RESUMEN
BACKGROUND: The performance of automatic liver segmentation and manual sampling MRI strategies needs be compared to determine interchangeability. OBJECTIVE: To compare automatic liver segmentation and manual sampling strategies (manual whole liver segmentation and standardized manual region of interest) for performance in quantifying liver volume and MRI-proton density fat fraction (MRI-PDFF), identifying steatosis grade, and time burden. METHODS: Fifty patients with obesity who underwent liver biopsy and MRI between December 2017 and November 2018 were included. Sampling strategies included automatic and manual whole liver segmentation and 4 and 9 large regions of interest. Intraclass correlation coefficient (ICC), Bland-Altman, linear regression, receiver operating characteristic curve, and Pearson correlation analyses were performed. RESULTS: Automatic whole liver segmentation liver volume and manual whole liver segmentation liver volume showed excellent agreement (ICC=0.97), high correlation (R2=0.96), and low bias (3.7%, 95% limits of agreement, -4.8%, 12.2%) in liver volume. There was the best agreement (ICC=0.99), highest correlation (R2=1.00), and minimum bias (0.84%, 95% limits of agreement, -0.20%, 1.89%) between automated whole liver segmentation MRI-PDFF and manual whole liver segmentation MRI-PDFF. There was no difference of each paired comparison of receiver operating characteristic curves for detecting steatosis (P=0.07-1.00). The minimum time burden for automatic whole liver segmentation was 0.32 s (0.32-0.33 s). CONCLUSION: Automatic measurement has similar effects to manual measurement in quantifying liver volume, MRI-PDFF, and detecting steatosis. Time burden of automatic whole liver segmentation is minimal among all sampling strategies. Manual measurement can be replaced by automatic measurement to improve quantitative efficiency.
RESUMEN
Objectives: To evaluate the potential improvement of prediction performance of a proposed double branch multimodality-contribution-aware TripNet (MCAT) in microvascular invasion (MVI) of hepatocellular carcinoma (HCC) based on a small sample. Methods: In this retrospective study, 121 HCCs from 103 consecutive patients were included, with 44 MVI positive and 77 MVI negative, respectively. A MCAT model aiming to improve the accuracy of deep neural network and alleviate the negative effect of small sample size was proposed and the improvement of MCAT model was verified among comparisons between MCAT and other used deep neural networks including 2DCNN (two-dimentional convolutional neural network), ResNet (residual neural network) and SENet (squeeze-and-excitation network), respectively. Results: Through validation, the AUC value of MCAT is significantly higher than 2DCNN based on CT, MRI, and both imaging (P < 0.001 for all). The AUC value of model with single branch pretraining based on small samples is significantly higher than model with end-to-end training in CT branch and double branch (0.62 vs 0.69, p=0.016, 0.65 vs 0.83, p=0.010, respectively). The AUC value of the double branch MCAT based on both CT and MRI imaging (0.83) was significantly higher than that of the CT branch MCAT (0.69) and MRI branch MCAT (0.73) (P < 0.001, P = 0.03, respectively), which was also significantly higher than common-used ReNet (0.67) and SENet (0.70) model (P < 0.001, P = 0.005, respectively). Conclusion: A proposed Double branch MCAT model based on a small sample can improve the effectiveness in comparison to other deep neural networks or single branch MCAT model, providing a potential solution for scenarios such as small-sample deep learning and fusion of multiple imaging modalities.
RESUMEN
[This corrects the article DOI: 10.3389/fcvm.2021.707508.].
RESUMEN
BACKGROUND: To investigate the influence of artificial intelligence (AI) based on deep learning on the diagnostic performance and consistency of inexperienced cardiovascular radiologists. METHODS: We enrolled 196 patents who had undergone both coronary computed tomography angiography (CCTA) and invasive coronary angiography (ICA) within 6 months. Four readers with less cardiovascular experience (Reader 1-Reader 4) and two cardiovascular radiologists (level II, Reader 5 and Reader 6) evaluated all images for ≥ 50% coronary artery stenosis, with ICA as the gold standard. Reader 3 and Reader 4 interpreted with AI system assistance, and the other four readers interpreted without the AI system. The sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and accuracy (area under the receiver operating characteristic curve (AUC)) of the six readers were calculated at the patient and vessel levels. Additionally, we evaluated the interobserver consistency between Reader 1 and Reader 2, Reader 3 and Reader 4, and Reader 5 and Reader 6. RESULTS: The AI system had 94% and 78% sensitivity at the patient and vessel levels, respectively, which were higher than that of Reader 5 and Reader 6. AI-assisted Reader 3 and Reader 4 had higher sensitivity (range + 7.2-+ 16.6% and + 5.9-+ 16.1%, respectively) and NPVs (range + 3.7-+ 13.4% and + 2.7-+ 4.2%, respectively) than Reader 1 and Reader 2 without AI. Good interobserver consistency was found between Reader 3 and Reader 4 in interpreting ≥ 50% stenosis (Kappa value = 0.75 and 0.80 at the patient and vessel levels, respectively). Only Reader 1 and Reader 2 showed poor interobserver consistency (Kappa value = 0.25 and 0.37). Reader 5 and Reader 6 showed moderate agreement (Kappa value = 0.55 and 0.61). CONCLUSIONS: Our study showed that using AI could effectively increase the sensitivity of inexperienced readers and significantly improve the consistency of coronary stenosis diagnosis via CCTA. Trial registration Clinical trial registration number: ChiCTR1900021867. Name of registry: Diagnostic performance of artificial intelligence-assisted coronary computed tomography angiography for the assessment of coronary atherosclerotic stenosis.
Asunto(s)
Inteligencia Artificial , Estenosis Coronaria/diagnóstico por imagen , Anciano , Área Bajo la Curva , Competencia Clínica , Angiografía por Tomografía Computarizada , Angiografía Coronaria , Aprendizaje Profundo , Humanos , Persona de Mediana Edad , Variaciones Dependientes del Observador , Estudios Retrospectivos , Sensibilidad y EspecificidadRESUMEN
Hepatocellular carcinoma (HCC) is a type of primary liver malignant tumor with a high recurrence rate and poor prognosis even undergoing resection or transplantation. Accurate discrimination of the histologic grades of HCC plays a critical role in the management and therapy of HCC patients. In this paper, we discuss a deep learning-based diagnostic model for HCC histologic grading with multimodal Magnetic Resonance Imaging (MRI) images to overcome the problem of limited well-annotated data and extract the discriminated fusion feature referring to the clinical diagnosis experience of radiologists. Accordingly, we propose a novel Multimodality-Contribution-Aware TripNet (MCAT) based on the metric learning and the attention-aware weighted multimodal fusion. The novelty of the method lies in the multimodality small-shot learning architecture designation and the multimodality adaptive weighted computing scheme. The comprehensive experiments are done on the clinic dataset with the well-annotation of lesion location by the professional radiologist. The experimental results show that our proposed MCAT is not only able to achieve acceptable quantitative measuring of HCC histologic grading based on the MRI sequences with small cases but also outperforms previous models in HCC histologic grading, reaching an accuracy of 84 percent, a sensitivity of 87 percent and precision of 89 percent.
Asunto(s)
Carcinoma Hepatocelular , Neoplasias Hepáticas , Carcinoma Hepatocelular/diagnóstico por imagen , Humanos , Neoplasias Hepáticas/diagnóstico por imagen , Imagen por Resonancia Magnética/métodos , Clasificación del TumorRESUMEN
One of the most common methods for diagnosing coronary artery disease is the use of the coronary artery calcium score CT. However, the current diagnostic method using the coronary artery calcium score CT requires a considerable time, because the radiologist must manually check the CT images one-by-one, and check the exact range. In this paper, three CNN models are applied for 1200 normal cardiovascular CT images, and 1200 CT images in which calcium is present in the cardiovascular system. We conduct the experimental test by classifying the CT image data into the original coronary artery calcium score CT images containing the entire rib cage, the cardiac segmented images that cut out only the heart region, and cardiac cropped images that are created by using the cardiac images that are segmented into nine sub-parts and enlarged. As a result of the experimental test to determine the presence of calcium in a given CT image using Inception Resnet v2, VGG, and Resnet 50 models, the highest accuracy of 98.52% was obtained when cardiac cropped image data was applied using the Resnet 50 model. Therefore, in this paper, it is expected that through further research, both the simple presence of calcium and the automation of the calcium analysis score for each coronary artery calcium score CT will become possible.
Asunto(s)
Aprendizaje Profundo , Calcio , Vasos Coronarios/diagnóstico por imagen , Redes Neurales de la Computación , Tomografía Computarizada por Rayos XRESUMEN
Aims: In this retrospective, multi-center study, we aimed to estimate the diagnostic accuracy and generalizability of an established deep learning (DL)-based fully automated algorithm in detecting coronary stenosis on coronary computed tomography angiography (CCTA). Methods and results: A total of 527 patients (33.0% female, mean age: 62.2 ± 10.2 years) with suspected coronary artery disease (CAD) who underwent CCTA and invasive coronary angiography (ICA) were enrolled from 27 hospitals from January 2016 to August 2019. Using ICA as a standard reference, the diagnostic accuracy of the DL algorithm in the detection of ≥50% stenosis was compared to that of expert readers. In the vessel-based evaluation, the DL algorithm had a higher sensitivity (65.7%) and negative predictive value (NPV) (78.8%) and a significantly higher area under the curve (AUC) (0.83, p < 0.001). In the patient-based evaluation, the DL algorithm achieved a higher sensitivity (90.0%), NPV (52.2%) and AUC (0.81). Generalizability analysis of the DL algorithm was conducted by comparing its diagnostic performance in subgroups stratified by sex, age, geographic area and CT scanner type. The AUCs of the DL algorithm in the aforementioned subgroups ranged from 0.79 to 0.86 and from 0.75 to 0.93 in the vessel-based and patient-based evaluations, both without significant group differences (p > 0.05). The DL algorithm significantly reduced post-processing time (160 [IQR:139-192] seconds), in comparison to manual work (p < 0.001). Conclusions: The DL algorithm performed no inferior to expert readers in CAD diagnosis on CCTA and had good generalizability and time efficiency.
RESUMEN
BACKGROUND: Deep learning based on segmentation models have been gradually applied in biomedical images and achieved state-of-the-art performance for 3D biomedical segmentation. However, most of existing biomedical segmentation researches take account of the application cases with adapting a single type of medical images from the corresponding examining method. Considering of practical clinic application of the radiology examination for diseases, the multiple image examination methods are normally required for final diagnosis especially in some severe diseases like cancers. Therefore, by considering the cases of employing multi-modal images and exploring the effective multi-modality fusion based on deep networks, we do the research to make full use of complementary information of multi-modal images referring to the clinic experiences of radiologists in image analysis. METHODS: Referring to the human radiologist diagnosis experience, we discuss and propose a new self-attention aware mechanism to improve the segmentation performance by paying the different attention on different modal images and different symptoms. Firstly, we propose a multi-path encoder and decoder deep network for 3D biomedical segmentation. Secondly, to leverage the complementary information among different modalities, we introduce a structure of attention mechanism called the Multi-Modality Self-Attention Aware (MMSA) convolution. Multi-modal images we used in the paper are different modalities of MR scanning images, which are input into the network separately. Then self-attention weight fusion of multi-modal features is performed with our proposed MMSA, which can adaptively adjust the fusion weights according to the learned contribution degree of different modalities and different features revealing the different symptoms from the labeled data. RESULTS: Experiments have been done on the public competition dataset BRATS-2015. The results show that our proposed method achieves dice scores of 0.8726, 0.6563, 0.8313 for the whole tumor, the tumor core and the enhancing tumor core, respectively. Comparing with the U-Net with SE block, the scores are increased by 0.0212,0.031,0.0304. CONCLUSIONS: We present a multi-modality self-attention aware convolution, which have better segmentation results based on the adaptive weighting fusion mechanism with exploiting the multiple medical image modalities. Experimental results demonstrate the effectiveness of our method and prominent application in the multi-modality fusion based medical image analysis.
Asunto(s)
Procesamiento de Imagen Asistido por Computador , HumanosRESUMEN
To make full use of natural waste, a novel Mg-Al mixed oxide adsorbent was synthesized by the dip-calcination method using the fluff of the chinar tree (FCT) and an Mg(II) and Al(III) chloride solution as raw materials. The adsorbents were characterized by X-ray diffraction (XRD), scanning electron microscopy (SEM), Fourier transform infrared (FT-IR) spectroscopy, and X-ray photoelectron spectroscopy (XPS). The effects of the Mg/Al molar ratio and calcination temperature on the performance of the novel Mg-Al mixed oxide adsorbent were investigated. The optimized Mg-Al mixed oxide adsorbent had a Langmuir adsorption capacity of 53 mg/g. This adsorption capacity was higher than that of the separate Mg oxide and Al oxide. The synergy between Mg and Al is beneficial to the adsorption performance of the material. The fluoride adsorption capacity of the optimized Mg-Al mixed oxide adsorbent is only slightly affected by ions such as Cl-, NO3 -, SO4 2-, Na+, and K+ and is excellent for use in recycling and real water. The hydroxyl groups on the surface of the Mg-Al mixed oxide adsorbent play a key role in the adsorption of fluorine. The as-obtained novel Mg-Al mixed oxide adsorbent is an efficient and environmentally friendly agent for fluoride removal from drinking water.
RESUMEN
PURPOSE: To evaluate the diagnostic performance of deep learning with a multichannel fusion three-dimensional convolutional neural network (MCF-3DCNN) in the differentiation of the pathologic grades of hepatocellular carcinoma (HCC) based on dynamic contrast-enhanced magnetic resonance images (DCE-MR images). METHODS AND MATERIALS: Fifty-one histologically proven HCCs from 42 consecutive patients from January 2015 to September 2017 were included in this retrospective study. Pathologic examinations revealed nine well-differentiated (WD), 35 moderately differentiated (MD), and seven poorly differentiated (PD) HCCs. DCE-MR images with five phases were collected using a 3.0 Tesla MR scanner. The 4D-tensor representation was employed to organize the collected data in one temporal and three spatial dimensions by referring to the phases and 3D scanning slices of the DCE-MR images. A deep learning diagnosis model with MCF-3DCNN was proposed, and the structure of MCF-3DCNN was determined to approximate clinical diagnosis experience by taking into account the significance of the spatial and temporal information from DCE-MR images. Then, MCF-3DCNN was trained based on well-labeled samples of HCC lesions from real patient cases by experienced radiologists. The accuracy when differentiating the pathologic grades of HCC was calculated, and the performance of MCF-3DCNN in lesion diagnosis was assessed. Additionally, the areas under the receiver operating characteristic curves (AUC) for distinguishing WD, MD, and PD HCCs were calculated. RESULTS: MCF-3DCNN achieved an average accuracy of 0.7396±0.0104 with regard to totally differentiating the pathologic grade of HCC. MCF-3DCNN also achieved the highest diagnostic performance for discriminating WD HCCs from others, with an average AUC, accuracy, sensitivity, and specificity of 0.96, 91.00%, 96.88%, and 89.62%, respectively. CONCLUSIONS: This study indicates that MCF-3DCNN can be a promising technology for evaluating the pathologic grade of HCC based on DCE-MR images.
Asunto(s)
Carcinoma Hepatocelular/diagnóstico , Neoplasias Hepáticas/diagnóstico , Hígado/efectos de los fármacos , Adulto , Anciano , Anciano de 80 o más Años , Carcinoma Hepatocelular/diagnóstico por imagen , Carcinoma Hepatocelular/patología , Quimioembolización Terapéutica/métodos , Medios de Contraste/administración & dosificación , Femenino , Gadolinio DTPA/administración & dosificación , Humanos , Hígado/patología , Neoplasias Hepáticas/diagnóstico por imagen , Neoplasias Hepáticas/patología , Imagen por Resonancia Magnética , Nanopartículas de Magnetita/administración & dosificación , Masculino , Persona de Mediana Edad , Redes Neurales de la Computación , Proyectos PilotoRESUMEN
Edge detection has been widely used in medical image processing, automatic diagnosis, et al. A novel edge detection algorithm, based on the fusion model, is proposed by combination with the two proposed models as follows: the matrix of most probable distribution of edge point and the matrix of the difference weight of each point. The most probable distribution of edge point can be obtained by analyzing the variance among 4-connected neighborhood points around each pixel under estimation in the image to label the all candidate edge points in the image. The difference weight of each point can be gotten by analyzing the brightness difference between the neighborhood point and the under-estimating pixel to represent the probability of being edge. The two matrices gotten from the different descriptions of spatial structure are fused together and derive from the final edge image with thresholding method on the fusion matrix. The experiments are performed based on the public diabetic retinopathy database DRIVE. According to the edge images obtained, the proposed method is subjectively analyzed to be complete and close to the Ground Truth image with very low noise in comparison with the Sobel, Canny and LOG edge detectors. The F1 measure, ROC measure and PFOM measure are separately adopted to make quantitative evaluation of the proposed edge detection algorithm. Experimental results show that the proposed method is able to improve the effect of edge detection on medical images.