Hybrid descriptive‐inferential method for key feature selection in prostate cancer radiomics

Barone, Stefano; Cannella, Roberto; Comelli, Albert; Pellegrino, A.; Salvaggio, Giuseppe; Stefano, Alessandro; Vernuccio, Federica

doi:10.1002/asmb.2642

Cited by 31 publications

(28 citation statements)

References 33 publications

(70 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In that way, the robustness of radiomics features can be evaluated after co-registration. Spearman's rank correlation coefficient, which belongs to the filter method group [25], is used to assess whether there is any association between two observed features and to estimate the strength of this relationship. In this way, it is possible to eliminate all features whose level of correlation is above a user-specified threshold.…”

Section: Feature Selection and Analysismentioning

confidence: 99%

“…For this reason, seventeen glioblastoma patients who underwent both MET-PET and MRI between a time range of three years (2016-2019) were used for our analysis by extracting radiomics features grouped into shape, first-and higher-order features. Usually, the feature extraction task is one of the five fundamental tasks of a radiomics workflow [25] together with image acquisition, target segmentation, feature selection, and implementation of the classification model to predict the clinical outcome. Nevertheless, our study will omit the final task focusing on the first four steps by newly adding the PET/MRI co-registration prior to the feature extraction process to evaluate its impact in a radiomics study.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Robustness of PET Radiomics Features: Impact of Co-Registration with MRI

et al. 2021

Self Cite

View full text Add to dashboard Cite

Radiomics holds great promise in the field of cancer management. However, the clinical application of radiomics has been hampered by uncertainty about the robustness of the features extracted from the images. Previous studies have reported that radiomics features are sensitive to changes in voxel size resampling and interpolation, image perturbation, or slice thickness. This study aims to observe the variability of positron emission tomography (PET) radiomics features under the impact of co-registration with magnetic resonance imaging (MRI) using the difference percentage coefficient, and the Spearman’s correlation coefficient for three groups of images: (i) original PET, (ii) PET after co-registration with T1-weighted MRI and (iii) PET after co-registration with FLAIR MRI. Specifically, seventeen patients with brain cancers undergoing [11C]-Methionine PET were considered. Successively, PET images were co-registered with MRI sequences and 107 features were extracted for each mentioned group of images. The variability analysis revealed that shape features, first-order features and two subgroups of higher-order features possessed a good robustness, unlike the remaining groups of features, which showed large differences in the difference percentage coefficient. Furthermore, using the Spearman’s correlation coefficient, approximately 40% of the selected features differed from the three mentioned groups of images. This is an important consideration for users conducting radiomics studies with image co-registration constraints to avoid errors in cancer diagnosis, prognosis, and clinical outcome prediction.

show abstract

Section: Feature Selection and Analysismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Robustness of PET Radiomics Features: Impact of Co-Registration with MRI

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…All the features (imaging and clinical) were correlated with the response data. Specifically, due to the redundancy, heterogeneity, and uncertainty of the information represented by the radiomics features, we used an innovative mixed descriptive-inferential sequential approach [ 27 , 28 ] for the feature selection and reduction process. For each feature, the point biserial correlation (pbc) index between features and the dichotomic outcome (PD vs. SD, PR, CR) was calculated, sorting the features in pbc descending order.…”

Section: Methodsmentioning

confidence: 99%

[68Ga]DOTATOC PET/CT Radiomics to Predict the Response in GEP-NETs Undergoing [177Lu]DOTATOC PRRT: The “Theragnomics” Concept

Laudicella

Comelli

Liberini

et al. 2022

Cancers

Self Cite

View full text Add to dashboard Cite

Despite impressive results, almost 30% of NET do not respond to PRRT and no well-established criteria are suitable to predict response. Therefore, we assessed the predictive value of radiomics [68Ga]DOTATOC PET/CT images pre-PRRT in metastatic GEP NET. We retrospectively analyzed the predictive value of radiomics in 324 SSTR-2-positive lesions from 38 metastatic GEP-NET patients (nine G1, 27 G2, and two G3) who underwent restaging [68Ga]DOTATOC PET/CT before complete PRRT with [177Lu]DOTATOC. Clinical, laboratory, and radiological follow-up data were collected for at least six months after the last cycle. Through LifeX, we extracted 65 PET features for each lesion. Grading, PRRT number of cycles, and cumulative activity, pre- and post-PRRT CgA values were also considered as additional clinical features. [68Ga]DOTATOC PET/CT follow-up with the same scanner for each patient determined the disease status (progression vs. response in terms of stability/reduction/disappearance) for each lesion. All features (PET and clinical) were also correlated with follow-up data in a per-site analysis (liver, lymph nodes, and bone), and for features significantly associated with response, the Δradiomics for each lesion was assessed on follow-up [68Ga]DOTATOC PET/CT performed until nine months post-PRRT. A statistical system based on the point-biserial correlation and logistic regression analysis was used for the reduction and selection of the features. Discriminant analysis was used, instead, to obtain the predictive model using the k-fold strategy to split data into training and validation sets. From the reduction and selection process, HISTO_Skewness and HISTO_Kurtosis were able to predict response with an area under the receiver operating characteristics curve (AUC ROC), sensitivity, and specificity of 0.745, 80.6%, 67.2% and 0.722, 61.2%, 75.9%, respectively. Moreover, a combination of three features (HISTO_Skewness; HISTO_Kurtosis, and Grading) did not improve the AUC significantly with 0.744. SUVmax. However, it could not predict response to PRRT (p = 0.49, AUC 0.523). The presented preliminary “theragnomics” model proved to be superior to conventional quantitative parameters to predict the response of GEP-NET lesions in patients treated with complete [177Lu]DOTATOC PRRT, regardless of the lesion site.

show abstract

“…Many feature selection techniques have been developed in the domain of ML. They can be generally categorized into three approaches: filter, wrapper, and embedded [45][46][47][48][49]. A wrapper approach is applied in this framework.…”

Section: Feature Integration and Selectionmentioning

confidence: 99%

A New Framework for Precise Identification of Prostatic Adenocarcinoma

Ayyad

Badawy

Shehata

et al. 2022

Sensors

View full text Add to dashboard Cite

Prostate cancer, which is also known as prostatic adenocarcinoma, is an unconstrained growth of epithelial cells in the prostate and has become one of the leading causes of cancer-related death worldwide. The survival of patients with prostate cancer relies on detection at an early, treatable stage. In this paper, we introduce a new comprehensive framework to precisely differentiate between malignant and benign prostate cancer. This framework proposes a noninvasive computer-aided diagnosis system that integrates two imaging modalities of MR (diffusion-weighted (DW) and T2-weighted (T2W)). For the first time, it utilizes the combination of functional features represented by apparent diffusion coefficient (ADC) maps estimated from DW-MRI for the whole prostate in combination with texture features with its first- and second-order representations, extracted from T2W-MRIs of the whole prostate, and shape features represented by spherical harmonics constructed for the lesion inside the prostate and integrated with PSA screening results. The dataset presented in the paper includes 80 biopsy confirmed patients, with a mean age of 65.7 years (43 benign prostatic hyperplasia, 37 prostatic carcinomas). Experiments were conducted using different well-known machine learning approaches including support vector machines (SVM), random forests (RF), decision trees (DT), and linear discriminant analysis (LDA) classification models to study the impact of different feature sets that lead to better identification of prostatic adenocarcinoma. Using a leave-one-out cross-validation approach, the diagnostic results obtained using the SVM classification model along with the combined feature set after applying feature selection (88.75% accuracy, 81.08% sensitivity, 95.35% specificity, and 0.8821 AUC) indicated that the system’s performance, after integrating and reducing different types of feature sets, obtained an enhanced diagnostic performance compared with each individual feature set and other machine learning classifiers. In addition, the developed diagnostic system provided consistent diagnostic performance using 10-fold and 5-fold cross-validation approaches, which confirms the reliability, generalization ability, and robustness of the developed system.

show abstract

Hybrid descriptive‐inferential method for key feature selection in prostate cancer radiomics

Cited by 31 publications

References 33 publications

Robustness of PET Radiomics Features: Impact of Co-Registration with MRI

Robustness of PET Radiomics Features: Impact of Co-Registration with MRI

[68Ga]DOTATOC PET/CT Radiomics to Predict the Response in GEP-NETs Undergoing [177Lu]DOTATOC PRRT: The “Theragnomics” Concept

A New Framework for Precise Identification of Prostatic Adenocarcinoma

Contact Info

Product

Resources

About