Pub Date : 2025-02-01DOI: 10.1016/j.acra.2024.09.001
Xiaoyu Huang , Yong Huang , Kexin Liu , Fenglin Zhang , Zhou Zhu , Kai Xu , Ping Li
Rationale and Objectives
This study aimed to develop a deep learning (DL) prognostic model to evaluate the significance of intra- and peritumoral radiomics in predicting outcomes for high-grade serous ovarian cancer (HGSOC) patients receiving platinum-based chemotherapy.
Materials and Methods
A DL model was trained and validated on retrospectively collected unenhanced computed tomography (CT) scans from 474 patients at two institutions, which were divided into a training set (N = 362), an internal test set (N = 86), and an external test set (N = 26). The model incorporated tumor segmentation and peritumoral region analysis, using various input configurations: original tumor regions of interest (ROIs), ROI subregions, and ROIs expanded by 1 and 3 pixels. Model performance was assessed via hazard ratios (HRs) and receiver operating characteristic (ROC) curves. Patients were stratified into high- and low-risk groups on the basis of the training set's optimal cutoff value.
Results
Among the input configurations, the model using an ROI with a 1-pixel peritumoral expansion achieved the highest predictive accuracy. The DL model exhibited robust performance for predicting progression-free survival, with HRs of 3.41 (95% CI: 2.85, 4.08; P < 0.001) in training set, 1.14 (95% CI: 1.03, 1.26; P = 0.012) in internal test set, and 1.32 (95% CI: 1.07, 1.63; P = 0.011) in external test set. KM survival analysis revealed significant differences between the high-risk and low-risk groups (P < 0.05).
Conclusion
The DL model effectively predicts survival outcomes in HGSOC patients receiving platinum-based chemotherapy, offering valuable insights for prognostic assessment and personalized treatment planning.
{"title":"Intratumoral and Peritumoral Radiomics for Predicting the Prognosis of High-grade Serous Ovarian Cancer Patients Receiving Platinum-Based Chemotherapy","authors":"Xiaoyu Huang , Yong Huang , Kexin Liu , Fenglin Zhang , Zhou Zhu , Kai Xu , Ping Li","doi":"10.1016/j.acra.2024.09.001","DOIUrl":"10.1016/j.acra.2024.09.001","url":null,"abstract":"<div><h3>Rationale and Objectives</h3><div>This study aimed to develop a deep learning (DL) prognostic model to evaluate the significance of intra- and peritumoral radiomics in predicting outcomes for high-grade serous ovarian cancer (HGSOC) patients receiving platinum-based chemotherapy.</div></div><div><h3>Materials and Methods</h3><div>A DL model was trained and validated on retrospectively collected unenhanced computed tomography (CT) scans from 474 patients at two institutions, which were divided into a training set (N = 362), an internal test set (N = 86), and an external test set (N = 26). The model incorporated tumor segmentation and peritumoral region analysis, using various input configurations: original tumor regions of interest (ROIs), ROI subregions, and ROIs expanded by 1 and 3 pixels. Model performance was assessed via hazard ratios (HRs) and receiver operating characteristic (ROC) curves. Patients were stratified into high- and low-risk groups on the basis of the training set's optimal cutoff value.</div></div><div><h3>Results</h3><div>Among the input configurations, the model using an ROI with a 1-pixel peritumoral expansion achieved the highest predictive accuracy. The DL model exhibited robust performance for predicting progression-free survival, with HRs of 3.41 (95% CI: 2.85, 4.08; P < 0.001) in training set, 1.14 (95% CI: 1.03, 1.26; P = 0.012) in internal test set, and 1.32 (95% CI: 1.07, 1.63; P = 0.011) in external test set. K<img>M survival analysis revealed significant differences between the high-risk and low-risk groups (P < 0.05).</div></div><div><h3>Conclusion</h3><div>The DL model effectively predicts survival outcomes in HGSOC patients receiving platinum-based chemotherapy, offering valuable insights for prognostic assessment and personalized treatment planning.</div></div>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":"32 2","pages":"Pages 877-887"},"PeriodicalIF":3.8,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142262201","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-01DOI: 10.1016/j.acra.2024.08.061
Connie Ge MD , Junbong Jang MS , Patrick Svrcek MD , Victoria Fleming MD , Young H. Kim MD, PhD
Rationale and Objectives
In this preliminary study, we aimed to develop a deep learning model using ultrasound single view cines that distinguishes between imaging of normal gallbladder, non-urgent cholelithiasis, and acute calculous cholecystitis requiring urgent intervention.
Methods
Adult patients presenting to the emergency department between 2017–2022 with right-upper-quadrant pain were screened, and ultrasound single view cines of normal imaging, non-urgent cholelithiasis, and acute cholecystitis were included based on final clinical diagnosis. Longitudinal-view cines were de-identified and gallbladder pathology was annotated for model training. Cines were randomly sorted into training (70%), validation (10%), and testing (20%) sets and divided into 12-frame segments. The deep learning model classified cines as normal (all segments normal), cholelithiasis (normal and non-urgent cholelithiasis segments), and acute cholecystitis (any cholecystitis segment present).
Results
A total of 186 patients with 266 cines were identified: Normal imaging (52 patients; 104 cines), non-urgent cholelithiasis (73;88), and acute cholecystitis (61;74). The model achieved a 91% accuracy for Normal vs. Abnormal imaging and an 82% accuracy for Urgent (acute cholecystitis) vs. Non-urgent (cholelithiasis or normal imaging). Furthermore, the model identified abnormal from normal imaging with 100% specificity, with no false positive results.
Conclusion
Our deep learning model, using only readily obtained single-view cines, exhibited a high degree of accuracy and specificity in discriminating between non-urgent imaging and acute cholecystitis requiring urgent intervention.
{"title":"Exploring Deep Learning Applications using Ultrasound Single View Cines in Acute Gallbladder Pathologies: Preliminary Results","authors":"Connie Ge MD , Junbong Jang MS , Patrick Svrcek MD , Victoria Fleming MD , Young H. Kim MD, PhD","doi":"10.1016/j.acra.2024.08.061","DOIUrl":"10.1016/j.acra.2024.08.061","url":null,"abstract":"<div><h3>Rationale and Objectives</h3><div>In this preliminary study, we aimed to develop a deep learning model using ultrasound single view cines that distinguishes between imaging of normal gallbladder, non-urgent cholelithiasis, and acute calculous cholecystitis requiring urgent intervention.</div></div><div><h3>Methods</h3><div>Adult patients presenting to the emergency department between 2017–2022 with right-upper-quadrant pain were screened, and ultrasound single view cines of normal imaging, non-urgent cholelithiasis, and acute cholecystitis were included based on final clinical diagnosis. Longitudinal-view cines were de-identified and gallbladder pathology was annotated for model training. Cines were randomly sorted into training (70%), validation (10%), and testing (20%) sets and divided into 12-frame segments. The deep learning model classified cines as normal (all segments normal), cholelithiasis (normal and non-urgent cholelithiasis segments), and acute cholecystitis (any cholecystitis segment present).</div></div><div><h3>Results</h3><div>A total of 186 patients with 266 cines were identified: Normal imaging (52 patients; 104 cines), non-urgent cholelithiasis (73;88), and acute cholecystitis (61;74). The model achieved a 91% accuracy for Normal vs. Abnormal imaging and an 82% accuracy for Urgent (acute cholecystitis) vs. Non-urgent (cholelithiasis or normal imaging). Furthermore, the model identified abnormal from normal imaging with 100% specificity, with no false positive results.</div></div><div><h3>Conclusion</h3><div>Our deep learning model, using only readily obtained single-view cines, exhibited a high degree of accuracy and specificity in discriminating between non-urgent imaging and acute cholecystitis requiring urgent intervention.</div></div>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":"32 2","pages":"Pages 770-775"},"PeriodicalIF":3.8,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142300170","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-01DOI: 10.1016/j.acra.2024.11.058
Reid D. Masterson BS, Shaun D. Grega BS, Katrina M. Fliotsos BS, Atul Agarwal MD, Richard B. Gunderman MD PhD
{"title":"Mock Residency Interviews: The Role of Medical Students and Residents","authors":"Reid D. Masterson BS, Shaun D. Grega BS, Katrina M. Fliotsos BS, Atul Agarwal MD, Richard B. Gunderman MD PhD","doi":"10.1016/j.acra.2024.11.058","DOIUrl":"10.1016/j.acra.2024.11.058","url":null,"abstract":"","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":"32 2","pages":"Pages 1149-1151"},"PeriodicalIF":3.8,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142822938","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}
This study evaluated the diagnostic performance of 18F-fluorocholine (FCH) PET/CT as the first-line functional imaging method for preoperative localization of hyperfunctioning parathyroid glands (HPGs) in patients with primary hyperparathyroidism (PHPT).
Materials and Methods
This retrospective single-center study included 80 consecutive patients with PHPT, referred for FCH PET/CT between January 2018 and July 2022, and who subsequently underwent surgery. The diagnostic performance of FCH PET/CT was compared to histological results for per-lesion analysis, and to postoperative resolution of biochemical PHPT for per-patient analysis.
Results
18F-FCH-PET/CT revealed 95 positive foci in 77/80 patients and was negative in 3/80 patients. Postoperative resolution of HPT was obtained in 67/80 patients (84%). Per-lesion analysis showed 80 true positives, five true negatives, 11 false negatives, and eight false positives. Seven PET-positive foci could not be compared to histology. In a first per-lesion analysis, excluding these seven anomalies, sensitivity and positive predictive value (PPV) of FCH PET/CT were 88% (95% CI: 79–94) and 91% (95% CI: 87–94), respectively. In a second per-lesion analysis considering the seven anomalies as false positives (maximum bias analysis), PPV was 84% (95% CI: 80%–87%). By per-patient analysis, FCH PET/CT correctly identified and located all pathological glands in 56/80 (70%, 95% CI: 59–80) patients.
Conclusion
18F-Fluorocholine PET/CT appears to be an effective pre-surgical imaging method for localization of hyperfunctioning parathyroid tissue in patients with PHPT.
{"title":"Diagnostic Performances of 18F-Fluorocholine PET/CT as First-Line Functional Imaging Method for Localization of Hyperfunctioning Parathyroid Tissue in Primary Hyperparathyroidism","authors":"Elsa Bouilloux MD , Nicolas Santucci MD , Aurélie Bertaut MD , Jean-Louis Alberini MD, PhD , Alexandre Cochet MD, PhD , Clément Drouet MD, MSc","doi":"10.1016/j.acra.2024.10.013","DOIUrl":"10.1016/j.acra.2024.10.013","url":null,"abstract":"<div><h3>Rationale and Objectives</h3><div>This study evaluated the diagnostic performance of <sup>18</sup>F-fluorocholine (FCH) PET/CT as the first-line functional imaging method for preoperative localization of hyperfunctioning parathyroid glands (HPGs) in patients with primary hyperparathyroidism (PHPT).</div></div><div><h3>Materials and Methods</h3><div>This retrospective single-center study included 80 consecutive patients with PHPT, referred for FCH PET/CT between January 2018 and July 2022, and who subsequently underwent surgery. The diagnostic performance of FCH PET/CT was compared to histological results for per-lesion analysis, and to postoperative resolution of biochemical PHPT for per-patient analysis.</div></div><div><h3>Results</h3><div><sup>18</sup>F-FCH-PET/CT revealed 95 positive foci in 77/80 patients and was negative in 3/80 patients. Postoperative resolution of HPT was obtained in 67/80 patients (84%). Per-lesion analysis showed 80 true positives, five true negatives, 11 false negatives, and eight false positives. Seven PET-positive foci could not be compared to histology. In a first per-lesion analysis, excluding these seven anomalies, sensitivity and positive predictive value (PPV) of FCH PET/CT were 88% (95% CI: 79–94) and 91% (95% CI: 87–94), respectively. In a second per-lesion analysis considering the seven anomalies as false positives (maximum bias analysis), PPV was 84% (95% CI: 80%–87%). By per-patient analysis, FCH PET/CT correctly identified and located all pathological glands in 56/80 (70%, 95% CI: 59–80) patients.</div></div><div><h3>Conclusion</h3><div><sup>18</sup>F-Fluorocholine PET/CT appears to be an effective pre-surgical imaging method for localization of hyperfunctioning parathyroid tissue in patients with PHPT.</div></div>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":"32 2","pages":"Pages 743-753"},"PeriodicalIF":3.8,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142512458","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 : 2025-02-01DOI: 10.1016/j.acra.2024.12.072
Kara Gaetke-Udager MD , Kimberly L. Shampain MD
{"title":"Dean’s Letter Final Adjectives: An Opportunity to Help Students Shine","authors":"Kara Gaetke-Udager MD , Kimberly L. Shampain MD","doi":"10.1016/j.acra.2024.12.072","DOIUrl":"10.1016/j.acra.2024.12.072","url":null,"abstract":"","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":"32 2","pages":"Pages 1115-1116"},"PeriodicalIF":3.8,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142967126","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 : 2025-02-01DOI: 10.1016/j.acra.2024.08.052
Kun Chen , Wengui Xu , Xiaofeng Li
Rationale and objective
To compare the performance of large language model (LLM) based Gemini and Generative Pre-trained Transformers (GPTs) in data mining and generating structured reports based on free-text PET/CT reports for breast cancer after user-defined tasks.
Materials and methods
Breast cancer patients (mean age, 50 years ± 11 [SD]; all female) who underwent consecutive 18F-FDG PET/CT for follow-up between July 2005 and October 2023 were retrospectively included in the study. A total of twenty reports from 10 patients were used to train user-defined text prompts for Gemini and GPTs, by which structured PET/CT reports were generated. The natural language processing (NLP) generated structured reports and the structured reports annotated by nuclear medicine physicians were compared in terms of data extraction accuracy and capacity of progress decision-making. Statistical methods, including chi-square test, McNemar test and paired samples t-test, were employed in the study.
Results
The structured PET/CT reports for 131 patients were generated by using the two NLP techniques, including Gemini and GPTs. In general, GPTs exhibited superiority over Gemini in data mining in terms of primary lesion size (89.6% vs. 53.8%, p < 0.001) and metastatic lesions (96.3% vs 89.6%, p < 0.001). Moreover, GPTs outperformed Gemini in making decision for progress (p < 0.001) and semantic similarity (F1 score 0.930 vs 0.907, p < 0.001) for reports.
Conclusion
GPTs outperformed Gemini in generating structured reports based on free-text PET/CT reports, which is potentially applied in clinical practice.
Data availability
The data used and/or analyzed during the current study are available from the corresponding author on reasonable request.
{"title":"The Potential of Gemini and GPTs for Structured Report Generation based on Free-Text 18F-FDG PET/CT Breast Cancer Reports","authors":"Kun Chen , Wengui Xu , Xiaofeng Li","doi":"10.1016/j.acra.2024.08.052","DOIUrl":"10.1016/j.acra.2024.08.052","url":null,"abstract":"<div><h3>Rationale and objective</h3><div>To compare the performance of large language model (LLM) based Gemini and Generative Pre-trained Transformers (GPTs) in data mining and generating structured reports based on free-text PET/CT reports for breast cancer after user-defined tasks.</div></div><div><h3>Materials and methods</h3><div>Breast cancer patients (mean age, 50 years ± 11 [SD]; all female) who underwent consecutive <sup>18</sup>F-FDG PET/CT for follow-up between July 2005 and October 2023 were retrospectively included in the study. A total of twenty reports from 10 patients were used to train user-defined text prompts for Gemini and GPTs, by which structured PET/CT reports were generated. The natural language processing (NLP) generated structured reports and the structured reports annotated by nuclear medicine physicians were compared in terms of data extraction accuracy and capacity of progress decision-making. Statistical methods, including chi-square test, McNemar test and paired samples t-test, were employed in the study.</div></div><div><h3>Results</h3><div>The structured PET/CT reports for 131 patients were generated by using the two NLP techniques, including Gemini and GPTs. In general, GPTs exhibited superiority over Gemini in data mining in terms of primary lesion size (89.6% vs. 53.8%, p < 0.001) and metastatic lesions (96.3% vs 89.6%, p < 0.001). Moreover, GPTs outperformed Gemini in making decision for progress (p < 0.001) and semantic similarity (F1 score 0.930 vs 0.907, p < 0.001) for reports.</div></div><div><h3>Conclusion</h3><div>GPTs outperformed Gemini in generating structured reports based on free-text PET/CT reports, which is potentially applied in clinical practice.</div></div><div><h3>Data availability</h3><div>The data used and/or analyzed during the current study are available from the corresponding author on reasonable request.</div></div>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":"32 2","pages":"Pages 624-633"},"PeriodicalIF":3.8,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142156567","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-01DOI: 10.1016/j.acra.2024.08.055
Xinyu Li, Fang Yuan, Li Ni, Xiaopan Li
Rationale and Objectives
At present, the application of magnetic resonance imaging (MRI) in the prediction of response to neoadjuvant therapy and concurrent chemoradiotherapy for the treatment of esophageal cancer still needs to be further explored, and its early differential value remains controversial, thus we carried out this systematic review with a meta-analysis. In the application, different MRI sequences and corresponding parameters are used for the differential diagnosis of the response to neoadjuvant therapy and concurrent chemoradiotherapy.
Methods
All relevant studies evaluated the efficacy and response to MRI in neoadjuvant therapy or concurrent chemoradiotherapy for esophageal cancer on Pubmed, Embase, Cohrane Library, and Web of Science databases published before October 10, 2023 (inclusive) were systematically searched. A revised tool was used to assess the quality of diagnostic accuracy studies (QUADAS-2) to assess the risk of bias in the included original studies. A subgroup analysis of MRI sequences diffusion weighted imaging (DWI), dynamic contrast enhanced (DCE) and their corresponding different parameters, as well as the acquisition timepoints (before and after treatment) for different parameters, was performed during the meta-analysis. The bivariate mixed-effects model was used for meta-analysis.
Results
21 studies were finally included, involving 1128 patients with esophageal cancer. The sensitivity, specificity, and area under receiver operating characteristic curve (ROC curve) of DWI sequence for identifying response to concurrent chemoradiotherapy were 0.82 (95% CI: 0.74–0.87), 0.81 (95% CI: 0.72–0.87) and 0.88 (95% CI: 0.56–0.98), respectively. The sensitivity, specificity, and area under ROC curve of DCE sequence for identifying response to concurrent chemoradiotherapy were 0.78 (95% CI: 0.70–0.84), 0.65 (95% CI: 0.59–0.70) and 0.73 (95% CI: 0.50–0.88), respectively. In patients with esophageal cancer, the sensitivity, specificity, and area under the ROC curve of DWI sequences for identifying response to neoadjuvant therapy were 0.80 (95% CI: 0.69 - 0.88), 0.81 (95% CI: 0.69 - 0.89), and 0.88 (95% CI: 0.34 - 0.99), respectively; the sensitivity, specificity, and area under the ROC curve of DCE sequences for identifying response to neoadjuvant therapy were 0.84 (95% CI: 0.76 - 0.90), 0.61 (95% CI: 0.53 - 0.68), and 0.70 (95% CI: 0.27 - 0.94), respectively.
Conclusions
Based on the available evidence, MRI had a very good value in the early identification of response to neoadjuvant therapy and concurrent chemoradiotherapy for esophageal cancer, especially DWI. Apparent diffusion coefficient (ADC) value changes before and after treatment could be used as predictors of pathological response. Also, ADC value changes before and after treatment could be used as a tool to guide clinical decision-making.
{"title":"Meta-Analysis of MRI in Predicting Early Response to Radiotherapy and Chemotherapy in Esophageal Cancer","authors":"Xinyu Li, Fang Yuan, Li Ni, Xiaopan Li","doi":"10.1016/j.acra.2024.08.055","DOIUrl":"10.1016/j.acra.2024.08.055","url":null,"abstract":"<div><h3>Rationale and Objectives</h3><div>At present, the application of magnetic resonance imaging (MRI) in the prediction of response to neoadjuvant therapy and concurrent chemoradiotherapy for the treatment of esophageal cancer still needs to be further explored, and its early differential value remains controversial, thus we carried out this systematic review with a meta-analysis. In the application, different MRI sequences and corresponding parameters are used for the differential diagnosis of the response to neoadjuvant therapy and concurrent chemoradiotherapy.</div></div><div><h3>Methods</h3><div>All relevant studies evaluated the efficacy and response to MRI in neoadjuvant therapy or concurrent chemoradiotherapy for esophageal cancer on Pubmed, Embase, Cohrane Library, and Web of Science databases published before October 10, 2023 (inclusive) were systematically searched. A revised tool was used to assess the quality of diagnostic accuracy studies (QUADAS-2) to assess the risk of bias in the included original studies. A subgroup analysis of MRI sequences diffusion weighted imaging (DWI), dynamic contrast enhanced (DCE) and their corresponding different parameters, as well as the acquisition timepoints (before and after treatment) for different parameters, was performed during the meta-analysis. The bivariate mixed-effects model was used for meta-analysis.</div></div><div><h3>Results</h3><div>21 studies were finally included, involving 1128 patients with esophageal cancer. The sensitivity, specificity, and area under receiver operating characteristic curve (ROC curve) of DWI sequence for identifying response to concurrent chemoradiotherapy were 0.82 (95% CI: 0.74–0.87), 0.81 (95% CI: 0.72–0.87) and 0.88 (95% CI: 0.56–0.98), respectively. The sensitivity, specificity, and area under ROC curve of DCE sequence for identifying response to concurrent chemoradiotherapy were 0.78 (95% CI: 0.70–0.84), 0.65 (95% CI: 0.59–0.70) and 0.73 (95% CI: 0.50–0.88), respectively. In patients with esophageal cancer, the sensitivity, specificity, and area under the ROC curve of DWI sequences for identifying response to neoadjuvant therapy were 0.80 (95% CI: 0.69 - 0.88), 0.81 (95% CI: 0.69 - 0.89), and 0.88 (95% CI: 0.34 - 0.99), respectively; the sensitivity, specificity, and area under the ROC curve of DCE sequences for identifying response to neoadjuvant therapy were 0.84 (95% CI: 0.76 - 0.90), 0.61 (95% CI: 0.53 - 0.68), and 0.70 (95% CI: 0.27 - 0.94), respectively.</div></div><div><h3>Conclusions</h3><div>Based on the available evidence, MRI had a very good value in the early identification of response to neoadjuvant therapy and concurrent chemoradiotherapy for esophageal cancer, especially DWI. Apparent diffusion coefficient (ADC) value changes before and after treatment could be used as predictors of pathological response. Also, ADC value changes before and after treatment could be used as a tool to guide clinical decision-making.</div></div>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":"32 2","pages":"Pages 798-812"},"PeriodicalIF":3.8,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142261938","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-01DOI: 10.1016/j.acra.2024.08.034
Sung-Hye You MD, PhD , Byungjun Kim MD, PhD , InSeong Kim PhD , Kyung-Sook Yang PhD , Kyung Min Kim MS , Bo Kyu Kim MD , Jae Ho Shin MD, PhD
Rationale and Objectives
The role of MR imaging in patients with cognitive impairment is to evaluate each component of Alzheimer’s disease (AD), small vessel disease (SVD), and glymphatic function. We want to validate the diagnostic performance of the comprehensive interpretation of these parameters to predict the cognitive impairment stage.
Materials and Methods
This retrospective single-center study included 359 patients with cognitive impairment who had undergone MRI (FLAIR, T2WI, 3D-T1WI, susceptibility-weighted imaging, and diffusion tensor imaging [DTI]) and a neuropsychological screening battery between January 2020 and July 2022. Each AD and SVD-related MR parameter was visually evaluated, and DTI analysis along the perivascular space (ALPS) index was calculated. Volumetry analysis was performed using Neurophet AQUA AI-based software. Using logistic regression analysis, four types of models were developed and compared by adding the components in the following order: (1) clinical factors and AD, (2) SVD, (3) glymphatic function-related MR parameters, and (4) volumetric data. Chi-square automatic interaction detection algorithm was used to develop diagnostic tree analysis (DTA) model to predict late-stage cognitive impairment.
Results
APOE4 status, years of education, medial temporal lobe atrophy score, Fazekas scale score, DTI-ALPS index, and white matter hyperintensity were significant predictors of late-stage cognitive impairment. The performance of the prediction model increased from Model 1 to Model 4 (AUC: 0.880, 0.899, 0.914, and 0.945, respectively). The overall accuracy of the DTA model was 87.47%.
Conclusion
Integrative brain MRI assessments in patients with cognitive impairment, AD, SVD, and glymphatic function-related MR parameters, improve the prediction of late-stage cognitive impairment.
{"title":"Integrative MR Imaging Interpretation in Cognitive Impairment with Alzheimer's Disease, Small Vessel Disease, and Glymphatic Function-Related MR Parameters","authors":"Sung-Hye You MD, PhD , Byungjun Kim MD, PhD , InSeong Kim PhD , Kyung-Sook Yang PhD , Kyung Min Kim MS , Bo Kyu Kim MD , Jae Ho Shin MD, PhD","doi":"10.1016/j.acra.2024.08.034","DOIUrl":"10.1016/j.acra.2024.08.034","url":null,"abstract":"<div><h3>Rationale and Objectives</h3><div>The role of MR imaging in patients with cognitive impairment is to evaluate each component of Alzheimer’s disease (AD), small vessel disease (SVD), and glymphatic function. We want to validate the diagnostic performance of the comprehensive interpretation of these parameters to predict the cognitive impairment stage.</div></div><div><h3>Materials and Methods</h3><div>This retrospective single-center study included 359 patients with cognitive impairment who had undergone MRI (FLAIR, T2WI, 3D-T1WI, susceptibility-weighted imaging, and diffusion tensor imaging [DTI]) and a neuropsychological screening battery between January 2020 and July 2022. Each AD and SVD-related MR parameter was visually evaluated, and DTI analysis along the perivascular space (ALPS) index was calculated. Volumetry analysis was performed using Neurophet AQUA AI-based software. Using logistic regression analysis, four types of models were developed and compared by adding the components in the following order: (1) clinical factors and AD, (2) SVD, (3) glymphatic function-related MR parameters, and (4) volumetric data. Chi-square automatic interaction detection algorithm was used to develop diagnostic tree analysis (DTA) model to predict late-stage cognitive impairment.</div></div><div><h3>Results</h3><div>APOE4 status, years of education, medial temporal lobe atrophy score, Fazekas scale score, DTI-ALPS index, and white matter hyperintensity were significant predictors of late-stage cognitive impairment. The performance of the prediction model increased from Model 1 to Model 4 (AUC: 0.880, 0.899, 0.914, and 0.945, respectively). The overall accuracy of the DTA model was 87.47%.</div></div><div><h3>Conclusion</h3><div>Integrative brain MRI assessments in patients with cognitive impairment, AD, SVD, and glymphatic function-related MR parameters, improve the prediction of late-stage cognitive impairment.</div></div>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":"32 2","pages":"Pages 932-950"},"PeriodicalIF":3.8,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142262191","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-01DOI: 10.1016/j.acra.2024.08.038
Le Wang , Jilin Peng , Baohong Wen , Ziyu Zhai , Sijie Yuan , Yulin Zhang , Ling Ii , Weijie Li , Yinghui Ding , Yixu Wang , Fanglei Ye
Rationale and Objectives
Isocitrate dehydrogenase 1 (IDH1) is a potential therapeutic target across various tumor types. Here, we aimed to devise a radiomic model capable of predicting the IDH1 expression levels in patients with head and neck squamous cell carcinoma (HNSCC) and examined its prognostic significance.
Materials and Methods
We utilized genomic data, clinicopathological features, and contrast-enhanced computed tomography (CECT) images from The Cancer Genome Atlas and the Cancer Imaging Archive for prognosis analysis and radiomic model construction. The selection of optimal features was conducted using the intraclass correlation coefficient, minimum redundancy maximum relevance, and recursive feature elimination algorithms. A radiomic model for IDH1 prediction and radiomic score (RS) were established using a gradient-boosting machine. Associations between IDH1 expression, RS, clinicopathological variables, and overall survival (OS) were determined using univariate and multivariate Cox proportional hazards regression analyses and Kaplan–Meier curves.
Results
IDH1 emerged as a distinct predictive factor in patients with HNSCC (hazard ratio [HR] 1.535, 95% confidence interval [CI]: 1.117–2.11, P = 0.008). The radiomic model, built on eight optimal features, demonstrated area under the curve values of 0.848 and 0.779 in the training and validation sets, respectively, for predicting IDH1 expression levels. Calibration and decision curve analyses validated the model’s suitability and clinical utility. RS was significantly associated with OS (HR = 2.22, 95% CI: 1.026–4.805, P = 0.043).
Conclusion
IDH1 expression is a significant prognostic marker. The developed radiomic model, derived from CECT features, offers a promising approach for diagnosing and prognosticating HNSCC.
原理与目的Isocitrate dehydrogenase 1（IDH1）是各种类型肿瘤的潜在治疗靶点。材料与方法 我们利用癌症基因组图谱（The Cancer Genome Atlas）和癌症影像档案（Cancer Imaging Archive）中的基因组数据、临床病理特征和对比增强计算机断层扫描（CECT）图像进行预后分析和放射学模型构建。使用类内相关系数、最小冗余最大相关性和递归特征消除算法选择最佳特征。利用梯度提升机器建立了 IDH1 预测放射学模型和放射学评分（RS）。结果IDH1成为HNSCC患者的一个独特的预测因素（危险比[HR]1.535，95%置信区间[CI]：1.117-2.11，P<0.05）：1.117-2.11, P = 0.008).基于八个最佳特征建立的放射组学模型在预测 IDH1 表达水平方面的训练集和验证集的曲线下面积值分别为 0.848 和 0.779。校准和决策曲线分析验证了该模型的适用性和临床实用性。RS与OS明显相关（HR=2.22，95% CI：1.026-4.805，P=0.043）。根据CECT特征建立的放射学模型为HNSCC的诊断和预后提供了一种很有前景的方法。
{"title":"Contrast-Enhanced Computed Tomography-Based Machine Learning Radiomics Predicts IDH1 Expression and Clinical Prognosis in Head and Neck Squamous Cell Carcinoma","authors":"Le Wang , Jilin Peng , Baohong Wen , Ziyu Zhai , Sijie Yuan , Yulin Zhang , Ling Ii , Weijie Li , Yinghui Ding , Yixu Wang , Fanglei Ye","doi":"10.1016/j.acra.2024.08.038","DOIUrl":"10.1016/j.acra.2024.08.038","url":null,"abstract":"<div><h3>Rationale and Objectives</h3><div>Isocitrate dehydrogenase 1 (IDH1) is a potential therapeutic target across various tumor types. Here, we aimed to devise a radiomic model capable of predicting the IDH1 expression levels in patients with head and neck squamous cell carcinoma (HNSCC) and examined its prognostic significance.</div></div><div><h3>Materials and Methods</h3><div>We utilized genomic data, clinicopathological features, and contrast-enhanced computed tomography (CECT) images from The Cancer Genome Atlas and the Cancer Imaging Archive for prognosis analysis and radiomic model construction. The selection of optimal features was conducted using the intraclass correlation coefficient, minimum redundancy maximum relevance, and recursive feature elimination algorithms. A radiomic model for IDH1 prediction and radiomic score (RS) were established using a gradient-boosting machine. Associations between IDH1 expression, RS, clinicopathological variables, and overall survival (OS) were determined using univariate and multivariate Cox proportional hazards regression analyses and Kaplan–Meier curves.</div></div><div><h3>Results</h3><div>IDH1 emerged as a distinct predictive factor in patients with HNSCC (hazard ratio [HR] 1.535, 95% confidence interval [CI]: 1.117–2.11, P = 0.008). The radiomic model, built on eight optimal features, demonstrated area under the curve values of 0.848 and 0.779 in the training and validation sets, respectively, for predicting IDH1 expression levels. Calibration and decision curve analyses validated the model’s suitability and clinical utility. RS was significantly associated with OS (HR<!--> <!-->=<!--> <!-->2.22, 95% CI: 1.026–4.805, P = 0.043).</div></div><div><h3>Conclusion</h3><div>IDH1 expression is a significant prognostic marker. The developed radiomic model, derived from CECT features, offers a promising approach for diagnosing and prognosticating HNSCC.</div></div>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":"32 2","pages":"Pages 976-987"},"PeriodicalIF":3.8,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142262199","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号