MRI-Based Radiomics Analysis for the Pretreatment Prediction of Pathologic Complete Tumor Response to Neoadjuvant Systemic Therapy in Breast Cancer Patients: A Multicenter Study

Granzier, R.; Ibrahim, Abdalla; Primakov, Sergey; Samiei, Sanaz; Nijnatten, Thiemo J A van; Boer, Maaike de; Heuts, E. M.; Hulsmans, F J; Chatterjee, A.; Lambin, Philippe; Lobbes, Marc; Woodruff, Henry C.; Smidt, Marjolein L.

doi:10.3390/cancers13102447

Cited by 26 publications

(16 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study, we used routine contrast-enhanced CT and clinical data to build a prediction model with high accuracy (AUC 0.87). Compared to previous studies using MRI (AUC from 0.52 to 0.98) or PET/CT (AUC from 0.70 to 0.73) [ 8 , 9 , 10 , 11 , 12 , 13 , 14 , 15 , 16 ], pCR could be predicted from the available images without any additional imaging studies, saving significant costs (time and money). Use of a relatively large sample size and the standardized radiomics feature definition and extraction process are additional strengths of this study, rendering this process more reproducible and comparable.…”

Section: Discussionmentioning

confidence: 86%

“…Several studies have also investigated the value of breast MRI for the a priori prediction of treatment response to NST, where a combination of radiomics and deep learning methods was used to build prediction models. However, the results varied significantly, with AUC ranging from 0.52 to 0.98 [ 10 , 11 , 12 , 13 , 14 , 15 , 16 ]. Because of the variations in pulse sequence selection, image acquisition, reconstruction parameters, and feature extraction, the performance of MR-based prediction models is limited due to a lack of reproducibility and generalizability.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Integration of Clinical and CT-Based Radiomic Features for Pretreatment Prediction of Pathologic Complete Response to Neoadjuvant Systemic Therapy in Breast Cancer

Tsai

et al. 2022

Cancers

View full text Add to dashboard Cite

The purpose of the present study was to examine the potential of a machine learning model with integrated clinical and CT-based radiomics features in predicting pathologic complete response (pCR) to neoadjuvant systemic therapy (NST) in breast cancer. Contrast-enhanced CT was performed in 329 patients with breast tumors (n = 331) before NST. Pyradiomics was used for feature extraction, and 107 features of seven classes were extracted. Feature selection was performed on the basis of the intraclass correlation coefficient (ICC), and six ICC thresholds (0.7–0.95) were examined to identify the feature set resulting in optimal model performance. Clinical factors, such as age, clinical stage, cancer cell type, and cell surface receptors, were used for prediction. We tried six machine learning algorithms, and clinical, radiomics, and clinical–radiomics models were trained for each algorithm. Radiomics and clinical–radiomics models with gray level co-occurrence matrix (GLCM) features only were also built for comparison. The linear support vector machine (SVM) regression model trained with radiomics features of ICC ≥0.85 in combination with clinical factors performed the best (AUC = 0.87). The performance of the clinical and radiomics linear SVM models showed statistically significant difference after correction for multiple comparisons (AUC = 0.69 vs. 0.78; p < 0.001). The AUC of the radiomics model trained with GLCM features was significantly lower than that of the radiomics model trained with all seven classes of radiomics features (AUC = 0.85 vs. 0.87; p = 0.011). Integration of clinical and CT-based radiomics features was helpful in the pretreatment prediction of pCR to NST in breast cancer.

show abstract

Section: Discussionmentioning

confidence: 86%

Section: Introductionmentioning

confidence: 99%

Integration of Clinical and CT-Based Radiomic Features for Pretreatment Prediction of Pathologic Complete Response to Neoadjuvant Systemic Therapy in Breast Cancer

Tsai

et al. 2022

Cancers

View full text Add to dashboard Cite

show abstract

“…Dataset 2. Dataset 2 consists of the images from 134 subjects with histologically confirmed invasive breast cancer imaged between 2011 and 2017 in Maastricht University Medical Cen-ter+ and collected retrospectively (Granzier et al (2020(Granzier et al ( , 2021).…”

Section: Datasetsmentioning

confidence: 99%

MSCDA: Multi-level Semantic-guided Contrast Improves Unsupervised Domain Adaptation for Breast MRI Segmentation in Small Datasets

Sheng¹,

Woodruff²,

Granzier³

et al. 2023

Preprint

View full text Add to dashboard Cite

Deep learning (DL) applied to breast tissue segmentation in magnetic resonance imaging (MRI) has received increased attention in the last decade, however, the domain shift which arises from different vendors, acquisition protocols, and biological heterogeneity, remains an important but challenging obstacle on the path towards clinical implementation. Recently, unsupervised domain adaptation (UDA) methods have attempted to mitigate this problem by incorporating self-training with contrastive learning. To better exploit the underlying semantic information of the image at different levels, we propose a Multi-level Semantic-guided Contrastive Domain Adaptation (MSCDA) framework to align the feature representation between domains. In particular, we extend the contrastive loss by incorporating pixel-to-pixel, pixel-to-centroid, and centroid-to-centroid contrasts to integrate semantic information of images. We utilize a category-wise cross-domain sampling strategy to sample anchors from target images and build a hybrid memory bank to store samples from source images. Two breast MRI datasets were retrospectively collected: The source dataset contains non-contrast MRI examinations from 11 healthy volunteers and the target dataset contains contrast-enhanced MRI examinations of 134 invasive breast cancer patients. We set up experiments from source T2W image to target dynamic contrast-enhanced (DCE)-T1W image (T2W-to-T1W) and from source T1W image to target T2W image (T1W-to-T2W). The proposed method achieved Dice similarity coefficient (DSC) of 89.2% and 84.0% in T2W-to-T1W and T1W-to-T2W, respectively, outperforming state-of-the-art methods. Notably, good performance is still achieved with a smaller source dataset, proving that our framework is label-efficient.

show abstract

“…Nevertheless, we do agree that the relationship of MRI-structure-based analysis and BRAF V600E mutation was likely worth studying even further in order to improve the potential pretreatment medication needed detected by MRI-based prediction in patients with cancer or carcinoma such as PTC. 6 , 7…”

Section: Dear Editormentioning

confidence: 99%

Thoughtful Response on “MRI-based Texture Analysis for Preoperative Prediction of BRAF V600E Mutation in Papillary Thyroid Carcinoma” [Letter]

Panjaitan¹,

Lestari²,

Maha³

2023

JMDH

View full text Add to dashboard Cite

MRI-Based Radiomics Analysis for the Pretreatment Prediction of Pathologic Complete Tumor Response to Neoadjuvant Systemic Therapy in Breast Cancer Patients: A Multicenter Study

Cited by 26 publications

References 59 publications

Integration of Clinical and CT-Based Radiomic Features for Pretreatment Prediction of Pathologic Complete Response to Neoadjuvant Systemic Therapy in Breast Cancer

Integration of Clinical and CT-Based Radiomic Features for Pretreatment Prediction of Pathologic Complete Response to Neoadjuvant Systemic Therapy in Breast Cancer

MSCDA: Multi-level Semantic-guided Contrast Improves Unsupervised Domain Adaptation for Breast MRI Segmentation in Small Datasets

Thoughtful Response on “MRI-based Texture Analysis for Preoperative Prediction of BRAF V600E Mutation in Papillary Thyroid Carcinoma” [Letter]

Contact Info

Product

Resources

About