-
International Journal of Surgery... Jun 2024Colorectal cancer (CRC) stands as the third most prevalent cancer globally, projecting 3.2 million new cases and 1.6 million deaths by 2040. Accurate lymph node... (Meta-Analysis)
Meta-Analysis
BACKGROUND
Colorectal cancer (CRC) stands as the third most prevalent cancer globally, projecting 3.2 million new cases and 1.6 million deaths by 2040. Accurate lymph node metastasis (LNM) detection is critical for determining optimal surgical approaches, including preoperative neoadjuvant chemoradiotherapy and surgery, which significantly influence CRC prognosis. However, conventional imaging lacks adequate precision, prompting exploration into radiomics, which addresses this shortfall by converting medical images into reproducible, quantitative data.
METHODS
Following PRISMA, Supplemental Digital Content 1 (http://links.lww.com/JS9/C77) and Supplemental Digital Content 2 (http://links.lww.com/JS9/C78), and AMSTAR-2 guidelines, Supplemental Digital Content 3 (http://links.lww.com/JS9/C79), we systematically searched PubMed, Web of Science, Embase, Cochrane Library, and Google Scholar databases until 11 January 2024, to evaluate radiomics models' diagnostic precision in predicting preoperative LNM in CRC patients. The quality and bias risk of the included studies were assessed using the Radiomics Quality Score (RQS) and the modified Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) tool. Subsequently, statistical analyses were conducted.
RESULTS
Thirty-six studies encompassing 8039 patients were included, with a significant concentration in 2022-2023 (20/36). Radiomics models predicting LNM demonstrated a pooled area under the curve (AUC) of 0.814 (95% CI: 0.78-0.85), featuring sensitivity and specificity of 0.77 (95% CI: 0.69, 0.84) and 0.73 (95% CI: 0.67, 0.78), respectively. Subgroup analyses revealed similar AUCs for CT and MRI-based models, and rectal cancer models outperformed colon and colorectal cancers. Additionally, studies utilizing cross-validation, 2D segmentation, internal validation, manual segmentation, prospective design, and single-center populations tended to have higher AUCs. However, these differences were not statistically significant. Radiologists collectively achieved a pooled AUC of 0.659 (95% CI: 0.627, 0.691), significantly differing from the performance of radiomics models (P<0.001).
CONCLUSION
Artificial intelligence-based radiomics shows promise in preoperative lymph node staging for CRC, exhibiting significant predictive performance. These findings support the integration of radiomics into clinical practice to enhance preoperative strategies in CRC management.
Topics: Humans; Colorectal Neoplasms; Lymphatic Metastasis; Lymph Nodes; Radiomics
PubMed: 38935817
DOI: 10.1097/JS9.0000000000001239 -
The Indian Journal of Radiology &... Jul 2024Although abundant literature is currently available on the use of deep learning for breast cancer detection in mammography, the quality of such literature is widely... (Review)
Review
Although abundant literature is currently available on the use of deep learning for breast cancer detection in mammography, the quality of such literature is widely variable. To evaluate published literature on breast cancer detection in mammography for reproducibility and to ascertain best practices for model design. The PubMed and Scopus databases were searched to identify records that described the use of deep learning to detect lesions or classify images into cancer or noncancer. A modification of Quality Assessment of Diagnostic Accuracy Studies (mQUADAS-2) tool was developed for this review and was applied to the included studies. Results of reported studies (area under curve [AUC] of receiver operator curve [ROC] curve, sensitivity, specificity) were recorded. A total of 12,123 records were screened, of which 107 fit the inclusion criteria. Training and test datasets, key idea behind model architecture, and results were recorded for these studies. Based on mQUADAS-2 assessment, 103 studies had high risk of bias due to nonrepresentative patient selection. Four studies were of adequate quality, of which three trained their own model, and one used a commercial network. Ensemble models were used in two of these. Common strategies used for model training included patch classifiers, image classification networks (ResNet in 67%), and object detection networks (RetinaNet in 67%). The highest reported AUC was 0.927 ± 0.008 on a screening dataset, while it reached 0.945 (0.919-0.968) on an enriched subset. Higher values of AUC (0.955) and specificity (98.5%) were reached when combined radiologist and Artificial Intelligence readings were used than either of them alone. None of the studies provided explainability beyond localization accuracy. None of the studies have studied interaction between AI and radiologist in a real world setting. While deep learning holds much promise in mammography interpretation, evaluation in a reproducible clinical setting and explainable networks are the need of the hour.
PubMed: 38912238
DOI: 10.1055/s-0043-1775737 -
Diagnostics (Basel, Switzerland) May 2024This study delves into the cutting-edge field of deep learning techniques, particularly deep convolutional neural networks (DCNNs), which have demonstrated unprecedented... (Review)
Review
OBJECTIVES
This study delves into the cutting-edge field of deep learning techniques, particularly deep convolutional neural networks (DCNNs), which have demonstrated unprecedented potential in assisting radiologists and orthopedic surgeons in precisely identifying meniscal tears. This research aims to evaluate the effectiveness of deep learning models in recognizing, localizing, describing, and categorizing meniscal tears in magnetic resonance images (MRIs).
MATERIALS AND METHODS
This systematic review was rigorously conducted, strictly following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Extensive searches were conducted on MEDLINE (PubMed), Web of Science, Cochrane Library, and Google Scholar. All identified articles underwent a comprehensive risk of bias analysis. Predictive performance values were either extracted or calculated for quantitative analysis, including sensitivity and specificity. The meta-analysis was performed for all prediction models that identified the presence and location of meniscus tears.
RESULTS
This study's findings underscore that a range of deep learning models exhibit robust performance in detecting and classifying meniscal tears, in one case surpassing the expertise of musculoskeletal radiologists. Most studies in this review concentrated on identifying tears in the medial or lateral meniscus and even precisely locating tears-whether in the anterior or posterior horn-with exceptional accuracy, as demonstrated by AUC values ranging from 0.83 to 0.94.
CONCLUSIONS
Based on these findings, deep learning models have showcased significant potential in analyzing knee MR images by learning intricate details within images. They offer precise outcomes across diverse tasks, including segmenting specific anatomical structures and identifying pathological regions. Contributions: This study focused exclusively on DL models for identifying and localizing meniscus tears. It presents a meta-analysis that includes eight studies for detecting the presence of a torn meniscus and a meta-analysis of three studies with low heterogeneity that localize and classify the menisci. Another novelty is the analysis of arthroscopic surgery as ground truth. The quality of the studies was assessed against the CLAIM checklist, and the risk of bias was determined using the QUADAS-2 tool.
PubMed: 38893617
DOI: 10.3390/diagnostics14111090 -
Cureus Apr 2024This review article explores spinal injuries in athletes participating in various sporting activities. It also highlights the various mechanisms of injuries that... (Review)
Review
This review article explores spinal injuries in athletes participating in various sporting activities. It also highlights the various mechanisms of injuries that contribute to spinal injuries in each sport. Electronic databases such as PubMed, Cochrane Library, Web of Science, Embase, MEDLINE Ovid, and Google Scholar were searched for articles from 2000 to 2022 on spine injuries in sports and radiological studies discussing the various injury patterns among athletes. Studies were scoured in accordance with the inclusion criteria, and relevant data such as the number of participants, sporting activities, spine injuries, and outcomes were retrieved. Fifteen articles that met the inclusion criteria were included in the study. Cervical spine injuries are common in athletes who participate in contact sports such as football. Similarly, athletes in collision sports such as football, rugby, and hockey are likely to suffer stingers due to traction and compression injuries. Players engaged in such as soccer, baseball, and swimming, are likely to suffer from spondylolysis. Soccer players are more prone to multiple lesions compared to athletes in sports such as baseball because the sport involves training exercises such as jogging and running without kicking any ball. In swimmers, spondylolysis is common in breaststroke and butterfly styles since they involve repeated flexion and hyperextension of the lumbar spine. CT is essential for diagnosing spondylolysis as it demonstrates the lesions more accurately. Ice hockey is associated with a significant incidence of cervical spine injuries, mostly due to players being constantly checked/pushed from behind. Spine injuries are common in elite athletes across several sports. About 10% of spinal injuries in the United States result from sports activities. In diagnosing spine injuries, imaging modalities such as MRI, CT, or plain radiographs are essential. From a radiologist's perspective, these tests help immensely in deciding which treatment is required for a particular athlete or how the injury can be optimally managed. Achieving recovery from a specific spine injury usually depends on the kind of injury and the rehabilitation process the athletes undergo before returning to play.
PubMed: 38784300
DOI: 10.7759/cureus.58780 -
Diagnostic and Interventional Imaging 2024The purpose of this study was to systematically review the reported performances of ChatGPT, identify potential limitations, and explore future directions for its... (Review)
Review
PURPOSE
The purpose of this study was to systematically review the reported performances of ChatGPT, identify potential limitations, and explore future directions for its integration, optimization, and ethical considerations in radiology applications.
MATERIALS AND METHODS
After a comprehensive review of PubMed, Web of Science, Embase, and Google Scholar databases, a cohort of published studies was identified up to January 1, 2024, utilizing ChatGPT for clinical radiology applications.
RESULTS
Out of 861 studies derived, 44 studies evaluated the performance of ChatGPT; among these, 37 (37/44; 84.1%) demonstrated high performance, and seven (7/44; 15.9%) indicated it had a lower performance in providing information on diagnosis and clinical decision support (6/44; 13.6%) and patient communication and educational content (1/44; 2.3%). Twenty-four (24/44; 54.5%) studies reported the proportion of ChatGPT's performance. Among these, 19 (19/24; 79.2%) studies recorded a median accuracy of 70.5%, and in five (5/24; 20.8%) studies, there was a median agreement of 83.6% between ChatGPT outcomes and reference standards [radiologists' decision or guidelines], generally confirming ChatGPT's high accuracy in these studies. Eleven studies compared two recent ChatGPT versions, and in ten (10/11; 90.9%), ChatGPTv4 outperformed v3.5, showing notable enhancements in addressing higher-order thinking questions, better comprehension of radiology terms, and improved accuracy in describing images. Risks and concerns about using ChatGPT included biased responses, limited originality, and the potential for inaccurate information leading to misinformation, hallucinations, improper citations and fake references, cybersecurity vulnerabilities, and patient privacy risks.
CONCLUSION
Although ChatGPT's effectiveness has been shown in 84.1% of radiology studies, there are still multiple pitfalls and limitations to address. It is too soon to confirm its complete proficiency and accuracy, and more extensive multicenter studies utilizing diverse datasets and pre-training techniques are required to verify ChatGPT's role in radiology.
Topics: Humans; Radiology; Forecasting
PubMed: 38679540
DOI: 10.1016/j.diii.2024.04.003 -
Clinical Colorectal Cancer Jun 2024A survey of medical oncologists (MOs), radiation oncologists (ROs), and surgical oncologists (SOs) who are experts in the management of patients with metastatic...
BACKGROUND
A survey of medical oncologists (MOs), radiation oncologists (ROs), and surgical oncologists (SOs) who are experts in the management of patients with metastatic colorectal cancer (mCRC) was conducted to identify factors used to consider metastasis-directed therapy (MDT).
MATERIALS AND METHODS
An online survey to assess clinical factors when weighing MDT in patients with mCRC was developed based on systematic review of the literature and integrated with clinical vignettes. Supporting evidence from the systematic review was included to aid in answering questions.
RESULTS
Among 75 experts on mCRC invited, 47 (response rate 62.7%) chose to participate including 16 MOs, 16 ROs, and 15 SOs. Most experts would not consider MDT in patients with 3 lesions in both the liver and lung regardless of distribution or timing of metastatic disease diagnosis (6 vs. 36 months after definitive treatment). Similarly, for patients with retroperitoneal lymph node and lung and liver involvement, most experts would not offer MDT regardless of timing of metastatic disease diagnosis. In general, SOs were willing to consider MDT in patients with more advanced disease, ROs were more willing to offer treatment regardless of metastatic site location, and MOs were the least likely to consider MDT.
CONCLUSIONS
Among experts caring for patients with mCRC, significant variation was noted among MOs, ROs, and SOs in the distribution and volume of metastatic disease for which MDT would be considered. This variability highlights differing opinions on management of these patients and underscores the need for well-designed prospective randomized trials to characterize the risks and potential benefits of MDT.
Topics: Humans; Colorectal Neoplasms; Surveys and Questionnaires; Oncologists; Liver Neoplasms; Neoplasm Metastasis; Male; Female; Practice Patterns, Physicians'; Lung Neoplasms; Radiation Oncologists; Clinical Decision-Making; Middle Aged
PubMed: 38365567
DOI: 10.1016/j.clcc.2024.01.004 -
Journal of Biomedical Physics &... Feb 2024Based on the Liver Imaging Data and Reporting System (LI-RADS) guidelines, Hepatocellular Carcinoma (HCC) can be diagnosed using imaging criteria in patients at risk of... (Review)
Review
Evidence Supporting Diagnostic Value of Liver Imaging Reporting and Data System for CT- and MR Imaging-based Diagnosis of Hepatocellular Carcinoma: A Systematic Review and Meta-analysis.
BACKGROUND
Based on the Liver Imaging Data and Reporting System (LI-RADS) guidelines, Hepatocellular Carcinoma (HCC) can be diagnosed using imaging criteria in patients at risk of HCC.
OBJECTIVE
This study aimed to assess the diagnostic value of LI-RADS in high-risk patients with HCC.
MATERIAL AND METHODS
This systematic review is conducted on international databases, including Google Scholar, Web of Science, PubMed, Embase, PROQUEST, and Cochrane Library, with appropriate keywords. Using the binomial distribution formula, the variance of each study was calculated, and all the data were analyzed using STATA version 16. The pooled sensitivity and specificity were determined using a random-effects meta-analysis approach. Also, we used the chi-squared test and I index to calculate heterogeneity among studies, and Funnel plots and Egger tests were used for evaluating publication bias.
RESULTS
The pooled sensitivity was estimated at 0.80 (95% CI 0.76-0.84). According to different types of Liver Imaging Reporting and Data Systems (LI-RADS), the highest pooled sensitivity was in version 2018 (0.83 (95% CI 0.79-0.87) (I: 80.6%, of chi 2 test for heterogeneity <0.001 and T: 0.001). The pooled specificity was estimated as 0.89 (95% CI 0.87-0.92). According to different types of LI-RADS, the highest pooled specificity was in version 2014 (93.0 (95% CI 89.0-96.0) (I: 81.7%, of chi 2 test for heterogeneity <0.001 and T: 0.001).
CONCLUSION
LI-RADS can assist radiologists in achieving the required sensitivity and specificity in high-risk patients suspected to have HCC. Therefore, this strategy can serve as an appropriate tool for identifying HCC.
PubMed: 38357604
DOI: 10.31661/jbpe.v0i0.2211-1562 -
European Journal of Radiology Mar 2024X-ray imaging plays a crucial role in diagnostic medicine. Yet, a significant portion of the global population lacks access to this essential technology due to a... (Review)
Review
X-ray imaging plays a crucial role in diagnostic medicine. Yet, a significant portion of the global population lacks access to this essential technology due to a shortage of trained radiologists. Eye-tracking data and deep learning models can enhance X-ray analysis by mapping expert focus areas, guiding automated anomaly detection, optimizing workflow efficiency, and bolstering training methods for novice radiologists. However, the literature shows contradictory results regarding the usefulness of eye-tracking data in deep-learning architectures for abnormality detection. We argue that these discrepancies between studies in the literature are due to (a) the way eye-tracking data is (or is not) processed, (b) the types of deep learning architectures chosen, and (c) the type of application that these architectures will have. We conducted a systematic literature review using PRISMA to address these contradicting results. We analyzed 60 studies that incorporated eye-tracking data in a deep-learning approach for different application goals in radiology. We performed a comparative analysis to understand if eye gaze data contains feature maps that can be useful under a deep learning approach and whether they can promote more interpretable predictions. To the best of our knowledge, this is the first survey in the area that performs a thorough investigation of eye gaze data processing techniques and their impacts in different deep learning architectures for applications such as error detection, classification, object detection, expertise level analysis, fatigue estimation and human attention prediction in medical imaging data. Our analysis resulted in two main contributions: (1) taxonomy that first divides the literature by task, enabling us to analyze the value eye movement can bring for each case and build guidelines regarding architectures and gaze processing techniques adequate for each application, and (2) an overall analysis of how eye gaze data can promote explainability in radiology.
Topics: Humans; Fixation, Ocular; Deep Learning; Radiography; Radiology; Eye Movements
PubMed: 38340426
DOI: 10.1016/j.ejrad.2024.111341 -
Emergency Radiology Apr 2024Pediatric distal forearm fractures, comprising 30% of musculoskeletal injuries in children, are conventionally diagnosed using radiography. Ultrasound has emerged as a... (Meta-Analysis)
Meta-Analysis Review
Pediatric distal forearm fractures, comprising 30% of musculoskeletal injuries in children, are conventionally diagnosed using radiography. Ultrasound has emerged as a safer diagnostic tool, eliminating ionizing radiation, enabling bedside examinations with real-time imaging, and proving effective in non-hospital settings. The objective of this study is to evaluate the diagnostic efficacy of ultrasound for detecting distal forearm fractures in the pediatric population. A systematic review and meta-analysis were conducted through a comprehensive literature search in PubMed, Scopus, Web of Science, and Embase databases until October 1, 2023, following established guidelines. Eligible studies, reporting diagnostic accuracy measures of ultrasound in pediatric patients with distal forearm fractures, were included. Relevant data elements were extracted, and data analysis was performed. The analysis included 14 studies with 1377 patients, revealing pooled sensitivity and specificity of 94.5 (95% CI 92.7-95.9) and 93.5 (95% CI 89.6-96.0), respectively. Considering pre-test probabilities of 25%, 50%, and 75% for pediatric distal forearm fractures, positive post-test probabilities were 83%, 44%, and 98%, while negative post-test probabilities were 2%, 6%, and 15%, respectively. The bivariate model indicated significantly higher diagnostic accuracy in the subgroup with trained ultrasound performers vs. untrained performers (p = 0.03). Furthermore, diagnostic accuracy was significantly higher in the subgroup examining radius fractures vs. ulna fractures (p < 0.001), while no significant differences were observed between 4-view and 6-view ultrasound subgroups or between radiologist ultrasound interpreters and non-radiologist interpreters. This study highlighted ultrasound's reliability in detecting pediatric distal forearm fractures, emphasizing the crucial role of expertise in precisely confirming fractures through ultrasound examinations.
Topics: Child; Humans; Wrist Fractures; Reproducibility of Results; Prospective Studies; Radius Fractures; Ulna Fractures; Ultrasonography; Forearm Injuries
PubMed: 38311698
DOI: 10.1007/s10140-024-02208-2 -
Clinical Imaging Mar 2024Although several studies have compared the performance of deep learning (DL) models and radiologists for the diagnosis of COVID-19 pneumonia on CT of the chest, these... (Meta-Analysis)
Meta-Analysis Review
PURPOSE
Although several studies have compared the performance of deep learning (DL) models and radiologists for the diagnosis of COVID-19 pneumonia on CT of the chest, these results have not been collectively evaluated. We performed a meta-analysis of original articles comparing the performance of DL models versus radiologists in detecting COVID-19 pneumonia.
METHODS
A systematic search was conducted on the three main medical literature databases, Scopus, Web of Science, and PubMed, for articles published as of February 1st, 2023. We included original scientific articles that compared DL models trained to detect COVID-19 pneumonia on CT to radiologists. Meta-analysis was performed to determine DL versus radiologist performance in terms of model sensitivity and specificity, taking into account inter and intra-study heterogeneity.
RESULTS
Twenty-two articles met the inclusion criteria. Based on the meta-analytic calculations, DL models had significantly higher pooled sensitivity (0.933 vs. 0.829, p < 0.001) compared to radiologists with similar pooled specificity (0.905 vs. 0.897, p = 0.746). In the differentiation of COVID-19 versus community-acquired pneumonia, the DL models had significantly higher sensitivity compared to radiologists (0.915 vs. 0.836, p = 0.001).
CONCLUSIONS
DL models have high performance for screening of COVID-19 pneumonia on chest CT, offering the possibility of these models for augmenting radiologists in clinical practice.
Topics: Humans; COVID-19; SARS-CoV-2; Deep Learning; Retrospective Studies; Pneumonia; Radiologists; COVID-19 Testing
PubMed: 38301371
DOI: 10.1016/j.clinimag.2024.110092