scholarly journals Progression Free Survival Prediction for Head and Neck Cancer using Deep Learning based on Clinical and PET-CT Imaging Data

2021 ◽  
Author(s):  
Mohamed A. Naser ◽  
Kareem A. Wahid ◽  
Abdallah Sherif Radwan Mohamed ◽  
Moamen Abobakr Abdelaal ◽  
Renjie He ◽  
...  
Keyword(s):  
Deep Learning ◽  
Head And Neck ◽  
Cross Validation ◽  
Progression Free Survival ◽  
Ct Images ◽  
Training Data ◽  
Learning Approaches ◽  
Test Set ◽  
Free Survival ◽  
Pet Ct

Determining progression-free survival (PFS) for head and neck squamous cell carcinoma (HNSCC) patients is a challenging but pertinent task that could help stratify patients for improved overall outcomes. PET/CT images provide a rich source of anatomical and metabolic data for potential clinical biomarkers that would inform treatment decisions and could help improve PFS. In this study, we participate in the 2021 HECKTOR Challenge to predict PFS in a large dataset of HNSCC PET/CT images using deep learning approaches. We develop a series of deep learning models based on the DenseNet architecture using a negative log-likelihood loss function that utilizes PET/CT images and clinical data as separate input channels to predict PFS in days. Internal model validation based on 10-fold cross-validation using the training data (N=224) yielded C-index values up to 0.622 (without) and 0.842 (with) censoring status considered in C-index computation, respectively. We then implemented model ensembling approaches based on the training data cross-validation folds to predict the PFS of the test set patients (N=101). External validation on the test set for the best ensembling method yielded a C-index value of 0.694. Our results are a promising example of how deep learning approaches can effectively utilize imaging and clinical data for medical outcome prediction in HNSCC, but further work in optimizing these processes is needed.

scholarly journals Prediction of 5-year Progression-Free Survival in Advanced Nasopharyngeal Carcinoma with Pretreatment PET/CT using Multi-Modality Deep Learning-based Radiomics

2021 ◽  
Author(s):  
Bingxin Gu ◽  
Mingyuan Meng ◽  
Lei Bi ◽  
Jinman Kim ◽  
David Dagan Feng ◽  
...  
Keyword(s):  
Deep Learning ◽  
Medical Image Analysis ◽  
Progression Free Survival ◽  
Ct Images ◽  
Tnm Stage ◽  
Support Vector ◽  
Free Survival ◽  
Prognostic Performance ◽  
Pet Ct ◽  
Testing Error

Abstract Purpose Deep Learning-based Radiomics (DLR) has achieved great success on medical image analysis. In this study, we aimed to explore the capability of our proposed end-to-end multi-modality DLR model using pretreatment PET/CT images to predict 5-year Progression-Free Survival (PFS) in advanced NPC.Methods A total of 170 patients with pathological confirmed advanced NPC (TNM stage III or IVa) were enrolled in this study. A 3D Convolutional Neural Network (CNN), with two branches to process PET and CT separately, was optimized to extract deep features from pretreatment multi-modality PET/CT images and use the derived features to predict the probability of 5-year PFS. Optionally, TNM stage, as a high-level clinical feature, can be integrated into our DLR model to further improve prognostic performance. Results For a comparison between Conventional Radiomic (CR) and DLR, 1456 handcrafted features were extracted, and three top CR methods, Random Forest (RF) + RF (AUC = 0.796 ± 0.009, testing error = 0.267 ± 0.007), RF + Adaptive Boosting (AdaBoost) (AUC = 0.783 ± 0.011, testing error = 0.286 ± 0.009), and L1-Logistic Regression (L1-LOG) + Kernel Support Vector Machines (KSVM) (AUC = 0.769 ± 0.008, testing error = 0.298 ± 0.006), were selected as benchmarks from 54 combinations of 6 feature selection methods and 9 classification methods. Compared to the three CR methods, our multi-modality DLR models using both PET and CT, with or without TNM stage (named PCT or PC model), resulted in the highest prognostic performance (PCT model: AUC = 0.842 ± 0.034, testing error = 0.194 ± 0.029; PC model: AUC = 0.825 ± 0.041, testing error = 0.223 ± 0.035). Furthermore, the multi-modality PCT model outperformed single-modality DLR models using only PET and TNM stage (named PT model: AUC = 0.818 ± 0.029, testing error = 0.218 ± 0.024) or only CT and TNM stage (named CT model: AUC = 0.657 ± 0.055, testing error = 0.375 ± 0.048). Conclusion Our study identified potential radiomics-based prognostic model for survival prediction in advanced NPC, and suggests that DLR could serve as a tool for aiding in cancer management.

scholarly journals Radiomics Analysis of PET and CT Components of 18F-FDG PET/CT Imaging for Prediction of Progression-Free Survival in Advanced High-Grade Serous Ovarian Cancer

2021 ◽  
Vol 11 ◽  
Author(s):  
Xihai Wang ◽  
Zaiming Lu
Keyword(s):  
Clinical Features ◽  
Cox Regression ◽  
Progression Free Survival ◽  
Predictive Performance ◽  
Ct Images ◽  
Metabolic Parameters ◽  
P Value ◽  
Free Survival ◽  
Pet Ct ◽  
Fdg Pet Ct

ObjectiveTo investigate radiomics features extracted from PET and CT components of 18F-FDG PET/CT images integrating clinical factors and metabolic parameters of PET to predict progression-free survival (PFS) in advanced high-grade serous ovarian cancer (HGSOC).MethodsA total of 261 patients were finally enrolled in this study and randomly divided into training (n=182) and validation cohorts (n=79). The data of clinical features and metabolic parameters of PET were reviewed from hospital information system(HIS). All volumes of interest (VOIs) of PET/CT images were semi-automatically segmented with a threshold of 42% of maximal standard uptake value (SUVmax) in PET images. A total of 1700 (850×2) radiomics features were separately extracted from PET and CT components of PET/CT images. Then two radiomics signatures (RSs) were constructed by the least absolute shrinkage and selection operator (LASSO) method. The RSs of PET (PET_RS) and CT components(CT_RS) were separately divided into low and high RS groups according to the optimum cutoff value. The potential associations between RSs with PFS were assessed in training and validation cohorts based on the Log-rank test. Clinical features and metabolic parameters of PET images (PET_MP) with P-value <0.05 in univariate and multivariate Cox regression were combined with PET_RS and CT_RS to develop prediction nomograms (Clinical, Clinical+ PET_MP, Clinical+ PET_RS, Clinical+ CT_RS, Clinical+ PET_MP + PET_RS, Clinical+ PET_MP + CT_RS) by using multivariate Cox regression. The concordance index (C-index), calibration curve, and net reclassification improvement (NRI) was applied to evaluate the predictive performance of nomograms in training and validation cohorts.ResultsIn univariate Cox regression analysis, six clinical features were significantly associated with PFS. Ten PET radiomics features were selected by LASSO to construct PET_RS, and 1 CT radiomics features to construct CT_RS. PET_RS and CT_RS was significantly associated with PFS both in training (P <0.00 for both RSs) and validation cohorts (P=0.01 for both RSs). Because there was no PET_MP significantly associated with PFS in training cohorts. Only three models were constructed by 4 clinical features with P-value <0.05 in multivariate Cox regression and RSs (Clinical, Clinical+ PET_RS, Clinical+ CT_RS). Clinical+ PET_RS model showed higher prognostic performance than other models in training cohort (C-index=0.70, 95% CI 0.68-0.72) and validation cohort (C-index=0.70, 95% CI 0.66-0.74). Calibration curves of each model for prediction of 1-, 3-year PFS indicated Clinical +PET_RS model showed excellent agreements between estimated and the observed 1-, 3-outcomes. Compared to the basic clinical model, Clinical+ PET_MS model resulted in greater improvement in predictive performance in the validation cohort.ConclusionPET_RS can improve diagnostic accuracy and provide complementary prognostic information compared with the use of clinical factors alone or combined with CT_RS. The newly developed radiomics nomogram is an effective tool to predict PFS for patients with advanced HGSOC.

scholarly journals The Predictive Value of PET/CT for Post-Transplant Outcomes in T Cell Lymphoma

Blood ◽  
2018 ◽  
Vol 132 (Supplement 1) ◽  
pp. 2914-2914
Author(s):  
Nancy Kaddis ◽  
Eric D Jacobsen ◽  
Ailbhe O'Neill ◽  
Nikhil Ramaiya ◽  
Robert A. Redd
Keyword(s):  
Predictive Value ◽  
Progression Free Survival ◽  
Ct Images ◽  
Negative Group ◽  
Free Survival ◽  
Positive Group ◽  
Post Transplant ◽  
Pet Ct

Abstract Objective 18F-fluorodeoxyglucose (FDG)-positron emission tomography (PET) is used routinely for response assessment and treatment decision making in Hodgkin lymphoma and B cell non-Hodgkin lymphoma. The predictive value of PET/CT in patients with peripheral T-cell lymphomas (PTCL) is not well defined. We performed a retrospective single institution analysis to determine the utility of pre-transplant PET/CT to predict outcomes following autologous stem cell transplant (ASCT) for PTCL. Materials and Methods PET/CT patient population We screened the Dana-Farber Cancer Institute database for patients undergoing ASCT between 2005 and 2015 and identified 109 PTCL patients. Patients had PET/CT performed within 3 months prior to transplant and follow up PET/CT within one year of ASCT. 38 patients met the inclusion criteria (17 women, 21 men, mean age at transplant 56 years, SD ±14.6, range 22-73). Image interpretation The FDG-PET/CT images were reviewed on HERMES GOLD (Hermes Medical Solutions AB, Stockholm, Sweden) workstation by a radiologist (AON) blinded to clinical details. Pre-transplant PET/CT images were read initially and then one week later the post-transplant PET/CT images were read with the reader blinded to the pre-transplant PET/CT findings. The Deauville five-point scale was used for staging and assessment of treatment response and recurrence. A Deauville score of 3 or less was considered a complete response (CR). Results There was mean of 1.3 months between the initial PET/CT and transplant. Mean of 5 months between transplant and follow up PET/CT. A total of 30 patients had a CR on pre-transplant PET/CT. There were 8 patients with persistent sites of FDG uptake on PET/CT with Deauville 4 (n=4), Deauville 5 (n=2) consistent with partial response to treatment. Pre-transplant PET/CT did not correlate with long term survival outcomes including 3-year PFS in our data; a negative pre-transplant PET/CT was not associated with improved 3-year PFS as compared to a positive pre-transplant PET/CT. A total of 26 patients (68%) had no evidence of disease on post-transplant PET or negative post treatment PET/CT. Of those, 23 (88%) had a 3 -year progression free survival, 13 (50%) had a 5-year progression free survival, and 5 (19%) had died of recurrent disease at the time of our analysis. On post-transplant, a total of 12 patients had positive PET/CT with 6 achieving partial remission and 6 having progressive disease on post-transplant PET/CT. In terms of outcome, the 3-year PFS for the PET positive group was 42% (5/12). Of those, 2 (17%) had durable 5-year PFS with treatment after transplant while the other 10 (83%) eventually died of their disease. The 3-year PFS rate in the PET negative group was 88% (23/26) (95% CI: 70 - 98%) and 42% (5/12) (95% CI: 15 - 72%%) for PET positive group. The difference in the 3-year PFS in the PET negative group is significantly larger than that of the PET negative group (p<0.005). The 5-year PFS in the PET negative group was 50% (13/26) and 17% (2/12) for the PET positive group with a marginally significant difference (p=0.08) Conclusions: Patients with a negative post-transplant PET/CT had a 3-year PFS of 88% and 5-year PFS of 50% compared to a 3-year PFS of 42% and a 5-year PFS of 17% in patients with a positive post-transplant PET/CT. This suggests that post-transplant PET/CT is a clinically meaningful predictor of long-term disease-free survival. The PFS data in the patients with a negative post-transplant PET/CT compares favorably to that of patients not stratified by PET/CT in prospective trials including a 5-year PFS of 44% in the NLG-T-01 study which looked at 115 PTCL patients who underwent ASCT in the up-front setting (d'Amore F, et al. J Clin Oncol. 2012 Sep 1;30(25):3093-9). Our findings that negative pre-transplant PET/CT are not predictive of survival or associated with an improved 3-year PFS in comparison to positive pre-transplant PET/CT was in keeping with the findings of another retrospective analysis of 48 patients, which compared the 3-year PFS and OS of patients with positive and negative pre-transplant PET/CT studies (Shea L, et al. Leuk Lymphoma. 2015 January; 56(1): 256-259). Disclosures Jacobsen: Merck: Consultancy; Seattle Genetics: Consultancy.

scholarly journals Head and Neck Cancer Primary Tumor Auto Segmentation using Model Ensembling of Deep Learning in PET-CT Images

2021 ◽  
Author(s):  
Mohamed A. Naser ◽  
Kareem A. Wahid ◽  
Lisanne V. van Dijk ◽  
Renjie He ◽  
Moamen Abobakr Abdelaal ◽  
...  
Keyword(s):  
Deep Learning ◽  
Cross Validation ◽  
External Validation ◽  
Unmet Need ◽  
Ct Images ◽  
Majority Voting ◽  
Dice Similarity Coefficient ◽  
Primary Tumors ◽  
Label Fusion ◽  
Pet Ct

Auto-segmentation of primary tumors in oropharyngeal cancer using PET/CT images is an unmet need that has the potential to improve radiation oncology workflows. In this study, we develop a series of deep learning models based on a 3D Residual Unet (ResUnet) architecture that can segment oropharyngeal tumors with high performance as demonstrated through internal and external validation of large-scale datasets (training size = 224 patients, testing size = 101 patients) as part of the 2021 HECKTOR Challenge. Specifically, we leverage ResUNet models with either 256 or 512 bottleneck layer channels that are able to demonstrate internal validation (10-fold cross-validation) mean Dice similarity coefficient (DSC) up to 0.771 and median 95% Hausdorff distance (95% HD) as low as 2.919 mm. We employ label fusion ensemble approaches, including Simultaneous Truth and Performance Level Estimation (STAPLE) and a voxel-level threshold approach based on majority voting (AVERAGE), to generate consensus segmentations on the test data by combining the segmentations produced through different trained cross-validation models. We demonstrate that our best performing ensembling approach (256 channels AVERAGE) achieves a mean DSC of 0.770 and median 95% HD of 3.143 mm through independent external validation on the test set. Concordance of internal and external validation results suggests our models are robust and can generalize well to unseen PET/CT data. We advocate that ResUNet models coupled to label fusion ensembling approaches are promising candidates for PET/CT oropharyngeal primary tumors auto-segmentation, with future investigations targeting the ideal combination of channel combinations and label fusion strategies to maximize seg-mentation performance.

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.

scholarly journals Fully Automated Delineation of Gross Tumor Volume for Head and Neck Cancer on PET-CT Using Deep Learning: A Dual-Center Study

2018 ◽  
Vol 2018 ◽  
pp. 1-12 ◽  
Author(s):  
Bin Huang ◽  
Zhewei Chen ◽  
Po-Man Wu ◽  
Yufeng Ye ◽  
Shi-Ting Feng ◽  
...  
Keyword(s):  
Head And Neck Cancer ◽  
Deep Learning ◽  
Head And Neck ◽  
Neck Cancer ◽  
Gold Standard ◽  
Gross Tumor Volume ◽  
Tumor Volume ◽  
Ct Images ◽  
Dice Similarity Coefficient ◽  
Pet Ct

Purpose. In this study, we proposed an automated deep learning (DL) method for head and neck cancer (HNC) gross tumor volume (GTV) contouring on positron emission tomography-computed tomography (PET-CT) images. Materials and Methods. PET-CT images were collected from 22 newly diagnosed HNC patients, of whom 17 (Database 1) and 5 (Database 2) were from two centers, respectively. An oncologist and a radiologist decided the gold standard of GTV manually by consensus. We developed a deep convolutional neural network (DCNN) and trained the network based on the two-dimensional PET-CT images and the gold standard of GTV in the training dataset. We did two experiments: Experiment 1, with Database 1 only, and Experiment 2, with both Databases 1 and 2. In both Experiment 1 and Experiment 2, we evaluated the proposed method using a leave-one-out cross-validation strategy. We compared the median results in Experiment 2 (GTVa) with the performance of other methods in the literature and with the gold standard (GTVm). Results. A tumor segmentation task for a patient on coregistered PET-CT images took less than one minute. The dice similarity coefficient (DSC) of the proposed method in Experiment 1 and Experiment 2 was 0.481∼0.872 and 0.482∼0.868, respectively. The DSC of GTVa was better than that in previous studies. A high correlation was found between GTVa and GTVm (R = 0.99, P<0.001). The median volume difference (%) between GTVm and GTVa was 10.9%. The median values of DSC, sensitivity, and precision of GTVa were 0.785, 0.764, and 0.789, respectively. Conclusion. A fully automatic GTV contouring method for HNC based on DCNN and PET-CT from dual centers has been successfully proposed with high accuracy and efficiency. Our proposed method is of help to the clinicians in HNC management.

PO-1655 Tuning deep learning models for automatic segmentation of head and neck cancers in PET/CT images

2021 ◽  
Vol 161 ◽  
pp. S1374-S1376
Author(s):  
B.N. Huynh ◽  
A.R. Groendahl ◽  
Y.M. Moe ◽  
O. Tomic ◽  
E. Dale ◽  
...  
Keyword(s):  
Deep Learning ◽  
Head And Neck ◽  
Automatic Segmentation ◽  
Ct Images ◽  
Head And Neck Cancers ◽  
Learning Models ◽  
Pet Ct

scholarly journals Effectiveness of nivolumab affected by prior cetuximab use and neck dissection in Japanese patients with recurrent or metastatic head and neck cancer: results from a retrospective observational study in a real-world setting

2021 ◽  
Author(s):  
Shin Kariya ◽  
Yasushi Shimizu ◽  
Nobuhiro Hanai ◽  
Ryuji Yasumatsu ◽  
Tomoya Yokota ◽  
...  
Keyword(s):  
Head And Neck Cancer ◽  
Head And Neck ◽  
Neck Dissection ◽  
Neck Cancer ◽  
Median Overall Survival ◽  
Response Rate ◽  
Objective Response ◽  
Progression Free Survival ◽  
Japanese Patients ◽  
Free Survival

Abstract Background To examine the effect of prior use of cetuximab and neck dissection on the effectiveness of nivolumab, we conducted a large-scale subgroup analysis in Japanese patients with recurrent/metastatic head and neck cancer. Methods Data on the effectiveness of nivolumab were extracted from patient medical records. All patients were analyzed for effectiveness by prior cetuximab use. In the analyses for prior neck dissection, only patients with locally advanced disease were included. Results Of 256 patients analyzed, 155 had received prior cetuximab. Nineteen of 50 patients with local recurrence underwent neck dissection. The objective response rate was 14.7 vs 17.2% (p = 0.6116), median progression-free survival was 2.0 vs 3.1 months (p = 0.0261), and median overall survival was 8.4 vs 12 months (p = 0.0548) with vs without prior cetuximab use, respectively. The objective response rate was 23.1 vs 25.9% (p = 0.8455), median progression-free survival was 1.8 vs 3.0 months (p = 0.6650), and median overall survival was 9.1 vs 9.9 months (p = 0.5289) with vs without neck dissection, respectively. Conclusions These findings support the use of nivolumab for patients with recurrent/metastatic head and neck cancer regardless of prior cetuximab use or neck dissection history. Trial registration number UMIN-CTR (UMIN000032600), Clinicaltrials.gov (NCT03569436)

Sign in / Sign up

Export Citation Format

Share Document