scholarly journals Assessing PD-L1 Expression Status Using Radiomic Features from Contrast-Enhanced Breast MRI in Breast Cancer Patients: Initial Results

Cancers ◽  
2021 ◽  
Vol 13 (24) ◽  
pp. 6273
Author(s):  
Roberto Lo Gullo ◽  
Hannah Wen ◽  
Jeffrey S. Reiner ◽  
Raza Hoda ◽  
Varadan Sevilimedu ◽  
...  

The purpose of this retrospective study was to assess whether radiomics analysis coupled with machine learning (ML) based on standard-of-care dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) can predict PD-L1 expression status in patients with triple negative breast cancer, and to compare the performance of this approach with radiologist review. Patients with biopsy-proven triple negative breast cancer who underwent pre-treatment breast MRI and whose PD-L1 status was available were included. Following 3D tumor segmentation and extraction of radiomic features, radiomic features with significant differences between PD-L1+ and PD-L1− patients were determined, and a final predictive model to predict PD-L1 status was developed using a coarse decision tree and five-fold cross-validation. Separately, all lesions were qualitatively assessed by two radiologists independently according to the BI-RADS lexicon. Of 62 women (mean age 47, range 31–81), 27 had PD-L1− tumors and 35 had PD-L1+ tumors. The final radiomics model to predict PD-L1 status utilized three MRI parameters, i.e., variance (FO), run length variance (RLM), and large zone low grey level emphasis (LZLGLE), for a sensitivity of 90.7%, specificity of 85.1%, and diagnostic accuracy of 88.2%. There were no significant associations between qualitative assessed DCE-MRI imaging features and PD-L1 status. Thus, radiomics analysis coupled with ML based on standard-of-care DCE-MRI is a promising approach to derive prognostic and predictive information and to select patients who could benefit from anti-PD-1/PD-L1 treatment.

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Ayane Yamaguchi ◽  
Maya Honda ◽  
Hiroshi Ishiguro ◽  
Masako Kataoka ◽  
Tatsuki R. Kataoka ◽  
...  

AbstractThis study aimed to evaluate the predictions of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) for prognosis of triple-negative breast cancer (TNBC), especially with residual disease (RD) after preoperative chemotherapy. This retrospective analysis included 74 TNBC patients who received preoperative chemotherapy. DCE-MRI findings from three timepoints were examined: at diagnosis (MRIpre), at midpoint (MRImid) and after chemotherapy (MRIpost). These findings included cancer lesion size, washout index (WI) as a kinetic parameter using the difference in signal intensity between early and delayed phases, and time-signal intensity curve types. Distant disease-free survival was analysed using the log-rank test to compare RD group with and without a fast-washout curve. The diagnostic performance of DCE-MRI findings, including positive predictive value (PPV) for pathological responses, was also calculated. RD without fast washout curve was a significantly better prognostic factor, both at MRImid and MRIpost (hazard ratio = 0.092, 0.098, p < 0.05). PPV for pathological complete remission at MRImid was 76.7% by the cut-off point at negative WI value or lesion size = 0, and 66.7% at lesion size = 0. WI and curve types derived from DCE-MRI at the midpoint of preoperative chemotherapy can help not only assess tumour response but also predict prognosis.


2012 ◽  
Vol 12 (5) ◽  
pp. 331-339 ◽  
Author(s):  
Melania Costantini ◽  
Paolo Belli ◽  
Daniela Distefano ◽  
Enida Bufi ◽  
Marialuisa Di Matteo ◽  
...  

2014 ◽  
Vol 25 (3) ◽  
pp. 474-481 ◽  
Author(s):  
Ren-Hua Yeh ◽  
Jyh-Cherng Yu ◽  
Chi-Hong Chu ◽  
Ching-Liang Ho ◽  
Hung-Wen Kao ◽  
...  

2020 ◽  
Vol 30 (6) ◽  
pp. 3363-3370
Author(s):  
Taiyo L. Harada ◽  
Takayoshi Uematsu ◽  
Kazuaki Nakashima ◽  
Takashi Sugino ◽  
Seiichirou Nishimura ◽  
...  

2020 ◽  
Vol 2020 ◽  
pp. 1-9
Author(s):  
Karima Oualla ◽  
Loay Kassem ◽  
Lamiae Nouiakh ◽  
Lamiae Amaadour ◽  
Zineb Benbrahim ◽  
...  

Triple-negative breast cancer (TNBC) is characterized by the absence of estrogen receptor (ER), progesterone receptor (PR), and human epidermal growth factor receptor 2 (HER2). It accounts for 15%–20% of all breast cancers and is associated with an aggressive evolution and poor outcomes with the majority of recurrences and deaths occurring in the first 5 years. Chemotherapy remains the mainstay of treatment in the absence of effective targets, but the good understanding of immune tumor microenvironment, the identification of immune-related targets, and the role of tumor-infiltrating lymphocytes (TILs) in TNBC has allowed to develop promising immunotherapeutic strategies for this unique subset of breast cancer. Recently, immunotherapy is being extensively explored in TNBC and clinical trials have shown promising results. In this article, we tried to explain the rationale and mechanisms of targeting the immune system in TNBC, to report the results from recent clinical trials that put immunotherapy as a new standard of care in TNBC in addition to ongoing trials and future directions in the next decade.


2021 ◽  
Vol 11 ◽  
Author(s):  
Yongxia Zhang ◽  
Fengjie Liu ◽  
Han Zhang ◽  
Heng Ma ◽  
Jian Sun ◽  
...  

PurposeTo evaluate the value of radiomics analysis in contrast-enhanced spectral mammography (CESM) for the identification of triple-negative breast cancer (TNBC).MethodCESM images of 367 pathologically confirmed breast cancer patients (training set: 218, testing set: 149) were retrospectively analyzed. Cranial caudal (CC), mediolateral oblique (MLO), and combined models were built on the basis of the features extracted from subtracted images on CC, MLO, and the combination of CC and MLO, respectively, in the tumour region. The performance of the models was evaluated through receiver operating characteristic (ROC) curve analysis, the Hosmer-Lemeshow test, and decision curve analysis (DCA). The areas under ROC curves (AUCs) were compared through the DeLong test.ResultsThe combined CC and MLO model had the best AUC and sensitivity of 0.90 (95% confidence interval: 0.85–0.96) and 0.97, respectively. The Hosmer–Lemeshow test yielded a non-significant statistic with p-value of 0.59. The clinical usefulness of the combined CC and MLO model was confirmed if the threshold was between 0.02 and 0.81 in the DCA.ConclusionsMachine learning models based on subtracted images in CESM images were valuable for distinguishing TNBC and NTNBC. The model with the combined CC and MLO features had the best performance compared with models that used CC or MLO features alone.


Sign in / Sign up

Export Citation Format

Share Document