The value of restriction spectrum imaging in predicting lymph node metastases in rectal cancer: a comparative study with diffusion-weighted imaging and diffusion kurtosis imaging.

To investigate the efficacy of three-compartment restriction spectrum imaging (RSI), diffusion kurtosis imaging (DKI), and diffusion-weighted imaging (DWI) in the assessment of lymph node metastases (LNM) in rectal cancer. A total of 77 patients with rectal cancer who underwent pelvic MRI were enrolled. RSI-derived parameters (f1, f2, and f3), DKI-derived parameters (Dapp and Kapp), and the DWI-derived parameter (ADC) were calculated and compared using a Mann-Whitney U test or independent samples t-test. Logistic regression (LR) analysis was used to identify independent predictors of LNM status. Area under the receiver operating characteristic curve (AUC) and Delong analysis were performed to assess the diagnostic performance of each parameter. The LNM-positive group exhibited significantly higher f1 and Kapp levels and significantly lower f3, Dapp, and ADC levels compared to the LNM-negative group (p < 0.05). There was no difference in f2 levels between the two groups (p = 0.783). LR analysis showed that Dapp and Kapp were independent predictors of a positive LNM status. AUC and Delong analysis showed that DKI (Dapp + Kapp) exhibited significantly higher diagnostic efficacy (AUC = 0.908; sensitivity = 87.10%; specificity = 86.96%) than RSI (f1 + f3) and DWI (ADC), with AUCs were 0.842 and 0.771 (Z = 2.113, 3.453; p = 0.035, < 0.001, respectively). The AUC performance between RSI and DWI was also statistically significant (Z = 1.972, p = 0.049). The RSI model is superior to conventional DWI but inferior to DKI in differentiation between LNM-positive and LNM-negative rectal cancers. Further study is needed before it could serve as a promising biomarker for guiding effective treatment strategies. The three-compartment restriction spectrum imaging was able to differentiate between LNM-positive and LNM-negative rectal cancers with high accuracy, which has the potential to serve as a promising biomarker that could guide treatment strategies. Three-compartment restriction spectrum imaging could differentiate lymph node metastases in rectal cancer. Diffusion kurtosis imaging and diffusion-weighted were associated with lymph node metastases in rectal cancer. The combination of different parameters has the potential to serve as a promising biomarker.

被引量：- 发表：1970

The top 100 most-cited articles on artificial intelligence in breast radiology: a bibliometric analysis.

Artificial intelligence (AI) in radiology is a rapidly evolving field. In breast imaging, AI has already been applied in a real-world setting and multiple studies have been conducted in the area. The aim of this analysis is to identify the most influential publications on the topic of artificial intelligence in breast imaging. A retrospective bibliometric analysis was conducted on artificial intelligence in breast radiology using the Web of Science database. The search strategy involved searching for the keywords 'breast radiology' or 'breast imaging' and the various keywords associated with AI such as 'deep learning', 'machine learning,' and 'neural networks'. From the top 100 list, the number of citations per article ranged from 30 to 346 (average 85). The highest cited article titled 'Artificial Neural Networks In Mammography-Application To Decision-Making In The Diagnosis Of Breast-Cancer' was published in Radiology in 1993. Eighty-three of the articles were published in the last 10 years. The journal with the greatest number of articles was Radiology (n = 22). The most common country of origin was the United States (n = 51). Commonly occurring topics published were the use of deep learning models for breast cancer detection in mammography or ultrasound, radiomics in breast cancer, and the use of AI for breast cancer risk prediction. This study provides a comprehensive analysis of the top 100 most-cited papers on the subject of artificial intelligence in breast radiology and discusses the current most influential papers in the field. This article provides a concise summary of the top 100 most-cited articles in the field of artificial intelligence in breast radiology. It discusses the most impactful articles and explores the recent trends and topics of research in the field. Multiple studies have been conducted on AI in breast radiology. The most-cited article was published in the journal Radiology in 1993. This study highlights influential articles and topics on AI in breast radiology.

被引量：- 发表：1970

A practical risk stratification system based on ultrasonography and clinical characteristics for predicting the malignancy of soft tissue masses.

被引量：- 发表：1970

Explainable breast cancer molecular expression prediction using multi-task deep-learning based on 3D whole breast ultrasound.

被引量：- 发表：1970

An ensemble machine learning model assists in the diagnosis of gastric ectopic pancreas and gastric stromal tumors.

被引量：- 发表：1970