scholarly journals Hepatocellular Carcinoma Drug-Eluting Bead Transarterial Chemoembolization (DEB-TACE): Outcome Analysis Using a Model Based On Pre-Treatment CT Texture Features

Diagnostics ◽  
2021 ◽  
Vol 11 (6) ◽  
pp. 956
Author(s):  
Marcello Andrea Tipaldi ◽  
Edoardo Ronconi ◽  
Elena Lucertini ◽  
Miltiadis Krokidis ◽  
Marta Zerunian ◽  
...  
Keyword(s):  
Texture Analysis ◽  
Clinical Data ◽  
Transarterial Chemoembolization ◽  
Prognostic Value ◽  
Texture Features ◽  
Response To Therapy ◽  
Survival Prediction ◽  
Ct Examination ◽  
Drug Eluting ◽  
Pre Treatment

(1) Introduction and Aim: The aim of this study is to investigate the prognostic value, in terms of response and survival, of CT-based radiomics features for patients with HCC undergoing drug-eluting beads transarterial chemoembolization (DEB-TACE). (2) Materials and Methods: Pre-treatment CT examinations of 50 patients with HCC, treated with DEB-TACE were manually segmented to obtain the tumor volumetric region of interest, extracting radiomics features with TexRAD. Response to therapy evaluation was performed basing on post-procedural CT examination compared to pre-procedural CT, using modified RECIST criteria for HCC. The prognostic value of texture analysis was evaluated, investigating the correlation between radiomics features, response to therapy and overall survival. Three models based on texture and clinical variables and a combination of them were finally built; (3) Results: Entropy, skewness, MPP and kurtosis showed a significant correlation with complete response (CR) to TACE (all p < 0.001). A predictive model to identify patients with a high and low probability of CR was evaluated with an ROC curve, with an AUC of 0.733 (p < 0.001). The three models built for survival prediction yielded an HR of 2.19 (95% CI: 2.03–2.35) using texture features, of 1.7 (95% CI: 1.54–1.9) using clinical data and of 4.61 (95% CI: 4.24–5.01) combining both radiomics and clinical data (all p < 0.0001). (4) Conclusion: Texture analysis based on pre-treatment CT examination is associated with response to therapy and survival in patients with HCC undergoing DEB-TACE, especially if combined with clinical data.

scholarly journals Fully Automated Brain Tumor Segmentation and Survival Prediction of Gliomas using Deep Learning and MRI

2019 ◽  
Author(s):  
Chandan Ganesh Bangalore Yogananda ◽  
Sahil S. Nalawade ◽  
Gowtham K. Murugesan ◽  
Ben Wagner ◽  
Marco C. Pinho ◽  
...  
Keyword(s):  
Deep Learning ◽  
Brain Tumor ◽  
Texture Features ◽  
Response To Therapy ◽  
Validation Dataset ◽  
Tumor Segmentation ◽  
Survival Prediction ◽  
Accuracy Score ◽  
Mr Images ◽  
Brain Tumor Segmentation

ABSTRACTTumor segmentation of magnetic resonance (MR) images is a critical step in providing objective measures of predicting aggressiveness and response to therapy in gliomas. It has valuable applications in diagnosis, monitoring, and treatment planning of brain tumors. The purpose of this work was to develop a fully automated deep learning method for brain tumor segmentation and survival prediction. Well curated brain tumor cases with multi-parametric MR Images from the BraTS2019 dataset were used. A three-group framework was implemented, with each group consisting of three 3D-Dense-UNets to segment whole tumor (WT), tumor core (TC) and enhancing tumor (ET). This method was implemented to decompose the complex multi-class segmentation problem into individual binary segmentation problems for each sub-component. Each group was trained using different approaches and loss functions. The output segmentations of a particular label from their respective networks from the 3 groups were ensembled and post-processed. For survival analysis, a linear regression model based on imaging texture features and wavelet texture features extracted from each of the segmented components was implemented. The networks were tested on the BraTS2019 validation dataset including 125 cases for the brain tumor segmentation task and 29 cases for the survival prediction task. The segmentation networks achieved average dice scores of 0.901, 0.844 and 0.801 for WT, TC and ET respectively. The survival prediction network achieved an accuracy score of 0.55 and mean squared error (MSE) of 119244. This method could be implemented as a robust tool to assist clinicians in primary brain tumor management and follow-up.

Prognostic value of systemic inflammatory markers in first- and subsequent-line immunotherapy and durability of response in NSCLC.

2021 ◽  
Vol 39 (15_suppl) ◽  
pp. e21210-e21210
Author(s):  
Fahmin Basher ◽  
Diana Saravia ◽  
Gilberto Lopes
Keyword(s):  
Tumor Microenvironment ◽  
Prognostic Value ◽  
Checkpoint Inhibitors ◽  
Laboratory Data ◽  
Response To Therapy ◽  
Smoking History ◽  
Comprehensive Cancer Center ◽  
Cancer Center ◽  
First Line ◽  
Pre Treatment

e21210 Background: Treatment of advanced non-small cell lung cancer with immune checkpoint inhibitors (ICI) has been shown to yield durable responses. High neutrophil-to-lymphocyte ratios (NLR), low lymphocyte-to-monocyte ratios (LMR) and high platelet-to-lymphocyte ratios (PLRs) have been used as surrogates for increased levels of inflammation in the tumor microenvironment that can predict cancer progression and response to therapy. However, the comparative prognostic role of these markers account for when immunotherapy is utilized has not been explicitly determined. Methods: We performed a retrospective review of 233 patients with advanced stage NSCLC at the University of Miami / Sylvester Comprehensive Cancer Center who received ICI either as first-line (1L) or second-line (2L) therapy and for whom laboratory data, in particular absolute neutrophil, lymphocyte, monocyte, and platelet counts, were available pre-treatment and 4 weeks after initiation of immunotherapy. Results: Using receiver operating characteristic (ROC) curves, we identified cutoff values with optimal prognostic value for NLR (4), LMR (2), and PLR (200). Median age, histology, and smoking history were equivalent across each group. Improved OS was observed in our cohort for patients in which pre-treatment NLR < 4 (54.4m vs. 35.9m, p = 0.0069), LMR > 2 (54.4m vs. 32.3m, p = 0.0016), and PLR < 200 (54.4m vs. 27.5m, p = 0.0007), while PFS was unaffected when looking strictly at these cutoffs. We then observed that PFS could be better predicted after stratifying NLR, LMR, or PLR when taking into account whether ICI was administered as 1L or 2L. We also determined that changes in (Δ) NLR or LMR (but not PLR) by at least 20% between baseline and 4 weeks after initiation of ICI could predict duration of response to ICI. Conclusions: In conclusion, the NLR, LMR, and PLR are powerful surrogates for the tumor microenvironment and can predict responses to ICI in advanced NSCLC when used in the context of previous lines of therapy and subsequent pro-inflammatory changes. Our study shows that ICI used in the first-line setting results in more durable responses, and can overcome an unfavorable tumor microenvironment. In addition, we demonstrate that in NSCLC, durability of responses can be predicted by changes in these systemic inflammatory response markers early after the initiation of ICI.[Table: see text]

Radiomics features on CT scans to predict response to HER2-targeted therapy of hepatic metastases from colorectal cancer.

2019 ◽  
Vol 37 (15_suppl) ◽  
pp. e15086-e15086
Author(s):  
Valentina Giannini ◽  
Simone Mazzetti ◽  
Arianna Defeudis ◽  
Giovanni Cappello ◽  
Lorenzo Vassallo ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Texture Analysis ◽  
Hepatic Metastases ◽  
Texture Features ◽  
Response To Therapy ◽  
Ct Scans ◽  
Imaging Biomarkers ◽  
Test Set ◽  
Extended Analysis ◽  
Ct Texture Analysis

e15086 Background: Metastatic Colorectal cancer (mCRC) is the 2nd cause of cancer death worldwide. Repeated cycles of therapies, combined with surgery in oligo-metastatic cases, are the therapeutic standard in mCRC. However, this strategy is seldom resolutive. Different lesions in in the same patient could have different responses to systemic therapy. Recently, CT texture analysis (CTTA) had been shown to potentially provide with prognostic and predictive markers, overcoming the limitations of biopsy sampling in defining tumor heterogeneity. The aim of this study is to use CT texture analysis (CTTA) to identify imaging biomarkers of HER2+ mCRC able to predict lesion response to therapy. Methods: The dataset is composed of 39 extended RAS wild type patients with amplified HER2 mCRC enrolled in the HERACLES trial (NCT03225937) that received either a lapatinib+trastuzumab treatment (n = 23) or a pertuzumab+ trastuzumab-emtansine treatment (n = 16). All patients underwent CT examination every 8 weeks, until disease progression. All mCRC on baseline CT were semi-automatically segmented and quantitative features extracted: size, mean, percentiles, 28 texture features. A logistic regression model was created using: (i) the whole dataset of mCRC as training and test set and (ii) 100 randomly generated training sets (with 70% of responder (R+) mCRC and an equal number of non-responder (R-) mCRC), and 100 test sets including the remaining mCRC. A mCRC was classified as R+ if size decreased (-10%) or was stable (±10%); as R- if size increased (+10%), during subsequent CT scans. Results: A total of 199 metastases were included (75R+ and 124R-). The training set was composed of 53R+ and 53R- mCRC and the test set of 22R+ and 71R- mCRC. Using the whole dataset, the model reached an AUC = 0.82 (sensitivity = 84%, specificity = 70%), while it reached a mean AUC of 0.70 (sensitivity = 68%, specificity = 67%) within the 100 repetitions. Conclusions: CTTA might help in stratifying different behaviors of mCRC, opening the way for lesion-specific therapies, with conceivable cost and life savings. Further extended analysis is needed to better characterize and validate predictive value of these biomarkers.

scholarly journals P-OGC57 Predicting survival and response to therapy using diagnostic biopsies: A machine learning approach to facilitate treatment decisions for oesophageal adenocarcinoma

2021 ◽  
Vol 108 (Supplement_9) ◽  
Author(s):  
Saqib Rahman ◽  
Joseph Early ◽  
Ben Sharpe ◽  
Megan Lloyd ◽  
Matt De Vries ◽  
...  
Keyword(s):  
Machine Learning ◽  
Overall Survival ◽  
High Resolution ◽  
Clinical Data ◽  
Neoadjuvant Treatment ◽  
Response To Therapy ◽  
Oesophageal Adenocarcinoma ◽  
Complex Data ◽  
Pre Treatment ◽  
Diagnostic Biopsies

Abstract Background Standard of care for locally advanced oesophageal adenocarcinoma is neoadjuvant chemotherapy or chemoradiotherapy followed by surgery. Only a minority of patients (&lt;25%) derive significant survival benefit from neoadjuvant treatment and there are no reliable means of establishing prior to treatment in whom this benefit will occur. Moreover, accurate prediction of survival prior to treatment is also not possible. The availability of machine learning techniques provides the potential to use complex data sources to answer these problems. In this study, we assessed the utility of high-resolution digital microscopy of pre-treatment biopsies in predicting both response to neoadjuvant therapy and overall survival. Methods A total of 157 cases were included in the study. Pre-treatment clinical information, including neoadjuvant treatment, was obtained, along with diagnostic biopsies. Diagnostic biopsies were converted into high-resolution whole slide-images and features extracted using the pre-trained convolutional neural network Xception. Single representative images were converted into patches from which predictive models were trained. Elastic net regression classifiers were derived and validated with bootstrapping and 1000 resampled datasets. The response to treatment was considered according to Mandard tumour regression grade (TRG). Model performance was quantified using the C-index (for TRG) and time-dependent AUC (tAUC, fo Overall survival) along with calibration plots. Results Median survival was 78.9months (95%CI 35.9 months – not reached). Survival at 5-years was 52.1%. Neoadjuvant treatment was received by 123 patients (78.3%), with a significant response seen in 45 cases (36.6%). A response was more likely in those patients who received chemoradiotherapy than chemotherapy (53.3% vs 23.1% p &lt; 0.001) and in older patients (median age 69.4 vs 66.0 years, p = 0.038), with other characteristics similar. A predictive model for response to neoadjuvant treatment derived from image features and clinical data achieved good discrimination (C-index 0.767, 95%CI 0.701-0.833) and calibration. Accuracy of prediction of overall survival was more modest (tAUC 0.640, 95%CI 0.518-0.762). Conclusions Using a small dataset, utility of a feature extraction pipeline in prediction of patient level outcomes has been demonstrated. This was more marked in prediction of response to neoadjuvant treatment than overall survival, which may reflect the importance of pre-treatment clinical data in determining the former outcome. Further study to refine the methodology and confirmation in larger datasets are required before expansion to clinical settings.

Overall survival in intermediate-stage hepatocellular carcinoma (HCC) patients after first transarterial chemoembolization (TACE): Proposal of a new scoring system.

2015 ◽  
Vol 33 (3_suppl) ◽  
pp. 386-386
Author(s):  
Rodolfo Sacco ◽  
Valeria Mismas ◽  
Antonio Romano ◽  
Barbara Ginanni ◽  
Sara Marceglia ◽  
...  
Keyword(s):  
Overall Survival ◽  
Scoring System ◽  
Intermediate Stage ◽  
Complete Response ◽  
Clinical Decision ◽  
Response To Therapy ◽  
Treatment Characteristics ◽  
Drug Eluting Beads ◽  
Drug Eluting ◽  
Pre Treatment

386 Background: TACE is the standard treatment for patients with intermediate-stage HCC (BCLC-B according to the Barcelona Clinic Liver Cancer [BCLC] classification). However, prognostic factors for survival after the first TACE cycle are unclear. We correlated pre-treatment characteristics and response to therapy with overall survival (OS) and time to tumor progression (TTP), in order to propose a scoring system aimed at facilitating clinical decision after the first TACE. Methods: We retrospectively analyzed 149 patients (125 males; mean age 65.1±9.2 years) with BCLC-B HCC who received ≥1 cycle of TACE (Lipidol TACE, n=106; drug-eluting beads TACE, n=43). Univariate and multivariate analysis were used to correlate pre-treatment characteristics and response to TACE with OS and TTP. Identified predictive factors were used to define a score for each patient. Results: Median OS was 23 (95% Confidence interval [CI] 11.5-27) months, and median TTP was 11 months (CI 7-11). Complete response (CR) was reported in 63 patients (42.3%) and partial response (PR) in 71 (47.7%). Age >65 years (Hazard Ratio [HR] 1.77; 95% CI: 1.18-2.67), ascites (HR 2.44; 95% CI 1.32-4.29), total diameter of nodules >61 mm (HR: 1.96; 95% CI 1.28-3.08) and response at 1 month (HR 1.70; 95% CI 1.30-2.20) were predictors of survival and were used to build the scoring system (Table). Three groups of patients with different OS and TTP were then identified. Patients with score 0-1 had a longer OS (57.8 months) and TTP (12.7 months) than those with score 2-3 (21.1 and 8.2 months) or score 4-6 (8.0 and 6.3 months) (p<0.001 for both comparisons). Conclusions: This scoring system may allow the identification of three groups of patients with different prognosis after a first cycle of TACE and may therefore be useful in guiding clinical decisions, in particular whether continuing TACE therapy after a first cycle or moving to different therapies. Validation of this scoring system on a larger population is ongoing. [Table: see text]

Sign in / Sign up

Export Citation Format

Share Document