Deep Learning-Based Radiomics Models for Early Recurrence Prediction of Hepatocellular Carcinoma with Multi-phase CT Images and Clinical Data

2019 ◽  
Author(s):  
Weibin WANG ◽  
Qingqing CHEN ◽  
Yutaro IWAMOTO ◽  
Xianhua HAN ◽  
Qiaowei ZHANG ◽  
...  
Keyword(s):  
Hepatocellular Carcinoma ◽  
Deep Learning ◽  
Clinical Data ◽  
Early Recurrence ◽  
Ct Images ◽  
Recurrence Prediction ◽  
Multi Phase

scholarly journals Deep Fusion Models of Multi-Phase CT and Selected Clinical Data for Preoperative Prediction of Early Recurrence in Hepatocellular Carcinoma

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 139212-139220
Author(s):  
Weibin Wang ◽  
Qingqing Chen ◽  
Yutaro Iwamoto ◽  
Panyanat Aonpong ◽  
Lanfen Lin ◽  
...  
Keyword(s):  
Hepatocellular Carcinoma ◽  
Clinical Data ◽  
Early Recurrence ◽  
Preoperative Prediction ◽  
Multi Phase

scholarly journals 5-year Recurrence Prediction After Hepatocellular Carcinoma Resection Using Deep Learning and Cox Regression Models: A Large Prospective Study

2021 ◽  
Author(s):  
Hon-Yi Shi ◽  
King-The Lee ◽  
Chong-Chi Chiu ◽  
Jhi-Joung Wang ◽  
Ding-Ping Sun ◽  
...  
Keyword(s):  
Neural Network ◽  
Hepatocellular Carcinoma ◽  
Deep Learning ◽  
Surgical Resection ◽  
Scale Score ◽  
Cox Regression ◽  
Recurrence Prediction ◽  
Feature Importance ◽  
Importance Analysis ◽  
Hcc Recurrence

Abstract BackgroundRisk of hepatocellular carcinoma (HCC) recurrence after surgical resection is unknown. Therefore, the aim of this study was 5-year recurrence prediction after HCC resection using deep learning and Cox regression models.MethodsThis study recruited 520 HCC patients who had undergone surgical resection at three medical centers in southern Taiwan between April, 2011, and December, 2015. Two popular deep learning algorithms: a deep neural network (DNN) model and a recurrent neural network (RNN) model and a Cox proportional hazard (CPH) regression model were designed to solve both classification problems and regression problems in predicting HCC recurrence. A feature importance analysis was also performed to identify confounding factors in the prediction of HCC recurrence in patients who had undergone resection.ResultsAll performance indices for the DNN model were significantly higher than those for the RNN model and the traditional CPH model (p<0.001). The most important confounding factor in 5-year recurrence after HCC resection was surgeon volume followed by, in order of importance, hospital volume, preoperative Beck Depression Scale score, preoperative Beck Anxiety Scale score, co-residence with family, tumor stage, and tumor size. ConclusionsThe DNN model is useful for early baseline prediction of 5-year recurrence after HCC resection. Its prediction accuracy can be improved by further training with temporal data collected from treated patients. The feature importance analysis performed in this study to investigate model interpretability provided important insights into the potential use of deep learning models for predicting recurrence after HCC resection and for identifying predictors of recurrence.

Deep learning to develop transcriptomic model for survival prediction in TCGA patients with hepatocellular carcinoma.

2020 ◽  
Vol 38 (15_suppl) ◽  
pp. e14057-e14057
Author(s):  
Hao Yu ◽  
Wei Dai ◽  
Chi Leung Chiang ◽  
Shisuo Du ◽  
Zhao-Chong Zeng ◽  
...  
Keyword(s):  
Hepatocellular Carcinoma ◽  
Deep Learning ◽  
Creatinine Level ◽  
Clinical Data ◽  
Cox Regression ◽  
P Value ◽  
Survival Prediction ◽  
Signal Pathways ◽  
Test Set ◽  
Hidden Layer

e14057 Background: This study aimed to investigate the prognostic value of transcriptome and clinical data of Hepatocellular carcinoma (HCC) patients for overall survival (OS) by deep learning method. Methods: A total of 371 HCC patients with 20530 level three RNA-sequencing data were from The Cancer Genome Atlas (TCGA). Cox-nnet model, a deep learning model through an artificial neural network extension of the Cox regression model, was used for OS prediction. The patients were randomly split into train-set and test-set (7:3). In train-set, the significant genes associated with OS under univariate Cox regression were considered for modeling. Clinical parameters, including age, gender, pathologic stage, child pugh classification, creatinine level etc. were also considered. The Cox-nnet model was developed by cross-validation. Its discrimination was determined by the concordance index (CI) in the independent test-set and compared with multivariable Cox regression. The clustering method Uniform Manifold Approximation and Projection (UMAP) was used for revealing biological information from the hidden layer in the model. Results: In the train-set (n = 259), 1505 genes and two clinical variables (child pugh score and creatinine level) were significantly associated with OS (adjusted P-value < 0.05). To avoid overfitting, only 40 most significant genes were included in the Cox-nnet model. In the test-set (n = 112), the CI of Cox-nnet (0.76, se = 0.04) is better than the CI of multivariable Cox regression (0.71, se = 0.05). The difference between good or poor survival subgroups classified by Cox-nnet was remarkably significant ( P-value = 1e-4, median OS: 80.7 vs. 25.1 months). In the Cox-nnet model with all significant variables, the weights in the hidden layer were clustered by UMAP into 3 positive clusters and 2 negative clusters, which are enriched in GO/KEGG. The “cell cycle” and “complement and coagulation cascades” are the most important signal pathways in positive and negative clusters, respectively. Conclusions: Combining transcriptomic and clinical data, and with deep learning algorithm, we built and validated a robust model for survival prediction in HCC patients. Our study would be useful to explore the clinical implications in survival prediction and corresponding genetic mechanisms. Clinical trial information: 5U24CA143799, 5U24CA143835, 5U24CA143840, 5U24CA143843, 5U24CA143845, 5U24CA143848, 5U24CA1438.

Comparison of Machine Learning-Based Radiomics Models for Early Recurrence Prediction of Hepatocellular Carcinoma

2019 ◽  
Vol 7 (4) ◽  
pp. 117-125 ◽  
Author(s):  
Panyanat Aonpong ◽  
◽  
Qingqin Chen ◽  
Yutaro Iwamoto ◽  
Lanfen Lin ◽  
...  
Keyword(s):  
Machine Learning ◽  
Hepatocellular Carcinoma ◽  
Early Recurrence ◽  
Recurrence Prediction

scholarly journals Predicting microvascular invasion in hepatocellular carcinoma: a deep learning model validated across hospitals

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Shu-Cheng Liu ◽  
Jesyin Lai ◽  
Jhao-Yu Huang ◽  
Chia-Fong Cho ◽  
Pei Hua Lee ◽  
...  
Keyword(s):  
Hepatocellular Carcinoma ◽  
Deep Learning ◽  
Ct Images ◽  
Microvascular Invasion ◽  
University Hospital ◽  
Arterial Phase ◽  
Support Vector ◽  
Imaging Features ◽  
Clinical Factors ◽  
Validation Set

Abstract Background The accuracy of estimating microvascular invasion (MVI) preoperatively in hepatocellular carcinoma (HCC) by clinical observers is low. Most recent studies constructed MVI predictive models utilizing radiological and/or radiomics features extracted from computed tomography (CT) images. These methods, however, rely heavily on human experiences and require manual tumor contouring. We developed a deep learning-based framework for preoperative MVI prediction by using CT images of arterial phase (AP) with simple tumor labeling and without the need of manual feature extraction. The model was further validated on CT images that were originally scanned at multiple different hospitals. Methods CT images of AP were acquired for 309 patients from China Medical University Hospital (CMUH). Images of 164 patients, who took their CT scanning at 54 different hospitals but were referred to CMUH, were also collected. Deep learning (ResNet-18) and machine learning (support vector machine) models were constructed with AP images and/or patients’ clinical factors (CFs), and their performance was compared systematically. All models were independently evaluated on two patient cohorts: validation set (within CMUH) and external set (other hospitals). Subsequently, explainability of the best model was visualized using gradient-weighted class activation map (Grad-CAM). Results The ResNet-18 model built with AP images and patients’ clinical factors was superior than other models achieving a highest AUC of 0.845. When evaluating on the external set, the model produced an AUC of 0.777, approaching its performance on the validation set. Model interpretation with Grad-CAM revealed that MVI relevant imaging features on CT images were captured and learned by the ResNet-18 model. Conclusions This framework provide evidence showing the generalizability and robustness of ResNet-18 in predicting MVI using CT images of AP scanned at multiple different hospitals. Attention heatmaps obtained from model explainability further confirmed that ResNet-18 focused on imaging features on CT overlapping with the conditions used by radiologists to estimate MVI clinically.

scholarly journals Combining Tumor Segmentation Masks with PET/CT Images and Clinical Data in a Deep Learning Framework for Improved Prognostic Prediction in Head and Neck Squamous Cell Carcinoma

2021 ◽  
Author(s):  
Kareem A. Wahid ◽  
Renjie He ◽  
Cem Dede ◽  
Abdallah Sherif Radwan Mohamed ◽  
Moamen Abobakr Abdelaal ◽  
...  
Keyword(s):  
Squamous Cell Carcinoma ◽  
Deep Learning ◽  
Clinical Data ◽  
Cross Validation ◽  
External Validation ◽  
Ct Images ◽  
Tumor Segmentation ◽  
Learning Framework ◽  
Pet Ct ◽  
Additional Input

PET/CT images provide a rich data source for clinical prediction models in head and neck squamous cell carcinoma (HNSCC). Deep learning models often use images in an end-to-end fashion with clinical data or no additional input for predictions. However, in the context of HNSCC, the tumor region of interest may be an informative prior in the generation of improved prediction performance. In this study, we utilize a deep learning framework based on a DenseNet architecture to combine PET images, CT images, primary tumor segmentation masks, and clinical data as separate channels to predict progression-free survival (PFS) in days for HNSCC patients. Through internal validation (10-fold cross-validation) based on a large set of training data provided by the 2021 HECKTOR Challenge, we achieve a mean C-index of 0.855 +- 0.060 and 0.650 +- 0.074 when observed events are and are not included in the C-index calculation, respectively. Ensemble approaches applied to cross-validation folds yield C-index values up to 0.698 in the independent test set (external validation). Importantly, the value of the added segmentation mask is underscored in both internal and external validation by an improvement of the C-index when compared to models that do not utilize the segmentation mask. These promising results highlight the utility of including segmentation masks as additional input channels in deep learning pipelines for clinical outcome prediction in HNSCC.

Sign in / Sign up

Export Citation Format

Share Document