Multi-Level Multi-Modality Fusion Radiomics: Application to PET and CT Imaging for Prognostication of Head and Neck Cancer

Lv, Wenbing; Ashrafinia, Saeed; Ma, Jianhua; Lu, Lijun; Rahmim, Arman

doi:10.1109/jbhi.2019.2956354

Cited by 72 publications

(54 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the prediction of LR, no effective intra-tumoral features were found in either PET or CT images, which is consistent with the findings of Vallieres et al [11]. However, when integrating 4 clinical features or 3 CT_Peri_6 features to 3 CT_Intra features, models showed improved performance compared to any one of them alone, highlighting the supplementary information between different modalities [43] and intra-and peri-tumoral regions. In general, the performance of radiomics features in CT is better than that of in PET, we speculate that, PET image with lower resolution may limit its ability to capture effective texture features compared to CT image with higher resolution.…”

Section: Figure 4 (A-c) Receiver Operating Characteristic Curves (Roc) Comparison Of Selected Models As Listed In Table 3 (D-f) Kaplan-mesupporting

confidence: 87%

Complementary Value of Intra- and Peri-Tumoral PET/CT Radiomics for Outcome Prediction in Head and Neck Cancer

Feng

et al. 2021

IEEE Access

Self Cite

View full text Add to dashboard Cite

To investigate the prognostic value of peri-tumoral radiomics features of pre-treatment PET/CT images in patients with head and neck cancer. 166 patients from 4 centers (111 for training and 55 for external independent testing) were retrospectively analyzed. 11 regions were used for feature extraction, (1) Intra-tumoral region (Intra) was first dilated radially along the edge by 3, 6, 9, 12 and 15 mm to obtain (2) 5 solid combined regions (noted as Comb_3, 6, 9, 12, and 15, respectively), and (3) 5 hollow annular regions with equal ring width of 3 mm were then generated as peri-tumoral regions (noted as Peri_3, 6, 9, 12 and 15, respectively). 92 individual/integrated models were constructed by using features from Clinical alone, CT or PET alone, Clinical+PET, Clinical+CT, PET+CT, Clinical+PET+CT, Intra+Peri, Clinical+Intra+Peri and Clinical+PET+CT (Intra+Peri). In individual models, only 4 models showed p<0.05 (PET_Peri_3 and PET_Comb_6 for distant metastasis (DM) prediction, Clinical and PET_Peri_6 for death prediction). In integrated models, Clinical+CT (Intra+Peri_6), PET (Intra+Peri_3) and Clinical+PET_Peri_6 achieved the best performance for the prediction of local recurrence (LR), DM and death with AUC of 0.75, 0.80 and 0.87, C-index of 0.71, 0.80 and 0.83, p-value of 0.003, 0.008 and 0.001, respectively. Peri-tumoral regions that located closer to the intra-tumoral region (Peri_3 and Peri_6) showed better performance compared to those located further. The integration of intra-tumoral and peritumoral radiomics features achieved better performance than either of them alone, PET and CT radiomics features also provided complementary information to clinical features.

show abstract

Section: Figure 4 (A-c) Receiver Operating Characteristic Curves (Roc) Comparison Of Selected Models As Listed In Table 3 (D-f) Kaplan-mesupporting

confidence: 87%

Complementary Value of Intra- and Peri-Tumoral PET/CT Radiomics for Outcome Prediction in Head and Neck Cancer

Feng

et al. 2021

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…Combining features discretized with different widths/bin numbers can as shown in our study introduce complementary information and be a more reproducible and simple strategy as it also avoids the uncertain assumption or the extensive search of the optimal feature discretization width/bin number. Combining feature discretization schemes has also been done in previous studies [33][34].…”

Section: Discussionmentioning

confidence: 99%

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

Ferreira

Lovinfosse

Hermesse

et al. 2021

Preprint

View full text Add to dashboard Cite

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.

show abstract

“…Although multi-modality images indicated more valuable information, it was yet to be decided whether simply concatenate the multi-modality image features or fuse the multi-modality images to generate new image features. In the present studies, the feature concatenation and feature average methods were the most commonly used method for multi-modality fusion [ 8 – 10 ]. In addition, several studies attempted to integrate multi-modality images via the image fusion method [ 11 , 12 ].…”

Section: Introductionmentioning

confidence: 99%

PET/MR fusion texture analysis for the clinical outcome prediction in soft-tissue sarcoma

et al. 2022

View full text Add to dashboard Cite

Background Various fusion strategies (feature-level fusion, matrix-level fusion, and image-level fusion) were used to fuse PET and MR images, which might lead to different feature values and classification performance. The purpose of this study was to measure the classification capability of features extracted using various PET/MR fusion methods in a dataset of soft-tissue sarcoma (STS). Methods The retrospective dataset included 51 patients with histologically proven STS. All patients had pre-treatment PET and MR images. The image-level fusion was conducted using discrete wavelet transformation (DWT). During the DWT process, the MR weight was set as 0.1, 0.2, 0.3, 0.4, …, 0.9. And the corresponding PET weight was set as 1- (MR weight). The fused PET/MR images was generated using the inverse DWT. The matrix-level fusion was conducted by fusing the feature calculation matrix during the feature extracting process. The feature-level fusion was conducted by concatenating and averaging the features. We measured the predictive performance of features using univariate analysis and multivariable analysis. The univariate analysis included the Mann-Whitney U test and receiver operating characteristic (ROC) analysis. The multivariable analysis was used to develop the signatures by jointing the maximum relevance minimum redundancy method and multivariable logistic regression. The area under the ROC curve (AUC) value was calculated to evaluate the classification performance. Results By using the univariate analysis, the features extracted using image-level fusion method showed the optimal classification performance. For the multivariable analysis, the signatures developed using the image-level fusion-based features showed the best performance. For the T1/PET image-level fusion, the signature developed using the MR weight of 0.1 showed the optimal performance (0.9524(95% confidence interval (CI), 0.8413–0.9999)). For the T2/PET image-level fusion, the signature developed using the MR weight of 0.3 showed the optimal performance (0.9048(95%CI, 0.7356–0.9999)). Conclusions For the fusion of PET/MR images in patients with STS, the signatures developed using the image-level fusion-based features showed the optimal classification performance than the signatures developed using the feature-level fusion and matrix-level fusion-based features, as well as the single modality features. The image-level fusion method was more recommended to fuse PET/MR images in future radiomics studies.

show abstract

Multi-Level Multi-Modality Fusion Radiomics: Application to PET and CT Imaging for Prognostication of Head and Neck Cancer

Cited by 72 publications

References 41 publications

Complementary Value of Intra- and Peri-Tumoral PET/CT Radiomics for Outcome Prediction in Head and Neck Cancer

Complementary Value of Intra- and Peri-Tumoral PET/CT Radiomics for Outcome Prediction in Head and Neck Cancer

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

PET/MR fusion texture analysis for the clinical outcome prediction in soft-tissue sarcoma

Contact Info

Product

Resources

About