RESUMO
Determining histological subtypes, such as invasive ductal and invasive lobular carcinomas (IDCs and ILCs) and immunohistochemical markers, such as estrogen response (ER), progesterone response (PR), and the HER2 protein status is important in planning breast cancer treatment. MRI-based radiomic analysis is emerging as a non-invasive substitute for biopsy to determine these signatures. We explore the effectiveness of radiomics-based and CNN (convolutional neural network)-based classification models to this end. T1-weighted dynamic contrast-enhanced, contrast-subtracted T1, and T2-weighted MR images of 429 breast cancer tumors from 323 patients are used. Various combinations of input data and classification schemes are applied for ER+ vs. ER-, PR+ vs. PR-, HER2+ vs. HER2-, and IDC vs. ILC classification tasks. The best results were obtained for the ER+ vs. ER- and IDC vs. ILC classification tasks, with their respective AUCs reaching 0.78 and 0.73 on test data. The results with multi-contrast input data were generally better than the mono-contrast alone. The radiomics and CNN-based approaches generally exhibited comparable results. ER and IDC/ILC classification results were promising. PR and HER2 classifications need further investigation through a larger dataset. Better results by using multi-contrast data might indicate that multi-parametric quantitative MRI could be used to achieve more reliable classifiers.
RESUMO
Introduction: In this study, we aim to build radiomics and multiomics models based on transcriptomics and radiomics to predict the response from patients treated with the PD-L1 inhibitor. Materials and methods: One hundred and ninety-five patients treated with PD-1/PD-L1 inhibitors were included. For all patients, 342 radiomic features were extracted from pretreatment computed tomography scans. The training set was built with 110 patients treated at the Léon Bérard Cancer Center. An independent validation cohort was built with the 85 patients treated in Dijon. The two sets were dichotomized into two classes, patients with disease control and those considered non-responders, in order to predict the disease control at 3 months. Various models were trained with different feature selection methods, and different classifiers were evaluated to build the models. In a second exploratory step, we used transcriptomics to enrich the database and develop a multiomic signature of response to immunotherapy in a 54-patient subgroup. Finally, we considered the HOT/COLD status. We first trained a radiomic model to predict the HOT/COLD status and then prototyped a hybrid model integrating radiomics and the HOT/COLD status to predict the response to immunotherapy. Results: Radiomic signature for 3 months' progression-free survival (PFS) classification: The most predictive model had an area under the receiver operating characteristic curve (AUROC) of 0.94 on the training set and 0.65 on the external validation set. This model was obtained with the t-test selection method and with a support vector machine (SVM) classifier. Multiomic signature for PFS classification: The most predictive model had an AUROC of 0.95 on the training set and 0.99 on the validation set. Radiomic model to predict the HOT/COLD status: the most predictive model had an AUROC of 0.93 on the training set and 0.86 on the validation set. HOT/COLD radiomic hybrid model for PFS classification: the most predictive model had an AUROC of 0.93 on the training set and 0.90 on the validation set. Conclusion: In conclusion, radiomics could be used to predict the response to immunotherapy in non-small-cell lung cancer patients. The use of transcriptomics or the HOT/COLD status, together with radiomics, may improve the working of the prediction models.
RESUMO
BACKGROUND: Overweight and obesity are major worldwide health concerns characterized by an abnormal accumulation of fat in adipose tissue (AT) and liver. PURPOSE: To evaluate the volume and the fatty acid (FA) composition of the subcutaneous adipose tissue (SAT) and the visceral adipose tissue (VAT) and the fat content in the liver from 3D chemical-shift-encoded (CSE)-MRI acquisition, before and after a 31-day overfeeding protocol. STUDY TYPE: Prospective and longitudinal study. SUBJECTS: Twenty-one nonobese healthy male volunteers. FIELD STRENGTH/SEQUENCE: A 3D spoiled-gradient multiple echo sequence and STEAM sequence were performed at 3T. ASSESSMENT: AT volume was automatically segmented on CSE-MRI between L2 to L4 lumbar vertebrae and compared to the dual-energy X-ray absorptiometry (DEXA) measurement. CSE-MRI and MR spectroscopy (MRS) data were analyzed to assess the proton density fat fraction (PDFF) in the liver and the FA composition in SAT and VAT. Gas chromatography-mass spectrometry (GC-MS) analyses were performed on 13 SAT samples as a FA composition countermeasure. STATISTICAL TESTS: Paired t-test, Pearson's correlation coefficient, and Bland-Altman plots were used to compare measurements. RESULTS: SAT and VAT volumes significantly increased (P < 0.001). CSE-MRI and DEXA measurements were strongly correlated (r = 0.98, P < 0.001). PDFF significantly increased in the liver (+1.35, P = 0.002 for CSE-MRI, + 1.74, P = 0.002 for MRS). FA composition of SAT and VAT appeared to be consistent between localized-MRS and CSE-MRI (on whole segmented volume) measurements. A significant difference between SAT and VAT FA composition was found (P < 0.001 for CSE-MRI, P = 0.001 for MRS). MRS and CSE-MRI measurements of the FA composition were correlated with the GC-MS results (for ndb: rMRS/GC-MS = 0.83 P < 0.001, rCSE-MRI/GC-MS = 0.84, P = 0.001; for nmidb: rMRS/GC-MS = 0.74, P = 0.006, rCSE-MRI/GC-MS = 0.66, P = 0.020) DATA CONCLUSION: The follow-up of liver PDFF, volume, and FA composition of AT during an overfeeding diet was demonstrated through different methods. The CSE-MRI sequence associated with a dedicated postprocessing was found reliable for such quantification. LEVEL OF EVIDENCE: 1 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2019;49:1587-1599.