scholarly journals Comparison of radiomic pre-processing steps in the reproducible prediction of disease free survival across multi-scanners/centers

2021 ◽  
Author(s):  
Marta Ferreira ◽  
Pierre Lovinfosse ◽  
Johanne Hermesse ◽  
Marjolein Decuypere ◽  
Caroline Rousseau ◽  
...  
Keyword(s):  
Feature Selection ◽  
Locally Advanced ◽  
Feature Selection Method ◽  
Disease Free Survival ◽  
Selection Method ◽  
Prediction Performance ◽  
Data Set ◽  
Free Survival ◽  
Processing Steps ◽  
Disease Free

Abstract Background Features reproducibility and the generalizability of the models are currently among the most important limitations when integrating radiomics into the clinics. Radiomic features are sensitive to imaging acquisition protocols, reconstruction algorithms and parameters, as well as by the different steps of the usual radiomics workflow. We propose a framework for comparing the reproducibility of different pre-processing steps in PET/CT radiomic analysis in the prediction of disease free survival (DFS) across multi-scanners/centers. Results We evaluated and compared the prediction performance of several models that differ in i) the type of intensity discretization, ii) feature selection method, iii) features type i.e, original or tumour to liver ratio radiomic features (OR or TLR). We trained our models using data from one scanner/center and tested on two external scanner/centers. Our results show that there is a low reproducibility in predictions across scanners and discretization methods. Despite of this, TLR based models were generally more robust than OR. Maximum relevance minimum redundancy (MRMR) forward feature selection with Pearson correlation was the feature selection method that had the best mean area under the precision recall curve when using it combining the features from all discretization’s bin’s number (D_All_FBN) with TLR features for two of the four classifiers. Conclusion We evaluated and compared the prediction performance of several models in a data set containing hundred fifty-eight patients with locally advanced cervical cancer (LACC) from three distinct scanners. In our cohort of LAAC patients pre-processing of radiomic features in [18F]FDG PET affects DFS predictions performances across scanners and combining the D_All_FBN TLR approach with the MRMR forward Pearson feature selection method might help increasing robustness of radiomic studies.

Design of novel multi filter union feature selection framework for breast cancer dataset

2021 ◽  
pp. 1063293X2110160
Author(s):  
Dinesh Morkonda Gunasekaran ◽  
Prabha Dhandayudam
Keyword(s):  
Breast Cancer ◽  
Feature Selection ◽  
Care Center ◽  
Feature Selection Method ◽  
Selection Method ◽  
Cancer Center ◽  
Breast Cancer Dataset ◽  
Data Set ◽  
Health Care Center ◽  
Cancer Data

Nowadays women are commonly diagnosed with breast cancer. Feature based Selection method plays an important step while constructing a classification based framework. We have proposed Multi filter union (MFU) feature selection method for breast cancer data set. The feature selection process based on random forest algorithm and Logistic regression (LG) algorithm based union model is used for selecting important features in the dataset. The performance of the data analysis is evaluated using optimal features subset from selected dataset. The experiments are computed with data set of Wisconsin diagnostic breast cancer center and next the real data set from women health care center. The result of the proposed approach shows high performance and efficient when comparing with existing feature selection algorithms.

Intensification of neoadjuvant therapy in patients with locally advanced rectal cancer

2021 ◽  
Vol 11 (2) ◽  
pp. 19-28
Author(s):  
Z. Z. Mamedli ◽  
A. V. Polynovskiy ◽  
D. V. Kuzmichev ◽  
S. I. Tkachev ◽  
A. A. Aniskin
Keyword(s):  
Rectal Cancer ◽  
Locally Advanced ◽  
Pathologic Complete Response ◽  
Disease Free Survival ◽  
Complete Response ◽  
Advanced Rectal Cancer ◽  
Locally Advanced Rectal Cancer ◽  
Control Group ◽  
Free Survival ◽  
Disease Free

The aim of the study: to increase the frequency of achieving pathologic complete response and increase disease-free survival in the investigational group of patients with locally advanced rectal cancer T3(MRF+)–4N0–2M0 by developing a new strategy for neoadjuvant therapy.Materials and methods. In total, 414 patients were assigned to treatment. Control group I included 89 patients who underwent radiotherapy (RT) 52–56 Gy/26–28 fractions with concurrent capecitabine twice daily 5 days per week. Control group II included 160 patients who underwent RT 52–56 Gy/26–28 fractions with concurrent capecitabine twice daily 5 days per week and oxaliplatin once a week, during the course of RT. Study group III consisted of 165 patients. This group combined RT 52–56 Gy/26–28 fractions with concurrent capecitabine twice daily 5 days per week and additional consecutive CapOx cycles. This group was divided into 2 subgroups: subgroup IIIa included 106 patients with consolidating chemotherapy (after CRT); subgroup IIIb included 59 patients who underwent “sandwich” treatment. Therapy consisted of conducting from 1 to 2 cycles of induction CapOx (up to CRT) and from 1 to 2 cycles of consolidating CapOx with an interval of 7 days. In the interval between the courses of drug therapy, RT 52–56 Gy/26–28 fractions was performed. According to the results of the control examination, further treatment tactics were determined. The primary end points were 5-year disease-free survival and the achievement of a pathologic complete response.Results. Pathologic complete response was significantly more often recorded in patients in the investigational group III (17.48 %; p = 0.021) compared with control groups (7.95 % in the I group and 8.28 % in the II group). 5-year disease-free survival in patients in the study groups was: 71.5 % in the III group, 65.6 % in the II group and 56.9 % in the I group.Conclusion. The shift in emphasis on strengthening the neoadjuvant effect on the tumor and improving approaches to drug therapy regimens have significantly improved disease-free survival of patients with locally advanced rectal cancer.

A prospective, randomized, controlled, multicenter study of apatinib combined with S-1 plus docetaxel as adjuvant therapy for locally advanced gastric cancer.

2021 ◽  
Vol 39 (15_suppl) ◽  
pp. e16019-e16019
Author(s):  
Zhili Shan ◽  
Feng Guo ◽  
Hong Chen ◽  
Dapeng Li ◽  
Zhongqi Mao ◽  
...  
Keyword(s):  
Gastric Cancer ◽  
Advanced Gastric Cancer ◽  
Locally Advanced ◽  
Disease Free Survival ◽  
Free Survival ◽  
Randomized Controlled ◽  
Locally Advanced Gastric Cancer ◽  
Group A ◽  
Group B ◽  
Disease Free

e16019 Background: Postoperative adjuvant chemotherapy is commonly given after the curative resection of gastric cancer (GC) in both Eastern and Western countries. Several studies have investigated the feasibility and safety of S-1 plus docetaxel or S-1 plus cisplatin. However, the best choice of adjuvant treatment for patients with gastric cancer is still debated. Apatinib, an oral small molecular of VEGFR-2 TKI, has been confirmed to improve OS and PFS with acceptable safety profile in patients with advanced gastric cancer refractory to two or more lines of prior chemotherapy. In this study, we aimed to evaluate the efficacy and safety of apatinib combined with S-1/docetaxel for locally advanced gastric cancer (T3-4aN+M0). Methods: This is a prospective, randomized, controlled, multicenter clinical study. Patients with locally advanced gastric cancer, pathological stage T3-4aN+M0 who underwent D2 lymphadenectomy without prior anti-cancer therapy were included. All these patients were assigned to group A or B. Patients in group A received 6 cycles (21 days a cycle) of adjuvant therapy using S-1 (80-120mg/d, d1-14), and docetaxel (40mg/m2, d1). Group B received the same regimen with the addition of apatinib (250mg, qd.). The primary endpoint was disease-free survival (DFS). The final analysis cutoff date was 30 November, 2020. Results: A total of 45 patients were enrolled from January 2019 to November, 2010 and assigned to group A (21) or group B (24). The DFS was not reached in both of the groups. The 1-year disease-free survival rate was 60% in group A and 90% in the group B, while the difference was not significant. The main AEs in group A were anemia (55%), nausea (50%) and neutropenia (40%); The most common AEs in group B were anemia (45%) neutropenia (40%) and diarrhea (25%). There were no treatment-related deaths. The longest administered time of apatinib with no progression was 457 days. And the median time to receive apatinib was 329 days. Conclusions: Combination of apatinib with S-1/docexal chemotherapy shows clinical benefits in locally advanced gastric cancer (T3-4aN+M0), with tolerable toxicity. The study is still ongoing to reach our final endpoint, DFS. Clinical trial information: ChiCTR2000038900.

A Risk Score Model Associated with Tumor Microenvironment Predicts Disease-Free Survival After Radical Prostatectomy

2020 ◽  
Author(s):  
Hao Zhao ◽  
Xuening Zhang ◽  
Zhan Shi ◽  
Songhe Shi
Keyword(s):  
Tumor Microenvironment ◽  
Gleason Score ◽  
Risk Score ◽  
Regression Models ◽  
Cox Regression ◽  
External Validation ◽  
Disease Free Survival ◽  
Data Set ◽  
Free Survival ◽  
Disease Free

Abstract Background Tumor microenvironment (TME) and immune checkpoint inhibitors has been shown to promote active immune responses through different mechanisms. We aimed to identify the important prognostic genes and prognostic characteristics related to TME in prostate cancer (PCa).Methods The gene transcriptome profiles and clinical information of PCa patients were obtained from the TCGA database, and the immune, stromal and estimate scores were calculated by the ESTIMATE algorithm. We evaluated the prognostic value of risk score (RS) model based on univariate Cox and LASSO Cox regression models analysis, and established a nomogram to predict disease-free survival (DFS) in PCa patients. The GSE70768 data set was used for external validation. Finally, 22 subsets of tumor-infiltrating immune cells (Tiics) were analyzed using the Cibersort algorithm.Results In this study, the patients with higher immune, stromal, and estimate scores were associated with poorer DFS, higher Gleason score, and higher AJCC T stage. Based on the immune and stromal scores, the Venny diagram screened out 515 cross DEGs. The univariate COX and Lasso Cox regression models were used to select 18 DEGs from 515 DEGs, and constructed a RS model. The DFS of the high-RS group was significantly lower than that of the low-RS group (P<0.001). The AUC of 1-year, 3-year and 5-year DFS rates in RS model were 0.778, 0.754 and 0.750, respectively. In addition, the RS model constructed from 18 genes was found to be more sensitive than Gleason score (1, 3, 5 year AUC= 0.704, 0.677 and 0.682). The nomograms of DFS were established based on RS and Gleason scores. The AUC of the nomograms in the first, third, and fifth years were 0.802, 0.808, and 0.796, respectively. These results have been further validated in GEO. In addition, the proportion of Tregs was higher in high-RS patients (P<0.05), and the expression of five immune checkpoints (CTLA-4, PD-1, LAG-3, TIM-3 and TIGIT) was higher in high-RS patients (P<0.05).Conclusion We identified 18 TME-related genes from the TCGA database, which were significantly related to DFS in PCa patients.

Nuclear Morphometry and Prognosis in Favorable Histology Wilms' Tumor: A Prospective Reevaluation

1999 ◽  
Vol 17 (7) ◽  
pp. 2123-2123 ◽  
Author(s):  
Norman E. Breslow ◽  
Alan W. Partin ◽  
Benjamin R. Lee ◽  
Katherine A. Guthrie ◽  
J. Bruce Beckwith ◽  
...  
Keyword(s):  
Sensitivity And Specificity ◽  
Discriminant Function ◽  
Wilms Tumor ◽  
Disease Free Survival ◽  
Data Set ◽  
Free Survival ◽  
Favorable Histology ◽  
Relative Risks ◽  
Nuclear Morphometry ◽  
Disease Free

PURPOSE: This study was designed to evaluate the ability of a previously published nuclear morphometry discriminant function to predict disease-free survival in patients with Wilms' tumor. PATIENTS AND METHODS: We identified 218 patients with stage I-IV Wilms' tumor of favorable histology who were entered onto the National Wilms' Tumor Study (NWTS) between January 1, 1990 and April 15, 1994. The nuclear morphometry score was calculated for each patient as follows: MVf = (0.02 × AGE) + (1.17 × SNRF) + (90.6 × LEFD) − 94, with AGE denoting age at diagnosis in months, SNRF the skewness of the nuclear roundness factor, and LEFD the lowest value of nuclear ellipticity as measured by the feret diameter method. Relative risks of relapse were estimated for the total score and for each of its components. Sensitivity and specificity were determined for the criterion of “MVf is greater than −0.35” as a predictor of relapse. RESULTS: By contrast with previously published results, neither the SNRF nor the LEFD made any contribution to the prediction of disease-free survival. Sensitivity and specificity of the criterion of “MVf is greater than −0.35” were 71% and 56%, respectively. CONCLUSION: Re-evaluation of a published nuclear morphometry score showed that it did not predict disease-free survival in patients with Wilms' tumor. The earlier study very likely overestimated the predictive power of nuclear morphometry by using the same data set both to develop the score and to evaluate its properties. Because of the huge number of combinations of nuclear morphometry measurements that may enter into the multivariate discriminant function, use of appropriate statistical methods is essential to estimate accurately the sensitivity and specificity.

scholarly journals Rare Case of Pleomorphic Sarcoma of Oropharynx

2019 ◽  
Vol 05 (02) ◽  
pp. 072-074
Author(s):  
Sajal Goel ◽  
Deepak K. Mittal ◽  
Pankaj Sharma ◽  
Nita Khurana
Keyword(s):  
Locally Advanced ◽  
Adult Life ◽  
Disease Free Survival ◽  
Neck Region ◽  
Head And Neck Region ◽  
Free Survival ◽  
Nonsurgical Management ◽  
Pleomorphic Sarcoma ◽  
First Time ◽  
Disease Free

Abstract Introduction Pleomorphic sarcoma is the commonest soft tissue sarcoma of adult life. Less than 10% cases of this disease occur as primary in head and neck region. Although a case of pleomorphic sarcoma of lower extremity with metastasis to base of tongue had been reported earlier, a pleomorphic sarcoma arising from oropharynx is being reported for the first time. Case Report A 75-year-old male chronic smoker was evaluated for complaints of dysphagia, change in voice, and multiple episodes of oral bleeding. He was found to have a locally advanced pleomorphic sarcoma of oropharynx. He was treated nonsurgically. He showed complete clinical and radiologic response. The disease-free survival is 12 months and overall survival is 74 months. Conclusion This report highlights the importance of nonsurgical management of a case that would have otherwise needed surgery.

Sign in / Sign up

Export Citation Format

Share Document