Pub Date : 2024-09-26DOI: 10.1016/j.acra.2024.09.023
Yanghua Fan, Shuaiwei Guo, Chuming Tao, Hua Fang, Anna Mou, Ming Feng, Zhen Wu
Rationale and objectives: The first-line treatment for prolactinoma is drug therapy with dopamine agonists (DAs). However, some patients with resistance to DA treatment should prioritize surgical treatment. Therefore, it is crucial to accurately identify the drug treatment response of prolactinoma before treatment. The present study was performed to determine the DA treatment response of prolactinoma using a clinical radiomic model that incorporated radiomic and clinical features before treatment.
Materials and methods: In total, 255 patients diagnosed with prolactinoma were retrospectively divided to training and validation sets. An elastic net algorithm was used to screen the radiomic features, and a fusion radiomic model was established. A clinical radiomic model was then constructed to integrate the fusion radiomic model and the most important clinical features through multivariate logistic regression analysis for individual prediction. The calibration, discrimination, and clinical applicability of the established models were evaluated. 60 patients with prolactinoma from other centers were used to validate the performance of the constructed model.
Results: The fusion radiomic model was constructed from three significant radiomic features, and the area under the curve in the training set and validation set was 0.930 and 0.910, respectively. The clinical radiomic model was constructed using the radiomic model and three clinical features. The model exhibited good recognition and calibration abilities as evidenced by its area under the curve of 0.96, 0.92, and 0.92 in the training, validation, and external multicenter validation set, respectively. Analysis of the decision curve showed that the fusion radiomic model and clinical radiomic model had good clinical application value for DA treatment response prediction in patients with prolactinoma.
Conclusion: Our clinical radiomic model demonstrated high sensitivity and excellent performance in predicting DA treatment response in prolactinoma. This model holds promise for the noninvasive development of individualized diagnosis and treatment strategies for patients with prolactinoma.
{"title":"Noninvasive radiomics approach predicts dopamine agonists treatment response in patients with prolactinoma: a multicenter study.","authors":"Yanghua Fan, Shuaiwei Guo, Chuming Tao, Hua Fang, Anna Mou, Ming Feng, Zhen Wu","doi":"10.1016/j.acra.2024.09.023","DOIUrl":"https://doi.org/10.1016/j.acra.2024.09.023","url":null,"abstract":"<p><strong>Rationale and objectives: </strong>The first-line treatment for prolactinoma is drug therapy with dopamine agonists (DAs). However, some patients with resistance to DA treatment should prioritize surgical treatment. Therefore, it is crucial to accurately identify the drug treatment response of prolactinoma before treatment. The present study was performed to determine the DA treatment response of prolactinoma using a clinical radiomic model that incorporated radiomic and clinical features before treatment.</p><p><strong>Materials and methods: </strong>In total, 255 patients diagnosed with prolactinoma were retrospectively divided to training and validation sets. An elastic net algorithm was used to screen the radiomic features, and a fusion radiomic model was established. A clinical radiomic model was then constructed to integrate the fusion radiomic model and the most important clinical features through multivariate logistic regression analysis for individual prediction. The calibration, discrimination, and clinical applicability of the established models were evaluated. 60 patients with prolactinoma from other centers were used to validate the performance of the constructed model.</p><p><strong>Results: </strong>The fusion radiomic model was constructed from three significant radiomic features, and the area under the curve in the training set and validation set was 0.930 and 0.910, respectively. The clinical radiomic model was constructed using the radiomic model and three clinical features. The model exhibited good recognition and calibration abilities as evidenced by its area under the curve of 0.96, 0.92, and 0.92 in the training, validation, and external multicenter validation set, respectively. Analysis of the decision curve showed that the fusion radiomic model and clinical radiomic model had good clinical application value for DA treatment response prediction in patients with prolactinoma.</p><p><strong>Conclusion: </strong>Our clinical radiomic model demonstrated high sensitivity and excellent performance in predicting DA treatment response in prolactinoma. This model holds promise for the noninvasive development of individualized diagnosis and treatment strategies for patients with prolactinoma.</p>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":null,"pages":null},"PeriodicalIF":3.8,"publicationDate":"2024-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142331772","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-25DOI: 10.1016/j.acra.2024.09.020
Robyn F Distelbrink, Enise Celebi, Constantijne H Mom, Jaap Stoker, Shandra Bipat
Purpose: To assess the diagnostic performance of Diffusion Weighted Imaging (DWI) and provide optimal apparent diffusion coefficient (ADC) cut-off values for differentiating between benign and metastatic lymph nodes in women with uterine cervical cancer.
Method: MEDLINE and EMBASE databases were searched. Methodological quality was assessed with QUADAS-2. Data analysis was performed for three subgroups: (1) All studies; (2) Studies with maximum b-values of 800 s/mm², and (3) Studies containing b-values of 1000 s/mm². Receiver-operating characteristics (ROC) curves were constructed and the area under the curve (AUC) was calculated. The maximum Youden index was used to determine optimal ADC cut-off values, following calculations of sensitivity and specificity.
Results: 16 articles (1156 patients) were included. Overall, their quality was limited. For all studies combined, the optimum ADC cut-off value was 0.985×10⁻³ mm²/s at maximum Youden Index of 0.77, resulting in sensitivity and specificity of 84%, and 94%, respectively. Studies with b-values up to 800 s/mm², gave an optimum ADC cut-off value of 0.985×10⁻³ mm²/s at maximum Youden Index of 0.62, with a sensitivity and specificity of 62%, and 100%. Studies containing b-values of 1000 s/mm² gave an optimum ADC cut-off value of 0.9435×10⁻³ mm²/s at maximum Youden Index of 0.93, with a sensitivity and specificity of 100%, and 93%, respectively.
Conclusion: Studies using DWI including b-values of 1000 s/mm² have higher sensitivity and specificity than those with b-values up to 800 s/mm². At the cut-off value of 0.9435×10⁻³ mm²/s DWI can sufficiently discriminate between benign and metastatic lymph nodes.
{"title":"Diffusion Weighted Imaging for the Assessment of Lymph Node Metastases in Women with Cervical Cancer: A Meta-analysis of the Apparent Diffusion Coefficient Values.","authors":"Robyn F Distelbrink, Enise Celebi, Constantijne H Mom, Jaap Stoker, Shandra Bipat","doi":"10.1016/j.acra.2024.09.020","DOIUrl":"https://doi.org/10.1016/j.acra.2024.09.020","url":null,"abstract":"<p><strong>Purpose: </strong>To assess the diagnostic performance of Diffusion Weighted Imaging (DWI) and provide optimal apparent diffusion coefficient (ADC) cut-off values for differentiating between benign and metastatic lymph nodes in women with uterine cervical cancer.</p><p><strong>Method: </strong>MEDLINE and EMBASE databases were searched. Methodological quality was assessed with QUADAS-2. Data analysis was performed for three subgroups: (1) All studies; (2) Studies with maximum b-values of 800 s/mm², and (3) Studies containing b-values of 1000 s/mm². Receiver-operating characteristics (ROC) curves were constructed and the area under the curve (AUC) was calculated. The maximum Youden index was used to determine optimal ADC cut-off values, following calculations of sensitivity and specificity.</p><p><strong>Results: </strong>16 articles (1156 patients) were included. Overall, their quality was limited. For all studies combined, the optimum ADC cut-off value was 0.985×10⁻³ mm²/s at maximum Youden Index of 0.77, resulting in sensitivity and specificity of 84%, and 94%, respectively. Studies with b-values up to 800 s/mm², gave an optimum ADC cut-off value of 0.985×10⁻³ mm²/s at maximum Youden Index of 0.62, with a sensitivity and specificity of 62%, and 100%. Studies containing b-values of 1000 s/mm² gave an optimum ADC cut-off value of 0.9435×10⁻³ mm²/s at maximum Youden Index of 0.93, with a sensitivity and specificity of 100%, and 93%, respectively.</p><p><strong>Conclusion: </strong>Studies using DWI including b-values of 1000 s/mm² have higher sensitivity and specificity than those with b-values up to 800 s/mm². At the cut-off value of 0.9435×10⁻³ mm²/s DWI can sufficiently discriminate between benign and metastatic lymph nodes.</p>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":null,"pages":null},"PeriodicalIF":3.8,"publicationDate":"2024-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142331767","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-25DOI: 10.1016/j.acra.2024.08.044
Hillary W Garner, Priscilla J Slanetz, Jonathan O Swanson, Brent D Griffith, Carolynn M DeBenedectis, Jennifer E Gould, Tara L Holm, Michele Retrouvey, Angelisa M Paladin, Anna Rozenshtein
Rationale and objectives: The Association of Program Directors in Radiology (APDR) administers an annual survey to assess issues and experiences related to residency program management and education. Response data from the 2023 survey provides insights on the impact of COVID-19 on resident recruitment (Part I) and education (Part II), which can be used to facilitate planning and resource allocation for the evolving needs of programs and their leadership.
Materials and methods: An observational, cross-sectional study of the APDR membership was performed using a web-based survey consisting of 45 questions, 12 of which pertain to resident education in the post-pandemic era and are discussed in Part II of a two-part survey analysis. All active APDR members (n = 393) were invited to participate in the survey.
Results: The response rate was 32% (124 of 393). Results were tallied using Qualtrics software and qualitative responses were tabulated or summarized as comments.
Conclusions: The primary challenges to resident education are faculty burnout, rising case volumes, and remote instruction. However, most program leaders report that in-person readouts are much more common than remote readouts. The ability to offer both in-person and remote AIRP sessions is viewed positively. Most program leaders require Authorized User certification, although many do not think all residents need it. Assessment of procedural competence varies by the type of procedure and is similar to graduates' self-assessment of competence.
{"title":"What Program Directors Think About Resident Education: Results of the 2023 Spring Survey of the Association of Program Directors in Radiology (APDR) Part II.","authors":"Hillary W Garner, Priscilla J Slanetz, Jonathan O Swanson, Brent D Griffith, Carolynn M DeBenedectis, Jennifer E Gould, Tara L Holm, Michele Retrouvey, Angelisa M Paladin, Anna Rozenshtein","doi":"10.1016/j.acra.2024.08.044","DOIUrl":"https://doi.org/10.1016/j.acra.2024.08.044","url":null,"abstract":"<p><strong>Rationale and objectives: </strong>The Association of Program Directors in Radiology (APDR) administers an annual survey to assess issues and experiences related to residency program management and education. Response data from the 2023 survey provides insights on the impact of COVID-19 on resident recruitment (Part I) and education (Part II), which can be used to facilitate planning and resource allocation for the evolving needs of programs and their leadership.</p><p><strong>Materials and methods: </strong>An observational, cross-sectional study of the APDR membership was performed using a web-based survey consisting of 45 questions, 12 of which pertain to resident education in the post-pandemic era and are discussed in Part II of a two-part survey analysis. All active APDR members (n = 393) were invited to participate in the survey.</p><p><strong>Results: </strong>The response rate was 32% (124 of 393). Results were tallied using Qualtrics software and qualitative responses were tabulated or summarized as comments.</p><p><strong>Conclusions: </strong>The primary challenges to resident education are faculty burnout, rising case volumes, and remote instruction. However, most program leaders report that in-person readouts are much more common than remote readouts. The ability to offer both in-person and remote AIRP sessions is viewed positively. Most program leaders require Authorized User certification, although many do not think all residents need it. Assessment of procedural competence varies by the type of procedure and is similar to graduates' self-assessment of competence.</p>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":null,"pages":null},"PeriodicalIF":3.8,"publicationDate":"2024-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142331775","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-25DOI: 10.1016/j.acra.2024.09.024
Ze Lin, Ying Liu, Chengcheng Xia, Pei Huang, Zhiwei Peng, Li Yi, Yu Wang, Xiao Yu, Bing Fan, Minjing Zuo
<p><strong>Rationale and objectives: </strong>To evaluate the ability of dual-energy CT(DECT)-based quantitative parameters and radiomics features to differentiate solid lung adenocarcinoma (ADC) from squamous cell carcinoma (SCC).</p><p><strong>Methods: </strong>This study included 213 patients diagnosed with ADC and SCC who underwent DECT scans at two centers from November 2022 to December 2023. Patients at center 1 were randomly divided into training (n = 114) and internal test set (n = 50) in a 7:3 ratio, with center 2 serving as the external test set (n = 49). Radiologic and clinical data were combined to establish a clinical-radiologic model. Ten types of DECT energy images including conventional images, iodine density (ID), effective atomic number (Z<sub>eff</sub>), electron density, and virtual mono-energetic images (VMI) were reconstructed in both arterial phases (AP) and venous phases (VP). Quantitative parameters were measured at the uniform enhanced solid portion of the tumor and normalized to the aorta, used to develop a quantification model and calculate the quantitative score (quantscore). Radiologists manually delineated the tumor ROI at the largest level for extracting radiomics features in these 10 energy images. These features were used to establish 10 uni-energy models from which the best-performing features were selected to construct the final radiomics model and calculate a radiomics score (radscore). Then, a combined model was developed using the akaike information criterion(AIC) and compared to the clinical-radiological model to test its diagnostic validity.</p><p><strong>Results: </strong>The independent predictors of the clinical-radiological model included age, gender, and central or peripheral location, and the AUCs for the training set, internal test set, and external test set were 0.808, 0.837, and 0.802. The quantification model incorporated 40 keV CT values, Z<sub>eff</sub>, normalized Z<sub>eff</sub>, and the slope of the spectral attenuation curve (λHU) in the AP and normalized ID, Z<sub>eff</sub>, and λHU in the VP. Uni-energy models based on AP ID maps, AP Z<sub>eff</sub> maps, and VP VMI 65 keV significantly outperformed AUC= 0.5, and 11 radiomics features were selected from these three models to construct the final radiomics model. The combined model, incorporating age, gender, quantscore, and radscore, significantly outperformed the clinical-radiological model in the training set (AUC=0.952 vs 0.808, P < 0.001), and demonstrated higher performance in both the internal and external test sets, although these differences did not reach statistical significance (AUC=0.870 vs 0.837, for the internal test set [P = 0.542], 0.888 vs 0.802 for the external test sets [P = 0.128]). The evaluation of the combined model demonstrated good discriminative ability and potential for generalization.</p><p><strong>Conclusion: </strong>The combined model, integrating quantitative parameters and radiomics features from DECT multi-
{"title":"Dual-energy CT Radiomics Combined with Quantitative Parameters for Differentiating Lung Adenocarcinoma From Squamous Cell Carcinoma: A Dual-center Study.","authors":"Ze Lin, Ying Liu, Chengcheng Xia, Pei Huang, Zhiwei Peng, Li Yi, Yu Wang, Xiao Yu, Bing Fan, Minjing Zuo","doi":"10.1016/j.acra.2024.09.024","DOIUrl":"https://doi.org/10.1016/j.acra.2024.09.024","url":null,"abstract":"<p><strong>Rationale and objectives: </strong>To evaluate the ability of dual-energy CT(DECT)-based quantitative parameters and radiomics features to differentiate solid lung adenocarcinoma (ADC) from squamous cell carcinoma (SCC).</p><p><strong>Methods: </strong>This study included 213 patients diagnosed with ADC and SCC who underwent DECT scans at two centers from November 2022 to December 2023. Patients at center 1 were randomly divided into training (n = 114) and internal test set (n = 50) in a 7:3 ratio, with center 2 serving as the external test set (n = 49). Radiologic and clinical data were combined to establish a clinical-radiologic model. Ten types of DECT energy images including conventional images, iodine density (ID), effective atomic number (Z<sub>eff</sub>), electron density, and virtual mono-energetic images (VMI) were reconstructed in both arterial phases (AP) and venous phases (VP). Quantitative parameters were measured at the uniform enhanced solid portion of the tumor and normalized to the aorta, used to develop a quantification model and calculate the quantitative score (quantscore). Radiologists manually delineated the tumor ROI at the largest level for extracting radiomics features in these 10 energy images. These features were used to establish 10 uni-energy models from which the best-performing features were selected to construct the final radiomics model and calculate a radiomics score (radscore). Then, a combined model was developed using the akaike information criterion(AIC) and compared to the clinical-radiological model to test its diagnostic validity.</p><p><strong>Results: </strong>The independent predictors of the clinical-radiological model included age, gender, and central or peripheral location, and the AUCs for the training set, internal test set, and external test set were 0.808, 0.837, and 0.802. The quantification model incorporated 40 keV CT values, Z<sub>eff</sub>, normalized Z<sub>eff</sub>, and the slope of the spectral attenuation curve (λHU) in the AP and normalized ID, Z<sub>eff</sub>, and λHU in the VP. Uni-energy models based on AP ID maps, AP Z<sub>eff</sub> maps, and VP VMI 65 keV significantly outperformed AUC= 0.5, and 11 radiomics features were selected from these three models to construct the final radiomics model. The combined model, incorporating age, gender, quantscore, and radscore, significantly outperformed the clinical-radiological model in the training set (AUC=0.952 vs 0.808, P < 0.001), and demonstrated higher performance in both the internal and external test sets, although these differences did not reach statistical significance (AUC=0.870 vs 0.837, for the internal test set [P = 0.542], 0.888 vs 0.802 for the external test sets [P = 0.128]). The evaluation of the combined model demonstrated good discriminative ability and potential for generalization.</p><p><strong>Conclusion: </strong>The combined model, integrating quantitative parameters and radiomics features from DECT multi-","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":null,"pages":null},"PeriodicalIF":3.8,"publicationDate":"2024-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142331769","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-25DOI: 10.1016/j.acra.2024.08.045
Hillary W Garner, Priscilla J Slanetz, Jonathan O Swanson, Brent D Griffith, Carolynn M DeBenedectis, Jennifer E Gould, Tara L Holm, Michele Retrouvey, Angelisa M Paladin, Anna Rozenshtein
Rationale and objectives: The Association of Program Directors in Radiology (APDR) administers an annual survey to assess issues and experiences related to residency program management and education. Our purpose is to provide the response data from the 2023 survey and discuss its insights on the impact of COVID-19 on resident recruitment (Part I) and education (Part II), which can be used to facilitate planning and resource allocation for the evolving needs of programs and their leadership. In Part I, we consider the effects of ERAS preference signaling, the virtual interview format, and the potential of a universal interview release date.
Materials and methods: An observational, cross-sectional study of the APDR membership was performed using a web-based survey consisting of 45 questions, 23 of which pertain to virtual recruitment and are discussed in Part I of a two-part survey analysis. All active APDR members (n = 393) were invited to participate in the survey.
Results: The response rate was 32% (124 of 393). 83% reported that signaling increased the likelihood of an interview offer. 96% reported only offering virtual interviews; however, 59% intended to offer virtual-only interviews in the future. 53% would adhere to a universal interview release date but an additional 44% would do so depending on the agreed date, Results were tallied using Qualtrics software and qualitative responses were tabulated or summarized as comments.
Conclusions: Virtual recruitment is expected to continue for many programs and most respondents would accept a universal interview release date. Preference signaling and geographic signaling are considered positive additions to the application process.
{"title":"What Program Directors Think About Resident Recruitment: Results of the 2023 Spring Survey of the Association of Program Directors in Radiology (APDR) Part I.","authors":"Hillary W Garner, Priscilla J Slanetz, Jonathan O Swanson, Brent D Griffith, Carolynn M DeBenedectis, Jennifer E Gould, Tara L Holm, Michele Retrouvey, Angelisa M Paladin, Anna Rozenshtein","doi":"10.1016/j.acra.2024.08.045","DOIUrl":"https://doi.org/10.1016/j.acra.2024.08.045","url":null,"abstract":"<p><strong>Rationale and objectives: </strong>The Association of Program Directors in Radiology (APDR) administers an annual survey to assess issues and experiences related to residency program management and education. Our purpose is to provide the response data from the 2023 survey and discuss its insights on the impact of COVID-19 on resident recruitment (Part I) and education (Part II), which can be used to facilitate planning and resource allocation for the evolving needs of programs and their leadership. In Part I, we consider the effects of ERAS preference signaling, the virtual interview format, and the potential of a universal interview release date.</p><p><strong>Materials and methods: </strong>An observational, cross-sectional study of the APDR membership was performed using a web-based survey consisting of 45 questions, 23 of which pertain to virtual recruitment and are discussed in Part I of a two-part survey analysis. All active APDR members (n = 393) were invited to participate in the survey.</p><p><strong>Results: </strong>The response rate was 32% (124 of 393). 83% reported that signaling increased the likelihood of an interview offer. 96% reported only offering virtual interviews; however, 59% intended to offer virtual-only interviews in the future. 53% would adhere to a universal interview release date but an additional 44% would do so depending on the agreed date, Results were tallied using Qualtrics software and qualitative responses were tabulated or summarized as comments.</p><p><strong>Conclusions: </strong>Virtual recruitment is expected to continue for many programs and most respondents would accept a universal interview release date. Preference signaling and geographic signaling are considered positive additions to the application process.</p>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":null,"pages":null},"PeriodicalIF":3.8,"publicationDate":"2024-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142331858","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-25DOI: 10.1016/j.acra.2024.09.032
Parya Valizadeh, Payam Jannatdoust, Amir Hassankhani, Melika Amoukhteh, Paniz Adli, Benjamin Robert Jacobson, Sherief Ghozy, Pauravi S Vasavada, David F Kallmes, Ali Gholamrezanezhad
{"title":"Diversity Patterns in Interventional Radiology Residency Applicants.","authors":"Parya Valizadeh, Payam Jannatdoust, Amir Hassankhani, Melika Amoukhteh, Paniz Adli, Benjamin Robert Jacobson, Sherief Ghozy, Pauravi S Vasavada, David F Kallmes, Ali Gholamrezanezhad","doi":"10.1016/j.acra.2024.09.032","DOIUrl":"https://doi.org/10.1016/j.acra.2024.09.032","url":null,"abstract":"","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":null,"pages":null},"PeriodicalIF":3.8,"publicationDate":"2024-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142331768","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Rationale and objectives: Recent radiomics studies on predicting pathological outcomes of glioma have shown immense potential. However, the predictive ability remains suboptimal due to the tumor intrinsic heterogeneity. We aimed to achieve better pathological prediction outcomes by combining habitat analysis with deep learning.
Materials and methods: 387 cases of primary glioma from three hospitals were collected, along with their T1 contrast-enhanced and T2-weighted MR sequences, pathological reports and clinical histories. The training set consisted of 264 patients, 82 patients composed the test set, and 41 patients were used as the validation set for hyperparameter tuning and optimal model selection. All groups were sourced from different centers. Through radiomics, deep learning, habitat analysis and combined analysis, we extracted imaging features separately and jointly modeled them with clinical features. We identified the optimal models for predicting glioma grades, Ki67 expression levels, P53 mutation and IDH1 mutation.
Results: Using a LightGBM model with DenseNet161 features based on habitat subregions, the best tumor grade prediction model was achieved. A LightGBM model with ResNet50 features based on habitat subregions yielded the best Ki67 expression level prediction model. An SVM model with Radiomics and Inception_v3 features provided the best prediction of P53 mutation. The best model for predicting IDH1 mutation was achieved by an MLP model with Radiomics features based on habitat subregions. Clinical features might be potentially helpful for the prediction with relatively weak evidence.
Conclusion: Habitat+Deep Learning feature extraction methods were optimal for predicting grades and Ki67 levels. Deep Learning is optimal for predicting P53 mutation, while the combination of Habitat+ Radiomics models yielded the best prediction for IDH1 mutation.
{"title":"Deep Learning and Habitat Radiomics for the Prediction of Glioma Pathology Using Multiparametric MRI: A Multicenter Study.","authors":"Yunyang Zhu, Jing Wang, Chen Xue, Xiaoyang Zhai, Chaoyong Xiao, Ting Lu","doi":"10.1016/j.acra.2024.09.021","DOIUrl":"https://doi.org/10.1016/j.acra.2024.09.021","url":null,"abstract":"<p><strong>Rationale and objectives: </strong>Recent radiomics studies on predicting pathological outcomes of glioma have shown immense potential. However, the predictive ability remains suboptimal due to the tumor intrinsic heterogeneity. We aimed to achieve better pathological prediction outcomes by combining habitat analysis with deep learning.</p><p><strong>Materials and methods: </strong>387 cases of primary glioma from three hospitals were collected, along with their T1 contrast-enhanced and T2-weighted MR sequences, pathological reports and clinical histories. The training set consisted of 264 patients, 82 patients composed the test set, and 41 patients were used as the validation set for hyperparameter tuning and optimal model selection. All groups were sourced from different centers. Through radiomics, deep learning, habitat analysis and combined analysis, we extracted imaging features separately and jointly modeled them with clinical features. We identified the optimal models for predicting glioma grades, Ki67 expression levels, P53 mutation and IDH1 mutation.</p><p><strong>Results: </strong>Using a LightGBM model with DenseNet161 features based on habitat subregions, the best tumor grade prediction model was achieved. A LightGBM model with ResNet50 features based on habitat subregions yielded the best Ki67 expression level prediction model. An SVM model with Radiomics and Inception_v3 features provided the best prediction of P53 mutation. The best model for predicting IDH1 mutation was achieved by an MLP model with Radiomics features based on habitat subregions. Clinical features might be potentially helpful for the prediction with relatively weak evidence.</p><p><strong>Conclusion: </strong>Habitat+Deep Learning feature extraction methods were optimal for predicting grades and Ki67 levels. Deep Learning is optimal for predicting P53 mutation, while the combination of Habitat+ Radiomics models yielded the best prediction for IDH1 mutation.</p>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":null,"pages":null},"PeriodicalIF":3.8,"publicationDate":"2024-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142331857","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-24DOI: 10.1016/j.acra.2024.09.028
Xi Yi, Guiliang Wang, Yu Yang, Yilei Che
<p><strong>Rationale and objectives: </strong>This study aims to develop and validate a new diagnostic model based on the Kaiser score for preoperative diagnosis of the malignancy probability of enhancing lesions on breast MRI.</p><p><strong>Materials and methods: </strong>This study collected consecutive inpatient data (including imaging data, clinical data, and pathological data) from two different institutions. All patients underwent preoperative breast Dynamic Contrast-Enhanced Magnetic Resonance Imaging (DCE-MRI) examinations and were found to have enhancing lesions. These lesions were confirmed as benign or malignant by surgical resection or biopsy pathology (all carcinomas in situ were confirmed by pathology after surgical resection). Data from one institution were used as the training set(284 cases), and data from the other institution were used as the validation set(107 cases). The Kaiser score was directly incorporated into the diagnostic model as a single predictive variable. Other predictive variables were screened using Least Absolute Shrinkage and Selection Operator (LASSO) regression. Multivariate logistic regression was employed to integrate the Kaiser score and other selected predictive variables to construct a new diagnostic model, presented in the form of a nomogram. Receiver operating characteristic (ROC) curve, DeLong test, net reclassification improvement (NRI), and integrated discrimination improvement (IDI) were adopted to evaluate and compare the discrimination of the diagnostic model for breast enhancing lesions based on Kaiser score (hereinafter referred to as the "breast lesion diagnostic model") and the Kaiser score alone. Calibration curves were used to assess the calibration of the breast lesion diagnostic model, and decision curve analysis (DCA) was used to evaluate the clinical efficacy of the diagnostic model and the Kaiser score.</p><p><strong>Results: </strong>LASSO regression indicated that, besides the indicators already included in the Kaiser score system, "age", "MIP sign", "associated imaging features", and "clinical breast examination (CBE) results" were other valuable diagnostic parameters for breast enhancing lesions. In the training set, the AUCs of the breast lesion diagnostic model and the Kaiser score were 0.948 and 0.869, respectively, with a statistically significant difference (p < 0.05). In the validation set, the AUCs of the breast lesion diagnostic model and the Kaiser score were 0.956 and 0.879, respectively, with a statistically significant difference (p < 0.05). The DeLong test, NRI, and IDI showed that the breast lesion diagnostic model had a higher discrimination ability for breast enhancing lesions compared to the Kaiser score alone, with statistically significant differences (p < 0.05). The calibration curves indicated good calibration of the breast lesion diagnostic model. DCA demonstrated that the breast lesion diagnostic model had higher clinical application value, with greater net c
理论依据和目标:本研究旨在开发并验证一种基于凯撒评分的新诊断模型,用于术前诊断乳腺 MRI 增强病灶的恶性概率:本研究收集了来自两家不同机构的连续住院患者数据(包括成像数据、临床数据和病理数据)。所有患者在术前都接受了乳腺动态对比增强磁共振成像(DCE-MRI)检查,并发现了增强病灶。这些病灶经手术切除或活检病理证实为良性或恶性(所有原位癌均在手术切除后经病理证实)。一家机构的数据被用作训练集(284 例),另一家机构的数据被用作验证集(107 例)。Kaiser 评分作为单一预测变量被直接纳入诊断模型。其他预测变量采用最小绝对收缩和选择操作器(LASSO)回归法进行筛选。多变量逻辑回归用于整合 Kaiser 评分和其他选定的预测变量,以构建新的诊断模型,并以提名图的形式呈现。采用接收者操作特征曲线(ROC)、DeLong 检验、净再分类改进(NRI)和综合判别改进(IDI)来评估和比较基于 Kaiser 评分的乳腺增强病变诊断模型(以下简称 "乳腺病变诊断模型")和单独使用 Kaiser 评分的诊断模型的判别能力。校准曲线用于评估乳腺病变诊断模型的校准,决策曲线分析(DCA)用于评估诊断模型和 Kaiser 评分的临床疗效:LASSO回归结果表明,除了Kaiser评分系统中已包含的指标外,"年龄"、"MIP标志"、"相关影像学特征 "和 "临床乳腺检查(CBE)结果 "也是对乳腺增强病变有价值的诊断参数。在训练集中,乳腺病变诊断模型和 Kaiser 评分的 AUC 分别为 0.948 和 0.869,差异有统计学意义(p 结论:乳腺病变诊断模型和 Kaiser 评分的 AUC 差异不大:基于 Kaiser 评分的乳腺病变诊断模型综合了 "年龄"、"MIP 标志"、"相关影像学特征 "和 "CBE 结果",可用于乳腺增强病变恶性概率的术前诊断,其诊断效果优于经典的 Kaiser 评分。
{"title":"Development and Validation of a Diagnostic Model for Enhancing Lesions on Breast MRI: Based on Kaiser Score.","authors":"Xi Yi, Guiliang Wang, Yu Yang, Yilei Che","doi":"10.1016/j.acra.2024.09.028","DOIUrl":"https://doi.org/10.1016/j.acra.2024.09.028","url":null,"abstract":"<p><strong>Rationale and objectives: </strong>This study aims to develop and validate a new diagnostic model based on the Kaiser score for preoperative diagnosis of the malignancy probability of enhancing lesions on breast MRI.</p><p><strong>Materials and methods: </strong>This study collected consecutive inpatient data (including imaging data, clinical data, and pathological data) from two different institutions. All patients underwent preoperative breast Dynamic Contrast-Enhanced Magnetic Resonance Imaging (DCE-MRI) examinations and were found to have enhancing lesions. These lesions were confirmed as benign or malignant by surgical resection or biopsy pathology (all carcinomas in situ were confirmed by pathology after surgical resection). Data from one institution were used as the training set(284 cases), and data from the other institution were used as the validation set(107 cases). The Kaiser score was directly incorporated into the diagnostic model as a single predictive variable. Other predictive variables were screened using Least Absolute Shrinkage and Selection Operator (LASSO) regression. Multivariate logistic regression was employed to integrate the Kaiser score and other selected predictive variables to construct a new diagnostic model, presented in the form of a nomogram. Receiver operating characteristic (ROC) curve, DeLong test, net reclassification improvement (NRI), and integrated discrimination improvement (IDI) were adopted to evaluate and compare the discrimination of the diagnostic model for breast enhancing lesions based on Kaiser score (hereinafter referred to as the \"breast lesion diagnostic model\") and the Kaiser score alone. Calibration curves were used to assess the calibration of the breast lesion diagnostic model, and decision curve analysis (DCA) was used to evaluate the clinical efficacy of the diagnostic model and the Kaiser score.</p><p><strong>Results: </strong>LASSO regression indicated that, besides the indicators already included in the Kaiser score system, \"age\", \"MIP sign\", \"associated imaging features\", and \"clinical breast examination (CBE) results\" were other valuable diagnostic parameters for breast enhancing lesions. In the training set, the AUCs of the breast lesion diagnostic model and the Kaiser score were 0.948 and 0.869, respectively, with a statistically significant difference (p < 0.05). In the validation set, the AUCs of the breast lesion diagnostic model and the Kaiser score were 0.956 and 0.879, respectively, with a statistically significant difference (p < 0.05). The DeLong test, NRI, and IDI showed that the breast lesion diagnostic model had a higher discrimination ability for breast enhancing lesions compared to the Kaiser score alone, with statistically significant differences (p < 0.05). The calibration curves indicated good calibration of the breast lesion diagnostic model. DCA demonstrated that the breast lesion diagnostic model had higher clinical application value, with greater net c","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":null,"pages":null},"PeriodicalIF":3.8,"publicationDate":"2024-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142331766","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-21DOI: 10.1016/j.acra.2024.09.009
Paolo Spinnato, Giulio Vara
{"title":"Differentiating Malignant From Benign Soft-tissue Tumors by Ultrasound and MRI-Based Radiomics: Paving the Way for a Non-invasive Sarcoma Screening.","authors":"Paolo Spinnato, Giulio Vara","doi":"10.1016/j.acra.2024.09.009","DOIUrl":"https://doi.org/10.1016/j.acra.2024.09.009","url":null,"abstract":"","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":null,"pages":null},"PeriodicalIF":3.8,"publicationDate":"2024-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142300169","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Rationale and objectives: To investigate the clinical and computed tomography characteristics of inflammatory solid pulmonary nodules (SPNs) with morphology suggesting malignancy, hereinafter referred to as atypical inflammatory SPNs (AI-SPNs).
Materials and methods: The CT data of 515 patients with SPNs who underwent surgical resection were retrospectively analyzed. These patients were divided into inflammatory and malignant groups and their clinical and imaging features were compared. Binary logistic regression analysis was performed to identify the independent factors for diagnosing AI-SPNs. An external validation cohort included 133 consecutive patients to test the model's predictive efficiency.
Results: Univariate analysis showed that age < 62 years, male sex, maximum spiculation length > 9 mm, polygonal shapes, three-planar ratio > 1.48, Lung window/mediastinal window (L/M) ratio > 1.13, pleural tag type I, satellite lesions, and halo sign were more frequent in AI-SPNs, whereas pleural tag type III, bronchial truncation, and perifocal fibrosis were more common in malignant SPNs (M-SPNs) (all P < 0.05). Binary logistic regression showed age < 62 years, male sex, polygonal shape, three-planar ratio > 1.48, L/M ratio > 1.13, pleural tag type I, satellite lesions, halo sign, and absence of bronchial truncation were independent factors for diagnosing AI-SPNs (AUC, sensitivity, specificity, and accuracy of 0.951, 83.30%, 92.30%, and 87.20%, respectively). In the external validation cohort, the AUC, sensitivity, specificity, and accuracy were 0.969, 90.47%, 90.00%, and 90.23%, respectively.
Conclusion: AI-SPNs and M-SPNs exhibited different clinical and imaging characteristics. A good understanding of these differences may help reduce diagnostic errors in AI-SPNs and enable to choose an optimal treatment strategy.
{"title":"Clinical and Computed Tomography Characteristics of Inflammatory Solid Pulmonary Nodules with Morphology Suggesting Malignancy.","authors":"Wei-Hua Zhao, Li-Juan Zhang, Xian Li, Tian-You Luo, Fa-Jin Lv, Qi Li","doi":"10.1016/j.acra.2024.09.016","DOIUrl":"https://doi.org/10.1016/j.acra.2024.09.016","url":null,"abstract":"<p><strong>Rationale and objectives: </strong>To investigate the clinical and computed tomography characteristics of inflammatory solid pulmonary nodules (SPNs) with morphology suggesting malignancy, hereinafter referred to as atypical inflammatory SPNs (AI-SPNs).</p><p><strong>Materials and methods: </strong>The CT data of 515 patients with SPNs who underwent surgical resection were retrospectively analyzed. These patients were divided into inflammatory and malignant groups and their clinical and imaging features were compared. Binary logistic regression analysis was performed to identify the independent factors for diagnosing AI-SPNs. An external validation cohort included 133 consecutive patients to test the model's predictive efficiency.</p><p><strong>Results: </strong>Univariate analysis showed that age < 62 years, male sex, maximum spiculation length > 9 mm, polygonal shapes, three-planar ratio > 1.48, Lung window/mediastinal window (L/M) ratio > 1.13, pleural tag type I, satellite lesions, and halo sign were more frequent in AI-SPNs, whereas pleural tag type III, bronchial truncation, and perifocal fibrosis were more common in malignant SPNs (M-SPNs) (all P < 0.05). Binary logistic regression showed age < 62 years, male sex, polygonal shape, three-planar ratio > 1.48, L/M ratio > 1.13, pleural tag type I, satellite lesions, halo sign, and absence of bronchial truncation were independent factors for diagnosing AI-SPNs (AUC, sensitivity, specificity, and accuracy of 0.951, 83.30%, 92.30%, and 87.20%, respectively). In the external validation cohort, the AUC, sensitivity, specificity, and accuracy were 0.969, 90.47%, 90.00%, and 90.23%, respectively.</p><p><strong>Conclusion: </strong>AI-SPNs and M-SPNs exhibited different clinical and imaging characteristics. A good understanding of these differences may help reduce diagnostic errors in AI-SPNs and enable to choose an optimal treatment strategy.</p>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":null,"pages":null},"PeriodicalIF":3.8,"publicationDate":"2024-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142300162","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}