Multi-modal radiomics model based on four imaging modalities for predicting pathological complete response to neoadjuvant treatment in breast cancer DOI Creative Commons

Yuwen Liang,

Haonan Xu, Jie Lin

и другие.

BMC Cancer, Год журнала: 2025, Номер 25(1)

Опубликована: Июнь 2, 2025

The radiomics model based on single imaging modality has been demonstrated as a promising approach for predicting the response to neoadjuvant treatment (NAT) in breast cancer. However, whether integrating multiple modalities improve performance of is undetermined. This study aims develop multi-modal four modalities, including ultrasound (US), mammography (MM), computed tomography (CT), and magnetic resonance (MRI), pathological complete (pCR) cancer after NAT. Patients who underwent surgery NAT from January 2019 July 2023 were retrospectively studied. Univariate multivariate analyses performed identify independent clinical risk factors pCR. radiomic features extracted volume interest modalities. least absolute shrinkage selection operator was used developing signatures. developed by combining combined A nomogram visualize model. Model internally validated using five-fold cross-validation. In total, 89 patients included, with pCR rate 31.5% (28/89). Multivariate identified PR status (OR = 4.450, 95% confidence interval [CI], 1.228-18.063, P 0.028), HER2 9.95, CI, 1.525-201.894, 0.044) T stage 0.253, 0.076-0.753, 0.016) AUCs brier scores signatures US, MM, CT, MRI 0.702 (95% CI: 0.583-0.821), 0.762 0.660-0.865), 0.814 0.725-0.903), 0.787 0.685-0.889) 0.198, 0.177, 0.165, 0.170 respectively. superior all an AUC 0.904 0.838-0.970) score 0.111. After adding factors, further improved, achieving 0.943 0.893-0.992) 0.082. showed potential value. could accurately predict NAT, which Incorporating may muti-modal model, provide valuable information guiding decisions.

Язык: Английский

Intratumoral microbiota-aided fusion radiomics model for predicting tumor response to neoadjuvant chemoimmunotherapy in triple-negative breast cancer DOI Creative Commons
Yilin Chen, Yu‐Hong Huang, Wei Li

и другие.

Journal of Translational Medicine, Год журнала: 2025, Номер 23(1)

Опубликована: Март 20, 2025

Neoadjuvant chemoimmunotherapy (NACI) has emerged as the standard treatment for early-stage triple-negative breast cancer (TNBC). However, reliable biomarkers identifying patients who are likely to benefit from NACI lacking. This study aims develop an intratumoral microbiota-aided radiomics model predicting pathological complete response (pCR) in with TNBC. Intratumoral microbiota characterized by 16S rDNA sequencing and quantified through experimental assays. Single-cell RNA is performed analyze tumor microenvironment of tumors various responses NACI. Radiomics features extracted regions on longitudinal magnetic resonance images (MRIs) scanned before after training set. On basis (pCR or non-pCR) scoring, we select key construct a fusion integrating multi-timepoint (pre-NACI post-NACI) MRI predict efficacy immunotherapy, followed independent external validation. A total 124 enrolled, 88 set 36 validation Tumors achieves pCR present significantly greater load than achieve non-pCR (p < 0.05). Additionally, group exhibit infiltration tumor-associated SPP1+ macrophages, which negatively correlated load. 17 use them model. The highest AUC 0.945 set, outperforming pre-NACI (AUC = 0.875) post-NACI 0.917) models. In this maintains superior 0.873, surpassing those 0.769) 0.802) Clinically, distinguishes do not accuracy 77.8%. Decision curve analysis demonstrates net clinical across varying risk thresholds. Our could serve powerful noninvasive tool TNBC

Язык: Английский

Процитировано

0
Synthetic imaging for research and education in nuclear medicine: Who’s afraid of the black box? DOI
Luca Urso, Luigi Manco, Luca Filippi

и другие.

European Journal of Nuclear Medicine and Molecular Imaging, Год журнала: 2025, Номер unknown

Опубликована: Март 22, 2025

Язык: Английский

Процитировано

0
Dual-region MRI radiomic analysis indicates increased risk in high-risk breast lesions: bridging intratumoral and peritumoral radiomics for precision decision-making DOI Creative Commons
Yuting Yang, Tingting Liao, Xiaohui Lin

и другие.

BMC Cancer, Год журнала: 2025, Номер 25(1)

Опубликована: Май 6, 2025

To evaluate the clinical utility of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI)-derived clinicoradiological characteristics and intratumoral/peritumoral radiomic features in predicting pathological upgrades (malignant transformation) high-risk breast lesions. Retrospectively collected data 174 patients with lesions who underwent preoperative MRI examinations were confirmed by biopsy pathology Shenzhen People's Hospital between January 1, 2019 2024. The dataset was randomly divided into a training set (n = 121) test 53) at ratio 7:3. Initially, during second stage DCE-MRI, region interest (ROI) delineated along maximum cross-section lesion, then automatically expanded outward 3 mm, 5 7 mm as peritumoral ROIs. intratumoral, each peritumoral, combined intratumoral models established respectively. Independent risk factors predictive malignant identified through univariate multivariable logistic regression analyses, which subsequently incorporated characteristics. Finally, model integrating features. performance analyzed using receiver operating characteristic (ROC) curves, area under curve (AUC) calculated. radiomics achieved highest diagnostic among all models, AUC values 0.704 0.654 for sets, In set, showed (AUC 0.883), superior to that 0.745, P 0.003), 0.791, 0.027), 0.704, 0.001), 0.830, 0.004). also 0.851). constructed had best performance, sensitivity, specificity, accuracy 79.4%, 82.7%, 81.8% 72.7%, 85.7%, 83.0% model, integrates data, exhibited strong clinically applicable nomogram stratify individualized upgrade risk, assisting clinicians making more precise decisions.

Язык: Английский

Процитировано

0
18F-FDG PET/CT Radiomics for Predicting Therapy Response in Primary Mediastinal B-Cell Lymphoma: A Bi-Centric Pilot Study DOI Open Access
Fabiana Esposito, Luigi Manco, Luca Urso

и другие.

Cancers, Год журнала: 2025, Номер 17(11), С. 1827 - 1827

Опубликована: Май 30, 2025

Purpose: This bi-centric pilot study investigates the predictive value of pre-treatment [18F]FDG PET/CT radiomics for assessing therapy response in primary mediastinal B-cell lymphoma (PMBCL). Methods: All PMBCL patients underwent with between January 2011 and 2022 at Policlinico Tor Vergata University Hospital Rome (70% training 30% internal validation cohort) Sant’Anna Ferrara (external cohort). The Deauville score (DS) was used as a predictor (DS1-DS3 vs. DS4/DS5). A total 121 quantitative features (RFts) were extracted from manually segmented volumes interest (VOIs) PET CT images, according to IBSI. ComBat harmonization applied correct center variability features, followed by class balancing SMOTE. Two machine learning (ML) prediction models, model model, independently developed using robust RFts. For each ML two different algorithms trained (i.e., Random Forest, RF, Support Vector Machine, SVM) 10-fold cross validation, tested on internal/external set. Receiver operating characteristic (ROC) curves, area under curve (AUC), classification accuracy (CA), precision (Prec), sensitivity (Sen), specificity (Spec), true positive (TP) scores, negative (TN) scores computed. Results: entire dataset composed 29 samples cohort (23 D1–D3 6 D4/D5) 9 (4 5 D4/D5). 27 RFts identified imaging modality. Both models effectively predicted score. performance metrics best classifier (SVM) external AUC = 0.75/0.80, CA 0.85/0.77, Prec 0.97/0.67, Sen 0.60/0.80, Spec 0.98/0.75, TP 75.0%/66.7%, TN 77.8%/85.7%, respectively. Conclusions: radiomic PMBLC could predict

Язык: Английский

Процитировано

0
Multi-modal radiomics model based on four imaging modalities for predicting pathological complete response to neoadjuvant treatment in breast cancer DOI Creative Commons

Yuwen Liang,

Haonan Xu, Jie Lin

и другие.

BMC Cancer, Год журнала: 2025, Номер 25(1)

Опубликована: Июнь 2, 2025

The radiomics model based on single imaging modality has been demonstrated as a promising approach for predicting the response to neoadjuvant treatment (NAT) in breast cancer. However, whether integrating multiple modalities improve performance of is undetermined. This study aims develop multi-modal four modalities, including ultrasound (US), mammography (MM), computed tomography (CT), and magnetic resonance (MRI), pathological complete (pCR) cancer after NAT. Patients who underwent surgery NAT from January 2019 July 2023 were retrospectively studied. Univariate multivariate analyses performed identify independent clinical risk factors pCR. radiomic features extracted volume interest modalities. least absolute shrinkage selection operator was used developing signatures. developed by combining combined A nomogram visualize model. Model internally validated using five-fold cross-validation. In total, 89 patients included, with pCR rate 31.5% (28/89). Multivariate identified PR status (OR = 4.450, 95% confidence interval [CI], 1.228-18.063, P 0.028), HER2 9.95, CI, 1.525-201.894, 0.044) T stage 0.253, 0.076-0.753, 0.016) AUCs brier scores signatures US, MM, CT, MRI 0.702 (95% CI: 0.583-0.821), 0.762 0.660-0.865), 0.814 0.725-0.903), 0.787 0.685-0.889) 0.198, 0.177, 0.165, 0.170 respectively. superior all an AUC 0.904 0.838-0.970) score 0.111. After adding factors, further improved, achieving 0.943 0.893-0.992) 0.082. showed potential value. could accurately predict NAT, which Incorporating may muti-modal model, provide valuable information guiding decisions.

Язык: Английский

Процитировано

0