Lymph node metastasis prediction and biological pathway associations underlying DCE-MRI deep learning radiomics in invasive breast cancer.

BACKGROUND: The relationship between the biological pathways related to deep learning radiomics (DLR) and lymph node metastasis (LNM) of breast cancer is still poorly understood. This study explored the value of DLR based on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) in LNM of invasive breast cancer. It also analyzed the biological significance of DLR phenotype based on genomics. METHODS: Two cohorts from the Cancer Imaging Archive project were used, one as the training cohort (TCGA-Breast, n = 88) and one as the validation cohort (Breast-MRI-NACT Pilot, n = 57). Radiomics and deep learning features were extracted from preoperative DCE-MRI. After dual selection by principal components analysis (PCA) and relief methods, radiomics and deep learning models for predicting LNM were constructed by the random forest (RF) method. A post-fusion strategy was used to construct the DLR nomograms (DLRNs) for predicting LNM. The performance of the models was evaluated using the receiver operating characteristic (ROC) curve and Delong test. In the training cohort, transcriptome data were downloaded from the UCSC Xena online database, and biological pathways related to the DLR phenotypes were identified. Finally, hub genes were identified to obtain DLR gene expression (RadDeepGene) scores. RESULTS: DLRNs were based on area under curve (AUC) evaluation (training cohort, AUC = 0.98; validation cohort, AUC = 0.87), which were higher than single radiomics models or GoogLeNet models. The Delong test (radiomics model, P = 0.04; GoogLeNet model, P = 0.01) also validated the above results in the training cohorts, but they were not statistically significant in the validation cohort. The GoogLeNet phenotypes were related to multiple classical tumor signaling pathways, characterizing the biological significance of immune response, signal transduction, and cell death. In all, 20 genes related to GoogLeNet phenotypes were identified, and the RadDeepGene score represented a high risk of LNM (odd ratio = 164.00, P < 0.001). CONCLUSIONS: DLRNs combining radiomics and deep learning features of DCE-MRI images improved the preoperative prediction of LNM in breast cancer, and the potential biological characteristics of DLRN were identified through genomics.

[Changes and clinical significance of serum soluble Apo-1/Fas in pancreatic cancer].

OBJECTIVE: To detect changes of serum soluble Apo-1/Fas (sApo-1/Fas) in pancreatic cancer patients and to investigate its clinical value in assessing the effect of chemotherapy. METHODS: The serum level of sApo-1/Fas in 30 normal control subjects and 58 pancreatic cancer patients were detected using enzyme-linked immunosorbent assay (ELISA), and the sApo-1/Fas level of 48 pancreatic cancer patients, before and after chemotherapy was compared. RESULTS: Compared with the level of the control group, the level of serum soluble Apo-1/Fas was significantly correlated with clinical stage but not with age, sex or pathologic type of pancreatic cancer. It was elevated gradually from stage II to IV (P < 0.01). However, it would obviously decrease in pancreatic cancer patients after chemotherapy (P < 0.01). CONCLUSION: The serum soluble Apo-1/Fas may be involved in the development of pancreatic cancer, and it may be used as one parameter to assess the disease status and prognosis of pancreatic cancer patient.

[Clinical value of serum soluble Apo-1/Fas for predicting biological behaviors and prognosis of gastric carcinoma].

BACKGROUND & OBJECTIVE: Literatures reported that the soluble Apo-1/Fas(sApo-1/Fas) levels in serum of patients with malignant carcinoma were higher than that in normal control subject, but there were fewer studies was seldom to detect the level of sApo-1/Fas in patients with malignancy carcinoma and effect of chemotherapy; the subject is to detect the level of sApo-1/Fas in patients with gastric carcinoma and effect of chemotherapy on it, and to investigate its clinical value. METHODS: Enzyme linked immunosorbent assays(ELISA) was available to detect the level of sApo-1/Fas in 42 case of patients with gastric carcinoma before and after chemotherapy, as compared with 30 case of normal control subject. RESULTS: Levels of sApo-1/Fas were elevated in all subgroups of patients with gastric carcinoma as compared to the controls (P < 0.01), sApo-1/Fas was correlated with clinical stage and histological grade, and not with sex, age; the sApo-1/Fas level in stage IV was higher in comparison with stage III and II (P < 0.05-0.01), and in stage III it was higher than in stage II (P < 0.05); being lower in the well differentiated and moderately differentiated than the poorly differentiated(P < 0.05-0.01), that the sApo-1/Fas levels were remarkably reduced in complete remission or partial remission patients(P < 0.01) after chemotherapy. CONCLUSION: sApo-1/Fas may play closely reflect growth and regulation in gastric carcinoma, it may be a predictor for biological behaviors and prognosis of gastric carcinoma; sApo-1/Fas may be a new target in treating gastric carcinoma.