RESUMO
BACKGROUND: Renal cell carcinoma (RCC) is a heterogeneous group of kidney cancers. Renal capsule invasion is an essential factor for RCC staging. To develop radiomics models from CT images for the preoperative prediction of capsule invasion in RCC patients. METHODS: This retrospective study included patients with RCC admitted to the Chongqing University Cancer Hospital (01/2011-05/2019). We built a radiomics model to distinguish patients grouped as capsule invasion versus non-capsule invasion, using preoperative CT scans. We evaluated effects of three imaging phases, i.e., unenhanced phases (UP), corticomedullary phases (CMP), and nephrographic phases (NP). Five different machine learning classifiers were compared. The effects of tumor and tumor margins are also compared. Five-fold cross-validation and the area under the receiver operating characteristic curve (AUC) are used to evaluate model performance. RESULTS: This study included 126 RCC patients, including 46 (36.5%) with capsule invasion. CMP exhibited the highest AUC (AUC = 0.81) compared to UP and NP, when using the forward neural network (FNN) classifier. The AUCs using features extracted from the tumor region were generally higher than those of the marginal regions in the CMP (0.81 vs. 0.73) and NP phase (AUC = 0.77 vs. 0.76). For UP, the best result was obtained from the marginal region (AUC = 0.80). The robustness analysis on the UP, CMP, and NP achieved the AUC of 0.76, 0.79, and 0.77, respectively. CONCLUSIONS: Radiomics features in renal CT imaging are associated with the renal capsule invasion in RCC patients. Further evaluation of the models is warranted.
Assuntos
Carcinoma de Células Renais/diagnóstico por imagem , Carcinoma de Células Renais/patologia , Processamento de Imagem Assistida por Computador/métodos , Neoplasias Renais/diagnóstico por imagem , Neoplasias Renais/patologia , Tomografia Computadorizada por Raios X/métodos , Adulto , Idoso , Idoso de 80 Anos ou mais , Diagnóstico Diferencial , Feminino , Humanos , Aprendizado de Máquina , Masculino , Pessoa de Meia-Idade , Invasividade Neoplásica , Período Pré-Operatório , Estudos RetrospectivosRESUMO
BACKGROUND: The diagnostic performance of diffusion-weighted imaging (DWI) combined with dynamic contrast-enhanced (DCE)-magnetic resonance imaging (MRI) for the detection of prostate cancer (PCa) has not been studied systematically to date. PURPOSE: To investigate the value of DWI combined with DCE-MRI quantitative analysis in the diagnosis of PCa. MATERIAL AND METHODS: A systematic search was conducted through PubMed, MEDLINE, the Cochrane Library, and EMBASE databases without any restriction to language up to 10 December 2019. Studies that used a combination of DWI and DCE-MRI for diagnosing PCa were included. RESULTS: Nine studies with 778 participants were included. The combination of DWI and DCE-MRI provide accurate performance in diagnosing PCa with pooled sensitivity, specificity, positive likelihood ratio, negative likelihood ratio, and diagnostic odds ratios of 0.79 (95% confidence interval [CI] = 0.76-0.81), 0.85 (95% CI = 0.83-0.86), 6.58 (95% CI = 3.93-11.00), 0.24 (95% CI = 0.17-0.34), and 36.43 (95% CI = 14.41-92.12), respectively. The pooled area under the summary receiver operating characteristic curve was 0.9268. Moreover, 1.5-T MR scanners demonstrated a slightly better performance than 3.0-T scanners. CONCLUSION: Combined DCE-MRI and DWI could demonstrate a highly accurate area under the curve, sensitivity, and specificity for detecting PCa. More studies with large sample sizes are warranted to confirm these results.
Assuntos
Meios de Contraste , Imagem de Difusão por Ressonância Magnética/métodos , Aumento da Imagem/métodos , Imagem Multimodal/métodos , Neoplasias da Próstata/diagnóstico por imagem , Humanos , Imageamento por Ressonância Magnética/métodos , Masculino , Próstata/diagnóstico por imagem , Reprodutibilidade dos Testes , Sensibilidade e EspecificidadeRESUMO
BACKGROUND: Early diagnosis of prostate cancer improves its prognosis, while it is essential to upgrade screening tools. This study aimed to explore the value of a novel functional magnetic resonance imaging (MRI) technique, namely amide proton transfer (APT)-weighted MRI, combined with serum prostate-specific antigen (PSA) levels to differentiate malignant prostate lesions from benign prostate lesions. METHODS: Data of patients who underwent prostate examinations at Chongqing University Cancer Hospital between July 2019 and March 2022 were retrospectively analyzed. All patients underwent T2-weighted imaging (T2WI), APT, diffusion-weighted imaging (DWI), and dynamic contrast-enhanced (DCE) MRI. Two radiologists analyzed the images independently. The ability of the quantitative parameters alone or in different combinations in differentiating malignant prostate lesions from benign prostate lesions were compared by using receiver operating characteristic (ROC) curves. According to the DeLong test, the combined parameters were significantly different from the corresponding single parameter (P < 0.05). RESULTS: A total of 79 patients were finally enrolled, including 52 patients in the malignant group and 27 patients in the benign group. The separate assessment of indexes revealed that APTmax, APTmean, mean apparent diffusion coefficient (ADCmean), ADCmax, ADCmin, tPAD, free prostate-specific antigen (FPSA), FPSA/total prostate-specific antigen (tPSA), and PSA density (PSAD) were significantly different between the two groups (P < 0.05), while APTmin was not significantly different between the two groups (P > 0.05). APTmax and APTmean had the high values of area under the ROC curve (AUC), which were 0.780 and 0.710, respectively. APTmax had a high sensitivity, and APTmean had a high specificity. The combination of APTmax, APTmean, ADCmean, and PSAD had the highest AUC value (AUC: 0.880, sensitivity: 86.540, specificity: 78.260). CONCLUSION: APTmax, APTmean, ADCmean, ADCmin, tPAD, FPSA, and PSAD showed to have a high value in differentiating malignant prostate lesions from benign prostate lesions in the separate assessment of indexes. The combination of APTmax, APTmean, ADCmean, and PSAD had the highest diagnostic value.