RESUMO
OBJECTIVES: To comprehensively evaluate the reporting quality, risk of bias, and radiomics methodology quality of radiomics models for predicting microvascular invasion in hepatocellular carcinoma. METHODS: A systematic search of available literature was performed in PubMed, Embase, Web of Science, Scopus, and the Cochrane Library up to January 21, 2022. Studies that developed and/or validated machine learning models based on radiomics data to predict microvascular invasion in hepatocellular carcinoma were included. These studies were reviewed by two investigators and the consensus data were used for analyzing. The reporting quality, risk of bias, and radiomics methodological quality were evaluated by Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis (TRIPOD), Prediction model Risk of Bias Assessment Tool, and Radiomics Quality Score (RQS), respectively. RESULTS: A total of 30 studies met eligibility criteria with 24 model developing studies and 6 model developing and external validation studies. The median overall TRIPOD adherence was 75.4% (range 56.7-94.3%). All studies were at high risk of bias with at least 2 of 20 sources of bias. Furthermore, 28 studies showed unclear risks of bias in up to 5 signaling questions because of the lack of specified reports. The median RQS score was 37.5% (range 25-61.1%). CONCLUSION: Current radiomic models for MVI-status prediction have moderate to good reporting quality, moderate radiomics methodology quality, and high risk of bias in model development and validation. KEY POINTS: ⢠Current microvascular invasion prediction radiomics studies have moderate to good reporting quality, moderate radiomics methodology quality, and high risk of bias in model development and validation. ⢠Data representativeness, feature robustness, events-per-variable ratio, evaluation metrics, and appropriate validation are five main aspects futures studies should focus more on to improve the quality of radiomics. ⢠Both Radiomics Quality Score and Prediction model Risk of Bias Assessment Tool are needed to comprehensively evaluate a radiomics study.
Assuntos
Carcinoma Hepatocelular , Neoplasias Hepáticas , Humanos , Carcinoma Hepatocelular/patologia , Neoplasias Hepáticas/diagnóstico , PrognósticoRESUMO
The chemical exchange saturation transfer technique serves as a valuable tool for generating in vivo image contrast based on the content of various proton groups, including amide protons, amine protons, and aliphatic protons. Among these, amide proton transfer-weighted (APTw) imaging has seen extensive development as a means to assess the biochemical status of lesions. The exchange from saturated amide protons to bulk water protons during and following the saturation ratio frequency pulse contributes to detectable APT signals. While APTw imaging has garnered significant attention in the central nervous system, demonstrating noteworthy findings in cerebral neoplasia, stroke, and Alzheimer's disease over the past decade, its application in the abdomen has been a relatively recent progression. Notably, studies have explored its utility in hepatocellular carcinoma, prostate cancer, and cervical carcinoma within the abdominal context. Despite these advancements, there is a paucity of reviews on APTw imaging in abdominal applications. This paper aims to fill this gap by providing a concise overview of the fundamental theories underpinning APTw imaging. Additionally, we systematically summarize its diverse clinical applications in the abdomen, with a particular focus on the digestive and urogenital systems. Finally, the manuscript concludes by discussing technical limitations and factors influencing APTw imaging in abdominal applications, along with prospects for future research.
Assuntos
Neoplasias Hepáticas , Prótons , Masculino , Humanos , Imageamento por Ressonância Magnética/métodos , Amidas , Abdome/diagnóstico por imagemRESUMO
PURPOSE: To evaluate the diagnostic performance of image-based artificial intelligence (AI) studies in predicting muscle-invasive bladder cancer (MIBC). (2) To assess the reporting quality and methodological quality of these studies by Checklist for Artificial Intelligence in Medical Imaging (CLAIM), Radiomics Quality Score (RQS), and Prediction model Risk of Bias Assessment Tool (PROBAST). MATERIALS AND METHODS: We searched Medline, Embase, Web of Science, and The Cochrane Library databases up to October 30, 2023. The eligible studies were evaluated using CLAIM, RQS, and PROBAST. Pooled sensitivity, specificity, and the diagnostic performances of these models for MIBC were also calculated. RESULTS: Twenty-one studies containing 4256 patients were included, of which 17 studies were employed for the quantitative statistical analysis. The CLAIM study adherence rate ranged from 52.5% to 75%, with a median of 64.1%. The RQS points of each study ranged from 2.78% to 50% points, with a median of 30.56% points. All models were rated as high overall ROB. The pooled area under the curve was 0.85 (95% confidence interval (CI) 0.81-0.88) for computed tomography, 0.92 (95% CI 0.89-0.94) for MRI, 0.89 (95% CI 0.86-0.92) for radiomics and 0.91 (95% CI 0.88-0.93) for deep learning, respectively. CONCLUSION: Although AI-powered muscle-invasive bladder cancer-predictive models showed promising performance in the meta-analysis, the reporting quality and the methodological quality were generally low, with a high risk of bias. CRITICAL RELEVANCE STATEMENT: Artificial intelligence might improve the management of patients with bladder cancer. Multiple models for muscle-invasive bladder cancer prediction were developed. Quality assessment is needed to promote clinical application. KEY POINTS: Image-based artificial intelligence models could aid in the identification of muscle-invasive bladder cancer. Current studies had low reporting quality, low methodological quality, and a high risk of bias. Future studies could focus on larger sample sizes and more transparent reporting of pathological evaluation, model explanation, and failure and sensitivity analyses.
RESUMO
Kidney diseases result from various causes, which can generally be divided into neoplastic and non-neoplastic diseases. Deep learning based on medical imaging is an established methodology for further data mining and an evolving field of expertise, which provides the possibility for precise management of kidney diseases. Recently, imaging-based deep learning has been widely applied to many clinical scenarios of kidney diseases including organ segmentation, lesion detection, differential diagnosis, surgical planning, and prognosis prediction, which can provide support for disease diagnosis and management. In this review, we will introduce the basic methodology of imaging-based deep learning and its recent clinical applications in neoplastic and non-neoplastic kidney diseases. Additionally, we further discuss its current challenges and future prospects and conclude that achieving data balance, addressing heterogeneity, and managing data size remain challenges for imaging-based deep learning. Meanwhile, the interpretability of algorithms, ethical risks, and barriers of bias assessment are also issues that require consideration in future development. We hope to provide urologists, nephrologists, and radiologists with clear ideas about imaging-based deep learning and reveal its great potential in clinical practice.Critical relevance statement The wide clinical applications of imaging-based deep learning in kidney diseases can help doctors to diagnose, treat, and manage patients with neoplastic or non-neoplastic renal diseases.Key points⢠Imaging-based deep learning is widely applied to neoplastic and non-neoplastic renal diseases.⢠Imaging-based deep learning improves the accuracy of the delineation, diagnosis, and evaluation of kidney diseases.⢠The small dataset, various lesion sizes, and so on are still challenges for deep learning.
RESUMO
BACKGROUND: This study aimed to develop and internally validate computed tomography (CT)-based radiomic models to predict the lesion-level short-term response to tyrosine kinase inhibitors (TKIs) in patients with advanced renal cell carcinoma (RCC). METHODS: This retrospective study included consecutive patients with RCC that were treated using TKIs as the first-line treatment. Radiomic features were extracted from noncontrast (NC) and arterial-phase (AP) CT images. The model performance was assessed using the area under the receiver operating characteristic curve (AUC), calibration curve, and decision curve analysis (DCA). RESULTS: A total of 36 patients with 131 measurable lesions were enrolled (training: validation = 91: 40). The model with five delta features achieved the best discrimination capability with AUC values of 0.940 (95% CI, 0.890â0.990) in the training cohort and 0.916 (95% CI, 0.828â1.000) in the validation cohort. Only the delta model was well calibrated. The DCA showed that the net benefit of the delta model was greater than that of the other radiomic models, as well as that of the treat-all and treat-none criteria. CONCLUSIONS: Models based on CT delta radiomic features may help predict the short-term response to TKIs in patients with advanced RCC and aid in lesion stratification for potential treatments.
RESUMO
Renal cell carcinoma with extrarenal fat (perinephric or renal sinus fat) and renal vein invasion is the main evidence for the T3a stage according to the American Joint Committee on Cancer tumor-node-metastasis (TNM) staging system. Extrarenal fat invasion of renal cell carcinoma is defined as the presence of perinephric fat invasion or renal sinus fat invasion. Renal vein invasion is defined as the presence of main or segmental (branch) renal vein invasion. Accurate assessment of extrarenal fat and renal vein invasion is crucial for urologists to adopt the optimal therapeutic schedule, including radical nephrectomy or nephron-sparing treatments. Currently, imaging is still the most widely used means of examination for diagnosis and staging of renal cell carcinoma, especially multidetector computed tomography (MDCT). Therefore, we have, herein, summarized the latest progress and the future direction regarding imaging for assessing perinephric or renal sinus fat and renal vein invasion of renal cell carcinoma to assist clinical treatment selection and patient risk stratification.
RESUMO
Haze pollution is one of the most concerning environmental issues, and controlling haze pollution without affecting economic development is of immense significance. Using the panel data composed of PM2.5 concentration and other data from 278 cities in China between 2003 and 2016, this paper empirically investigates the impact of urban innovation on haze pollution and its transmission mechanism. Based on the fixed effect model, the research finds that increasing urban innovation significantly reduces haze pollution. Even after dealing with possible endogenous problems, the result still holds. Energy consumption and industrial agglomeration are two important transmission channels through which urban innovation affects haze pollution. Furthermore, time heterogeneity analysis shows that the negative effect of urban innovation on haze pollution increases with time. Spatial heterogeneity analysis shows that urban innovation has a more significant mitigation effect on haze pollution in eastern cities than in central and western cities in China. This paper indicates that technological innovation, as the main driving force for development, can provide vital support to China to improve the ecological environment.