Academic Radiology最新文献

{"title":"A Stacked Multimodality Model Based on Functional MRI Features and Deep Learning Radiomics for Predicting the Early Response to Radiotherapy in Nasopharyngeal Carcinoma","authors":"Xiaowen Wang ,&nbsp;Jian Song ,&nbsp;Qingtao Qiu ,&nbsp;Ya Su ,&nbsp;Lizhen Wang ,&nbsp;Xiujuan Cao","doi":"10.1016/j.acra.2024.10.011","DOIUrl":"10.1016/j.acra.2024.10.011","url":null,"abstract":"<div><h3>Background</h3><div>This study aimed to construct and assess a comprehensive model that integrates MRI-derived deep learning radiomics, functional imaging (fMRI), and clinical indicators to predict early efficacy of radiotherapy in nasopharyngeal carcinoma (NPC).</div></div><div><h3>Methods</h3><div>This retrospective study recruited NPC patients with radiotherapy from two Chinese hospitals between October 2018 and July 2022, divided into a training set (hospital I, 194 cases), an internal validation set (hospital I, 82 cases), and an external validation set (hospital II, 40 cases). We extracted 3404 radiomic features and 2048 deep learning features from multi-sequence MRI includes T1WI, CE-T1WI, T2WI and T2WI/FS. Additionally, both the Apparent diffusion coefficient (ADC), its maximum (ADCmax) and Tumor blood flow (TBF), its maximum (TBFmax) were obtained by Diffusion-weighted imaging (DWI) and Arterial spin labeling (ASL) respectively. We used four classifiers (LR, XGBoost, SVM and KNN) and stacked algorithm as model construction methods. The area under the receiver operating characteristic curve (AUC) and decision curve analysis was used to assess models.</div></div><div><h3>Results</h3><div>The manual radiomics model based on XGBoost and the deep learning model based on KNN (the AUCs in the training set: 0.909, 0.823, respectively) showed better predictive efficacy than other machine learning algorithms. The stacked model that integrated MRI-based deep learning radiomics, fMRI, and hematological indicators, has the strongest efficacy prediction ability of AUC in the training set [0.984 (95%CI: 0.972–0.996)], the internal validation set [0.936 (95%CI: 0.885–0.987)], and the external validation set [0.959 (95%CI: 0.901–1.000)].</div></div><div><h3>Conclusion</h3><div>Our research has developed a clinical-radiomics integrated model based on MRI which can predict early radiotherapy response in NPC and provide guidance for personalized treatment.</div></div>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":"32 3","pages":"Pages 1631-1644"},"PeriodicalIF":3.8,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142577175","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}

{"title":"Early and noninvasive prediction of response to neoadjuvant therapy for breast cancer via longitudinal ultrasound and MR deep learning: A multicentre study","authors":"Qiao Zeng ,&nbsp;Lan Liu ,&nbsp;Chongwu He ,&nbsp;Xiaoqiang Zeng ,&nbsp;Pengfei Wei ,&nbsp;Dong Xu ,&nbsp;Ning Mao ,&nbsp;Tenghua Yu","doi":"10.1016/j.acra.2024.10.033","DOIUrl":"10.1016/j.acra.2024.10.033","url":null,"abstract":"<div><h3>Rationale and Objectives</h3><div>The early prediction of response to neoadjuvant chemotherapy (NAC) will aid in the development of personalized treatments for patients with breast cancer. This study investigated the value of longitudinal multimodal deep learning (DL) based on breast MR and ultrasound (US) in predicting pathological complete response (pCR) after NAC.</div></div><div><h3>Materials and Methods</h3><div>We retrospectively reviewed the pre-NAC and post-2nd-NAC MR and/or US images of 448 patients enrolled from three centers and extracted DL features from the largest section of the breast tumour using ResNet50. T test, Pearson correlation analysis and least absolute shrinkage and selection operator regression were used to select the most significant DL features for the pre-NAC and post-2nd-NAC MR and US DL models. The stacking model integrates different single-modality DL models and meaningful clinical data. The diagnostic performance of the models was evaluated.</div></div><div><h3>Results</h3><div>In all the patients, the pCR rate was 36.65%. There was no significant difference in diagnostic performance between the different single-modality DL models (DeLong test, p &gt; 0.05). The stacking model integrating the above four DL models with HER2 status yielded areas under the curves of 0.951-0.979, accuracies of 91.55%–92.65%, sensitivities of 90.63%–93.94%, and specificities of 89.47%–94.44% in the cohorts.</div></div><div><h3>Conclusion</h3><div>Longitudinal multimodal DL can be useful in predicting pCR. The stacking model can be used as a new tool for the early noninvasive prediction of the response to NAC, as evidenced by its excellent performance, and therefore aid the development of personalized treatment strategies for patients with breast cancer.</div></div>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":"32 3","pages":"Pages 1264-1273"},"PeriodicalIF":3.8,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142631690","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}

{"title":"Feasibility of Ultra-low Radiation and Contrast Medium Dosage in Aortic CTA Using Deep Learning Reconstruction at 60 kVp: An Image Quality Assessment","authors":"Ke Qi MM ,&nbsp;Chensi Xu ME ,&nbsp;Dian Yuan MM ,&nbsp;Yicun Zhang MM ,&nbsp;Mengyuan Zhang MM ,&nbsp;Weiting Zhang MM ,&nbsp;Jiong Zhang MM ,&nbsp;Bojun You MM ,&nbsp;Jianbo Gao PhD ,&nbsp;Jie Liu MM","doi":"10.1016/j.acra.2024.10.042","DOIUrl":"10.1016/j.acra.2024.10.042","url":null,"abstract":"<div><h3>Objective</h3><div>To assess the viability of using ultra-low radiation and contrast medium (CM) dosage in aortic computed tomography angiography (CTA) through the application of low tube voltage (60<!--> <!-->kVp) and a novel deep learning image reconstruction algorithm (ClearInfinity, DLIR-CI).</div></div><div><h3>Methods</h3><div>Iodine attenuation curves obtained from a phantom study informed the administration of CM protocols. Non-obese participants undergoing aortic CTA were prospectively allocated into two groups and then obtained three reconstruction groups. The conventional group (100<!--> <!-->kVp-CV group) underwent imaging at 100<!--> <!-->kVp and received 210 mg iodine/kg in combination with a hybrid iterative reconstruction algorithm (ClearView, HIR-CV). The experimental group was imaged at 60<!--> <!-->kVp with 105 mg iodine/kg, while images were reconstructed with HIR-CV (60<!--> <!-->kVp-CV group) and with DLIR-CI (60<!--> <!-->kVp-CI group). Student's t-test was used to compare differences in CM protocol and radiation dose. One-way ANOVA compared CT attenuation, image noise, SNR, and CNR among the three reconstruction groups, while the Kruskal–Wallis H test assessed subjective image quality scores. Post hoc analysis was performed with Bonferroni correction for multiple comparisons, and consistency analysis conducted in subjective image quality assessment was measured using Cohen's kappa.</div></div><div><h3>Results</h3><div>The radiation dose (1.12 ± 0.23<!--> <!-->mSv vs. 2.03 ± 0.82<!--> <!-->mSv) and CM dosage (19.04 ± 3.03<!--> <!-->mL vs. 38.11 ± 6.47<!--> <!-->mL) provided the reduction of 45% and 50% in the experimental group compared to the conventional group. The CT attenuation, SNR, and CNR of 60<!--> <!-->kVp-CI were superior to or equal to those of 100<!--> <!-->kVp-CV. Compared to the 60<!--> <!-->kVp-CV group, images in 60<!--> <!-->kVp-CI showed higher SNR and CNR (all <em>P</em> &lt; 0.001). There was no difference between the 60<!--> <!-->kVp-CI and 100<!--> <!-->kVp-CV group in terms of the subjective image quality of the aorta in various locations (all <em>P</em> &gt; 0.05), with 60<!--> <!-->kVp-CI images were deemed diagnostically sufficient across all vascular segments.</div></div><div><h3>Conclusion</h3><div>For non-obese patients, the combined use of 60<!--> <!-->kVp and DLIR-CI algorithm can be preserving image quality while enabling radiation dose and contrast medium savings for aortic CTA compared to 100<!--> <!-->kVp using HIR-CV.</div></div>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":"32 3","pages":"Pages 1506-1516"},"PeriodicalIF":3.8,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142631716","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}

{"title":"Accuracy and Readability of ChatGPT on Potential Complications of Interventional Radiology Procedures: AI-Powered Patient Interviewing","authors":"Esat Kaba ,&nbsp;Mehmet Beyazal ,&nbsp;Fatma Beyazal Çeliker ,&nbsp;İbrahim Yel ,&nbsp;Thomas J. Vogl","doi":"10.1016/j.acra.2024.10.028","DOIUrl":"10.1016/j.acra.2024.10.028","url":null,"abstract":"<div><h3>Rationale and Objectives</h3><div>It is crucial to inform the patient about potential complications and obtain consent before interventional radiology procedures. In this study, we investigated the accuracy, reliability, and readability of the information provided by ChatGPT-4 about potential complications of interventional radiology procedures.</div></div><div><h3>Materials and Methods</h3><div>Potential major and minor complications of 25 different interventional radiology procedures (8 non-vascular, 17 vascular) were asked to ChatGPT-4 chatbot. The responses were evaluated by two experienced interventional radiologists (&gt;25 years and 10 years of experience) using a 5-point Likert scale according to Cardiovascular and Interventional Radiological Society of Europe guidelines. The correlation between the two interventional radiologists' scoring was evaluated by the Wilcoxon signed-rank test, Intraclass Correlation Coefficient (ICC), and Pearson correlation coefficient (PCC). In addition, readability and complexity were quantitatively assessed using the Flesch-Kincaid Grade Level, Flesch Reading Ease scores, and Simple Measure of Gobbledygook (SMOG) index.</div></div><div><h3>Results</h3><div>Interventional radiologist 1 (IR1) and interventional radiologist 2 (IR2) gave 104 and 109 points, respectively, out of a potential 125 points for the total of all procedures. There was no statistically significant difference between the total scores of the two IRs (p = 0.244). The IRs demonstrated high agreement across all procedure ratings (ICC<!--> <!-->=<!--> <!-->0.928). Both IRs scored 34 out of 40 points for the eight non-vascular procedures. 17 vascular procedures received 70 points out of 85 from IR1 and 75 from IR2. The agreement between the two observers' assessments was good, with PCC values of 0.908 and 0.896 for non-vascular and vascular procedures, respectively. Readability levels were overall low. The mean Flesch-Kincaid Grade Level, Flesch Reading Ease scores, and SMOG index were 12.51 ± 1.14 (college level) 30.27 ± 8.38 (college level), and 14.46 ± 0.76 (college level), respectively. There was no statistically significant difference in readability between non-vascular and vascular procedures (p = 0.16).</div></div><div><h3>Conclusion</h3><div>ChatGPT-4 demonstrated remarkable performance, highlighting its potential to enhance accessibility to information about interventional radiology procedures and support the creation of educational materials for patients. Based on the findings of our study, while ChatGPT provides accurate information and shows no evidence of hallucinations, it is important to emphasize that a high level of education and health literacy are required to fully comprehend its responses.</div></div>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":"32 3","pages":"Pages 1547-1553"},"PeriodicalIF":3.8,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142649717","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}

{"title":"Non-invasive Prediction of Lymph Node Metastasis in NSCLC Using Clinical, Radiomics, and Deep Learning Features From 18F-FDG PET/CT Based on Interpretable Machine Learning","authors":"Furui Duan ,&nbsp;Minghui Zhang ,&nbsp;Chunyan Yang ,&nbsp;Xuewei Wang ,&nbsp;Dalong Wang","doi":"10.1016/j.acra.2024.11.037","DOIUrl":"10.1016/j.acra.2024.11.037","url":null,"abstract":"<div><h3>Purpose</h3><div>This study aimed to develop and evaluate a machine learning model combining clinical, radiomics, and deep learning features derived from PET/CT imaging to predict lymph node metastasis (LNM) in patients with non-small cell lung cancer (NSCLC). The model's interpretability was enhanced using Shapley additive explanations (SHAP).</div></div><div><h3>Methods</h3><div>A total of 248 NSCLC patients who underwent preoperative PET/CT scans were included and divided into training, test, and external validation sets. Radiomics features were extracted from segmented tumor regions on PET/CT images, and deep learning features were generated using the ResNet50 architecture. Feature selection was performed using minimum-redundancy maximum-relevance (mRMR), and the least absolute shrinkage and selection operator (LASSO) algorithm. Four models—clinical, radiomics, deep learning radiomics (DL_radiomics), and combined model—were constructed using the XGBoost algorithm and evaluated based on diagnostic performance metrics, including area under the receiver operating characteristic curve (AUC), accuracy, F1 score, sensitivity, and specificity. Shapley Additive exPlanations (SHAP) was used for model interpretability.</div></div><div><h3>Results</h3><div>The combined model achieved the highest AUC in the test set (AUC<!--> <!-->=<!--> <!-->0.853), outperforming the clinical (AUC<!--> <!-->=<!--> <!-->0.758), radiomics (AUC<!--> <!-->=<!--> <!-->0.831), and DL_radiomics (AUC<!--> <!-->=<!--> <!-->0.834) models. Decision curve analysis (DCA) demonstrated that the combined model offered greater clinical net benefits. SHAP was used for global interpretation, and the summary plot indicated that the features <em>ct_original_glrlm_LongRunHighGrayLevelEmphasis</em>, and <em>pet_gradient_glcm_lmc1</em> were the most important for the model’s predictions.</div></div><div><h3>Conclusion</h3><div>The combined model, combining clinical, radiomics, and deep learning features from PET/CT, significantly improved the accuracy of LNM prediction in NSCLC patients. SHAP-based interpretability provided valuable insights into the model's decision-making process, enhancing its potential clinical application for preoperative decision-making in NSCLC.</div></div>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":"32 3","pages":"Pages 1645-1655"},"PeriodicalIF":3.8,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142814980","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}

{"title":"How to Succeed on Your Residency Interview","authors":"Talal Mourad BA ,&nbsp;Omer A. Awan MD, MPH, CIIP","doi":"10.1016/j.acra.2024.04.037","DOIUrl":"10.1016/j.acra.2024.04.037","url":null,"abstract":"","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":"32 3","pages":"Pages 1768-1770"},"PeriodicalIF":3.8,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141181313","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}

{"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 ,&nbsp;Enise Celebi ,&nbsp;Constantijne H. Mom ,&nbsp;Jaap Stoker ,&nbsp;Shandra Bipat","doi":"10.1016/j.acra.2024.09.020","DOIUrl":"10.1016/j.acra.2024.09.020","url":null,"abstract":"<div><h3>Purpose</h3><div>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.</div></div><div><h3>Method</h3><div>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.</div></div><div><h3>Results</h3><div>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.</div></div><div><h3>Conclusion</h3><div>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.</div></div>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":"32 3","pages":"Pages 1465-1475"},"PeriodicalIF":3.8,"publicationDate":"2025-03-01","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":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Fully Automated and Explainable Measurement of Liver Surface Nodularity in CT: Utility for Staging Hepatic Fibrosis","authors":"Tejas Sudharshan Mathai PhD ,&nbsp;Meghan G. Lubner MD ,&nbsp;Perry J. Pickhardt MD ,&nbsp;Ronald M. Summers MD, PhD","doi":"10.1016/j.acra.2024.09.050","DOIUrl":"10.1016/j.acra.2024.09.050","url":null,"abstract":"<div><h3>Rationale and Objectives</h3><div>In the United States, cirrhosis was the 12th leading cause of death in 2016. Despite end-stage cirrhosis being irreversible, earlier stages of hepatic fibrosis can be reversed via early diagnosis and intervention. The objective is to investigate the utility of a fully automated technique to measure liver surface nodularity (LSN) for staging hepatic fibrosis (stages F0–F4).</div></div><div><h3>Materials and Methods</h3><div>In this retrospective study, a dataset consisting of patients with multiple etiologies of liver disease collected at Institution-A (METAVIR F0–F4, 2000–2016) was used. The LSN was automatically measured in contrast-enhanced CT volumes and compared against scores from a manual tool. Area under the receiver operating characteristics curve (AUC) was used to distinguish between clinically significant fibrosis (≥<!--> <!--> F2), advanced fibrosis (≥<!--> <!-->F3), and end-stage cirrhosis (F4).</div></div><div><h3>Results</h3><div>The study sample had 480 patients (304 men, 176 women, mean age, 49<!--> <!-->±<!--> <!-->9). Automatically derived LSN scores progressively increased with the fibrosis stage: F0 (1.64 [mean]<!--> <!-->±<!--> <!-->1.13 [standard deviation]), F1 (2.16<!--> <!-->±<!--> <!-->2.39), F2 (2.17<!--> <!-->±<!--> <!-->2.55), F3 (2.23<!--> <!-->±<!--> <!-->2.52), and F4 (4.21<!--> <!-->±<!--> <!-->2.94). For discriminating significant fibrosis (≥<!--> <!-->F2), advanced fibrosis (≥<!--> <!-->F3), and cirrhosis (F4), the automated tool achieved ROC AUCs of 73.9%, 82.5%, and 87.8% respectively. The sensitivity and specificity for significant fibrosis (nodularity threshold 1.51) was 85.2% and 73.3%, advanced fibrosis (nodularity threshold 1.73) was 84.2% and 79.5%, and cirrhosis (nodularity threshold 2.18) was 86.5% and 79.5%. Statistical tests revealed that the automated LSN scores distinguished patients with advanced fibrosis (<em>p</em> <!-->&lt;<!--> <!-->.001) and cirrhosis (<em>p<!--> </em>&lt;<!--> <!-->.001).</div></div><div><h3>Conclusion</h3><div>The fully automated LSN measurement retained its predictive power for distinguishing between advanced fibrosis and cirrhosis. The clinical impact is that the fully automated LSN measurement may be useful for early interventions and population-based studies. It can automatically predict the fibrosis stage in ∼45 s in comparison to the ∼2 min needed to manually measure the LSN in a CT volume.</div></div>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":"32 3","pages":"Pages 1398-1408"},"PeriodicalIF":3.8,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142395010","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}

{"title":"FS-YOLOv9: A Frequency and Spatial Feature-Based YOLOv9 for Real-time Breast Cancer Detection","authors":"Haitian Gui ,&nbsp;Tao Su ,&nbsp;Xinhua Jiang ,&nbsp;Li Li ,&nbsp;Lang Xiong ,&nbsp;Ji Zhou ,&nbsp;Zhiyong Pang","doi":"10.1016/j.acra.2024.09.048","DOIUrl":"10.1016/j.acra.2024.09.048","url":null,"abstract":"<div><h3>Rationale and Objectives</h3><div>Breast cancer screening is critical for reducing mortality rates. YOLOv9, a new real-time object-detection model, is ideal for cancer screening. A customized YOLOv9 model with enhancements for detecting breast cancer on the basis of species and morphological diversity has potential clinical significance.</div></div><div><h3>Materials and Methods</h3><div>The internal dataset consisted of 687 cases split 3:1 for cross-validation. Additionally, 98 cases from external datasets were used for testing. We developed an FS-YOLOv9 model customized for breast cancer detection that incorporated an extra max-pooling layer before the Conv1 of the Adown to enhance high-brightness features. The Adown of the P3 in the backbone was replaced with a high-frequency Haar wavelet convolution kernel, which ignored the low-frequency components during down-sampling to enhance morphology and texture features. The reliability and robustness of our model was determined by measuring the F1 score, the area under curve of free-response receiver operating characteristic (FAUC), mean average precision (mAP), recall, and precision, and comparing them with the findings for the official YOLOv9, YOLOv8, YOLOv5 models.</div></div><div><h3>Results</h3><div>In comparison with the official YOLOv9 model, FS-YOLOv9 showed a higher average F1 score (0.700 vs. 0.669), FAUC (0.695 vs. 0.662), and mAP50 (0.713 vs. 0.679) in the internal dataset; in the external testing dataset, the FS-YOLOv9 improved the average F1 score, FAUC, and mAP50 by 4.58%, 5.78%, and 4.41% respectively.</div></div><div><h3>Conclusion</h3><div>Our FS-YOLOv9 model showed significantly improved performance in detecting breast cancer, making it more practical for high-risk breast cancer diagnosis.</div></div>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":"32 3","pages":"Pages 1228-1240"},"PeriodicalIF":3.8,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142480007","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}

{"title":"Evaluation of predictive performance for new vertebral compression fracture between Hounsfield units value and vertebral bone quality score following percutaneous vertebroplasty or kyphoplasty","authors":"Zhengbo Wang BS ,&nbsp;Lingzhi Li BS ,&nbsp;Tianyou Zhang BS,&nbsp;Ruya Li MS,&nbsp;Wei Ren BS,&nbsp;Helong Zhang BS,&nbsp;Zhiwen Tao BS,&nbsp;Yongxin Ren MD","doi":"10.1016/j.acra.2024.11.039","DOIUrl":"10.1016/j.acra.2024.11.039","url":null,"abstract":"<div><h3>Rationale and Objectives</h3><div>New vertebral compression fractures (NVCF) are very common in patients following percutaneous vertebroplasty (PVP) or kyphoplasty (PKP). The study aims to evaluate the comparative predictive performance of vertebral bone quality (VBQ) score and Hounsfield units (HU) value in forecasting NVCF after surgery.</div></div><div><h3>Materials and Methods</h3><div>This study retrospectively analyzed patients who underwent PVP/PKP at our institution between 2020 and 2021. The VBQ score and HU value were obtained from preoperative magnetic resonance imaging (MRI) and computed tomography (CT) scans, respectively. Subsequently, the forecasting capabilities of these two parameters were assessed by contrasting their receiver operating characteristic (ROC) curve.</div></div><div><h3>Results</h3><div>A total of 303 eligible patients (56 with NVCF and 247 without) were identified in the study. Six relevant literature factors were identified and included in the multivariate analysis revealed that lower HU value (OR = 0.967, 95% CI = 0.953–0.981, <em>P</em> &lt; 0.001) and higher VBQ score (OR = 3.964, 95% CI = 2.369–6.631, <em>P</em> &lt; 0.001) emerged as independent predictors of NCVF occurrence. Compared to the ROC curve of the HU value, demonstrating a diagnostic accuracy of 83.2% (95% CI = 77.5%−88.9%, <em>P</em> &lt; 0.001), the VBQ score was 85.8%. And, a statistically significant negative correlation was observed between the VBQ score and the T-score (r = −0.529, <em>P</em> &lt; 0.001).</div></div><div><h3>Conclusion</h3><div>In patients undergoing PVP/PKP, VBQ score, and HU value are independently associated with the occurrence of NVCF. Assessing the HU value and the VBQ score could play an effective role in planning PVP/PKP operations.</div></div>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":"32 3","pages":"Pages 1562-1573"},"PeriodicalIF":3.8,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142792761","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}