This study proposes an automated neurofibroma detection method for whole-body magnetic resonance imaging (WBMRI) based on radiomics and ensemble learning. A dynamic weighted box fusion mechanism integrating two dimensional (2D) object detection and three dimensional (3D) segmentation is developed, where the fusion weights are dynamically adjusted according to the respective performance of the models in different tasks. The 3D segmentation model leverages spatial structural information to effectively compensate for the limited boundary perception capability of 2D methods. In addition, a radiomics-based false positive reduction strategy is introduced to improve the robustness of the detection system. The proposed method is evaluated on 158 clinical WBMRI cases with a total of 1,380 annotated tumor samples, using five-fold cross-validation. Experimental results show that, compared with the best-performing single model, the proposed approach achieves notable improvements in average precision, sensitivity, and overall performance metrics, while reducing the average number of false positives by 17.68. These findings demonstrate that the proposed method achieves high detection accuracy with enhanced false positive suppression and strong generalization potential.
Lung cancer is one of the leading causes of cancer deaths worldwide. Many options including surgery, radiotherapy, chemotherapy, targeted therapy and immunotherapy have been applied in the treatment for lung cancer patients. However, how to develop individualized treatment plans for patients and accurately determine the prognosis of patients is still a very difficult clinical problem. In recent years, radiomics, as an emerging method for medical image analysis, has gradually received the attention from researchers. It is based on the assumption that medical images contain a vast amount of biological information about patients that is difficult to identify with naked eyes but can be accessed by computer. One of the most common uses of radiomics is the diagnosis and treatment of non-small cell lung cancer (NSCLC). In this review, we reviewed the current researches on chest CT-based radiomics in the diagnosis and treatment of NSCLC and provided a brief summary of the current state of research in this field, covering various aspects of qualitative diagnosis, efficacy prediction, and prognostic analysis of lung cancer. We also briefly described the main current technical limitations of this technology with the aim of gaining a broader understanding of its potential role in the diagnosis and treatment of NSCLC and advancing its development as a tool for individualized management of NSCLC patients.
ObjectiveTo explore the value of a radiomics model based on ultrasound imaging in predicting the HER-2 status of breast cancer prior to surgery.MethodsA total of 230 patients with invasive breast cancer were retrospectively analyzed, all the patients underwent preoperative breast ultrasound examination. According to the order of examination time, the patients were categorized into training group (n=115) and validation group (n=115). Image J software was used to manually delineate the lesion area in the ultrasound image along the tumor boundary. Pyradiomics was used to extract 1 820 features from each lesion area, and three statistical methods were used to screen features. A logistic regression model was used to construct ultrasound imaging radiomics model. The receive operating characteristic curve (ROC), calibration curve and decision curve were used to evaluate the performance and value of ultrasound imaging radiomics model in predicting HER-2 status.ResultsNine key image features were identified to construct ultrasound imaging radiomics model. The area of under the ROC curve of the model in the training group and the validation group were 0.82 (95%CI 0.74 to 0.90) and 0.81 (95%CI 0.72 to 0.89), respectively. The calibration curve showed that the model had a good calibration in both the training and validation groups.ConclusionsUltrasound-based imaging radiomics model is of significant value in predicting the HER-2 status of breast cancer prior to surgery.
CT texture analysis (CTTA) can objectively evaluate the heterogeneity of tissues and their lesions beyond the ability of subjective visual interpretation by extracting the texture features of CT images, then performing analysis and quantitative and objective evaluation, reflecting the tissue micro environmental information. This article reviews the recent studies on the applications of CTTA in gastric cancers, in the aspects of identification of gastric tumors, prediction of stage, correlation with Lauren classification, prediction of occult peritoneal carcinomatosis, evaluation of efficacy and prognosis, and prediction of biomarkers. It is regarded that CTTA has a good application prospect in gastric cancers.
ObjectiveTo systematically review the value of radiomics in the diagnosis of glioblastoma. MethodsPubMed, EMbase, Web of Science and The Cochrane Library databases were electronically searched to collect studies on radiomics in the grading of gliomas or the differentiation diagnosis from inception to May 30th, 2021. Two reviewers independently screened literature, extracted data, and assessed the risk of bias and the quality of the included studies. Meta-analysis was then performed using Meta-Disc 1.4 software and RevMan 5.3 software. ResultsA total of 37 studies involving 2 746 subjects were included. The results of meta-analysis showed that the pooled sensitivity, specificity, and diagnostic odds ratio for the diagnosis of glioblastoma by radiomics were 0.91 (95%CI 0.89 to 0.92), 0.88 (95%CI 0.87 to 0.90), and 78.00 (95%CI 50.81 to 119.72), respectively. The area under the summary receiver operating characteristic (SROC) curve was 0.95. The key radiomic features for correct diagnosis of glioblastoma included intensity features and texture features of the lesions. ConclusionThe current evidence shows that radiomics provides good diagnostic accuracy for glioblastoma. Due to the limited quality and quantity of the included studies, more high-quality studies are required to verify the above conclusions.
ObjectiveTo investigate the radiomics features to distinguish invasive lung adenocarcinoma with micropapillary or solid structure. MethodsA retrospective analysis was conducted on patients who received surgeries and pathologically confirmed invasive lung adenocarcinoma in our hospital from April 2016 to August 2019. The dataset was randomly divided into a training set [including a micropapillary/solid structure positive group (positive group) and a micropapillary/solid structure negative group (negative group)] and a testing set (including a positive group and a negative group) with a ratio of 7∶3. Two radiologists drew regions of interest on preoperative high-resolution CT images to extract radiomics features. Before analysis, the intraclass correlation coefficient was used to determine the stable features, and the training set data were balanced using synthetic minority oversampling technique. After mean normalization processing, further radiomics features selection was conducted using the least absolute shrinkage and selection operator algorithm, and a 5-fold cross validation was performed. Receiver operating characteristic (ROC) curves were depicted on the training and testing sets to evaluate the diagnostic performance of the radiomics model. ResultsA total of 340 patients were enrolled, including 178 males and 162 females with an average age of 60.31±6.69 years. There were 238 patients in the training set, including 120 patients in the positive group and 118 patients in the negative group. There were 102 patients in the testing set, including 52 patients in the positive group and 50 patients in the negative group. The radiomics model contained 107 features, with the final 2 features selected for the radiomics model, that is, Original_ glszm_ SizeZoneNonUniformityNormalized and Original_ shape_ SurfaceVolumeRatio. The areas under the ROC curve of the training and the testing sets of the radiomics model were 0.863 (95%CI 0.815-0.912) and 0.857 (95%CI 0.783-0.932), respectively. The sensitivity was 91.7% and 73.7%, the specificity was 78.8% and 84.0%, and the accuracy was 85.3% and 78.4%, respectively. ConclusionThere are differences in radiomics features between invasive pulmonary adenocarcinoma with or without micropapillary and solid structures, and the radiomics model is demonstrated to be with good diagnostic value.
Radiomics transforms the medical images into minable high-throughput data, extracts the in-depth information invisible to the naked eye, in order to provide support for clinical diagnosis and treatment decision-making processes through the analysis of these data. Recently, radiomics has garnered widespread attention from researchers, with a continuously increasing number of research publications. However, there is still a lack of transparency in reporting radiomics studies. To guide the reporting of radiomics research, the CheckList for EvaluAtion of Radiomics research (CLEAR) was developed by the CLEAR working group using an expert consensus process. This checklist, which was published in May 2023, comprises 58 items and has been endorsed by the European Society of Radiology (ESR) and the European Society for Medical Imaging Informatics (EuSoMII). With authorization from the CLEAR working group, this article introduces and interprets the content of this checklist, to promote the understanding and application of CLEAR among radiomics researchers in China, and to enhance the transparency of radiomics research reporting.
Differential diagnosis of benign and malignant ground glass nodule (GGN) is of great significance to the early detection, diagnosis and treatment of lung cancer. Increasing attention has been paid to radiomics technology application in early diagnosis of benign and malignant GGN, which can analyze the characteristic appearances of GGN in non-invasive manner. This article reviews the latest research progress of radiomics in the diagnosis of GGN.
Currently, the types of kidney stones before surgery are mainly identified by human beings, which directly leads to the problems of low classification accuracy and inconsistent diagnostic results due to the reliance on human knowledge. To address this issue, this paper proposes a framework for identifying types of kidney stones based on the combination of radiomics and deep learning, aiming to achieve automated preoperative classification of kidney stones with high accuracy. Firstly, radiomics methods are employed to extract radiomics features released from the shallow layers of a three-dimensional (3D) convolutional neural network, which are then fused with the deep features of the convolutional neural network. Subsequently, the fused features are subjected to regularization, least absolute shrinkage and selection operator (LASSO) processing. Finally, a light gradient boosting machine (LightGBM) is utilized for the identification of infectious and non-infectious kidney stones. The experimental results indicate that the proposed framework achieves an accuracy rate of 84.5% for preoperative identification of kidney stone types. This framework can effectively distinguish between infectious and non-infectious kidney stones, providing valuable assistance in the formulation of preoperative treatment plans and the rehabilitation of patients after surgery.
ObjectivesTo investigate the predictive value for diabetic kidney disease (DKD) by utilizing deep learning to automatically segment fundus panoramic images and constructing multidimensional radiomics models integrated with clinical parameters. MethodsA diagnostic trial study. From December 2022 to March 2024, 353 patients with type 2 diabetes mellitus who were admitted for the first time to Department of Endocrinology of Yangzhou University Affiliated Jiangdu People's Hospital were included in the study. Among them, 114 cases had diabetic kidney disease (DKD), and 239 cases were non-DKD patients. All patients underwent non-mydriatic color fundus photography of both eyes, capturing 45° field of view fundus images centered on the macula (panoramic fundus images). A pre-trained U-Net model was used to automatically segment regions of interest (ROI) in the fundus panoramic images, and batch processing was performed to segment ROI for all images. Radiomics features were extracted separately from the ROI of both left and right fundus panoramic images. Feature-level fusion (feature concatenation) was applied to merge the radiomics features from both eyes, resulting in a fused feature set. Features from the left eye, right eye, and the fused set underwent feature selection using t-tests, Pearson correlation analysis, and LASSO regression to identify the optimal features for model building. Finally, the dataset was partitioned into a training set and an independent validation set at a 7:3 ratio. The training set underwent 5-fold cross-validation for hyperparameter tuning, ultimately yielding the optimal algorithm model classifier, separate radiomics models were built for the left eye, right eye, and the feature-level fusion set. Additionally, a decision-level fusion model (ensemble voting) was constructed by combining the outputs (results) of the left and right eye models. A clinical parameter model was also built based on multivariate analysis results. The area under the receiver operating characteristic curve (AUC) was used as the primary quantitative evaluation metric. DeLong's test compared AUC differences between models. The net reclassification index (NRI) and decision curve analysis (DCA) were employed to assess the superiority between different models. ResultsThe results of the ROC analysis showed that in the training and validation sets, the AUC values for the clinical model, left-eye radiomics model, right-eye radiomics model, feature-level fusion model, and decision-level fusion model were 0.826, 0.847, 0.883, 0.890, 0.907 and 0.588, 0.646, 0.642, 0.657, 0.689, respectively. The results of the DeLong test showed that in the training set, the AUC of the decision-level fusion model was significantly higher than that of the clinical model and the left-eye model (P=0.010,＜0.001). The AUC of the feature-level fusion model was significantly higher than that of the left-eye model (P=0.020). However, in the validation set, no statistically significant differences in AUC were observed among the models (P＞0.05). The results of the NRI Analysis showed that compared to the clinical model, the NRI values for all four radiomics models were positive in both training and validation sets, indicating superior DKD prediction performance by the radiomics models. Compared to the decision-level fusion model, the NRI values for the left-eye, right-eye, and feature-level fusion models were negative in both sets, suggesting that the decision-level fusion model had the best performance. The results of the DCA analysis showed that in both training and validation sets, the decision-level fusion model provided greater net clinical benefit across a range of threshold probabilities compared to the other four models. ConclusionThe radiomics model based on automatically segmented panoramic fundus images can predict the risk of DKD occurrence, with the integrated model of both eyes demonstrating higher predictive performance.