Performance of radiomics models for tumour-infiltrating lymphocyte (TIL) prediction in breast cancer: the role of the dynamic contrast-enhanced (DCE) MRI phase

Tang, Wenjie; Kong, Qingcong; Cheng, Zixuan; Liang, Yongquan; Jin, Zhe; Chen, Lei-Xin; Hu, Wen-Ke; Liang, Yingying; Wei, Xinhua; Guo, Yuan; Jiang, Xinqing

doi:10.1007/s00330-021-08173-5

Cited by 21 publications

(14 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, the analysis included 25 from among 6250 initial radiology features. Contrary to previous studies, considering the role of clinical factors (Ki-67 values and estrogen receptor values) did not improve the efficacy of predicting models [ 65 ].…”

Section: Breast Cancercontrasting

confidence: 73%

Tumor infiltrating lymphocytes and radiological picture of the tumor

et al. 2023

View full text Add to dashboard Cite

Tumor microenvironment (TME) is a complex entity that includes besides the tumor cells also a whole range of immune cells. Among various populations of immune cells infiltrating the tumor, tumor infiltrating lymphocytes (TILs) are a population of lymphocytes characterized by high reactivity against the tumor component. As, TILs play a key role in mediating responses to several types of therapy and significantly improve patient outcomes in some cancer types including for instance breast cancer and lung cancer, their assessment has become a good predictive tool in the evaluation of potential treatment efficacy. Currently, the evaluation of the density of TILs infiltration is performed by histopathological. However, recent studies have shed light on potential utility of several imaging methods, including ultrasonography, magnetic resonance imaging (MRI), positron emission tomography-computed tomography (PET-CT), and radiomics, in the assessment of TILs levels. The greatest attention concerning the utility of radiology methods is directed to breast and lung cancers, nevertheless imaging methods of TILs are constantly being developed also for other malignancies. Here, we focus on reviewing the radiological methods used to assess the level of TILs in different cancer types and on the extraction of the most favorable radiological features assessed by each method.

show abstract

Section: Breast Cancercontrasting

confidence: 73%

Tumor infiltrating lymphocytes and radiological picture of the tumor

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Currently, the status of the tumor microenvironment can be evaluated only once on histological specimens after surgery, and the assessment accuracy might be limited by the heterogeneity of biopsy. Previous studies have discovered that radiomic features, reflecting subtle homogeneity or heterogeneity utilizing the gray-level run length matrix, are associated with the expression of TILs ( 43 , 44 ). Radiomic analysis also achieved satisfactory performance for the prediction of clinical outcomes of immunotherapy patients across multiple cancers ( 45 – 47 ).…”

Section: Discussionmentioning

confidence: 99%

Crosstalk Between Metabolism and Immune Activity Reveals Four Subtypes With Therapeutic Implications in Clear Cell Renal Cell Carcinoma

et al. 2022

View full text Add to dashboard Cite

Clear cell renal cell carcinoma (ccRCC) is characterized by metabolic dysregulation and distinct immunological signatures. The interplay between metabolic and immune processes in the tumor microenvironment (TME) causes the complexity and heterogeneity of immunotherapy responses observed during ccRCC treatment. Herein, we initially identified two distinct metabolic subtypes (C1 and C2 subtypes) and immune subtypes (I1 and I2 subtypes) based on the occurrence of differentially expressed metabolism-related prognostic genes and immune-related components. Notably, we observed that immune regulators with upregulated expression actively participated in multiple metabolic pathways. Therefore, we further delineated four immunometabolism-based ccRCC subtypes (M1, M2, M3, and M4 subtypes) according to the results of the above classification. Generally, we found that high metabolic activity could suppress immune infiltration. Immunometabolism subtype classification was associated with immunotherapy response, with patients possessing the immune-inflamed, metabolic-desert subtype (M3 subtype) that benefits the most from immunotherapy. Moreover, differences in the shifts in the immunometabolism subtype after immunotherapy were observed in the responder and non-responder groups, with patients from the responder group transferring to subtypes with immune-inflamed characteristics and less active metabolic activity (M3 or M4 subtype). Immunometabolism subtypes could also serve as biomarkers for predicting immunotherapy response. To decipher the genomic and epigenomic features of the four subtypes, we analyzed multiomics data, including miRNA expression, DNA methylation status, copy number variations occurrence, and somatic mutation profiles. Patients with the M2 subtype possessed the highest VHL gene mutation rates and were more likely to be sensitive to sunitinib therapy. Moreover, we developed non-invasive radiomic models to reveal the status of immune activity and metabolism. In addition, we constructed a radiomic prognostic score (PRS) for predicting ccRCC survival based on the seven radiomic features. PRS was further demonstrated to be closely linked to immunometabolism subtype classification, immune score, and tumor mutation burden. The prognostic value of the PRS and the association of the PRS with immune activity and metabolism were validated in our cohort. Overall, our study established four immunometabolism subtypes, thereby revealing the crosstalk between immune and metabolic activities and providing new insights into personal therapy selection.

show abstract

“…Song et al [ 28 ] extracted features from the second contrast-enhanced phase with an AUC of 0.805. For tumor-infiltrating lymphocyte (TIL) prediction, Tang et al [ 29 ] found that image features extracted from the delayed phases can help improve the model performance. Therefore, both the second and fourth contrast-enhanced phases were used in our study, and we also found that the model of dyn4 exceeded the model of dyn2 in identifying ALNM, and the final formula of the rad-score contained more features from dyn4 than dyn2.…”

Section: Discussionmentioning

confidence: 99%

Deep Learning Radiomics of Preoperative Breast MRI for Prediction of Axillary Lymph Node Metastasis in Breast Cancer

et al. 2023

View full text Add to dashboard Cite

The objective of this study is to develop a radiomic signature constructed from deep learning features and a nomogram for prediction of axillary lymph node metastasis (ALNM) in breast cancer patients. Preoperative magnetic resonance imaging data from 479 breast cancer patients with 488 lesions were studied. The included patients were divided into two cohorts by time (training/testing cohort, n = 366/122). Deep learning features were extracted from diffusion-weighted imaging–quantitatively measured apparent diffusion coefficient (DWI-ADC) imaging and dynamic contrast-enhanced MRI (DCE-MRI) by a pretrained neural network of DenseNet121. After the selection of both radiomic and clinicopathological features, deep learning signature and a nomogram were built for independent validation. Twenty-three deep learning features were automatically selected in the training cohort to establish the deep learning signature of ALNM. Three clinicopathological factors, including LN palpability (odds ratio (OR) = 6.04; 95% confidence interval (CI) = 3.06–12.54, P = 0.004), tumor size in MRI (OR = 1.45, 95% CI = 1.18–1.80, P = 0.104), and Ki-67 (OR = 1.01; 95% CI = 1.00–1.02, P = 0.099), were selected and combined with radiomic signature to build a combined nomogram. The nomogram showed excellent predictive ability for ALNM (AUC 0.80 and 0.71 in training and testing cohorts, respectively). The sensitivity, specificity, and accuracy were 65%, 80%, and 75%, respectively, in the testing cohort. MRI-based deep learning radiomics in patients with breast cancer could be used to predict ALNM, providing a noninvasive approach to structuring the treatment strategy. Supplementary Information The online version contains supplementary material available at 10.1007/s10278-023-00818-9.

show abstract

Performance of radiomics models for tumour-infiltrating lymphocyte (TIL) prediction in breast cancer: the role of the dynamic contrast-enhanced (DCE) MRI phase

Cited by 21 publications

References 34 publications

Tumor infiltrating lymphocytes and radiological picture of the tumor

Tumor infiltrating lymphocytes and radiological picture of the tumor

Crosstalk Between Metabolism and Immune Activity Reveals Four Subtypes With Therapeutic Implications in Clear Cell Renal Cell Carcinoma

Deep Learning Radiomics of Preoperative Breast MRI for Prediction of Axillary Lymph Node Metastasis in Breast Cancer

Contact Info

Product

Resources

About