scholarly journals Integrating Clinical Data and Attentional CT Imaging Features for Esophageal Fistula Prediction in Esophageal Cancer

2021 ◽  
Vol 11 ◽  
Author(s):  
Yiyue Xu ◽  
Hui Cui ◽  
Taotao Dong ◽  
Bing Zou ◽  
Bingjie Fan ◽  
...  
Keyword(s):  
Neural Network ◽  
Esophageal Cancer ◽  
Computerized Tomography ◽  
Clinical Data ◽  
Ct Imaging ◽  
Superior Performance ◽  
Integrative Model ◽  
Imaging Features ◽  
Esophageal Fistula ◽  
Validation Set

Background and PurposeThis study aims to develop a risk model to predict esophageal fistula in esophageal cancer (EC) patients by learning from both clinical data and computerized tomography (CT) radiomic features.Materials and MethodsIn this retrospective study, computerized tomography (CT) images and clinical data of 186 esophageal fistula patients and 372 controls (1:2 matched by the diagnosis time of EC, sex, marriage, and race) were collected. All patients had esophageal cancer and did not receive esophageal surgery. 70% patients were assigned into training set randomly and 30% into validation set. We firstly use a novel attentional convolutional neural network for radiographic descriptor extraction from nine views of planes of contextual CT, segmented tumor and neighboring structures. Then clinical factors including general, diagnostic, pathologic, therapeutic and hematological parameters are fed into neural network for high-level latent representation. The radiographic descriptors and latent clinical factor representations are finally associated by a fully connected layer for patient level risk prediction using SoftMax classifier.Results512 deep radiographic features and 32 clinical features were extracted. The integrative deep learning model achieved C-index of 0.901, sensitivity of 0.835, and specificity of 0.918 on validation set with superior performance than non-integrative model using CT imaging alone (C-index = 0.857) or clinical data alone (C-index = 0.780).ConclusionThe integration of radiomic descriptors from CT and clinical data significantly improved the esophageal fistula prediction. We suggest that this model has the potential to support individualized stratification and treatment planning for EC patients.

scholarly journals Quantitative CT Analysis to Predict Esophageal Fistula in Patients With Advanced Esophageal Cancer Treated by Chemotherapy or Chemoradiotherapy

2021 ◽  
Author(s):  
Yan-Jie Shi ◽  
Chang Liu ◽  
Yi-Yuan Wei ◽  
Xiao-Ting Li ◽  
Lin Shen ◽  
...  
Keyword(s):  
Esophageal Cancer ◽  
Regression Analysis ◽  
Receiver Operating Characteristic ◽  
Cancer Patients ◽  
Operating Characteristic ◽  
Ct Imaging ◽  
Tumor Thickness ◽  
Esophageal Fistula ◽  
Advanced Esophageal Cancer ◽  
Ct Analysis

Abstract BackgroundEsophageal fistula is one of the most serious complications of chemotherapy or chemoradiotherapy (CRT) for advanced esophageal cancer. This study aimed to evaluate the performance of quantitative computed tomography (CT) analysis and to establish a practical imaging model for predicting esophageal fistula in esophageal cancer patients administered chemotherapy or chemoradiotherapy. MethodsThis study retrospectively enrolled 204 esophageal cancer patients (54 patients with fistula, 150 patients without fistula) and all patients were allocated to the test and validation cohorts according to the time of inclusion in a 1:1 ratio. Ulcer depth, tumor thickness and length, and minimum and maximum enhanced values for esophageal cancer were measured in pretreatment CT imaging. Logistic regression analysis was used to evaluate the associations of CT quantitative measurements with esophageal fistula. Receiver operating characteristic curve (ROC) analysis was also used. ResultsLogistic regression analysis showed that independent predictors of esophageal fistula included tumor thickness [odds ratio (OR)=1.167; p = 0.037], the ratio of ulcer depth to adjacent tumor thickness (OR=164.947; p < 0.001), and the ratio of minimum to maximum enhanced CT value (OR=0.006; p = 0.039) in the test cohort at baseline CT imaging. These predictors were used to establish a predictive model for predicting esophageal fistula, with areas under the receiver operating characteristic curves (AUCs) of 0.946 and 0.841 in the test and validation groups, respectively. ConclusionQuantitative pretreatment CT analysis has excellent performance for predicting fistula formation in esophageal cancer patients who treated by chemotherapy or chemoradiotherapy.

Prediction of esophageal fistula from esophageal cancer CT images using multi-view multi-scale attentional convolutional neural network (MM-Atten-CNN).

2020 ◽  
Vol 38 (15_suppl) ◽  
pp. 4553-4553
Author(s):  
Yiyue Xu ◽  
Hui Cui ◽  
Bingjie Fan ◽  
Bing Zou ◽  
Xindong Sun ◽  
...  
Keyword(s):  
Esophageal Cancer ◽  
Data Augmentation ◽  
Risk Model ◽  
Esophageal Fistula ◽  
Training Set ◽  
Multi Scale ◽  
Validation Set ◽  
3D Cnn ◽  
Coronal View ◽  
Ct Slices

4553 Background: We aimed to propose a risk model based on MM-Atten-CNN for predicting esophageal fistula in patients with esophageal cancer (EC) from computerized tomography (CT) -based radiomics. Methods: EC patients who didn’t received esophageal surgery between July 2014 and August 2019 were collected. Of these, 186 patients (cases) who developed esophageal fistula were enrolled and compared with 372 controls (1:2 matched with the diagnosis time of EC, sex, marriage, and race). All 558 patients were divided into training set (n = 390) and validation set (n = 168) randomly. The MM-Atten-CNN risk model was trained over 2D slices from nine views of planes, where there were three patches of contextual CT, segmented tumor and neighbouring information in each view. In the training set (130 cases and 260 controls), data augmentation was performed including pixel shifting [-10, -5, +5, +10] and rotation [-10, +10]. In total, there were (130+260) *16*2 = 12480 subjects used for training. Finally, the risk model was validated in the validation set (56 cases and 112 controls) and measured by accuracy (acc), sensitivity (sen), and specificity (spe). Results: The developed risk model achieved (acc, sen, spe) of (0.839, 0.807, 0.926), which were more predictive for the occurrence of esophageal fistula when compared to CNN models using single coronal view (acc 0.763, sen 0.581, spe 0.837), multi-view 2D contextual CT slices (acc 0.779, sen 0.656, spe 0.896), and 3D CNN using contextual CT volumes (acc 0.781, sen 0.689, spe 0.852). Conclusions: MM-Atten-CNN CT-based model improved the performance of esophageal fistula risk prediction, which has the potential to assist individualized stratification and treatment planning in EC patients.

PEMBELAJARAN SIMULASI PENCITRAAN CT DENGAN MENGGUNAKAN PRINSIP REKONSTRUKSI CITRA DALAM SOFTWARE MATLAB

2015 ◽  
Vol 8 (3) ◽  
pp. 161
Author(s):  
Samuel Gideon
Keyword(s):  
Image Reconstruction ◽  
Ct Imaging ◽  
The Body ◽  
Reconstruction Technique ◽  
Imaging Features ◽  
Back Projection ◽  
Cross Sectional ◽  
Low Contrast ◽  
Image Reconstruction Technique ◽  
Imaging Algorithms

This research was conducted as a learning alternatives for study of CT (computed tomograpghy) imaging using image reconstruction technique which are inversion matrix, back projection and filtered back projection. CT imaging can produce images of objects that do not overlap. Objects more easily distinguishable although given the relatively low contrast. The image is generated on CT imaging is the result of reconstruction of the original object. Matlab allows us to create and write imaging algorithms easily, easy to undersand and gives applied and exciting other imaging features. In this study, an example cross-sectional image recon-struction performed on the body of prostate tumors using. With these methods, medical prac-titioner (such as oncology clinician, radiographer and medical physicist) allows to simulate the reconstruction of CT images which almost resembles the actual CT visualization techniques.Keywords : computed tomography (CT), image reconstruction, Matlab

scholarly journals Drug-Drug Interaction Predicting by Neural Network Using Integrated Similarity

2019 ◽  
Vol 9 (1) ◽  
Author(s):  
Narjes Rohani ◽  
Changiz Eslahchi
Keyword(s):  
Neural Network ◽  
Drug Interaction ◽  
Side Effect ◽  
Network Architecture ◽  
Selection Process ◽  
Superior Performance ◽  
Multiple Drug ◽  
Interaction Prediction ◽  
Benchmark Datasets ◽  
Drug Drug Interaction

Abstract Drug-Drug Interaction (DDI) prediction is one of the most critical issues in drug development and health. Proposing appropriate computational methods for predicting unknown DDI with high precision is challenging. We proposed "NDD: Neural network-based method for drug-drug interaction prediction" for predicting unknown DDIs using various information about drugs. Multiple drug similarities based on drug substructure, target, side effect, off-label side effect, pathway, transporter, and indication data are calculated. At first, NDD uses a heuristic similarity selection process and then integrates the selected similarities with a nonlinear similarity fusion method to achieve high-level features. Afterward, it uses a neural network for interaction prediction. The similarity selection and similarity integration parts of NDD have been proposed in previous studies of other problems. Our novelty is to combine these parts with new neural network architecture and apply these approaches in the context of DDI prediction. We compared NDD with six machine learning classifiers and six state-of-the-art graph-based methods on three benchmark datasets. NDD achieved superior performance in cross-validation with AUPR ranging from 0.830 to 0.947, AUC from 0.954 to 0.994 and F-measure from 0.772 to 0.902. Moreover, cumulative evidence in case studies on numerous drug pairs, further confirm the ability of NDD to predict unknown DDIs. The evaluations corroborate that NDD is an efficient method for predicting unknown DDIs. The data and implementation of NDD are available at https://github.com/nrohani/NDD.

CT imaging features of the normal parathyroid gland in the dog

2020 ◽  
Vol 48 (05) ◽  
pp. 313-320
Author(s):  
Esther Lautscham ◽  
Clea von Klopmann ◽  
Sebastian Schaub ◽  
Christiane Stengel ◽  
Antje Hartmann
Keyword(s):  
Ct Scan ◽  
Parathyroid Gland ◽  
Spiral Ct ◽  
Ct Imaging ◽  
Field Of View ◽  
Imaging Features ◽  
Hounsfield Units ◽  
Klinische Relevanz

Zusammenfassung Gegenstand und Ziel Ziel dieser prospektiven Pilotstudie war zu beurteilen, ob die physiologische Glandula parathyroidea beim Hund computertomografisch dargestellt werden kann, und eine Beschreibung ihres CT-Erscheinungsbildes zu geben. Material und Methoden In die Studie wurden 25 Hunde aufgenommen, bei denen aufgrund von Erkrankungen im Halsbereich ohne Bezug zu Schild- oder Nebenschilddrüse ein CT-Scan erfolgte. Einschlusskriterium waren unauffällige Befunde bei der allgemeinen klinischen Untersuchung und der Blutuntersuchung (Blutbild und blutchemische Analyse). CT-Bilder vor und nach Kontrastmittelapplikation (30–45 Sekunden nach der Kontrastmittelinjektion, frühe venöse Phase) wurden mit einem 16-Schichten-Spiral-CT unter Verwendung eines Field of View von 18 cm, einer Schichtdicke von 1 mm und einer Matrix von 512 × 512 angefertigt. Zwei Radiologen begutachteten die CT-Aufnahmen unabhängig voneinander. Die Sichtbarkeit der Parathyreoidea wurde erfasst und die Interobserver-Reliabilität ermittelt. Bei den darstellbaren Nebenschilddrüsen wurden folgende Parameter bestimmt: Größe, Dichte (in Hounsfield Units [HU], vor und nach Kontrastmittelgabe), Dichte der Schilddrüse, Abgrenzung (exzellent, mäßig, schlecht). Ergebnisse Nur 20 bzw. 25 Nebenschilddrüsen waren durch die beiden Untersucher erkennbar. Die Anzahl differierte zwischen Nativaufnahmen und Bildern nach Kontrastmittelgabe nicht. Die Interobserver-Reliabilität hinsichtlich der Erkennbarkeit war moderat (κ = 0,40). Für Länge, Breite und Höhe der Nebenschilddrüsen (Mittelwert ± Standardabweichung) ergaben sich 4,2 × 2,5 × 2,9 mm ± 1,3 × 0,8 × 1,0 mm. Die Dichte betrug 39,7 ± 20,6 HU vor und 103,1 ± 47,1 HU nach Kontrastmittelgabe. Damit stellten sich die Nebenschilddrüsen im Vergleich zur Schilddrüse (vor und nach Kontrastmittelgabe 166,7 ± 34,3 HU bzw. 234,0 ± 60,1 HU) hypoattenuierend dar. Schlussfolgerung Diese Studie liefert die erste Beschreibung des CT-Erscheinungsbilds der angenommen physiologischen Nebenschilddrüse beim Hund. Die Sichtbarkeit des Organs war jedoch schlecht. Klinische Relevanz Trotz der schlechten Visualisierung der Nebenschilddrüse im CT ist sie gelegentlich wahrnehmbar. Die ermittelten Dimensionen waren teilweise größer als bisher für sonografische Darstellung beschrieben, ohne dass die untersuchten Hunde erkennbare Symptome eines Hyperparathyreodismus aufwiesen. Eine computertomografisch sichtbare Nebenschilddrüse impliziert daher möglicherweise nicht unbedingt eine Erkrankung. Weitere Studien dazu sind notwendig.

scholarly journals Automatic Modulation Classification Based on Deep Feature Fusion for High Noise Level and Large Dynamic Input

Sensors ◽  
2021 ◽  
Vol 21 (6) ◽  
pp. 2117
Author(s):  
Hui Han ◽  
Zhiyuan Ren ◽  
Lin Li ◽  
Zhigang Zhu
Keyword(s):  
Neural Network ◽  
Frequency Domain ◽  
Noise Level ◽  
Background Noise ◽  
Dynamic Range ◽  
Feature Fusion ◽  
Superior Performance ◽  
Modulation Classification ◽  
High Background ◽  
Automatic Modulation Classification

Automatic modulation classification (AMC) is playing an increasingly important role in spectrum monitoring and cognitive radio. As communication and electronic technologies develop, the electromagnetic environment becomes increasingly complex. The high background noise level and large dynamic input have become the key problems for AMC. This paper proposes a feature fusion scheme based on deep learning, which attempts to fuse features from different domains of the input signal to obtain a more stable and efficient representation of the signal modulation types. We consider the complementarity among features that can be used to suppress the influence of the background noise interference and large dynamic range of the received (intercepted) signals. Specifically, the time-series signals are transformed into the frequency domain by Fast Fourier transform (FFT) and Welch power spectrum analysis, followed by the convolutional neural network (CNN) and stacked auto-encoder (SAE), respectively, for detailed and stable frequency-domain feature representations. Considering the complementary information in the time domain, the instantaneous amplitude (phase) statistics and higher-order cumulants (HOC) are extracted as the statistical features for fusion. Based on the fused features, a probabilistic neural network (PNN) is designed for automatic modulation classification. The simulation results demonstrate the superior performance of the proposed method. It is worth noting that the classification accuracy can reach 99.8% in the case when signal-to-noise ratio (SNR) is 0 dB.

scholarly journals An efficient pruning scheme of deep neural networks for Internet of Things applications

2021 ◽  
Vol 2021 (1) ◽  
Author(s):  
Chen Qi ◽  
Shibo Shen ◽  
Rongpeng Li ◽  
Zhifeng Zhao ◽  
Qing Liu ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Internet Of Things ◽  
Deep Neural Networks ◽  
Computational Cost ◽  
Superior Performance ◽  
Compact Structure ◽  
Resource Limited ◽  
Benchmark Datasets ◽  
Iot Devices

AbstractNowadays, deep neural networks (DNNs) have been rapidly deployed to realize a number of functionalities like sensing, imaging, classification, recognition, etc. However, the computational-intensive requirement of DNNs makes it difficult to be applicable for resource-limited Internet of Things (IoT) devices. In this paper, we propose a novel pruning-based paradigm that aims to reduce the computational cost of DNNs, by uncovering a more compact structure and learning the effective weights therein, on the basis of not compromising the expressive capability of DNNs. In particular, our algorithm can achieve efficient end-to-end training that transfers a redundant neural network to a compact one with a specifically targeted compression rate directly. We comprehensively evaluate our approach on various representative benchmark datasets and compared with typical advanced convolutional neural network (CNN) architectures. The experimental results verify the superior performance and robust effectiveness of our scheme. For example, when pruning VGG on CIFAR-10, our proposed scheme is able to significantly reduce its FLOPs (floating-point operations) and number of parameters with a proportion of 76.2% and 94.1%, respectively, while still maintaining a satisfactory accuracy. To sum up, our scheme could facilitate the integration of DNNs into the common machine-learning-based IoT framework and establish distributed training of neural networks in both cloud and edge.

scholarly journals Early CT features of COVID-19 pneumonia, association with patients’ age and duration of presenting complaint

2021 ◽  
Vol 52 (1) ◽  
Author(s):  
Reem M. EL Kady ◽  
Hosam A. Hassan ◽  
Tareef S. Daqqaq ◽  
Rania Makboul ◽  
Hanan Mosleh Ibrahim
Keyword(s):  
Pleural Effusion ◽  
Ground Glass Opacity ◽  
Ct Imaging ◽  
Older Age ◽  
Ground Glass ◽  
Imaging Features ◽  
Age Group ◽  
Patient Age ◽  
Atypical Features ◽  
Patient Âgé

Abstract Background Coronavirus disease (COVID-19) is a respiratory syndrome with a variable degree of severity. Imaging is a vital component of disease monitoring and follow-up in coronavirus pulmonary syndromes. The study of temporal changes of CT findings of COVID-19 pneumonia can help in better understanding of disease pathogenesis and prediction of disease prognosis. In this study, we aim to determine the typical and atypical CT imaging features of COVID-19 and discuss the association of typical CT imaging features with the duration of the presenting complaint and patients’ age. Results The lesions showed unilateral distribution in 20% of cases and bilateral distribution in 80% of cases. The lesions involved the lower lung lobes in 30% of cases and showed diffuse involvement in 58.2% of cases. The lesions showed peripheral distribution in 74.5% of cases. The most common pattern was multifocal ground glass opacity found in 72.7% of cases. Atypical features like cavitation and pleural effusion can occur early in the disease course. There was significant association between increased number of the lesions, bilaterality, diffuse pattern of lung involvement and older age group (≥ 50 years old) and increased duration of presenting complaint (≥ 4 days). There was significant association between crazy-paving pattern and increased duration of presenting complaint. No significant association could be detected between any CT pattern and increased patient age. Conclusion The most common CT feature of COVID-19 was multifocal ground glass opacity. Atypical features like cavitation and pleural effusion can occur early in the course of the disease. Our cases showed more extensive lesions with bilateral and diffuse patterns of distribution in the older age group and with increased duration of presenting complaint. There was a significant association between crazy-paving pattern and increased duration of presenting complaint. No significant association could be detected between any CT pattern and increased patient age.

Sign in / Sign up

Export Citation Format

Share Document