-
La Radiologia Medica Apr 2024Artificial intelligence (AI) holds enormous potential for noninvasively identifying patients with rectal cancer who could achieve pathological complete response (pCR)... (Meta-Analysis)
Meta-Analysis Review
Image-based artificial intelligence for the prediction of pathological complete response to neoadjuvant chemoradiotherapy in patients with rectal cancer: a systematic review and meta-analysis.
OBJECTIVE
Artificial intelligence (AI) holds enormous potential for noninvasively identifying patients with rectal cancer who could achieve pathological complete response (pCR) following neoadjuvant chemoradiotherapy (nCRT). We aimed to conduct a meta-analysis to summarize the diagnostic performance of image-based AI models for predicting pCR to nCRT in patients with rectal cancer.
METHODS
This study followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. A literature search of PubMed, Embase, Cochrane Library, and Web of Science was performed from inception to July 29, 2023. Studies that developed or utilized AI models for predicting pCR to nCRT in rectal cancer from medical images were included. The Quality Assessment of Diagnostic Accuracy Studies-AI was used to appraise the methodological quality of the studies. The bivariate random-effects model was used to summarize the individual sensitivities, specificities, and areas-under-the-curve (AUCs). Subgroup and meta-regression analyses were conducted to identify potential sources of heterogeneity. Protocol for this study was registered with PROSPERO (CRD42022382374).
RESULTS
Thirty-four studies (9933 patients) were identified. Pooled estimates of sensitivity, specificity, and AUC of AI models for pCR prediction were 82% (95% CI: 76-87%), 84% (95% CI: 79-88%), and 90% (95% CI: 87-92%), respectively. Higher specificity was seen for the Asian population, low risk of bias, and deep-learning, compared with the non-Asian population, high risk of bias, and radiomics (all P < 0.05). Single-center had a higher sensitivity than multi-center (P = 0.001). The retrospective design had lower sensitivity (P = 0.012) but higher specificity (P < 0.001) than the prospective design. MRI showed higher sensitivity (P = 0.001) but lower specificity (P = 0.044) than non-MRI. The sensitivity and specificity of internal validation were higher than those of external validation (both P = 0.005).
CONCLUSIONS
Image-based AI models exhibited favorable performance for predicting pCR to nCRT in rectal cancer. However, further clinical trials are warranted to verify the findings.
Topics: Humans; Artificial Intelligence; Retrospective Studies; Neoadjuvant Therapy; Chemoradiotherapy; Rectal Neoplasms
PubMed: 38512622
DOI: 10.1007/s11547-024-01796-w -
Academic Radiology May 2024To evaluate radiomics in soft tissue sarcomas (STSs) for diagnostic accuracy, grading, and treatment response assessment, with a focus on clinical relevance. (Review)
Review
RATIONALE AND OBJECTIVES
To evaluate radiomics in soft tissue sarcomas (STSs) for diagnostic accuracy, grading, and treatment response assessment, with a focus on clinical relevance.
METHODS
In this diagnostic accuracy study, radiomics was applied using multiple MRI sequences and AI classifiers, with histopathological diagnosis as the reference standard. Statistical analysis involved meta-analysis, random-effects model, and Deeks' funnel plot asymmetry test.
RESULTS
Among 579 unique titles and abstracts, 24 articles were included in the systematic review, with 21 used for meta-analysis. Radiomics demonstrated a pooled sensitivity of 84% (95% CI: 80-87) and specificity of 63% (95% CI: 56-70), AUC of 0.93 for diagnosis, sensitivity of 84% (95% CI: 82-87) and specificity of 73% (95% CI: 68-77), AUC of 0.91 for grading, and sensitivity of 83% (95% CI: 67-94) and specificity of 67% (95% CI: 59-74), AUC of 0.87 for treatment response assessment.
CONCLUSION
Radiomics exhibits potential for accurate diagnosis, grading, and treatment response assessment in STSs, emphasizing the need for standardization and prospective trials.
CLINICAL RELEVANCE STATEMENT
Radiomics offers precise tools for STS diagnosis, grading, and treatment response assessment, with implications for optimizing patient care and treatment strategies in this complex malignancy.
PubMed: 38772802
DOI: 10.1016/j.acra.2024.03.029 -
Epilepsy & Behavior : E&B May 2023Different neurostimulation modalities are available to treat drug-resistant focal epilepsy when surgery is not an option including vagus nerve stimulation (VNS),... (Meta-Analysis)
Meta-Analysis Review
OBJECTIVES
Different neurostimulation modalities are available to treat drug-resistant focal epilepsy when surgery is not an option including vagus nerve stimulation (VNS), responsive neurostimulation (RNS), and deep brain stimulation (DBS). Head-to-head comparisons of efficacy do not exist between them nor are likely to be available in the future. We performed a meta-analysis on VNS, RNS, and DBS outcomes to compare seizure reduction efficacy for focal epilepsy.
METHODS
We systematically reviewed the literature for reported seizure outcomes following implantation with VNS, RNS, and DBS in focal-onset seizures and performed a meta-analysis. Prospective or retrospective clinical studies were included.
RESULTS
Sufficient data were available at years one (n = 642, two (n = 480), and three (n = 385) for comparing the three modalities with each other. Seizure reduction for the devices at years one, two, and three respectively were: RNS: 66.3%, 56.0%, 68.4%; DBS- 58.4%, 57.5%, 63.8%; VNS 32.9%, 44.4%, 53.5%. Seizure reduction at year one was greater for RNS (p < 0.01) and DBS (p < 0.01) compared to VNS.
CONCLUSIONS
Our findings indicate the seizure reduction efficacy of RNS is similar to DBS, and both had greater seizure reductions compared to VNS in the first-year post-implantation, with the differences diminishing with longer-term follow-up.
SIGNIFICANCE
The results help guide neuromodulation treatment in eligible patients with drug-resistant focal epilepsy.
Topics: Humans; Retrospective Studies; Prospective Studies; Deep Brain Stimulation; Epilepsies, Partial; Drug Resistant Epilepsy; Seizures; Vagus Nerve Stimulation; Treatment Outcome
PubMed: 36972642
DOI: 10.1016/j.yebeh.2023.109182 -
European Radiology Experimental Jan 2020A wide range of cancer immunotherapy approaches has been developed including non-specific immune-stimulants such as cytokines, cancer vaccines, immune checkpoint...
A wide range of cancer immunotherapy approaches has been developed including non-specific immune-stimulants such as cytokines, cancer vaccines, immune checkpoint inhibitors (ICIs), and adoptive T cell therapy. Among them, ICIs are the most commonly used and intensively studied. Since 2011, these drugs have received marketing authorisation for melanoma, lung, bladder, renal, and head and neck cancers, with remarkable and long-lasting treatment response in some patients. The novel mechanism of action of ICIs, with immune and T cell activation, leads to unusual patterns of response on imaging, with the advent of so-called pseudoprogression being more pronounced and frequently observed when compared to other anticancer therapies. Pseudoprogression, described in about 2-10% of patients treated with ICIs, corresponds to an increase of tumour burden and/or the appearance of new lesions due to infiltration by activated T cells before the disease responds to therapy. To overcome the limitation of response evaluation criteria in solid tumors (RECIST) to assess these specific changes, new imaging criteria-so-called immune-related response criteria and then immune-related RECIST (irRECIST)-were proposed. The major modification involved the inclusion of the measurements of new target lesions into disease assessments and the need for a 4-week re-assessment to confirm or not confirm progression. The RECIST working group introduced the new concept of "unconfirmed progression", into the irRECIST. This paper reviews current immunotherapeutic approaches and summarises radiologic criteria to evaluate new patterns of response to immunotherapy. Furthermore, imaging features of immunotherapy-related adverse events and available predictive biomarkers of response are presented.
Topics: Diagnostic Imaging; Humans; Immunotherapy; Neoplasms; Response Evaluation Criteria in Solid Tumors
PubMed: 31900689
DOI: 10.1186/s41747-019-0134-1 -
Radiology Sep 2005To compare diagnostic accuracy of computed tomography (CT), endoscopic ultrasonography (US), and fluorine 18 fluorodeoxyglucose (FDG) positron emission tomography (PET)... (Review)
Review
PURPOSE
To compare diagnostic accuracy of computed tomography (CT), endoscopic ultrasonography (US), and fluorine 18 fluorodeoxyglucose (FDG) positron emission tomography (PET) for assessment of response to neoadjuvant therapy in patients with esophageal cancer by using a systematic review of the literature.
MATERIALS AND METHODS
MEDLINE and EMBASE databases and Cochrane Database of Systematic Reviews were searched for relevant studies. Two reviewers independently assessed the methodological quality of each study. Summary receiver operating characteristic (ROC) analysis was used to summarize and compare the diagnostic accuracy of the three modalities.
RESULTS
Four studies with CT, 13 with endoscopic US, and seven with FDG PET met inclusion criteria. Percentages of the maximum score in regard to methodological quality ranged from 15% to 100%. Summary ROC analysis could be performed for three studies with CT, four with endoscopic US, and four with FDG PET. The maximum joint values for sensitivity and specificity were 54% for CT, 86% for endoscopic US, and 85% for FDG PET. Accuracy of CT was significantly lower than that of FDG PET (P < .006) and of endoscopic US (P < .003). Accuracy of FDG PET and that of endoscopic US were similar (P = .839). In all patients, CT was always feasible, whereas endoscopic US was not feasible in 6% of the patients, and FDG PET was not feasible in less than 1%.
CONCLUSION
CT has poor accuracy for assessment of response to neoadjuvant therapy in patients with esophageal cancer. Endoscopic US and FDG PET have equivalent good accuracy, but endoscopic US is not always feasible after chemotherapy and radiation therapy. FDG PET seems to be a promising noninvasive tool for assessment of neoadjuvant therapy in patients with esophageal cancer.
Topics: Endosonography; Esophageal Neoplasms; Fluorodeoxyglucose F18; Humans; Neoadjuvant Therapy; Positron-Emission Tomography; ROC Curve; Radiopharmaceuticals; Sensitivity and Specificity; Tomography, Emission-Computed
PubMed: 16118165
DOI: 10.1148/radiol.2363041042 -
Digestive Endoscopy : Official Journal... Apr 2024Endoscopic ultrasound-guided radiofrequency ablation (EUS-RFA) has been constantly increasing, particularly in the treatment of pancreatic neuroendocrine neoplasms... (Meta-Analysis)
Meta-Analysis Review
OBJECTIVE
Endoscopic ultrasound-guided radiofrequency ablation (EUS-RFA) has been constantly increasing, particularly in the treatment of pancreatic neuroendocrine neoplasms (pNENs). While emerging data in this field are accumulating, we aimed to assess the pooled efficacy and safety of EUS-RFA for pNENs.
METHODS
The PubMed/Medline, Embase, and Cochrane Library databases search was conducted to identify studies reporting EUS-RFA of pNENs with outcomes of interest (efficacy and safety). The primary outcome was radiological response. Efficacy was assessed by the pooled clinical response rate, whereas safety was assessed by the pooled adverse events (AEs) rate. Heterogeneity was assessed using I. Pooled estimates and the 95% confidence interval (CI) were calculated using a random-effect model.
RESULTS
Eleven studies involving 292 patients were included. The pooled technical success rate was 99.2% (95% CI 97.9-99.9%), with no heterogeneity. The pooled complete radiological response was 87.1% (95% CI 80.1-92.8%). The pooled partial response was 11.4% (95% CI 6.2-18.1%). The pooled clinical response rate for functional pNENs was 94.9% (95% CI 90.7-97.9%), with no heterogeneity. The pooled incidence of AEs was 20.0% (95% CI 14.0-26.7%); most AEs were mild to moderate in grade, while the pooled incidence of severe AEs was 0.9% (95% CI 0.2-2.3%). The most common AEs were transient mild abdominal pain in 19 patients (6.5%), and mild to moderate pancreatitis in 23 patients (7.9%). No cases of mortality were reported.
CONCLUSION
Endoscopic ultrasound-guided radiofrequency ablation resulted on a feasible approach for pNENs treatment, with excellent technical success, high radiological and clinical response, and acceptable AE rate.
Topics: Humans; Pancreatic Neoplasms; Endosonography; Radiofrequency Ablation; Pancreatitis; Ultrasonography, Interventional
PubMed: 37702096
DOI: 10.1111/den.14681 -
Radiotherapy and Oncology : Journal of... Jan 2020The aim was to perform a systematic review on the value of diffusion-weighted MRI (DW-MRI) with apparent diffusion coefficient (ADC) mapping in the prediction and...
PURPOSE
The aim was to perform a systematic review on the value of diffusion-weighted MRI (DW-MRI) with apparent diffusion coefficient (ADC) mapping in the prediction and assessment of response to chemo- and/or radiotherapy in oesophageal cancer.
MATERIALS AND METHODS
A systematic search was performed on Pubmed, Embase, Medline and Cochrane databases. Studies that evaluated the ADC for response evaluation before, during or after chemo- and/or radiotherapy were included. The Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) was used to assess the quality of the included studies.
RESULTS
Fourteen studies, comprising 516 patients, in which the response to treatment in oesophageal cancer was evaluated on ADC maps were included. Acquisition parameter settings for DW-MRI and ROI placement varied substantially. The reference standard was RECIST or endoscopic assessment in eight non-surgery studies and histopathology after surgery in six studies. A high pre-treatment ADC significantly correlated with good response in three out of 12 studies; conversely, one study reported a significantly higher pre-treatment ADC in poor responders. In five out of eight studies good responders showed a significantly larger relative increase in ADC two weeks after the onset of treatment (range 23-59%) than poor responders (range 1.5-17%). After chemo- and/or radiotherapy ADC results varied considerably, amongst others due to large variation in the interval between completion of therapy and DW-MRI.
CONCLUSION
DW-MRI for response evaluation to chemo- and/or radiotherapy in oesophageal cancer shows variable methods and results. A large relative ADC increase after two weeks of treatment seems most predictive for good response.
Topics: Chemoradiotherapy, Adjuvant; Diffusion Magnetic Resonance Imaging; Esophageal Neoplasms; Humans; Neoadjuvant Therapy
PubMed: 31431376
DOI: 10.1016/j.radonc.2019.07.006 -
Abdominal Radiology (New York) Aug 2021To perform a systematic review and meta-analysis using individual patient data to investigate the diagnostic performance of Liver Imaging Reporting and Data System... (Meta-Analysis)
Meta-Analysis
LI-RADS treatment response algorithm for detecting incomplete necrosis in hepatocellular carcinoma after locoregional treatment: a systematic review and meta-analysis using individual patient data.
PURPOSE
To perform a systematic review and meta-analysis using individual patient data to investigate the diagnostic performance of Liver Imaging Reporting and Data System (LI-RADS) Treatment Response (TR) algorithm for detecting incomplete necrosis on pathology.
METHODS
PubMed and EMBASE were searched from Jan 1, 2017 until October 14, 2020. Studies reporting diagnostic accuracy of LI-RADS TR algorithm on CT or MRI for detecting incomplete necrosis on pathology as a reference standard were included. Sensitivity and specificity were pooled using random-effects model. Subgroup analyses were performed for locoregional treatment (LRT) type and imaging modality.
RESULTS
Six studies (393 patients, 534 lesions) were included. Pooled sensitivity was 0.56 (95% confidence interval [CI] 0.43-0.69) and specificity was 0.91 (95%CI 0.84-0.96). Pooled sensitivity was highest using arterial phase hyperenhancement (APHE) (0.67 [95%CI 0.51-0.81]), followed by washout (0.43 [95%CI 0.26-0.62]) and enhancement similar to pretreatment (0.24 [95%CI 0.15-0.36]). Among lesions with incomplete necrosis, 2% (95%CI 0.00-0.05) manifested as washout but no APHE; 0% (95% CI 0.00-0.02) as enhancement similar to pretreatment without both APHE and washout. Pooled sensitivity was lower after ablation than embolization (0.42 [95%CI, 0.28-0.57] vs. 0.65 [95%CI, 0.53-0.77], p = 0.033). MRI and CT were comparable (p = 0.783 and 0.290 for sensitivity and specificity).
CONCLUSIONS
LI-RADS TR algorithm shows moderate sensitivity and high specificity for detecting incomplete necrosis after LRT. APHE is the dominant criterion, a washout contributes to small but meaningful extent, while the contribution of enhancement similar to pretreatment may be negligible. LRT type may affect performance of the algorithm.
Topics: Algorithms; Carcinoma, Hepatocellular; Contrast Media; Humans; Liver Neoplasms; Magnetic Resonance Imaging; Necrosis; Retrospective Studies; Sensitivity and Specificity
PubMed: 34027566
DOI: 10.1007/s00261-021-03122-8 -
Frontiers in Bioscience (Landmark... Dec 2021Both stress and hypertension (HTN) are considered major health problems that negatively impact the cerebral vasculature. In this article we summarize the possible... (Review)
Review
OBJECTIVES
Both stress and hypertension (HTN) are considered major health problems that negatively impact the cerebral vasculature. In this article we summarize the possible relationship between stress and HTN.
METHODS
We conducted a systematic review of the literature using a database search of MEDLINE, PubMed, Scopus, and Web of Science.
RESULTS
Psychological stress is known to be an important risk factor for essential hypertension. Acute stress can induce transient elevations of blood pressure in the context of the fight-or-flight response. With increased intensity and duration of a perceived harmful event, the normal physiological response is altered, resulting in a failure to return to the resting levels. These changes are responsible for the development of HTN. Genetic and behavioral factors are also very important for the pathogenesis of hypertension under chronic stress situation. In addition, HTN and chronic stress may lead to impaired auto-regulation, regional vascular remodeling, and breakdown of the blood brain barrier (BBB). The effects of both HTN and chronic stress on the cerebral blood vessels shows that both have common structural and functional effects including endothelial damage with subsequent increased wall thickness, vessel resistance, stiffness, arterial atherosclerosis, and altered hemodynamics.
CONCLUSION
Most of the above mentioned vascular effects of stress were primarily reported in animal models. Further in-vivo standardization of pathological vascular indices and imaging modalities is warranted. Radiological quantification of these cerebrovascular changes is therefore essential for in depth understanding of the healthy and diseased cerebral arteries functions, identification and stratification of patients at risk of cardiovascular and neurological adverse events, enactment of preventive measures prior to the onset of systemic HTN, and the initiation of personalized medical management.
Topics: Animals; Blood Pressure; Humans; Hypertension; Vascular Remodeling
PubMed: 34994178
DOI: 10.52586/5057 -
European Radiology Oct 2017Treatment response assessment in high-grade gliomas uses contrast enhanced T1-weighted MRI, but is unreliable. Novel advanced MRI techniques have been studied, but the... (Meta-Analysis)
Meta-Analysis Review
OBJECTIVE
Treatment response assessment in high-grade gliomas uses contrast enhanced T1-weighted MRI, but is unreliable. Novel advanced MRI techniques have been studied, but the accuracy is not well known. Therefore, we performed a systematic meta-analysis to assess the diagnostic accuracy of anatomical and advanced MRI for treatment response in high-grade gliomas.
METHODS
Databases were searched systematically. Study selection and data extraction were done by two authors independently. Meta-analysis was performed using a bivariate random effects model when ≥5 studies were included.
RESULTS
Anatomical MRI (five studies, 166 patients) showed a pooled sensitivity and specificity of 68% (95%CI 51-81) and 77% (45-93), respectively. Pooled apparent diffusion coefficients (seven studies, 204 patients) demonstrated a sensitivity of 71% (60-80) and specificity of 87% (77-93). DSC-perfusion (18 studies, 708 patients) sensitivity was 87% (82-91) with a specificity of 86% (77-91). DCE-perfusion (five studies, 207 patients) sensitivity was 92% (73-98) and specificity was 85% (76-92). The sensitivity of spectroscopy (nine studies, 203 patients) was 91% (79-97) and specificity was 95% (65-99).
CONCLUSION
Advanced techniques showed higher diagnostic accuracy than anatomical MRI, the highest for spectroscopy, supporting the use in treatment response assessment in high-grade gliomas.
KEY POINTS
• Treatment response assessment in high-grade gliomas with anatomical MRI is unreliable • Novel advanced MRI techniques have been studied, but diagnostic accuracy is unknown • Meta-analysis demonstrates that advanced MRI showed higher diagnostic accuracy than anatomical MRI • Highest diagnostic accuracy for spectroscopy and perfusion MRI • Supports the incorporation of advanced MRI in high-grade glioma treatment response assessment.
Topics: Brain Neoplasms; Diffusion Magnetic Resonance Imaging; Glioma; Humans; Magnetic Resonance Imaging; Magnetic Resonance Spectroscopy; Sensitivity and Specificity
PubMed: 28332014
DOI: 10.1007/s00330-017-4789-9