scholarly journals Non-invasive measurement of PD-L1 status and prediction of immunotherapy response using deep learning of PET/CT images

2021 ◽  
Vol 9 (6) ◽  
pp. e002118
Author(s):  
Wei Mu ◽  
Lei Jiang ◽  
Yu Shi ◽  
Ilke Tunali ◽  
Jhanelle E Gray ◽  
...  
Keyword(s):  
Checkpoint Inhibitors ◽  
Quantitative Imaging ◽  
External Validation ◽  
Progression Free Survival ◽  
Ct Images ◽  
Operating Characteristics ◽  
Convolutional Network ◽  
Nccn Guidelines ◽  
Pet Ct ◽  
Expression Status

BackgroundCurrently, only a fraction of patients with non-small cell lung cancer (NSCLC) treated with immune checkpoint inhibitors (ICIs) experience a durable clinical benefit (DCB). According to NCCN guidelines, Programmed death-ligand 1 (PD-L1) expression status determined by immunohistochemistry (IHC) of biopsies is the only clinically approved companion biomarker to trigger the use of ICI therapy. Based on prior work showing a relationship between quantitative imaging and gene expression, we hypothesize that quantitative imaging (radiomics) can provide an alternative surrogate for PD-L1 expression status in clinical decision support.Methods18F-FDG-PET/CT images and clinical data were curated from 697 patients with NSCLC from three institutions and these were analyzed using a small-residual-convolutional-network (SResCNN) to develop a deeply learned score (DLS) to predict the PD-L1 expression status. This developed model was further used to predict DCB, progression-free survival (PFS), and overall survival (OS) in two retrospective and one prospective test cohorts of ICI-treated patients with advanced stage NSCLC.ResultsThe PD-L1 DLS significantly discriminated between PD-L1 positive and negative patients (area under receiver operating characteristics curve ≥0.82 in the training, validation, and two external test cohorts). Importantly, the DLS was indistinguishable from IHC-derived PD-L1 status in predicting PFS and OS, suggesting the utility of DLS as a surrogate for IHC. A score generated by combining the DLS with clinical characteristics was able to accurately (C-indexes of 0.70–0.87) predict DCB, PFS, and OS in retrospective training, prospective testing and external validation cohorts.ConclusionHence, we propose DLS as a surrogate or substitute for IHC-determined PD-L1 measurement to guide individual pretherapy decisions pending in larger prospective trials.

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 Non-invasive decision support for NSCLC treatment using PET/CT radiomics

2020 ◽  
Vol 11 (1) ◽  
Author(s):  
Wei Mu ◽  
Lei Jiang ◽  
JianYuan Zhang ◽  
Yu Shi ◽  
Jhanelle E. Gray ◽  
...  
Keyword(s):  
Deep Learning ◽  
Kinase Inhibitors ◽  
Checkpoint Inhibitors ◽  
Treatment Strategies ◽  
Progression Free Survival ◽  
Mutation Status ◽  
Non Invasive ◽  
Therapy Choice ◽  
Pet Ct ◽  
Nsclc Patients

Abstract Two major treatment strategies employed in non-small cell lung cancer, NSCLC, are tyrosine kinase inhibitors, TKIs, and immune checkpoint inhibitors, ICIs. The choice of strategy is based on heterogeneous biomarkers that can dynamically change during therapy. Thus, there is a compelling need to identify comprehensive biomarkers that can be used longitudinally to help guide therapy choice. Herein, we report a 18F-FDG-PET/CT-based deep learning model, which demonstrates high accuracy in EGFR mutation status prediction across patient cohorts from different institutions. A deep learning score (EGFR-DLS) was significantly and positively associated with longer progression free survival (PFS) in patients treated with EGFR-TKIs, while EGFR-DLS is significantly and negatively associated with higher durable clinical benefit, reduced hyperprogression, and longer PFS among patients treated with ICIs. Thus, the EGFR-DLS provides a non-invasive method for precise quantification of EGFR mutation status in NSCLC patients, which is promising to identify NSCLC patients sensitive to EGFR-TKI or ICI-treatments.

scholarly journals Clinical, FDG-PET and molecular markers of immune checkpoint inhibitor response in patients with metastatic Merkel cell carcinoma

2020 ◽  
Vol 8 (2) ◽  
pp. e000700
Author(s):  
Alison M Weppler ◽  
Andrew Pattison ◽  
Prachi Bhave ◽  
Paolo De Ieso ◽  
Jeanette Raleigh ◽  
...  
Keyword(s):  
Cell Carcinoma ◽  
Merkel Cell Carcinoma ◽  
Immune Checkpoint ◽  
Fdg Pet ◽  
Checkpoint Inhibitors ◽  
Progression Free Survival ◽  
Prior History ◽  
Merkel Cell ◽  
Pet Ct ◽  
Fdg Pet Ct

BackgroundMetastatic Merkel cell carcinoma (mMCC) is an aggressive neuroendocrine malignancy of the skin with a poor prognosis. Immune checkpoint inhibitors (ICIs) have shown substantial efficacy and favorable safety in clinical trials.MethodsMedical records of patients (pts) with mMCC treated with ICIs from August 2015 to December 2018 at Peter MacCallum Cancer Centre in Australia were analyzed. Response was assessed with serial imaging, the majority with FDG-PET/CT scans. RNA sequencing and immunohistochemistry for PD-L1, CD3 and Merkel cell polyomavirus (MCPyV) on tumor samples was performed.Results23 pts with mMCC were treated with ICIs. A median of 8 cycles (range 1 to 47) were administered, with treatment ongoing in 6 pts. Objective responses (OR) were observed in 14 pts (61%): 10 (44%) complete responses (CR) and 4 (17%) partial responses (PR). Median time to response was 8 weeks (range 6 to 12) and 12-month progression-free survival rate was 39%. Increased OR were seen in pts aged less than 75 (OR 80% vs 46%), no prior history of chemotherapy (OR 64% vs 50%), patients with an immune-related adverse event (OR 100% vs 43%) and in MCPyV-negative tumors (OR 69% vs 43%). Pts with a CR had lower mean metabolic tumor volume on baseline FDG-PET/CT scan (CR: 35.7 mL, no CR: 187.8 mL, p=0.05). There was no correlation between PD-L1 positivity and MCPyV status (p=0.764) or OR (p=0.245). 10 pts received radiation therapy (RT) during ICI: 4 pts started RT concurrently (OR 75%, CR 50%), 3 pts had isolated ICI-resistant lesions successfully treated with RT and 3 pts with multisite progression continued to progress despite RT. Overall, 6 pts (26%) had grade 1–2 immune-related adverse events.ConclusionICIs showed efficacy and safety in mMCC consistent with trial data. Clinical and imaging predictors of response were identified.

scholarly journals Preoperative prediction of pathological grade in pancreatic ductal adenocarcinoma based on 18F-FDG PET/CT radiomics

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Haiqun Xing ◽  
Zhixin Hao ◽  
Wenjia Zhu ◽  
Dehui Sun ◽  
Jie Ding ◽  
...  
Keyword(s):  
Prediction Model ◽  
Pancreatic Ductal Adenocarcinoma ◽  
Fdg Pet ◽  
Ct Images ◽  
Ductal Adenocarcinoma ◽  
Pathological Grade ◽  
Operating Characteristics ◽  
Model Based ◽  
Pet Ct ◽  
Fdg Pet Ct

Abstract Purpose To develop and validate a machine learning model based on radiomic features derived from 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography/computed tomography (PET/CT) images to preoperatively predict the pathological grade in patients with pancreatic ductal adenocarcinoma (PDAC). Methods A total of 149 patients (83 men, 66 women, mean age 61 years old) with pathologically proven PDAC and a preoperative 18F-FDG PET/CT scan between May 2009 and January 2016 were included in this retrospective study. The cohort of patients was divided into two separate groups for the training (99 patients) and validation (50 patients) in chronological order. Radiomics features were extracted from PET/CT images using Pyradiomics implemented in Python, and the XGBoost algorithm was used to build a prediction model. Conventional PET parameters, including standardized uptake value, metabolic tumor volume, and total lesion glycolysis, were also measured. The quality of the proposed model was appraised by means of receiver operating characteristics (ROC) and areas under the ROC curve (AUC). Results The prediction model based on a twelve-feature-combined radiomics signature could stratify PDAC patients into grade 1 and grade 2/3 groups with AUC of 0.994 in the training set and 0.921 in the validation set. Conclusion The model developed is capable of predicting pathological differentiation grade of PDAC based on preoperative 18F-FDG PET/CT radiomics features.

scholarly journals On-treatment immune prognostic score for patients with relapsed and/or metastatic head and neck squamous cell carcinoma treated with immunotherapy

2021 ◽  
Vol 9 (6) ◽  
pp. e002718
Author(s):  
Pablo Nenclares ◽  
Lucinda Gunn ◽  
Heba Soliman ◽  
Mateo Bover ◽  
Amy Trinh ◽  
...  
Keyword(s):  
Squamous Cell Carcinoma ◽  
Cell Carcinoma ◽  
Head And Neck ◽  
Squamous Cell ◽  
Scoring System ◽  
Checkpoint Inhibitors ◽  
Prognostic Score ◽  
External Validation ◽  
Progression Free Survival ◽  
Neck Squamous Cell Carcinoma

BackgroundPrevious studies have suggested that inflammatory markers (neutrophil-to-lymphocyte ratio (NLR), lactate dehydrogenase (LDH) and fibrinogen) are prognostic biomarkers in patients with a variety of solid cancers, including those treated with immune checkpoint inhibitors (ICIs). We aimed to develop a model that predicts response and survival in patients with relapsed and/or metastatic (R/M) head and neck squamous cell carcinoma (HNSCC) treated with immunotherapy.MethodsAnalysis of 100 consecutive patients with unresectable R/M HNSCC who were treated with ICI. Baseline and on-treatment (day 28) NLR, fibrinogen and LDH were calculated and correlated with response, progression-free survival (PFS) and overall survival (OS) using univariate and multivariate analyses. The optimal cut-off values were derived using maximally selected log-rank statistics.ResultsLow baseline NLR and fibrinogen levels were associated with response. There was a statistically significant correlation between on-treatment NLR and fibrinogen and best overall response. On-treatment high NLR and raised fibrinogen were significantly associated with poorer outcome. In multivariate analysis, on-treatment NLR (≥4) and on-treatment fibrinogen (≥4 ng/mL) showed a significant negative correlation with OS and PFS. Using these cut-off points, we generated an on-treatment score for OS and PFS (0–2 points). The derived scoring system shows appropriate discrimination and suitability for OS (HR 2.4, 95% CI 1.7 to 3.4, p<0.0001, Harrell’s C 0.67) and PFS (HR 1.8, 95% CI 1.4 to 2.3, p<0.0001, Harrell’s C 0.68). In the absence of an external validation cohort, results of fivefold cross-validation of the score and evaluation of median OS and PFS on the Kaplan-Meier survival distribution between trained and test data exhibited appropriate accuracy and concordance of the model.ConclusionsNLR and fibrinogen levels are simple, inexpensive and readily available biomarkers that could be incorporated into an on-treatment scoring system and used to help predict survival and response to ICI in patients with R/M HNSCC.

scholarly journals Prediction of Microvascular Invasion in Hepatocellular Carcinoma via Deep Learning: A Multi-Center and Prospective Validation Study

Cancers ◽  
2021 ◽  
Vol 13 (10) ◽  
pp. 2368
Author(s):  
Jingwei Wei ◽  
Hanyu Jiang ◽  
Mengsu Zeng ◽  
Meiyun Wang ◽  
Meng Niu ◽  
...  
Keyword(s):  
Hepatocellular Carcinoma ◽  
Deep Learning ◽  
High Risk ◽  
External Validation ◽  
Progression Free Survival ◽  
Risk Groups ◽  
Postoperative Recurrence ◽  
Microvascular Invasion ◽  
Operating Characteristics ◽  
Enhanced Computed Tomography

Microvascular invasion (MVI) is a critical risk factor for postoperative recurrence of hepatocellular carcinoma (HCC). Preknowledge of MVI would assist tailored surgery planning in HCC management. In this multicenter study, we aimed to explore the validity of deep learning (DL) in MVI prediction using two imaging modalities—contrast-enhanced computed tomography (CE-CT) and gadoxetic acid-enhanced magnetic resonance imaging (EOB-MRI). A total of 750 HCCs were enrolled from five Chinese tertiary hospitals. Retrospective CE-CT (n = 306, collected between March, 2013 and July, 2019) and EOB-MRI (n = 329, collected between March, 2012 and March, 2019) data were used to train two DL models, respectively. Prospective external validation (n = 115, collected between July, 2015 and February, 2018) was performed to assess the developed models. Furthermore, DL-based attention maps were utilized to visualize high-risk MVI regions. Our findings revealed that the EOB-MRI-based DL model achieved superior prediction outcome to the CE-CT-based DL model (area under receiver operating characteristics curve (AUC): 0.812 vs. 0.736, p = 0.038; sensitivity: 70.4% vs. 57.4%, p = 0.015; specificity: 80.3% vs. 86.9%, p = 0.052). DL attention maps could visualize peritumoral high-risk areas with genuine histopathologic confirmation. Both DL models could stratify high and low-risk groups regarding progression free survival and overall survival (p < 0.05). Thus, DL can be an efficient tool for MVI prediction, and EOB-MRI was proven to be the modality with advantage for MVI assessment than CE-CT.

scholarly journals Prediction of immunotherapy response using deep learning of PET/CT images

2020 ◽  
Author(s):  
Wei Mu ◽  
Lei Jiang ◽  
Yu Shi ◽  
Ilke Tunali ◽  
Jhanelle E. Gray ◽  
...  
Keyword(s):  
Decision Support ◽  
Network Model ◽  
Clinical Decision Support ◽  
Clinical Characteristics ◽  
Clinical Decision ◽  
Ct Images ◽  
Non Invasive ◽  
Pet Ct ◽  
Nsclc Patients ◽  
Expression Status

AbstractCurrently only a fraction of patients with non-small cell lung cancer (NSCLC) experience durable clinical benefit (DCB) from immunotherapy, robust biomarkers to predict response prior to initiation of therapy are an emerging clinical need. PD-L1 expression status from immunohistochemistry is the only clinically approved biomarker, but a non-invasive complimentary approach that could be used when tissues are not available or when the IHC fails and can be assessed longitudinally would have important implications for clinical decision support. In this study, 18F-FDG-PET/CT images and clinical data were curated from 697 NSCLC patients from three institutions. Utilizing PET/CT images, a deeply-learned-score (DLS) was developed by training a small-residual-convolutional-network model to predict the PD-L1 expression status, which was further used to predict DCB, progression-free survival (PFS), and overall survival (OS) in both retrospective and prospective test cohorts of immunotherapy-treated patients with advanced stage NSCLC. This PD-L1 DLS significantly discriminated PD-L1 positive and negative patients (AUC≥0.82 in all cohorts). Further, higher PD-L1 DLS was significantly associated with higher probability of DCB, longer PFS, and longer OS. The DLS combined with clinical characteristics achieved C-indices of 0.86, 0.83 and 0.81 for DCB prediction, 0.73, 0.72 and 0.70 for PFS prediction, and 0.78, 0.72 and 0.75 for OS prediction in the retrospective, prospective and external cohorts, respectively. The DLS provides a non-invasive and promising approach to predict PD-L1 expression and to infer clinical outcomes for immunotherapy-treated NSCLC patients. Additionally, the multivariable models have the potential to guide individual pre-therapy decisions pending in larger prospective trials.Statement of SignificancePD-L1 expression status by immunohistochemistry (IHC) is the only clinically-approved biomarker to trigger immunotherapy treatment decisions, but a non-invasive complimentary approach that could be used when tissues are not available or when the IHC fails and can be assessed longitudinally would have important implications for clinical decision support. Utilizing PET/CT images, we developed and tested a convolutional neural network model to predict PD-L1 expression status with high accuracy in cohorts from different institutions. And the generated signature may serve as a prognostic biomarker for immunotherapy response in patients with NSCLC, and outperforms the clinical characteristics.

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 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.

Sign in / Sign up

Export Citation Format

Share Document