Rectal cancer response to neoadjuvant chemoradiotherapy evaluated with MRI: Development and validation of a classification algorithm

Rengo, Marco; Landolfi, Federica; Picchia, Simona; Bellini, Davide; Losquadro, Chiara; Badia, Stefano; Iannicelli, Elsa; Osti, Mattia Falchetto; Tombolini, Vincenzo; Carbone, Iacopo; Giunta, Gaetano; Laghi, Andréa

doi:10.1016/j.ejrad.2021.110146

Cited by 7 publications

(3 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this context, one of the major strengths of our approach is represented by the utilization of a commercially available software. Both TexRAD, for texture feature extraction, and WEKA, for machine learning algorithm development, have been widely utilized and validated, especially for oncologic imaging [14,30,31].…”

Section: Discussionmentioning

confidence: 99%

Development and Validation of Artificial-Intelligence-Based Radiomics Model Using Computed Tomography Features for Preoperative Risk Stratification of Gastrointestinal Stromal Tumors

Rengo

Onori

Bellini

et al. 2023

JPM

Self Cite

View full text Add to dashboard Cite

Background: preoperative risk assessment of gastrointestinal stromal tumors (GISTS) is required for optimal and personalized treatment planning. Radiomics features are promising tools to predict risk assessment. The purpose of this study is to develop and validate an artificial intelligence classification algorithm, based on CT features, to define GIST’s prognosis as determined by the Miettinen classification. Methods: patients with histological diagnosis of GIST and CT studies were retrospectively enrolled. Eight morphologic and 30 texture CT features were extracted from each tumor and combined to obtain three models (morphologic, texture and combined). Data were analyzed using a machine learning classification (WEKA). For each classification process, sensitivity, specificity, accuracy and area under the curve were evaluated. Inter- and intra-reader agreement were also calculated. Results: 52 patients were evaluated. In the validation population, highest performances were obtained by the combined model (SE 85.7%, SP 90.9%, ACC 88.8%, and AUC 0.954) followed by the morphologic (SE 66.6%, SP 81.8%, ACC 76.4%, and AUC 0.742) and texture (SE 50%, SP 72.7%, ACC 64.7%, and AUC 0.613) models. Reproducibility was high of all manual evaluations. Conclusions: the AI-based radiomics model using a CT feature demonstrates good predictive performance for preoperative risk stratification of GISTs.

show abstract

Section: Discussionmentioning

confidence: 99%

Development and Validation of Artificial-Intelligence-Based Radiomics Model Using Computed Tomography Features for Preoperative Risk Stratification of Gastrointestinal Stromal Tumors

Rengo

Onori

Bellini

et al. 2023

JPM

Self Cite

View full text Add to dashboard Cite

show abstract

“…In order to improve the potential of MRI in the assessment of nCRT response, several studies evaluated the combination of different MRI parameters in the prediction of pTRG [31][32][33][34][35]. Thus, Hotker et al investigated the combination of mrTRG and T2-weighted imaging, DWI, and DCE-MRI, respectively.…”

Section: Discussionmentioning

confidence: 99%

“…Aiming to distinguish complete responders and non-complete responders after nCRT, Rengo et al developed and validated a decision support model employing data-mining algorithms based on morphologic features derived from MRI images. The authors selected mrTRG, staging volume, tumor volume reduction rate, and signal intensity reduction rate for the algorithm's development and found a sensitivity of 85.71% and a 100% specificity in accurate classification of the patients [33]. In a prospective study on 126 patients, Hall et al concluded that addition of DWI to mrTRG improved both the sensitivity and specificity in the assessment of the complete response [34].…”

Section: Discussionmentioning

confidence: 99%

MRI Tumor Regression Grade Combined with T2-Weighted Volumetry May Predict Histopathological Response in Locally Advanced Rectal Cancer following Neoadjuvant Chemoradiotherapy—A New Scoring System Proposal

Jankovic,

Kovac,

Dakovic

et al. 2023

Diagnostics

View full text Add to dashboard Cite

Modern studies focus on the discovery of innovative methods to improve the value of post-treatment magnetic resonance imaging (MRI) in the prediction of pathological responses to preoperative neoadjuvant chemoradiotherapy (nCRT) in locally advanced rectal cancer (LARC). The aim of this study was to assess the potential benefits of combining magnetic resonance tumor regression grade (mrTRG) with T2-weighted volumetry in the prediction of pathological responses to nCRT in LARC. This was a cohort study conducted on patients with histopathologically confirmed LARC in a period from 2020 to 2022. After histopathological verification, all patients underwent initial MRI studies, while the follow-up MRI was performed after nCRT. Tumor characteristics, MRI estimated tumor regression grade (mrTRG) and tumor volumetry were evaluated both initially and at follow-up. All patients were classified into responders and non-responders according to pathological tumor regression grade (pTRG) and mrTRG. A total of 71 patients, mostly male (66.2%) were included in the study. The median tumor volume reduction rate was significantly higher in nCRT-responders compared to non-responders (79.9% vs. 63.3%) (p = 0.003). Based on ROC analysis, optimal cut-off value for tumor volume reduction rate was determined with an area under the curve (AUC) value of 0.724 (p = 0.003). Using the tumor volume reduction rate ≥75% with the addition of response to nCRT according to mrTRG, a new scoring system for prediction of pTRG to preoperative nCRT in LARC was developed. Diagnostic performance of prediction score was tested and the sensitivity, PPV, specificity, and NPV were 81.8%, 56.3%, 71.4%, and 89.7%, respectively. The combination of mrTRG and T2-weighted volumetry increases the MRI-based prediction of pTRG to preoperative nCRT in LARC. The proposed scoring system could aid in distinguishing responders to nCRT, as these patients could benefit from organ-preserving treatment and a “watch and wait” strategy.

show abstract

Improving the local excision strategy for rectal cancer after chemoradiotherapy: Surgical and oncological results

Meillat,

Weets,

Saadoun

et al. 2024

European Journal of Surgical Oncology

View full text Add to dashboard Cite

Rectal cancer response to neoadjuvant chemoradiotherapy evaluated with MRI: Development and validation of a classification algorithm

Cited by 7 publications

References 31 publications

Development and Validation of Artificial-Intelligence-Based Radiomics Model Using Computed Tomography Features for Preoperative Risk Stratification of Gastrointestinal Stromal Tumors

Development and Validation of Artificial-Intelligence-Based Radiomics Model Using Computed Tomography Features for Preoperative Risk Stratification of Gastrointestinal Stromal Tumors

MRI Tumor Regression Grade Combined with T2-Weighted Volumetry May Predict Histopathological Response in Locally Advanced Rectal Cancer following Neoadjuvant Chemoradiotherapy—A New Scoring System Proposal

Improving the local excision strategy for rectal cancer after chemoradiotherapy: Surgical and oncological results

Contact Info

Product

Resources

About