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.
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.
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 a leading cause of cancer-related deaths worldwide, with its high mortality rate primarily attributed to delayed diagnosis. Radiomics, by extracting abundant quantitative features from medical images, offers novel possibilities for early diagnosis and precise treatment of lung cancer. This article reviewed the latest advancements in radiomics for lung cancer management, particularly its integration with artificial intelligence (AI) to optimize diagnostic processes and personalize treatment strategies. Despite existing challenges, such as non-standardized image acquisition parameters and limitations in model reproducibility, the incorporation of AI significantly enhanced the precision and efficiency of image analysis, thereby improving the prediction of disease progression and the formulation of treatment plans. We emphasized the critical importance of standardizing image acquisition parameters and discussed the role of AI in advancing the clinical application of radiomics, alongside future research directions.
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.
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.
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.
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.
The macrotrabecular-massive (MTM) subtype of hepatocellular carcinoma (HCC) is a histological variant with higher malignant potential. Non-invasive preoperative identification of MTM-HCC is crucial for precise treatment. Current radiomics-based diagnostic models often integrate multi-phase features by simple feature concatenation, which may inadequately explore the latent complementary information between phases. This study proposes a feature fusion-based radiomics model using multi-phase contrast-enhanced computed tomography (mpCECT) images. Features were extracted from the arterial phase (AP), portal venous phase (PVP), and delayed phase (DP) CT images of 121 HCC patients. The fusion model was constructed and compared against the traditional concatenation model. Five-fold cross-validation demonstrated that the feature fusion model combining AP and PVP features achieved the best classification performance, with an area under the receiver operating characteristic curve (AUC) of 0.839. Furthermore, for any combination of two phases, the feature fusion model consistently outperformed the traditional feature concatenation approach. In conclusion, the proposed feature fusion model effectively enhances the discrimination capability compared to traditional models, providing a new tool for clinical practice.
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.