Deep Myometrial Infiltration of Endometrial Cancer on MRI: A Radiomics-Powered Machine Learning Pilot Study

Stanzione, Arnaldo; Cuocolo, Renato; Grosso, Renata Del; Nardiello, Anna; Romeo, Valeria; Travaglino, Antonio; Raffone, Antonio; Bifulco, Giuseppe; Zullo, Fulvio; Insabato, Luigi; Maurea, Simone; Mainenti, Pier Paolo

doi:10.1016/j.acra.2020.02.028

Cited by 75 publications

(51 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Ytre‐Hauge et al, 20 however, did not report on radiomic modeling and neither Ueno et al 19 nor Ytre‐Hauge et al 20 validated their findings in a separate validation cohort. In a recent study of 54 EC patients, using full tumor segmentations on T 2 ‐weighted images, Stanzione et al found that their random forest‐based radiomic model was able to predict DMI with an AUC of 0.92 and 0.94 in the training and validation/test sets, respectively 23 . In our larger study cohort ( n = 138), with tumor segmentations on CE T 1 ‐weighted images that reportedly discriminates better between EC tissue and the surrounding normal myometrium, 6,27 we, however, found a somewhat lower AUC for predicting DMI, both in the training and the validation sets (AUC T = 0.84, AUC V = 0.74).…”

Section: Discussionmentioning

confidence: 99%

Whole‐Volume Tumor MRI Radiomics for Prognostic Modeling in Endometrial Cancer

Fasmer

Hodneland

Dybvik

et al. 2020

Magnetic Resonance Imaging

View full text Add to dashboard Cite

Background In endometrial cancer (EC), preoperative pelvic MRI is recommended for local staging, while final tumor stage and grade are established by surgery and pathology. MRI‐based radiomic tumor profiling may aid in preoperative risk‐stratification and support clinical treatment decisions in EC. Purpose To develop MRI‐based whole‐volume tumor radiomic signatures for prediction of aggressive EC disease. Study Type Retrospective. Population A total of 138 women with histologically confirmed EC, divided into training (nT = 108) and validation cohorts (nV = 30). Field Strength/Sequence Axial oblique T1‐weighted gradient echo volumetric interpolated breath‐hold examination (VIBE) at 1.5T (71/138 patients) and DIXON VIBE at 3T (67/138 patients) at 2 minutes postcontrast injection. Assessment Primary tumors were manually segmented by two radiologists with 4 and 8 years' of experience. Radiomic tumor features were computed and used for prediction of surgicopathologically‐verified deep (≥50%) myometrial invasion (DMI), lymph node metastases (LNM), advanced stage (FIGO III + IV), nonendometrioid (NE) histology, and high‐grade endometrioid tumors (E3). Corresponding analyses were also conducted using radiomics extracted from the axial oblique image slice depicting the largest tumor area. Statistical Tests Logistic least absolute shrinkage and selection operator (LASSO) was applied for radiomic modeling in the training cohort. The diagnostic performances of the radiomic signatures were evaluated by area under the receiver operating characteristic curve in the training (AUCT) and validation (AUCV) cohorts. Progression‐free survival was assessed using the Kaplan–Meier and Cox proportional hazard model. Results The whole‐tumor radiomic signatures yielded AUCT/AUCV of 0.84/0.76 for predicting DMI, 0.73/0.72 for LNM, 0.71/0.68 for FIGO III + IV, 0.68/0.74 for NE histology, and 0.79/0.63 for high‐grade (E3) tumor. Single‐slice radiomics yielded comparable AUCT but significantly lower AUCV for LNM and FIGO III + IV (both P < 0.05). Tumor volume yielded comparable AUCT to the whole‐tumor radiomic signatures for prediction of DMI, LNM, FIGO III + IV, and NE, but significantly lower AUCT for E3 tumors (P < 0.05). All of the whole‐tumor radiomic signatures significantly predicted poor progression‐free survival with hazard ratios of 4.6–9.8 (P < 0.05 for all). Data Conclusion MRI‐based whole‐tumor radiomic signatures yield medium‐to‐high diagnostic performance for predicting aggressive EC disease. The signatures may aid in preoperative risk assessment and hence guide personalized treatment strategies in EC. Level of Evidence 4 Technical Efficacy Stage 2

show abstract

Section: Discussionmentioning

confidence: 99%

Whole‐Volume Tumor MRI Radiomics for Prognostic Modeling in Endometrial Cancer

Fasmer

Hodneland

Dybvik

et al. 2020

Magnetic Resonance Imaging

View full text Add to dashboard Cite

show abstract

“…A recent study used MRI radiomics-powered machine learning to help radiologists evaluate the presence of DMI, yielding an accuracy of 86% and an AUC of 0.92 and increasing the radiologists’ performance from 82% to 100% (p = 0.48). However, this study included only 54 patients and extracted features only from T2WI ( 31 ).…”

Section: Discussionmentioning

confidence: 99%

MRI-Based Radiomics Nomogram for Selecting Ovarian Preservation Treatment in Patients With Early-Stage Endometrial Cancer

et al. 2021

View full text Add to dashboard Cite

BackgroundOvarian preservation treatment (OPT) was recommended in young women with early-stage endometrial cancer [superficial myometrial invasion (MI) and grades (G) 1/2-endometrioid adenocarcinoma (EEC)]. A radiomics nomogram was developed to assist radiologists in assessing the depth of MI and in selecting eligible patients for OPT.MethodsFrom February 2014 to May 2021, 209 G 1/2-EEC patients younger than 45 years (mean 39 ± 4.3 years) were included. Of them, 104 retrospective patients were enrolled in the primary group, and 105 prospective patients were enrolled in the validation group. The radiomics features were extracted based on multi-parametric magnetic resonance imaging, and the least absolute shrinkage and selection operator algorithm was applied to reduce the dimensionality of the data and select the radiomics features that correlated with the depth of MI in G 1/2-EEC patients. A radiomics nomogram for evaluating the depth of MI was developed by combing the selected radiomics features with the cancer antigen 125 and tumor size. Receiver operating characteristic (ROC) curves were used to evaluate the diagnostic performance of the radiomics nomogram and of radiologists without and with the aid of the radiomics nomogram. The net reclassification index (NRI) and total integrated discrimination index (IDI) based on the total included patients to assess the clinical benefit of radiologists with the radiomics nomogram were calculated.ResultsIn the primary group, for evaluating the depth of MI, the AUCs were 0.96 for the radiomics nomogram; 0.80 and 0.86 for radiologists 1 and 2 without the aid of the nomogram, respectively; and 0.98 and 0.98 for radiologists 1 and 2 with the aid of the nomogram, respectively. In the validation group, the AUCs were 0.88 for the radiomics nomogram; 0.82 and 0.83 for radiologists 1 and 2 without the aid of the nomogram, respectively; and 0.94 and 0.94 for radiologists 1 and 2 with the aid of the nomogram, respectively. The yielded NRI and IDI values were 0.29 and 0.43 for radiologist 1 and 0.23 and 0.37 for radiologist 2, respectively.ConclusionsThe radiomics nomogram outperformed radiologists and could help radiologists in assessing the depth of MI and selecting eligible OPTs in G 1/2-EEC patients.

show abstract

“…Images underwent a preprocessing stage before feature extraction, including resampling to isotropic voxel, the normalization of pixel intensity values and discretization [ 20 ]. A freely accessible software (PyRadiomics, v 3.0) was used for image pre-processing and feature extraction [ 21 ].…”

Section: Methodsmentioning

confidence: 99%

A Combined Radiomics and Machine Learning Approach to Distinguish Clinically Significant Prostate Lesions on a Publicly Available MRI Dataset

et al. 2021

View full text Add to dashboard Cite

Although prostate cancer is one of the most common causes of mortality and morbidity in advancing-age males, early diagnosis improves prognosis and modifies the therapy of choice. The aim of this study was the evaluation of a combined radiomics and machine learning approach on a publicly available dataset in order to distinguish a clinically significant from a clinically non-significant prostate lesion. A total of 299 prostate lesions were included in the analysis. A univariate statistical analysis was performed to prove the goodness of the 60 extracted radiomic features in distinguishing prostate lesions. Then, a 10-fold cross-validation was used to train and test some models and the evaluation metrics were calculated; finally, a hold-out was performed and a wrapper feature selection was applied. The employed algorithms were Naïve bayes, K nearest neighbour and some tree-based ones. The tree-based algorithms achieved the highest evaluation metrics, with accuracies over 80%, and area-under-the-curve receiver-operating characteristics below 0.80. Combined machine learning algorithms and radiomics based on clinical, routine, multiparametric, magnetic-resonance imaging were demonstrated to be a useful tool in prostate cancer stratification.

show abstract

Deep Myometrial Infiltration of Endometrial Cancer on MRI: A Radiomics-Powered Machine Learning Pilot Study

Cited by 75 publications

References 34 publications

Whole‐Volume Tumor MRI Radiomics for Prognostic Modeling in Endometrial Cancer

Whole‐Volume Tumor MRI Radiomics for Prognostic Modeling in Endometrial Cancer

MRI-Based Radiomics Nomogram for Selecting Ovarian Preservation Treatment in Patients With Early-Stage Endometrial Cancer

A Combined Radiomics and Machine Learning Approach to Distinguish Clinically Significant Prostate Lesions on a Publicly Available MRI Dataset

Contact Info

Product

Resources

About