Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) may provide more information in diagnosis of malignant tumor compared to conventional magnetic resonance imaging (MRI). Nowadays, in order to utilize the information expediently and efficiently, many researchers are aiming at the development of computer-aided diagnosis (CAD) of malignant tumor based on DCE-MRI. In this review, we survey the research in this field and summarize the literature in four parts, i.e. ① image preprocessing——noise reduction and image registration; ② region of interests (ROI) segmentation; ③ feature extraction——exploring the image characteristics by analyzing the ROI quantitatively; ④ tumor lesion recognition and classification——distinguishing and classifying tumor lesions by learning the features of ROI. We summarize the application of CAD techniques of DCE-MRI for cancer diagnosis and, finally, give some discussion on how to improve the efficiency of CAD in the future research.
ObjectiveTo explore the application value of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) quantitative parameters and apparent diffusion coefficient (ADC) value in evaluating the differentiation degrees and T stages of rectal cancer.MethodsThe patients with rectal cancer from November 2017 to November 2019 in the Sichuan Provincial People’s Hospital were collected. The volume transfer constant (Ktrans), flux rate constant (Kep), and extravascular extracellular volume fraction (Ve), and ADC values of the tumors were measured and compared in the patients with the different differentiation degrees and T stages. The receiver operating characteristic (ROC) curve analysis was performed.ResultsAll of 53 eligible patients were included, including 13 cases of high differentiation, 30 cases of medium differentiation, and 10 cases of low differentiation; 5 cases of T1 stage, 8 cases of T2 stage, 24 cases of T3 stage, and 16 cases of T4 stage. ① There were statistical differences in the Ktrans and ADC values among the different differentiation degrees of rectal cancer (P=0.004, P<0.001), and no statistical differences in the Kep and Ve values (P>0.050) among them. The Ktrans value was increased with decreased differentiation degree (P<0.050), the ADC value was decreased with decreased differentiation degrees (P<0.050). ② There were statistical differences in the Ktrans and ADC values among the different T stages of rectal cancer (P=0.002; P=0.007), and no statistical differences in the Kep and Ve values (P>0.050) among them. The Ktrans and ADC values were statistically different between the T2 and T3 stages of rectal cancer (P=0.009, P=0.013). ③ The Ktrans and ADC values could distinguish the high and medium differentiation degrees of rectal cancer, its area under ROC curve (AUC) values were 0.677 and 0.763, respectively, and the corresponding best thresholds were 0.180/min and 1.179 mm2/s; The Ktrans and ADC values could distinguish the medium and low differentiation degrees of rectal cancer, its AUC values were 0.693 and 0.967, and the corresponding best thresholds were 0.281/min and 0.906 mm2/s; The Ktrans and ADC values could distinguish the T2 and T3 stages of rectal cancer, its AUC values were 0.862 and 0.742, and the corresponding best thresholds were 0.204/min and 1.579 mm2/s.ConclusionDCE-MRI quantitative parameters and ADC value before surgery to determine the different differentiation degrees and T stages of rectal cancer have certain reference value, the best Ktrans and ADC thresholds to distinguish different differentiation degrees and T2 to T3 stages can be obtained through statistical analysis.
ObjectiveTo evaluate the predictive value of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) combined with multislice computed tomography (MSCT) in the evaluation of neoadjuvant chemotherapy (NACT) for breast cancer. MethodsThe clinical, imaging, and pathological data of breast cancer patients who received NACT in the Affiliated Hospital of Southwest Medical University from February 2019 to August 2021 were retrospectively collected. Based on the results of postoperative pathological examination, the patients were assigned into significant remission (Miller-Payne grade Ⅰ–Ⅲ) and non-significant remission (Miller-Payne grade Ⅳ–Ⅴ). The variables with statistical significance by univariate analysis or factors with clinical significance judged based on professional knowledge were included to conduct the logistic regression multivariate analysis to screen the risk factors affecting the degree of pathological remission after NACT. Then, the screened risk factors were used to establish a prediction model for the degree of pathological remission of breast cancer after NACT, and the efficacy of this model was evaluated using the receiver operating characteristic (ROC) curve, calibration curve, and decision curve analysis (DCA) curve. ResultsAccording to the inclusion and exclusion criteria, a total of 211 breast cancer patients who received NACT were collected, including 116 patients with significant remission and 95 patients with non-significant remission. Logistic regression multivariate analysis results showed that the human epidermal growth factor receptor 2 positive, lower early enhancement rate after NACT, lower arterial stage net increment after NACT, and lower CT value of arterial phase of lesions would increase the probability of significant remission in patients with breast cancer after NACT (P<0.05). The area under the ROC curve of the model for predicting the degree of pathological remission of breast cancer after NACT was 0.984, the specificity was 93.7%, and the sensitivity was 95.7%. The calibration curve showed that the model result fit well with the actual result, and the DCA result showed that it had a high clinical net benefit value. ConclusionFrom the results of this study, DCE-MRI combined with MSCT enhanced scanning has a good predictive value for pathological remission degree after NACT for breast cancer, which can provide clinical guidance for further treatment.