RESUMEN
BACKGROUND: Accurate detection of lymph node metastasis (LNM) is crucial for determining the tumor stage, selecting optimal treatment, and estimating the prognosis for cervical cancer. This study aimed to assess the diagnostic efficacy of multimodal diffusion-weighted imaging (DWI) and morphological parameters alone or in combination, for detecting LNM in cervical cancer. METHODS: In this prospective study, we enrolled consecutive cervical cancer patients who received multimodal DWI (conventional DWI, intravoxel incoherent motion DWI, and diffusion kurtosis imaging) before treatment from June 2022 to June 2023. The largest lymph node (LN) observed on each side on imaging was matched with that detected on pathology to improve the accuracy of LN matching. Comparison of the diffusion and morphological parameters of LNs and the primary tumor between the positive and negative LN groups. A combined diagnostic model was constructed using multivariate logistic regression, and the diagnostic performance was evaluated using receiver operating characteristic curves. RESULTS: A total of 93 cervical cancer patients were enrolled: 35 with LNM (48 positive LNs were collected), and 58 without LNM (116 negative LNs were collected). The area under the curve (AUC) values for the apparent diffusion coefficient, diffusion coefficient, mean diffusivity, mean kurtosis, long-axis diameter, short-axis diameter of LNs, and the largest primary tumor diameter were 0.716, 0.720, 0.716, 0.723, 0.726, 0.798, and 0.744, respectively. Independent risk factors included the diffusion coefficient, mean kurtosis, short-axis diameter of LNs, and the largest primary tumor diameter. The AUC value of the combined model based on the independent risk factors was 0.920, superior to the AUC values of all the parameters mentioned above. CONCLUSION: Combining multimodal DWI and morphological parameters improved the diagnostic efficacy for detecting cervical cancer LNM than using either alone.
RESUMEN
RATIONALE AND OBJECTIVES: This study aims to explore the feasibility of MRI-based habitat radiomics for predicting response of platinum-based chemotherapy in patients with high-grade serous ovarian carcinoma (HGSOC), and compared to conventional radiomics and deep learning models. MATERIALS AND METHODS: A retrospective study was conducted on HGSOC patients from three hospitals. K-means algorithm was used to perform clustering on T2-weighted images (T2WI), contrast-enhanced T1-weighted images (CE-T1WI), and apparent diffusion coefficient (ADC) maps. After feature extraction and selection, the radiomics model, habitat model, and deep learning model were constructed respectively to identify platinum-resistant and platinum-sensitive patients. A nomogram was developed by integrating the optimal model and clinical independent predictors. The model performance and benefit was assessed using the area under the receiver operating characteristic curve (AUC), net reclassification index (NRI), and integrated discrimination improvement (IDI). RESULTS: A total of 394 eligible patients were incorporated. Three habitats were clustered, a significant difference in habitat 2 (weak enhancement, high ADC values, and moderate T2WI signal) was found between the platinum-resistant and platinum-sensitive groups (P < 0.05). Compared to the radiomics model (0.640) and deep learning model (0.603), the habitat model had a higher AUC (0.710). The nomogram, combining habitat signatures with a clinical independent predictor (neoadjuvant chemotherapy), yielded a highest AUC (0.721) among four models, with positive NRI and IDI. CONCLUSION: MRI-based habitat radiomics had the potential to predict response of platinum-based chemotherapy in patients with HGSOC. The nomogram combining with habitat signature had a best performance and good model gains for identifying platinum-resistant patients.