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.

scholarly journals Application of Multi-Scale Fusion Attention U-Net to Segment the Thyroid Gland on CT Localization Images for Radiotherapy

2021 ◽  
Author(s):  
Xiaobo Wen ◽  
Biao Zhao ◽  
Meifang Yuan ◽  
Jinzhi Li ◽  
Mengzhen Sun ◽  
...  
Keyword(s):  
Thyroid Gland ◽  
Clinical Work ◽  
Similarity Coefficient ◽  
Dice Similarity Coefficient ◽  
Training Set ◽  
Data Set ◽  
Test Set ◽  
Noise Interference ◽  
Multi Scale ◽  
Validation Set

Abstract Objectives: To explore the performance of Multi-scale Fusion Attention U-net (MSFA-U-net) in thyroid gland segmentation on CT localization images for radiotherapy. Methods: CT localization images for radiotherapy of 80 patients with breast cancer or head and neck tumors were selected; label images were manually delineated by experienced radiologists. The data set was randomly divided into the training set (n=60), the validation set (n=10), and the test set (n=10). Data expansion was performed in the training set, and the performance of the MSFA-U-net model was evaluated using the evaluation indicators Dice similarity coefficient (DSC), Jaccard similarity coefficient (JSC), positive predictive value (PPV), sensitivity (SE), and Hausdorff distance (HD). Results: With the MSFA-U-net model, the DSC, JSC, PPV, SE, and HD indexes of the segmented thyroid gland in the test set were 0.8967±0.0935, 0.8219±0.1115, 0.9065±0.0940, 0.8979±0.1104, and 2.3922±0.5423, respectively. Compared with U-net, HR-net, and Attention U-net, MSFA-U-net showed that DSC increased by 0.052, 0.0376, and 0.0346 respectively; JSC increased by 0.0569, 0.0805, and 0.0433, respectively; SE increased by 0.0361, 0.1091, and 0.0831, respectively; and HD increased by −0.208, −0.1952, and −0.0548, respectively. The test set image results showed that the thyroid edges segmented by the MSFA-U-net model were closer to the standard thyroid delineated by the experts, in comparison with those segmented by the other three models. Moreover, the edges were smoother, over-anti-noise interference was stronger, and oversegmentation and undersegmentation were reduced. Conclusion: The MSFA-U-net model can meet basic clinical requirements and improve the efficiency of physicians' clinical work.

Incorporation of PBRM1, BAP1, TP53 mutation status into the Memorial Sloan Kettering Cancer Center (MSKCC) risk model: A genomically annotated tool to improve stratification of patients (pts) with advanced renal cell carcinoma (RCC).

2018 ◽  
Vol 36 (6_suppl) ◽  
pp. 639-639 ◽  
Author(s):  
Martin Henner Voss ◽  
Yuan Cheng ◽  
Mahtab Marker ◽  
Fengshen Kuo ◽  
Toni K. Choueiri ◽  
...  
Keyword(s):  
Clinical Trial ◽  
Prognostic Value ◽  
Risk Model ◽  
Original Model ◽  
Phase Iii ◽  
Training Set ◽  
First Line ◽  
Mutation Status ◽  
New Model ◽  
Validation Set

639 Background: The MSKCC risk model, an established prognostic tool fo r metastatic RCC, integrates clinical + laboratory data, but is ignorant to tumor genomics. Mutations in BAP1, PBRM1, TP53, cumulatively found in over 50% of pts, have prognostic value in RCC. We sought to study the use of integrating mutation status into the MSKCC model using two large clinical trial datasets. Methods: Pts had received first line sunitinib or pazopanib on the phase III COMPARZ (training set, n = 357) or the phase II RECORD3 trial (validation set, n = 130). Genes were evaluated by next generation sequencing using archival tissue. Association of mutation status and overall survival (OS) was tested by multivariate Cox regression analysis (MVA) in the training set. An annotated model was constructed combining the original clinical variables and mutation status for the 3 genes. We compared risk group assignment and concordance index (c-index) for the original vs. new model in training and validation set. Results: Mutation status for each gene: BAP1, TP53 and PBRM1 independently correlated with OS on MVA (p≤0.0035). Comparing the original (clinical only) to the annotated (clinical + genomics) model, risk categories changed in 139 pts (39%). The C-index was improved with integration of genomic information (0.595 original model - > 0.628 new model). The independent validation cohort confirmed improvement of c-index for predicting OS with integration of genomic data (c-index 0.622 original model - > 0.641 new model). Conclusions: Mutation status for BAP1, PBRM1, and TP53 has prognostic value in pts with advanced RCC. The annotated risk model alters risk status in over 1/3 of pts and improves accuracy of estimating outcomes in patients receiving first-line therapy. Clinical trial information: NCT00720941. [Table: see text]

scholarly journals Jazz Bass Transcription Using a U-Net Architecture

Electronics ◽  
2021 ◽  
Vol 10 (6) ◽  
pp. 670
Author(s):  
Jakob Abeßer ◽  
Meinard Müller
Keyword(s):  
Network Architecture ◽  
Data Augmentation ◽  
Neural Network Architecture ◽  
Training Set ◽  
Pitch Estimation ◽  
Jazz Ensemble ◽  
Percentage Points ◽  
Augmentation Strategy ◽  
Augmentation Techniques ◽  
Validation Set

In this paper, we adapt a recently proposed U-net deep neural network architecture from melody to bass transcription. We investigate pitch shifting and random equalization as data augmentation techniques. In a parameter importance study, we study the influence of the skip connection strategy between the encoder and decoder layers, the data augmentation strategy, as well as of the overall model capacity on the system’s performance. Using a training set that covers various music genres and a validation set that includes jazz ensemble recordings, we obtain the best transcription performance for a downscaled version of the reference algorithm combined with skip connections that transfer intermediate activations between the encoder and decoder. The U-net based method outperforms previous knowledge-driven and data-driven bass transcription algorithms by around five percentage points in overall accuracy. In addition to a pitch estimation improvement, the voicing estimation performance is clearly enhanced.

scholarly journals Construction and verification of prognostic nomogram for early-onset esophageal cancer

2021 ◽  
Author(s):  
Xiaoxiao Liu ◽  
Wei Guo ◽  
Xiaobo Shi ◽  
Yue Ke ◽  
Yuxing Li ◽  
...  
Keyword(s):  
Esophageal Cancer ◽  
Early Onset ◽  
Older Patients ◽  
Clinicopathological Characteristics ◽  
Calibration Plot ◽  
Seer Database ◽  
Training Set ◽  
Related Factors ◽  
Cancer Specific Survival ◽  
Validation Set

This study aimed to build up nomogram models to evaluate overall survival (OS) and cancer-specific survival (CSS) in early-onset esophageal cancer (EOEC). Patients diagnosed with esophageal cancer (EC) from 2004 to 2015 were extracted from the Surveillance Epidemiology and End Results (SEER) database. Clinicopathological characteristics of younger versus older patients were compared, and survival analysis was performed in both groups. Independent related factors influencing the prognosis of EOEC were identified by univariate and multivariate Cox analysis, which were incorporated to construct a nomogram. The predictive capability of the nomogram was estimated by the concordance index (C-index), calibration plot, receiver operating characteristic (ROC) curve, and decision curve analysis (DCA). A total of 534 younger and 17,243 older patients were available from the SEER database. Younger patients were randomly segmented into a training set (n=266) and a validation set (n=268). In terms of the training set, the C-index of the OS nomogram was 0.740 (95% CI: 0.707-0.773), and that of the CSS nomogram was 0.752 (95% CI: 0.719-0.785). In view of the validation set, the C-index of OS and CSS were 0.706 (95% CI: 0.671-0.741) and 0.723 (95%CI: 0.690-0.756), respectively. Calibration curves demonstrated the consistent degree of fit between actual and predicted values in nomogram models. From the perspective of DCA, the nomogram models were more beneficial than the tumor-node-metastasis (TNM) and the SEER stage for EOEC. In brief, the nomogram model can be considered as an individualized quantitative tool to predict the prognosis of EOEC patients to assist clinicians in making treatment decisions.

Improved lymph node metastasis prediction from preoperative esophageal squamous cell cancer CT by graph attention convolutional neural network (GACNN).

2021 ◽  
Vol 39 (15_suppl) ◽  
pp. e16093-e16093
Author(s):  
Mingjun Ding ◽  
Hui Cui ◽  
Butuo Li ◽  
Bing Zou ◽  
Yiyue Xu ◽  
...  
Keyword(s):  
Lymph Node ◽  
Prediction Model ◽  
Squamous Cell ◽  
Data Augmentation ◽  
Cell Cancer ◽  
Morphological Features ◽  
Training Set ◽  
Contrast Enhanced Ct ◽  
Area Under Roc Curve ◽  
Validation Set

e16093 Background: Lymph node (LN) metastasis is the most important factor for decision making in esophageal squamous cell carcinoma (ESCC). A more accurate prediction model for LN metastatic status in ESCC patients is needed. Methods: In this retrospective study, 397 ESCC patients who took Contrast-Enhanced CT (CECT) within 15 days before surgery between October 2013 and November 2018 were collected. There are 924 (798 negative and 126 positive) LNs with pathologically confirmed status after surgery. All LNs were randomly divided into a training set (n = 663) and validation set (n = 185). Data augmentation including shifting and rotation was performed in the training set, resulting in 1326 negative and 1140 positive LN samples. The GACNN model was trained over CT volumetric patches centred at manually segmented LN samples. GACNN was composed of a 3D UNet encoder to extract deep features, and a graph attention layer to integrate morphological features extracted from segmented LN. The model was validated using the validation set (135 negative and 50 positive) and measured by area under ROC curve (auc), sensitivity (sen), and specificity (spe). Results: GACNN achieved better auc, sen, and spe of 0.802, 0.765, and 0.826, when compared to 3 other models including CT radiomics model (auc 0.733, sen 0.689, spe 0.765), 3D UNet encoder (auc 0.778, sen 0.722, spe 0.767), and our model without morphological features (auc 0.796, sen 0.754, spe 0.803). The improvement was statistically significant (p < 0.001). Conclusions: Our prediction model improved the prediction of LN metastasis, which has the potential to assist LN metastasis risk evaluation and personalized treatment planning in ESCC patients for surgery or radiotherapy.

scholarly journals VGG16 for Plant Image Classification with Transfer Learning and Data Augmentation

2018 ◽  
Vol 7 (4.11) ◽  
pp. 90 ◽  
Author(s):  
Mohamad Aqib Haqmi Abas ◽  
Nurlaila Ismail ◽  
Ahmad Ihsan Mohd Yassin ◽  
Mohd Nasir Taib
Keyword(s):  
Neural Network ◽  
Transfer Learning ◽  
Classification Accuracy ◽  
Data Augmentation ◽  
Accuracy Score ◽  
Training Set ◽  
Plant Recognition ◽  
Plant Image ◽  
Validation Set ◽  
Overfitting Problem

This paper discusses the potential of applying VGG16 model architecture for plant classification. Flower images are used instead of leaves as in other plant recognition model because the structure of shape and color of leaves are similar in nature. This might be disadvantageous when we want to use only leaves images as a sole feature of plants to classify the species. Previous work has demonstrated the effectiveness of using transfer learning, dropout and data augmentation as a method to reduce overfitting problem of convolutional neural network model when applied in limited amount of images data. We have successfully build and train the VGG16 model with 2800 flower images. The model able to achieve a classification accuracy score of 96.25% for training set, 93.93% for validation set and 89.96% for testing set.  

scholarly journals Mitigating Demographic Bias in Facial Datasets with Style-Based Multi-attribute Transfer

2021 ◽  
Author(s):  
Markos Georgopoulos ◽  
James Oldfield ◽  
Mihalis A. Nicolaou ◽  
Yannis Panagakis ◽  
Maja Pantic
Keyword(s):  
Deep Learning ◽  
Data Augmentation ◽  
State Of The Art ◽  
Skin Tone ◽  
Training Set ◽  
Demographic Groups ◽  
Underrepresented Groups ◽  
Qualitative And Quantitative ◽  
Multi Scale ◽  
Single Attribute

AbstractDeep learning has catalysed progress in tasks such as face recognition and analysis, leading to a quick integration of technological solutions in multiple layers of our society. While such systems have proven to be accurate by standard evaluation metrics and benchmarks, a surge of work has recently exposed the demographic bias that such algorithms exhibit–highlighting that accuracy does not entail fairness. Clearly, deploying biased systems under real-world settings can have grave consequences for affected populations. Indeed, learning methods are prone to inheriting, or even amplifying the bias present in a training set, manifested by uneven representation across demographic groups. In facial datasets, this particularly relates to attributes such as skin tone, gender, and age. In this work, we address the problem of mitigating bias in facial datasets by data augmentation. We propose a multi-attribute framework that can successfully transfer complex, multi-scale facial patterns even if these belong to underrepresented groups in the training set. This is achieved by relaxing the rigid dependence on a single attribute label, and further introducing a tensor-based mixing structure that captures multiplicative interactions between attributes in a multilinear fashion. We evaluate our method with an extensive set of qualitative and quantitative experiments on several datasets, with rigorous comparisons to state-of-the-art methods. We find that the proposed framework can successfully mitigate dataset bias, as evinced by extensive evaluations on established diversity metrics, while significantly improving fairness metrics such as equality of opportunity.

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.

Discriminating Malignancy in Thyroid Nodules: The Nomogram Versus the Kwak and ACR TI-RADS

2020 ◽  
Vol 163 (6) ◽  
pp. 1156-1165
Author(s):  
Juan Xiao ◽  
Qiang Xiao ◽  
Wei Cong ◽  
Ting Li ◽  
Shouluan Ding ◽  
...  
Keyword(s):  
Thyroid Nodules ◽  
Characteristic Curve ◽  
Area Under The Curve ◽  
Diagnostic Study ◽  
Diagnostic Efficiency ◽  
Training Set ◽  
Multivariable Logistic Regression Model ◽  
Predictive Values ◽  
Validation Set ◽  
Sensitivity Specificity

Objective To develop an easy-to-use nomogram for discrimination of malignant thyroid nodules and to compare diagnostic efficiency with the Kwak and American College of Radiology (ACR) Thyroid Imaging, Reporting and Data System (TI-RADS). Study Design Retrospective diagnostic study. Setting The Second Hospital of Shandong University. Subjects and Methods From March 2017 to April 2019, 792 patients with 1940 thyroid nodules were included into the training set; from May 2019 to December 2019, 174 patients with 389 nodules were included into the validation set. Multivariable logistic regression model was used to develop a nomogram for discriminating malignant nodules. To compare the diagnostic performance of the nomogram with the Kwak and ACR TI-RADS, the area under the receiver operating characteristic curve, sensitivity, specificity, and positive and negative predictive values were calculated. Results The nomogram consisted of 7 factors: composition, orientation, echogenicity, border, margin, extrathyroidal extension, and calcification. In the training set, for all nodules, the area under the curve (AUC) for the nomogram was 0.844, which was higher than the Kwak TI-RADS (0.826, P = .008) and the ACR TI-RADS (0.810, P < .001). For the 822 nodules >1 cm, the AUC of the nomogram was 0.891, which was higher than the Kwak TI-RADS (0.852, P < .001) and the ACR TI-RADS (0.853, P < .001). In the validation set, the AUC of the nomogram was also higher than the Kwak and ACR TI-RADS ( P < .05), each in the whole series and separately for nodules >1 or ≤1 cm. Conclusions When compared with the Kwak and ACR TI-RADS, the nomogram had a better performance in discriminating malignant thyroid nodules.

scholarly journals GPR B-Scan Image Denoising via Multi-Scale Convolutional Autoencoder with Data Augmentation

Electronics ◽  
2021 ◽  
Vol 10 (11) ◽  
pp. 1269
Author(s):  
Jiabin Luo ◽  
Wentai Lei ◽  
Feifei Hou ◽  
Chenghao Wang ◽  
Qiang Ren ◽  
...  
Keyword(s):  
Image Denoising ◽  
Data Augmentation ◽  
Noise Suppression ◽  
Random Noise ◽  
Similarity Index ◽  
Structural Similarity ◽  
Training Dataset ◽  
Generative Adversarial Network ◽  
Multi Scale ◽  
Convolutional Autoencoder

Ground-penetrating radar (GPR), as a non-invasive instrument, has been widely used in civil engineering. In GPR B-scan images, there may exist random noise due to the influence of the environment and equipment hardware, which complicates the interpretability of the useful information. Many methods have been proposed to eliminate or suppress the random noise. However, the existing methods have an unsatisfactory denoising effect when the image is severely contaminated by random noise. This paper proposes a multi-scale convolutional autoencoder (MCAE) to denoise GPR data. At the same time, to solve the problem of training dataset insufficiency, we designed the data augmentation strategy, Wasserstein generative adversarial network (WGAN), to increase the training dataset of MCAE. Experimental results conducted on both simulated, generated, and field datasets demonstrated that the proposed scheme has promising performance for image denoising. In terms of three indexes: the peak signal-to-noise ratio (PSNR), the time cost, and the structural similarity index (SSIM), the proposed scheme can achieve better performance of random noise suppression compared with the state-of-the-art competing methods (e.g., CAE, BM3D, WNNM).

Sign in / Sign up

Export Citation Format

Share Document