Pub Date : 2024-10-31DOI: 10.1186/s12880-024-01466-3
Anhui Zhu, Xiaoyan Hou, Na Guo, Weifang Zhang
Introduction: Preoperative evaluation of inferior vena cava (IVC) wall invasion is very important to improve outcomes of patients with renal cell carcinoma (RCC), and may allow surgical urologists to treat the IVC more effectively. The objective of this study was to evaluate preoperative 18F-FDG PET/CT in patients with RCC and IVC tumor thrombus (IVCTT) for the diagnosis of IVC wall invasion.
Methods: This retrospective case-control study evaluated 68 patients with RCC with level I-IV tumor thrombus. According to the histopathologic examination result, the patients were divided into IVC wall invasion group and non-invasion group. The 18F-FDG PET/CT features between two groups were analyzed. Furthermore, a logistic regression model was used to determine if there was an association between PET/CT features and IVC wall invasion.
Results: Sixty-eight patients were evaluated, and 55.9% (38/68) had IVC wall invasion. Compared with non-invasion group, invasion group had higher SUVmax of RCC, higher SURmax (tumor to tumor thrombus ratio, Tu/Th), higher IVCTT coronal diameter, and longer IVCTT craniocaudal extent (all p < 0.05). Multivariate analysis showed that SURmax (Tu/Th) (OR 8.760 [95%CI, 1.019-75.310]; p = 0.048) and the maximum coronal diameter of IVCTT (OR 1.143 [95%CI, 1.029-1.269]; p = 0.028) were predictors of IVC wall invasion. A model combining SURmax (Tu/Th) and the maximum coronal diameter of IVCTT achieved an AUC of 0.855 (95%CI, 0.757-0.954). The specificity and sensitivity for assessing IVC wall invasion was 92.1% and 76.7%, respectively.
Conclusions: Increases in SURmax (Tu/Th) and the maximum coronal diameter of IVCTT are associated with a higher probability of IVC wall invasion. Preoperative 18F-FDG PET/CT imaging may be used to assess IVC wall invasion.
{"title":"<sup>18</sup>F-FDG PET/CT for predicting inferior vena cava wall invasion in patients of renal cell carcinoma with the presence of inferior vena cava tumor thrombus.","authors":"Anhui Zhu, Xiaoyan Hou, Na Guo, Weifang Zhang","doi":"10.1186/s12880-024-01466-3","DOIUrl":"10.1186/s12880-024-01466-3","url":null,"abstract":"<p><strong>Introduction: </strong>Preoperative evaluation of inferior vena cava (IVC) wall invasion is very important to improve outcomes of patients with renal cell carcinoma (RCC), and may allow surgical urologists to treat the IVC more effectively. The objective of this study was to evaluate preoperative <sup>18</sup>F-FDG PET/CT in patients with RCC and IVC tumor thrombus (IVCTT) for the diagnosis of IVC wall invasion.</p><p><strong>Methods: </strong>This retrospective case-control study evaluated 68 patients with RCC with level I-IV tumor thrombus. According to the histopathologic examination result, the patients were divided into IVC wall invasion group and non-invasion group. The <sup>18</sup>F-FDG PET/CT features between two groups were analyzed. Furthermore, a logistic regression model was used to determine if there was an association between PET/CT features and IVC wall invasion.</p><p><strong>Results: </strong>Sixty-eight patients were evaluated, and 55.9% (38/68) had IVC wall invasion. Compared with non-invasion group, invasion group had higher SUVmax of RCC, higher SURmax (tumor to tumor thrombus ratio, Tu/Th), higher IVCTT coronal diameter, and longer IVCTT craniocaudal extent (all p < 0.05). Multivariate analysis showed that SURmax (Tu/Th) (OR 8.760 [95%CI, 1.019-75.310]; p = 0.048) and the maximum coronal diameter of IVCTT (OR 1.143 [95%CI, 1.029-1.269]; p = 0.028) were predictors of IVC wall invasion. A model combining SURmax (Tu/Th) and the maximum coronal diameter of IVCTT achieved an AUC of 0.855 (95%CI, 0.757-0.954). The specificity and sensitivity for assessing IVC wall invasion was 92.1% and 76.7%, respectively.</p><p><strong>Conclusions: </strong>Increases in SURmax (Tu/Th) and the maximum coronal diameter of IVCTT are associated with a higher probability of IVC wall invasion. Preoperative <sup>18</sup>F-FDG PET/CT imaging may be used to assess IVC wall invasion.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"24 1","pages":"295"},"PeriodicalIF":2.9,"publicationDate":"2024-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11526541/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142557128","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-30DOI: 10.1186/s12880-024-01478-z
Merve Gonca, İbrahim Şevki Bayrakdar, Özer Çelik
Background: We explored whether the feature aggregation and refinement network (FARNet) algorithm accurately identified posteroanterior (PA) cephalometric landmarks.
Methods: We identified 47 landmarks on 1,431 PA cephalograms of which 1,177 were used for training, 117 for validation, and 137 for testing. A FARNet-based artificial intelligence (AI) algorithm automatically detected the landmarks. Model effectiveness was calculated by deriving the mean radial error (MRE) and the successful detection rates (SDRs) within 2, 2.5, 3, and 4 mm. The Mann-Whitney U test was performed on the Euclidean differences between repeated manual identifications and AI trials. The direction in differences was analyzed, and whether differences moved in the same or opposite directions relative to ground truth on both the x and y-axis.
Results: The AI system (web-based CranioCatch annotation software (Eskişehir, Turkey)) identified 47 anatomical landmarks in PA cephalograms. The right gonion SDRs were the highest, thus 96.4, 97.8, 100, and 100% within 2, 2.5, 3, and 4 mm, respectively. The right gonion MRE was 0.94 ± 0.53 mm. The right condylon SDRs were the lowest, thus 32.8, 45.3, 54.0, and 67.9% within the same thresholds. The right condylon MRE was 3.31 ± 2.25 mm. The AI model's reliability and accuracy were similar to a human expert's. AI was better at four skeleton points than the expert, whereas the expert was better at one skeletal and seven dental points (P < 0.05). Most of the points exhibited significant deviations along the y-axis. Compared to ground truth, most of the points in AI and the second trial showed opposite movement on the x-axis and the same on the y-axis.
Conclusions: The FARNet algorithm streamlined orthodontic diagnosis.
{"title":"Does the FARNet neural network algorithm accurately identify Posteroanterior cephalometric landmarks?","authors":"Merve Gonca, İbrahim Şevki Bayrakdar, Özer Çelik","doi":"10.1186/s12880-024-01478-z","DOIUrl":"10.1186/s12880-024-01478-z","url":null,"abstract":"<p><strong>Background: </strong>We explored whether the feature aggregation and refinement network (FARNet) algorithm accurately identified posteroanterior (PA) cephalometric landmarks.</p><p><strong>Methods: </strong>We identified 47 landmarks on 1,431 PA cephalograms of which 1,177 were used for training, 117 for validation, and 137 for testing. A FARNet-based artificial intelligence (AI) algorithm automatically detected the landmarks. Model effectiveness was calculated by deriving the mean radial error (MRE) and the successful detection rates (SDRs) within 2, 2.5, 3, and 4 mm. The Mann-Whitney U test was performed on the Euclidean differences between repeated manual identifications and AI trials. The direction in differences was analyzed, and whether differences moved in the same or opposite directions relative to ground truth on both the x and y-axis.</p><p><strong>Results: </strong>The AI system (web-based CranioCatch annotation software (Eskişehir, Turkey)) identified 47 anatomical landmarks in PA cephalograms. The right gonion SDRs were the highest, thus 96.4, 97.8, 100, and 100% within 2, 2.5, 3, and 4 mm, respectively. The right gonion MRE was 0.94 ± 0.53 mm. The right condylon SDRs were the lowest, thus 32.8, 45.3, 54.0, and 67.9% within the same thresholds. The right condylon MRE was 3.31 ± 2.25 mm. The AI model's reliability and accuracy were similar to a human expert's. AI was better at four skeleton points than the expert, whereas the expert was better at one skeletal and seven dental points (P < 0.05). Most of the points exhibited significant deviations along the y-axis. Compared to ground truth, most of the points in AI and the second trial showed opposite movement on the x-axis and the same on the y-axis.</p><p><strong>Conclusions: </strong>The FARNet algorithm streamlined orthodontic diagnosis.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"24 1","pages":"294"},"PeriodicalIF":2.9,"publicationDate":"2024-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11526671/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142543505","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-29DOI: 10.1186/s12880-024-01467-2
Zhong-Yan Ma, Hai-Lin Zhang, Fa-Jin Lv, Wei Zhao, Dan Han, Li-Chang Lei, Qin Song, Wei-Wei Jing, Hui Duan, Shao-Lei Kang
Background: This study aims to assess the performance of an established an AI algorithm trained on conventional polychromatic computed tomography (CT) images (CPIs) to detect pulmonary ground-glass nodules (GGNs) on virtual monochromatic images (VMIs), and to screen the optimal virtual monochromatic energy for the clinical evaluation of GGNs.
Methods: Non-enhanced chest SDCT images of patients with pulmonary GGNs in our clinic from January 2022 to December 2022 were continuously collected: adenocarcinoma in situ (AIS, n = 40); minimally invasive adenocarcinoma (MIA, n = 44) and invasive adenocarcinoma (IAC, n = 46). A commercial CAD system based on deep convolutional neural networks (DL-CAD) was used to process the CPIs, 40, 50, 60, 70, and 80 keV monochromatic images of 130 spectral CT images. AI-based histogram parameters by logistic regression analysis. The diagnostic performance was evaluated by the receiver operating characteristic (ROC) curves, and Delong's test was used to compare the CPIs group with the VMIs group.
Results: When distinguishing IAC from MIA, the diagnostic efficiency of total mass was obtained at 80 keV, which was superior to those of other energy levels (P < 0.05). And Delong's test indicated that the differences between the area-under-the-curve (AUC) values of the CPIs group and the VMIs group were not statistically significant (P > 0.05).
Conclusion: The AI algorithm trained on CPIs showed consistent diagnostic performance on VMIs. When pulmonary GGNs are encountered in clinical practice, 80 keV could be the optimal virtual monochromatic energy for the identification of preoperative IAC on a non-enhanced chest CT.
{"title":"An artificial intelligence algorithm for the detection of pulmonary ground-glass nodules on spectral detector CT: performance on virtual monochromatic images.","authors":"Zhong-Yan Ma, Hai-Lin Zhang, Fa-Jin Lv, Wei Zhao, Dan Han, Li-Chang Lei, Qin Song, Wei-Wei Jing, Hui Duan, Shao-Lei Kang","doi":"10.1186/s12880-024-01467-2","DOIUrl":"10.1186/s12880-024-01467-2","url":null,"abstract":"<p><strong>Background: </strong>This study aims to assess the performance of an established an AI algorithm trained on conventional polychromatic computed tomography (CT) images (CPIs) to detect pulmonary ground-glass nodules (GGNs) on virtual monochromatic images (VMIs), and to screen the optimal virtual monochromatic energy for the clinical evaluation of GGNs.</p><p><strong>Methods: </strong>Non-enhanced chest SDCT images of patients with pulmonary GGNs in our clinic from January 2022 to December 2022 were continuously collected: adenocarcinoma in situ (AIS, n = 40); minimally invasive adenocarcinoma (MIA, n = 44) and invasive adenocarcinoma (IAC, n = 46). A commercial CAD system based on deep convolutional neural networks (DL-CAD) was used to process the CPIs, 40, 50, 60, 70, and 80 keV monochromatic images of 130 spectral CT images. AI-based histogram parameters by logistic regression analysis. The diagnostic performance was evaluated by the receiver operating characteristic (ROC) curves, and Delong's test was used to compare the CPIs group with the VMIs group.</p><p><strong>Results: </strong>When distinguishing IAC from MIA, the diagnostic efficiency of total mass was obtained at 80 keV, which was superior to those of other energy levels (P < 0.05). And Delong's test indicated that the differences between the area-under-the-curve (AUC) values of the CPIs group and the VMIs group were not statistically significant (P > 0.05).</p><p><strong>Conclusion: </strong>The AI algorithm trained on CPIs showed consistent diagnostic performance on VMIs. When pulmonary GGNs are encountered in clinical practice, 80 keV could be the optimal virtual monochromatic energy for the identification of preoperative IAC on a non-enhanced chest CT.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"24 1","pages":"293"},"PeriodicalIF":2.9,"publicationDate":"2024-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11523583/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142543502","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Purpose: This study aims to investigate the risk factors for lymph node metastasis (LNM) in synchronous multiple primary lung cancer (sMPLC) using clinical and CT features, and to offer guidance for preoperative LNM prediction and lymph node (LN) resection strategy.
Materials and methods: A retrospective analysis was conducted on the clinical data and CT features of patients diagnosed with sMPLC at the Third Affiliated Hospital of Kunming Medical University from January 1, 2018 to December 31, 2022. Patients were classified into two groups: the LNM group and the non-LNM (n-LNM) group. The study utilized univariate analysis to examine the disparities in clinical data and CT features between the two groups. Additionally, multivariate analysis was employed to discover the independent risk variables for LNM. The diagnostic efficacy of various parameters was evaluated using the receiver operating characteristic (ROC) curve.
Results: Among the 688 patients included in this study, 59 exhibited LNM. Univariate analysis revealed significant differences between the LNM and n-LNM groups in terms of gender, smoking history, CYFRA21-1 level, CEA level, NSE level, lesion type, total lesion diameter, main lesion diameter, spiculation sign, lobulation sign, cavity sign, and pleural traction sign. Logistic regression identified CEA level (OR = 1.042, 95%CI: 1.009-1.075), lesion type (OR = 9.683, 95%CI: 3.485-26.902), and main lesion diameter (OR = 1.677, 95%CI: 1.347-2.089) as independent predictors of LNM. The regression equation for the joint prediction was as follows: logit(p)= -7.569+0.041*CEA level +2.270* lesion type +0.517* main lesion diameter.ROC curve analysis showed that the AUC for CEA level was 0.765 (95% CI, 0.694-0.836), for lesion type was 0.794 (95% CI, 0.751-0.838), for main lesion diameter was 0.830 (95% CI, 0.784-0.875), and for the combine predict model was 0.895 (95% CI, 0.863-0.928).
Conclusion: The combination of clinical and imaging features can better predict the status of LNM of sMPLC, and the prediction efficiency is significantly higher than that of each factor alone, and can provide a basis for lymph node management decision.
{"title":"Clinical and CT characteristics for predicting lymph node metastasis in patients with synchronous multiple primary lung adenocarcinoma.","authors":"Yantao Yang, Ziqi Jiang, Qiubo Huang, Wen Jiang, Chen Zhou, Jie Zhao, Huilian Hu, Yaowu Duan, Wangcai Li, Jia Luo, Jiezhi Jiang, Lianhua Ye","doi":"10.1186/s12880-024-01464-5","DOIUrl":"10.1186/s12880-024-01464-5","url":null,"abstract":"<p><strong>Purpose: </strong>This study aims to investigate the risk factors for lymph node metastasis (LNM) in synchronous multiple primary lung cancer (sMPLC) using clinical and CT features, and to offer guidance for preoperative LNM prediction and lymph node (LN) resection strategy.</p><p><strong>Materials and methods: </strong>A retrospective analysis was conducted on the clinical data and CT features of patients diagnosed with sMPLC at the Third Affiliated Hospital of Kunming Medical University from January 1, 2018 to December 31, 2022. Patients were classified into two groups: the LNM group and the non-LNM (n-LNM) group. The study utilized univariate analysis to examine the disparities in clinical data and CT features between the two groups. Additionally, multivariate analysis was employed to discover the independent risk variables for LNM. The diagnostic efficacy of various parameters was evaluated using the receiver operating characteristic (ROC) curve.</p><p><strong>Results: </strong>Among the 688 patients included in this study, 59 exhibited LNM. Univariate analysis revealed significant differences between the LNM and n-LNM groups in terms of gender, smoking history, CYFRA21-1 level, CEA level, NSE level, lesion type, total lesion diameter, main lesion diameter, spiculation sign, lobulation sign, cavity sign, and pleural traction sign. Logistic regression identified CEA level (OR = 1.042, 95%CI: 1.009-1.075), lesion type (OR = 9.683, 95%CI: 3.485-26.902), and main lesion diameter (OR = 1.677, 95%CI: 1.347-2.089) as independent predictors of LNM. The regression equation for the joint prediction was as follows: logit(p)= -7.569+0.041*CEA level +2.270* lesion type +0.517* main lesion diameter.ROC curve analysis showed that the AUC for CEA level was 0.765 (95% CI, 0.694-0.836), for lesion type was 0.794 (95% CI, 0.751-0.838), for main lesion diameter was 0.830 (95% CI, 0.784-0.875), and for the combine predict model was 0.895 (95% CI, 0.863-0.928).</p><p><strong>Conclusion: </strong>The combination of clinical and imaging features can better predict the status of LNM of sMPLC, and the prediction efficiency is significantly higher than that of each factor alone, and can provide a basis for lymph node management decision.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"24 1","pages":"291"},"PeriodicalIF":2.9,"publicationDate":"2024-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11523887/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142543503","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-29DOI: 10.1186/s12880-024-01461-8
Lulu Xu, Jing Zhang, Siyun Liu, Guoyun He, Jian Shu
Background: Rebleeding after endoscopic treatment for esophagogastric varices (EGVs) in cirrhotic patients remains a significant clinical challenge, with high mortality rates and limited predictive tools. Current methods, relying on clinical indicators, often lack precision and fail to provide personalized risk assessments. This study aims to develop and validate a novel, non-invasive prediction model based on CT radiomics to predict rebleeding risk within one year of treatment, integrating radiomic features from key organs and clinical data.
Methods: 123 patients were enrolled and divided into rebleeding (n = 44) and non-bleeding group (n = 79) within 1 year after endoscopic treatment of EGVs. The liver, spleen, and the lower part of the esophagus were segmented and the extracted radiomics features were selected to construct liver/spleen/esophagus radiomics signatures based on logistic regression. Clinic-radiomics combined models and multi-organ combined radiomics models were constructed based on independent model scores using logistic regression. The model performance was evaluated by ROC analysis, calibration and decision curves. The continuous net reclassification improvement (NRI) and integrated discrimination improvement (IDI) indices were analyzed.
Results: The clinical-liver combined model had the highest AUC of 0.931 (95% CI: 0.887-0.974), which was followed by the liver-based model with AUC of 0.891 (95% CI: 0.835-0.74). The decision curves also showed that the clinical-liver combined model afforded a greater net benefit compared to other models within the threshold probability of 0.45 to 0.80. Significant improvements in discrimination (IDI, P < 0.05) and reclassification (NRI, P < 0.05) were obtained for clinical-liver combined model compared with the independent ones.
Conclusion: The independent and combined liver-based CT radiomics models performed well in predicting rebleeding within 1 year after endoscopic treatment of EGVs.
{"title":"Development and internal validation of prediction model for rebleeding within one year after endoscopic treatment of cirrhotic varices: consideration from organ-based CT radiomics signature.","authors":"Lulu Xu, Jing Zhang, Siyun Liu, Guoyun He, Jian Shu","doi":"10.1186/s12880-024-01461-8","DOIUrl":"10.1186/s12880-024-01461-8","url":null,"abstract":"<p><strong>Background: </strong>Rebleeding after endoscopic treatment for esophagogastric varices (EGVs) in cirrhotic patients remains a significant clinical challenge, with high mortality rates and limited predictive tools. Current methods, relying on clinical indicators, often lack precision and fail to provide personalized risk assessments. This study aims to develop and validate a novel, non-invasive prediction model based on CT radiomics to predict rebleeding risk within one year of treatment, integrating radiomic features from key organs and clinical data.</p><p><strong>Methods: </strong>123 patients were enrolled and divided into rebleeding (n = 44) and non-bleeding group (n = 79) within 1 year after endoscopic treatment of EGVs. The liver, spleen, and the lower part of the esophagus were segmented and the extracted radiomics features were selected to construct liver/spleen/esophagus radiomics signatures based on logistic regression. Clinic-radiomics combined models and multi-organ combined radiomics models were constructed based on independent model scores using logistic regression. The model performance was evaluated by ROC analysis, calibration and decision curves. The continuous net reclassification improvement (NRI) and integrated discrimination improvement (IDI) indices were analyzed.</p><p><strong>Results: </strong>The clinical-liver combined model had the highest AUC of 0.931 (95% CI: 0.887-0.974), which was followed by the liver-based model with AUC of 0.891 (95% CI: 0.835-0.74). The decision curves also showed that the clinical-liver combined model afforded a greater net benefit compared to other models within the threshold probability of 0.45 to 0.80. Significant improvements in discrimination (IDI, P < 0.05) and reclassification (NRI, P < 0.05) were obtained for clinical-liver combined model compared with the independent ones.</p><p><strong>Conclusion: </strong>The independent and combined liver-based CT radiomics models performed well in predicting rebleeding within 1 year after endoscopic treatment of EGVs.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"24 1","pages":"292"},"PeriodicalIF":2.9,"publicationDate":"2024-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11523671/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142543504","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-29DOI: 10.1186/s12880-024-01445-8
Han Jiang, Ziqiang Li, Nan Meng, Yu Luo, Pengyang Feng, Fangfang Fu, Yang Yang, Jianmin Yuan, Zhe Wang, Meiyun Wang
Background: Multiple models intravoxel incoherent motion (IVIM) based 18F-fluorodeoxyglucose positron emission tomography-magnetic resonance(18F-FDG PET/MR) could reflect the microscopic information of the tumor from multiple perspectives. However, its value in the prognostic assessment of non-small cell lung cancer (NSCLC) still needs to be further explored.
Objective: To compare the value of 18F-FDG PET/MR metabolic parameters and diffusion parameters in the prognostic assessment of patients with NSCLC.
Meterial and methods: Chest PET and IVIM scans were performed on 61 NSCLC patients using PET/MR. The maximum standard uptake value (SUVmax), metabolic tumor volume (MTV), total lesion glycolysis (TLG), diffusion coefficient (D), perfusion fraction (f), pseudo diffusion coefficient (D*) and apparent diffusion coefficient (ADC) were calculated. The impact of SUVmax, MTV, TLG, D, f, D*and ADC on survival was measured in terms of the hazard ratio (HR) effect size. Overall survival time (OS) and progression-free survival time (PFS) were evaluated with the Kaplan-Meier and Cox proportional hazard models. Log-rank test was used to analyze the differences in parameters between groups.
Results: 61 NSCLC patients had an overall median OS of 18 months (14.75, 22.85) and a median PFS of 17 months (12.00, 21.75). Univariate analysis showed that pathological subtype, TNM stage, surgery, SUVmax, MTV, TLG, D, D* and ADC were both influential factors for OS and PFS in NSCLC patients. Multifactorial analysis showed that MTV, D* and ADC were independent predicting factors for OS and PFS in NSCLC patients.
Conclusion: MTV, D* and ADC are independent predicting factors affecting OS and PFS in NSCLC patients. 18F-FDG PET/MR-derived metabolic parameters and diffusion parameters have clinical value for prognostic assessment of NSCLC patients.
{"title":"Predictive value of metabolic parameters and apparent diffusion coefficient derived from 18F-FDG PET/MR in patients with non-small cell lung cancer.","authors":"Han Jiang, Ziqiang Li, Nan Meng, Yu Luo, Pengyang Feng, Fangfang Fu, Yang Yang, Jianmin Yuan, Zhe Wang, Meiyun Wang","doi":"10.1186/s12880-024-01445-8","DOIUrl":"10.1186/s12880-024-01445-8","url":null,"abstract":"<p><strong>Background: </strong>Multiple models intravoxel incoherent motion (IVIM) based <sup>18</sup>F-fluorodeoxyglucose positron emission tomography-magnetic resonance(<sup>18</sup>F-FDG PET/MR) could reflect the microscopic information of the tumor from multiple perspectives. However, its value in the prognostic assessment of non-small cell lung cancer (NSCLC) still needs to be further explored.</p><p><strong>Objective: </strong>To compare the value of <sup>18</sup>F-FDG PET/MR metabolic parameters and diffusion parameters in the prognostic assessment of patients with NSCLC.</p><p><strong>Meterial and methods: </strong>Chest PET and IVIM scans were performed on 61 NSCLC patients using PET/MR. The maximum standard uptake value (SUV<sub>max</sub>), metabolic tumor volume (MTV), total lesion glycolysis (TLG), diffusion coefficient (D), perfusion fraction (f), pseudo diffusion coefficient (D*) and apparent diffusion coefficient (ADC) were calculated. The impact of SUV<sub>max</sub>, MTV, TLG, D, f, D*and ADC on survival was measured in terms of the hazard ratio (HR) effect size. Overall survival time (OS) and progression-free survival time (PFS) were evaluated with the Kaplan-Meier and Cox proportional hazard models. Log-rank test was used to analyze the differences in parameters between groups.</p><p><strong>Results: </strong>61 NSCLC patients had an overall median OS of 18 months (14.75, 22.85) and a median PFS of 17 months (12.00, 21.75). Univariate analysis showed that pathological subtype, TNM stage, surgery, SUV<sub>max</sub>, MTV, TLG, D, D* and ADC were both influential factors for OS and PFS in NSCLC patients. Multifactorial analysis showed that MTV, D* and ADC were independent predicting factors for OS and PFS in NSCLC patients.</p><p><strong>Conclusion: </strong>MTV, D* and ADC are independent predicting factors affecting OS and PFS in NSCLC patients. <sup>18</sup>F-FDG PET/MR-derived metabolic parameters and diffusion parameters have clinical value for prognostic assessment of NSCLC patients.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"24 1","pages":"290"},"PeriodicalIF":2.9,"publicationDate":"2024-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11523797/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142543506","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Objective: This study aims to assess the consistency of various CT-FFR software, to determine the reliability of current CT-FFR software, and to measure relevant influence factors. The goal is to build a solid foundation of enhanced workflow and technical principles that will ultimately improve the accuracy of measurements of coronary blood flow reserve fractions. This improvement is critical for assessing the level of ischemia in patients with coronary heart disease.
Methods: 103 participants were chosen for a prospective research using coronary computed tomography angiography (CCTA) assessment. Heart rate, heart rate variability, subjective picture quality, objective image quality, vascular shifting length, and other factors were assessed. CT-FFR software including K software and S software are used for CT-FFR calculations. The consistency of the two software is assessed using paired-sample t-tests and Bland-Altman plots. The error classification effect is used to construct the receiver operating characteristic curve.
Results: The CT-FFR measurements differed significantly between the K and S software, with a statistical significance of P < 0.05. In the Bland-Altman plot, 6% of the points (14 out of 216) fell outside the 95% consistency level. Single-factor analysis revealed that heart rate variability, vascular dislocation offset distance, subjective image quality, and lumen diameter significantly influenced the discrepancies in CT-FFR measurements between two software programs (P < 0.05). The ROC curve shows the highest AUC for the vessel shifting length, with an optimal cut-off of 0.85 mm.
Conclusion: CT-FFR measurements vary among software from different manufacturers, leading to potential misclassification of qualitative diagnostics. Vessel shifting length, subjective image quality score, HRv, and lumen diameter impacted the measurement stability of various software.
研究目的本研究旨在评估各种 CT-FFR 软件的一致性,确定当前 CT-FFR 软件的可靠性,并测量相关影响因素。目的是为增强工作流程和技术原理打下坚实基础,最终提高冠状动脉血流储备分数测量的准确性。这一改进对于评估冠心病患者的缺血程度至关重要。方法:选择 103 名参与者进行前瞻性研究,使用冠状动脉计算机断层扫描血管造影术(CCTA)进行评估。对心率、心率变异性、主观图像质量、客观图像质量、血管移位长度和其他因素进行了评估。CT-FFR 计算软件包括 K 软件和 S 软件。使用配对样本 t 检验和 Bland-Altman 图评估两种软件的一致性。误差分类效果用于构建接收者操作特征曲线:结果:K 软件和 S 软件的 CT-FFR 测量结果差异显著,统计学意义为 P 结论:K 软件和 S 软件的 CT-FFR 测量结果差异显著,统计学意义为 P:不同制造商生产的软件的 CT-FFR 测量结果存在差异,可能导致定性诊断的错误分类。血管移动长度、主观图像质量评分、HRv 和管腔直径影响了不同软件的测量稳定性。
{"title":"CT coronary fractional flow reserve based on artificial intelligence using different software: a repeatability study.","authors":"Jing Li, Zhenxing Yang, Zhenting Sun, Lei Zhao, Aishi Liu, Xing Wang, Qiyu Jin, Guoyu Zhang","doi":"10.1186/s12880-024-01465-4","DOIUrl":"10.1186/s12880-024-01465-4","url":null,"abstract":"<p><strong>Objective: </strong>This study aims to assess the consistency of various CT-FFR software, to determine the reliability of current CT-FFR software, and to measure relevant influence factors. The goal is to build a solid foundation of enhanced workflow and technical principles that will ultimately improve the accuracy of measurements of coronary blood flow reserve fractions. This improvement is critical for assessing the level of ischemia in patients with coronary heart disease.</p><p><strong>Methods: </strong>103 participants were chosen for a prospective research using coronary computed tomography angiography (CCTA) assessment. Heart rate, heart rate variability, subjective picture quality, objective image quality, vascular shifting length, and other factors were assessed. CT-FFR software including K software and S software are used for CT-FFR calculations. The consistency of the two software is assessed using paired-sample t-tests and Bland-Altman plots. The error classification effect is used to construct the receiver operating characteristic curve.</p><p><strong>Results: </strong>The CT-FFR measurements differed significantly between the K and S software, with a statistical significance of P < 0.05. In the Bland-Altman plot, 6% of the points (14 out of 216) fell outside the 95% consistency level. Single-factor analysis revealed that heart rate variability, vascular dislocation offset distance, subjective image quality, and lumen diameter significantly influenced the discrepancies in CT-FFR measurements between two software programs (P < 0.05). The ROC curve shows the highest AUC for the vessel shifting length, with an optimal cut-off of 0.85 mm.</p><p><strong>Conclusion: </strong>CT-FFR measurements vary among software from different manufacturers, leading to potential misclassification of qualitative diagnostics. Vessel shifting length, subjective image quality score, HRv, and lumen diameter impacted the measurement stability of various software.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"24 1","pages":"288"},"PeriodicalIF":2.9,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11515450/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142494655","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Background: To construct and compare merged models integrating clinical factors, MRI-based radiomics features and deep learning (DL) models for predicting pathological complete response (pCR) to neoadjuvant chemoradiotherapy (nCRT) in patients with locally advanced rectal cancer (LARC).
Methods: Totally 197 patients with LARC administered surgical resection after nCRT were assigned to cohort 1 (training and test sets); meanwhile, 52 cases were assigned to cohort 2 as a validation set. Radscore and DL models were established for predicting pCR applying pre- and post-nCRT MRI data, respectively. Different merged models integrating clinical factors, Radscore and DL model were constituted. Their predictive performances were validated and compared by receiver operating characteristic (ROC) and decision curve analyses (DCA).
Results: Merged models were established integrating selected clinical factors, Radscore and DL model for pCR prediction. The areas under the ROC curves (AUCs) of the pre-nCRT merged model were 0.834 (95% CI: 0.737-0.931) and 0.742 (95% CI: 0.650-0.834) in test and validation sets, respectively. The AUCs of the post-nCRT merged model were 0.746 (95% CI: 0.636-0.856) and 0.737 (95% CI: 0.646-0.828) in test and validation sets, respectively. DCA showed that the pretreatment algorithm could yield enhanced clinically benefit than the post-nCRT approach.
Conclusions: The pre-nCRT merged model including clinical factors, Radscore and DL model constitutes an effective non-invasive tool for pCR prediction in LARC.
{"title":"Predicting pathological complete response following neoadjuvant chemoradiotherapy (nCRT) in patients with locally advanced rectal cancer using merged model integrating MRI-based radiomics and deep learning data.","authors":"Haidi Lu, Yuan Yuan, Minglu Liu, Zhihui Li, Xiaolu Ma, Yuwei Xia, Feng Shi, Yong Lu, Jianping Lu, Fu Shen","doi":"10.1186/s12880-024-01474-3","DOIUrl":"10.1186/s12880-024-01474-3","url":null,"abstract":"<p><strong>Background: </strong>To construct and compare merged models integrating clinical factors, MRI-based radiomics features and deep learning (DL) models for predicting pathological complete response (pCR) to neoadjuvant chemoradiotherapy (nCRT) in patients with locally advanced rectal cancer (LARC).</p><p><strong>Methods: </strong>Totally 197 patients with LARC administered surgical resection after nCRT were assigned to cohort 1 (training and test sets); meanwhile, 52 cases were assigned to cohort 2 as a validation set. Radscore and DL models were established for predicting pCR applying pre- and post-nCRT MRI data, respectively. Different merged models integrating clinical factors, Radscore and DL model were constituted. Their predictive performances were validated and compared by receiver operating characteristic (ROC) and decision curve analyses (DCA).</p><p><strong>Results: </strong>Merged models were established integrating selected clinical factors, Radscore and DL model for pCR prediction. The areas under the ROC curves (AUCs) of the pre-nCRT merged model were 0.834 (95% CI: 0.737-0.931) and 0.742 (95% CI: 0.650-0.834) in test and validation sets, respectively. The AUCs of the post-nCRT merged model were 0.746 (95% CI: 0.636-0.856) and 0.737 (95% CI: 0.646-0.828) in test and validation sets, respectively. DCA showed that the pretreatment algorithm could yield enhanced clinically benefit than the post-nCRT approach.</p><p><strong>Conclusions: </strong>The pre-nCRT merged model including clinical factors, Radscore and DL model constitutes an effective non-invasive tool for pCR prediction in LARC.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"24 1","pages":"289"},"PeriodicalIF":2.9,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11515279/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142494657","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-23DOI: 10.1186/s12880-024-01468-1
Yoosoo Jeong, Chanho Song, Seungmin Lee, Jaebum Son
{"title":"Correction: For a clinical application of optical triangulation to assess respiratory rate using an RGB camera and a line laser.","authors":"Yoosoo Jeong, Chanho Song, Seungmin Lee, Jaebum Son","doi":"10.1186/s12880-024-01468-1","DOIUrl":"https://doi.org/10.1186/s12880-024-01468-1","url":null,"abstract":"","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"24 1","pages":"287"},"PeriodicalIF":2.9,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11498960/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142494644","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Background: This study aimed to conduct a systematic review and meta-analysis to summarize the available evidence comparing the diagnostic accuracy of periapical radiography (PA) and cone-beam computed tomography (CBCT) for detection of vertical root fractures (VRFs).
Methods: A search was conducted in PubMed, Scopus, and Web of Science for articles published regarding all types of human teeth. Data were analyzed by Comprehensive Meta-Analysis statistical software V3 software program. The I2 statistic was applied to analyze heterogeneity among the studies.
Results: Twenty-three articles met the criteria for inclusion in the systematic review and 16 for the meta-analysis. The sensitivity and specificity for detection of VRFs were calculated to be 0.51 and 0.87, respectively for PA radiography, and 0.70 and 0.84, respectively for CBCT.
Conclusions: The sensitivity of CBCT was higher than PA radiography; however, difference between the specificity of the two modalities was not statistically significant.
背景:本研究旨在进行系统回顾和荟萃分析,总结现有证据,比较根尖周放射摄影术(PA)和锥束计算机断层扫描(CBCT)在检测垂直根折(VRFs)方面的诊断准确性:方法:在 PubMed、Scopus 和 Web of Science 中搜索有关各类人类牙齿的文章。数据采用综合元分析统计软件 V3 软件程序进行分析。采用I2统计量分析研究之间的异质性:结果:23 篇文章符合系统综述的纳入标准,16 篇符合荟萃分析的纳入标准。经计算,PA 放射摄影检测 VRF 的灵敏度和特异度分别为 0.51 和 0.87,CBCT 分别为 0.70 和 0.84:结论:CBCT 的灵敏度高于 PA 放射摄影,但两种模式的特异性差异无统计学意义。
{"title":"Is cone-beam computed tomography more accurate than periapical radiography for detection of vertical root fractures? A systematic review and meta-analysis.","authors":"Abbas Shokri, Fatemeh Salemi, Tara Taherpour, Hamed Karkehabadi, Kousar Ramezani, Foozie Zahedi, Maryam Farhadian","doi":"10.1186/s12880-024-01472-5","DOIUrl":"10.1186/s12880-024-01472-5","url":null,"abstract":"<p><strong>Background: </strong>This study aimed to conduct a systematic review and meta-analysis to summarize the available evidence comparing the diagnostic accuracy of periapical radiography (PA) and cone-beam computed tomography (CBCT) for detection of vertical root fractures (VRFs).</p><p><strong>Methods: </strong>A search was conducted in PubMed, Scopus, and Web of Science for articles published regarding all types of human teeth. Data were analyzed by Comprehensive Meta-Analysis statistical software V3 software program. The I2 statistic was applied to analyze heterogeneity among the studies.</p><p><strong>Results: </strong>Twenty-three articles met the criteria for inclusion in the systematic review and 16 for the meta-analysis. The sensitivity and specificity for detection of VRFs were calculated to be 0.51 and 0.87, respectively for PA radiography, and 0.70 and 0.84, respectively for CBCT.</p><p><strong>Conclusions: </strong>The sensitivity of CBCT was higher than PA radiography; however, difference between the specificity of the two modalities was not statistically significant.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"24 1","pages":"286"},"PeriodicalIF":2.9,"publicationDate":"2024-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11515760/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142494656","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}