry have been investigated with quantitative genetic brain mapping using gene-heritability. Twins provide a useful natural model for studying the effects of genetics and environment on the brain. Studies based on MRI have found that the asymmetry of human brain structure has a genetic basis. From the perspective of quantitative genetic analysis, this article reviews recent findings on the genetic effects of asymmetry and genetic covariance between hemispheres from three aspects: the asymmetry of heritability, the heritability of asymmetry and the genetic correlation. At last, the article shows the limitations and future research directions in this field. The purpose of this systematic review is to quickly guide researchers to understand the origins and genetic mechanism of interhemispheric differences, and provide a genetic basis for further understanding and exploring individual differences in laterized cognitive behavior.

[Application of deep learning in cancer prognosis prediction model].

In recent years, deep learning has provided a new method for cancer prognosis analysis. The literatures related to the application of deep learning in the prognosis of cancer are summarized and their advantages and disadvantages are analyzed, which can be provided for in-depth research. Based on this, this paper systematically reviewed the latest research progress of deep learning in the construction of cancer prognosis model, and made an analysis on the strengths and weaknesses of relevant methods. Firstly, the construction idea and performance evaluation index of deep learning cancer prognosis model were clarified. Secondly, the basic network structure was introduced, and the data type, data amount, and specific network structures and their merits and demerits were discussed. Then, the mainstream method of establishing deep learning cancer prognosis model was verified and the experimental results were analyzed. Finally, the challenges and future research directions in this field were summarized and expected. Compared with the previous models, the deep learning cancer prognosis model can better improve the prognosis prediction ability of cancer patients. In the future, we should continue to explore the research of deep learning in cancer recurrence rate, cancer treatment program and drug efficacy evaluation, and fully explore the application value and potential of deep learning in cancer prognosis model, so as to establish an efficient and accurate cancer prognosis model and realize the goal of precision medicine.

Segmentation of pulmonary vascular tree by incorporating vessel enhancement filter and variational region-growing.

BACKGROUND: Automatic segmentation of pulmonary vascular tree in the thoracic computed tomography (CT) image is a promising but challenging task with great clinical potential values. It is difficult to segment the whole vascular tree in reasonable time and acceptable accuracy. OBJECTIVE: To develop a novel pulmonary vessel segmentation approach by incorporating vessel enhancement filters and the anisotropic diffusion filter with the variational region growing. METHODS: First, the airway wall from the lung lobes is eliminated from CT images by using multi-scale morphological operations. Second, a Hessian-based multi-scale vesselness filter and medialness filter are applied to detect and enhance the potential vessel. Third, an anisotropic diffusion filter is used to remove noise and enhance the tube-like structures in CT images. Last, the vascular tree is segmented by applying variational region growing algorithm. RESULTS: Applying to the CT images collected from the entire dataset of VESSEL12 challenge, we achieved an average sensitivity of 92.9%, specificity of 91.6% and the area under the ROC curve of AUC = 0.972. CONCLUSIONS: This study demonstrated feasibility of segmenting the pulmonary vessel effectively by incorporating vessel enhancement filters and the anisotropic diffusion filter with the variational region growing algorithm. Our method cannot only segment both large and peripheral vessels, but also distinguish the vessels from the adjacent tissues, especially the airway walls.

Correlation between CT based radiomics features and gene expression data in non-small cell lung cancer.

OBJECTIVE: Radiogenomics investigates radiographic imaging phenotypes associated with gene expression patterns. This study aims to explore relationships between CT imaging radiomics features and gene expression data in non-small cell lung cancer (NSCLC). METHODS: Eighty-nine NSCLC patients are included in the study. Radiomics features are extracted and selected to quantify the phenotype of tumors on CT-scans. Co-expressed genes are also clustered and the first principal component of the cluster is represented, which is defined as a metagene. Then, statistical analysis was performed to assess association of CT radiomics features with metagenes. In addition, predictive models are built and metagene enrichment are conducted to further evaluate performance of NSCLC radiogenomics statistically and biologically. RESULTS: There are 187 significant pairwise correlations between a CT radiomics feature and a metagene of NSCLC, where eighteen metagenes are annotated with Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) terms. Metagenes are predicted in terms of radiomics features with an accuracy of 41.89% -89.93%. CONCLUSIONS: This study reveals the associations between CT imaging radiomics features and NSCLC co-expressed gene sets. The findings suggest that CT radiomics features can reflect important biological information of NSCLC patients, which may have a significant clinical impact as CT is routinely used in clinical practice, assisting in improving medical decision-support at low cost.