Chaoxue Zhang

Integrative deep learning and radiomics analysis for ovarian tumor classification and diagnosis: a multicenter large-sample comparative study

This study aims to evaluate the effectiveness of combining transvaginal ultrasound (US)-based radiomics and deep learning model for the accurate differentiation between benign and malignant ovarian tumors in large-scale studies. A multicenter retrospective study collected grayscale and color US images of ovarian tumors. Patients were divided into training, internal, and external validation groups. Models including a convolutional neural networks (CNN), optimal radiomics, and a combined model were constructed and evaluated for predictive performance using area under curve (AUC), sensitivity, and specificity. The DeLong test compared model AUCs with O-RADS and expert assessments. 3193 images from 2078 patients were analyzed. The CNN achieved AUCs of 0.970 (internal) and 0.959 (external), respectively. Optimal radiomic model achieved AUCs of 0.949 (internal) and 0.954 (external), respectively. The combined CNN-radiomics model attained the highest AUC of 0.977 (internal) and 0.972 (external), respectively, outperforming individual models, O-RADS, and expert methods (p < 0.05). The combined CNN-radiomics model using transvaginal US images provides more accurate and reliable ovarian tumor diagnosis, enhancing malignancy prediction and offering clinicians a more precise diagnostic tool.

A Transvaginal Ultrasound-Based Deep Learning Model for the Noninvasive Diagnosis of Myometrial Invasion in Patients with Endometrial Cancer: Comparison with Radiologists

This study aimed to determine the feasibility of using the deep learning (DL) method to determine the degree (whether myometrial invasion [MI] >50%) of MI in patients with endometrial cancer (EC) based on ultrasound (US) images. From September 2017 to April 2023, 1289 US images of 604 patients with EC who underwent surgical resection at center 1, center 2 or center 3 were obtained and divided into a training set and an internal validation set. Ninety-five patients from center 4 and center 5 were randomly selected as the external testing set according to the same criteria as those for the primary cohort. This study evaluated three DL models trained on the training set and tested them on the validation and testing sets. The models' performance was analyzed based on accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC), and the performance of the models was subsequently compared with that of 15 radiologists. In the final clinical diagnosis of MI in patients with EC, EfficientNet-B6 showed the best performance in the testing set in terms of area under the curve (AUC) [0.814, 95% CI (0.746-0.882]; accuracy [0.802, 95% CI (0.733-0.855]; sensitivity [0.623]; specificity [0.879]; positive likelihood ratio (PLR) [6.750]; and negative likelihood ratio (NLR) [0.389]. The diagnostic efficacy of EfficientNet-B6 was significantly better than that of the 15 radiologists, with an average diagnostic accuracy of 0.681, average AUC of 0.678, AUC of the best performance of 0.739, accuracy of 0.716, sensitivity of 0.806, specificity 0.672, PLR2.457, and NLR 0.289. Based on the preoperative US images of patients with EC, the DL model can accurately determine the degree of endometrial MI; the performance of this model is significantly better than that of radiologists, and it can effectively assist in clinical treatment decisions.

A Novel Ultrasound-Based Radiomics Model for the Preoperative Prediction of Lymph Node Metastasis in Cervical Cancer

The purpose of this retrospective study was to establish a combined model based on ultrasound (US)-radiomics and clinical factors to predict preoperative lymph node metastasis (LNM) in cervical cancer (CC) patients non-invasively. A total of 131 CC patients who had cervical lesions found by transvaginal sonography (TVS) from the First Affiliated Hospital of Anhui Medical University (Hefei, China) were retrospectively analyzed. The clinical independent predictors were selected using univariate and multivariate logistic regression analysis. US-radiomics features were extracted from US images; after selecting the most significant features by univariate analysis, Spearman's correlation analysis, and the least absolute shrinkage and selection operator (LASSO) algorithm; four machine-learning classification algorithms were used to build the US-radiomics model. Fivefold cross-validation was then used to test the performance of the model and compare the ability of the clinical, US-radiomics and combined models to predict LNM in CC patients. Red blood cell, platelet and squamous cell carcinoma-associated antigen were independent clinical predictors of LNM (+) in CC patients. eXtreme Gradient Boosting performed the best among the four machine-learning classification algorithms. Fivefold cross-validation confirmed that eXtreme Gradient Boosting indeed performs the best, with average area under the curve values in the training and validation sets of 0.897 and 0.898. In the three prediction models, both the US-radiomics model and the combined model showed good predictive efficacy, with average area under the curve values in the training and validation sets of 0.897, 0.898 and 0.912, 0.905, respectively. US-radiomics features combined with clinical factors can preoperatively predict LNM in CC patients non-invasively.