Abdominal Radiology最新文献

{"title":"Body packing in the emergency department: a pictorial essay with common imaging findings.","authors":"Angélica María De Luque Correa, Valeria Vanessa Varela Betancourt, Carlos Alfonso Diaz Lizarraga, Marlly Giselle Ortiz Rodríguez, Nelson Francisco Alfonso Jaime, José David Cardona Ortegón","doi":"10.1007/s00261-025-04928-6","DOIUrl":"https://doi.org/10.1007/s00261-025-04928-6","url":null,"abstract":"<p><p>Body packing, a method used to traffic illicit drugs, primarily involves the gastrointestinal tract as a concealment route. Commonly trafficked substances include cocaine, heroin, marijuana, methamphetamine, and cannabis, often sealed in handmade latex packets characterized by specific imaging signs. Prompt diagnosis is crucial for initiating appropriate treatment, recognizing complications, and ensuring proper medico-legal handling. Abdominal radiographs are the preferred initial imaging modality due to their low cost and widespread availability, though their sensitivity varies depending on packet size, location, and interpreter expertise. Abdominopelvic non-contrast CT is the gold standard for detecting gastrointestinal packages, offering high sensitivity and specificity. Low-dose CT protocols are recommended to minimize radiation exposure without compromising diagnostic accuracy, particularly for follow-up or in cases without complications. Contrast-enhanced CT is reserved for assessing suspected complications such as bowel obstruction or perforation. This pictorial review highlights key imaging findings correlated with clinical features, aiming to facilitate accurate recognition, timely intervention, and prevention of complications in suspected cases.</p>","PeriodicalId":7126,"journal":{"name":"Abdominal Radiology","volume":" ","pages":""},"PeriodicalIF":2.3,"publicationDate":"2025-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143952653","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Preoperative radiomics models using CT and MRI for microsatellite instability in colorectal cancer: a systematic review and meta-analysis.","authors":"Gianluca Capello Ingold, João Martins da Fonseca, Sanda Kolenda Zloić, Sarah Verdan Moreira, Karabo Kago Marole, Emma Finnegan, Marcia Harumy Yoshikawa, Silvija Daugėlaitė, Tábata Xavit Souza E Silva, Marco Aurélio Soato Ratti","doi":"10.1007/s00261-025-04981-1","DOIUrl":"https://doi.org/10.1007/s00261-025-04981-1","url":null,"abstract":"<p><strong>Objective: </strong>Microsatellite instability (MSI) is a novel predictive biomarker for chemotherapy and immunotherapy response, as well as prognostic indicator in colorectal cancer (CRC). The current standard for MSI identification is polymerase chain reaction (PCR) testing or the immunohistochemical analysis of tumor biopsy samples. However, tumor heterogeneity and procedure complications pose challenges to these techniques. CT and MRI-based radiomics models offer a promising non-invasive approach for this purpose.</p><p><strong>Materials and methods: </strong>A systematic search of PubMed, Embase, Cochrane Library and Scopus was conducted to identify studies evaluating the diagnostic performance of CT and MRI-based radiomics models for detecting MSI status in CRC. Pooled area under the curve (AUC), sensitivity, and specificity were calculated in RStudio using a random-effects model. Forest plots and a summary ROC curve were generated. Heterogeneity was assessed using I² statistics and explored through sensitivity analyses, threshold effect assessment, subgroup analyses and meta-regression.</p><p><strong>Results: </strong>17 studies with a total of 6,045 subjects were included in the analysis. All studies extracted radiomic features from CT or MRI images of CRC patients with confirmed MSI status to train machine learning models. The pooled AUC was 0.815 (95% CI: 0.784-0.840) for CT-based studies and 0.900 (95% CI: 0.819-0.943) for MRI-based studies. Significant heterogeneity was identified and addressed through extensive analysis.</p><p><strong>Conclusion: </strong>Radiomics models represent a novel and promising tool for predicting MSI status in CRC patients. These findings may serve as a foundation for future studies aimed at developing and validating improved models, ultimately enhancing the diagnosis, treatment, and prognosis of colorectal cancer.</p>","PeriodicalId":7126,"journal":{"name":"Abdominal Radiology","volume":" ","pages":""},"PeriodicalIF":2.3,"publicationDate":"2025-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143952060","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Diagnostic and prognostic value of quantitative ¹⁸F-FDG PET/CT metabolic parameters combined with clinical indicators in patients with locally recurrent rectal cancer.","authors":"Junjie Li, Yin Zhou, Liu Liu, Hua Pang","doi":"10.1007/s00261-025-04968-y","DOIUrl":"https://doi.org/10.1007/s00261-025-04968-y","url":null,"abstract":"<p><strong>Purpose: </strong>To evaluate the diagnostic and prognostic value of quantitative ¹⁸F-fluorodeoxyglucose positron emission tomography/computed tomography (¹⁸F-FDG PET/CT) metabolic parameters combined with clinical indicators in patients with locally recurrent rectal cancer (LRRC).</p><p><strong>Materials and methods: </strong>The quantitative ¹⁸F-FDG PET/CT metabolic parameters and clinical indicators of all patients with suspected LRRC after curative resection of rectal or distal sigmoid colon cancer were retrospectively analyzed. The sensitivity, specificity, and accuracy of ¹⁸F-FDG PET/CT metabolic parameters were assessed using receiver operating characteristic (ROC) curves. Kaplan-Meier (KM) analysis and log-rank tests were used to estimate overall survival (OS). Univariable and multivariable Cox regression models were used to determine the potential predictors of OS.</p><p><strong>Results: </strong>A total of 92 patients were included, with 59 confirmed LRRC cases and 33 benign lesions. Among all parameters, maximum standardized uptake value (SUV_max) demonstrated the highest diagnostic performance for LRRC (cut-off = 4.71 g/mL, AUC = 0.923, sensitivity = 93.22%, specificity = 84.85%, accuracy = 90.22%). In comparison, total lesion glycolysis of the local lesion (TLG_local) exhibited relatively lower efficacy (cut-off = 33 g, AUC = 0.785, sensitivity =77.97%, specificity = 72.73%, accuracy = 76.09%). KM survival analysis revealed that TLG_local > 33 g was significantly associated with shorter OS (p = 0.001). Multivariable Cox analysis identified TLG_local > 33 g (HR = 3.62, 95% CI: 1.39-9.44, p = 0.008), sacral involvement (HR = 2.68, 95% CI: 1.13-6.37, p = 0.025), and surgical resection (HR = 0.19, 95% CI: 0.06-0.66, p = 0.009) as independent prognostic factors for OS.</p><p><strong>Conclusion: </strong>¹⁸F-FDG PET/CT metabolic parameters demonstrated significant diagnostic and prognostic value in the setting of suspected LRRC. SUV_max exhibited the highest diagnostic accuracy for LRRC, and TLG_local was an independent predictor of OS.</p><p><strong>Clinical relevance statement: </strong>This study highlights the diagnostic and prognostic value of ¹⁸F-FDG PET/CT metabolic parameters in locally recurrent rectal cancer (LRRC). Maximum standardized uptake value shows high diagnostic accuracy, and total lesion glycolysis of the local lesion serves as both a diagnostic and prognostic marker for risk stratification. Additionally, sacral involvement and surgical treatment are independent predictors of overall survival. These findings underscore the importance of integrating metabolic parameters into clinical practice to enhance early detection and assist in treatment decision-making for patients with suspected LRRC.</p>","PeriodicalId":7126,"journal":{"name":"Abdominal Radiology","volume":" ","pages":""},"PeriodicalIF":2.3,"publicationDate":"2025-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143952155","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A case of uterine leiomyosarcoma in a survivor of hereditary retinoblastoma.","authors":"Mitsuhiro Kirita, Yuki Himoto, Yuka Kuriyama Matsumoto, Yasuhisa Kurata, Aki Kido, Yusuke Yamaoka, Koji Yamanoi, Masaki Mandai, Sachiko Minamiguchi, Yuji Nakamoto","doi":"10.1007/s00261-025-04943-7","DOIUrl":"https://doi.org/10.1007/s00261-025-04943-7","url":null,"abstract":"<p><p>Survivors of hereditary retinoblastoma have increased risk of subsequent primary malignancies due to RB1 mutation. We report uterine leiomyosarcoma (LMS) in a hereditary retinoblastoma survivor. She had follow-up for leiomyomas, with pelvic MRI showing typical leiomyomas two years prior. She presented with abdominal distention, and MRI revealed a massive tumor with LMS characteristics where a leiomyoma was previously observed. Chest CT showed a nodule suspicious for metastasis in the left lung. Total hysterectomy with bilateral salpingo-oophorectomy and partial lung resection was performed. Pathology confirmed LMS with pulmonary metastasis. Immunostaining showed complete RB1 loss in tumor cells. LMS was suspected to have arisen near a pre-existing leiomyoma or resulted from its malignant transformation. Continuous follow-up is necessary in hereditary retinoblastoma survivors.</p>","PeriodicalId":7126,"journal":{"name":"Abdominal Radiology","volume":" ","pages":""},"PeriodicalIF":2.3,"publicationDate":"2025-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143958800","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A multi-center study: development and validation of a BpMRI focused model in transition zone PI-RADS 3 and 4 lesions to detect clinically significant prostate cancer.","authors":"Ying Yi, Zhiyin Chen, Hang Wang, Dongliang Cheng, Chun Luo, Hai Zhao","doi":"10.1007/s00261-025-04974-0","DOIUrl":"https://doi.org/10.1007/s00261-025-04974-0","url":null,"abstract":"<p><strong>Objective: </strong>To develop and validate a biparametric magnetic resonance imaging(BpMRI) focused model for detecting clinically significant prostate cancer(csPCa)( Gleason score ≥ 7) in TZ PI-RADS 3 and 4 lesions, compared to the Risk-based model (PI-RADS ≥ 3 and PSA density (PSAD) ≥ 0.15 ng/ml/cm³).</p><p><strong>Methods: </strong>A multi-center, retrospective cohort analysis was conducted on consecutive patients with PI-RADS 3 or 4 and eligible biopsy result. Multivariable logistic regression identified predictors of csPCa, followed by the areas under the curve(AUC) and decision curve analysis (DCA) comparisons between the Risk-based and BpMRI focused models, with external validation.</p><p><strong>Results: </strong>A total of 121 patients with 231 lesions in the development cohort(cohort 1) and 45 patients with 81 lesions the external validation cohort(cohort 2) were included between January 2020 and December 2024. The AUCs of the BpMRI-focused model were higher than those of the risk-based model in both the development cohort (0.71 [95% CI: 0.62-0.81] vs. 0.83 [95% CI: 0.74-0.92], p < 0.05) and the external validation cohort (0.75 [95% CI: 0.63-0.87] vs. 0.87 [95% CI: 0.79-0.95], p < 0.05). Furthermore, the BpMRI Focused Model significantly reduced the number of false positives for clinically significant prostate cancer compared to the Risk-Based Model [54 (23%) vs. 142 (61%), p < 0.002], while maintaining a cancer detection rate comparable to the PI-RADS ≥ 3 strategy (both p > 0.05). Additionally, the BpMRI Focused Model achieved a higher biopsy avoidance rate for csPCa [15 (6%)] compared to the Risk-Based Model [10 (4%)], though the difference was not statistically significant (p = 0.30).</p><p><strong>Conclusion: </strong>In clinical decision-making, lesions in the TZ with PI-RADS 3 or 4 can be incorporated into the BpMRI focused model to reduce unnecessary biopsies.</p>","PeriodicalId":7126,"journal":{"name":"Abdominal Radiology","volume":" ","pages":""},"PeriodicalIF":2.3,"publicationDate":"2025-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143956116","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"¹⁸F-FDG PET/CT volumetric parameter predicts prognosis for neuroblastoma with MYCN gain.","authors":"Siqi Li, Jun Liu, Guanyun Wang, Ying Kan, Wei Wang, Jigang Yang","doi":"10.1007/s00261-025-04973-1","DOIUrl":"https://doi.org/10.1007/s00261-025-04973-1","url":null,"abstract":"<p><strong>Purpose: </strong>The aim of the study was to evaluate the value of ¹⁸F-FDG PET/CT metabolic parameters in neuroblastoma (NB) with MYCN gain.</p><p><strong>Methods: </strong>A retrospective analysis was conducted on 87 patients with NB (29 with MYCN gain and 58 with MYCN normal). The region of interest of primary tumors were manually delineated using 3D slicer™ software, and ¹⁸F-FDG PET/CT metabolic parameters, including SUV_max, SUV_peak, SUV_mean, MTV and TLG were extracted. Logistic regression analyses were used to identify the relationship between ¹⁸F-FDG PET/CT metabolic parameters and MYCN gain. Cox proportional hazards regression models were used to assess the associations between ¹⁸F-FDG PET/CT metabolic parameters and EFS and OS. Survival curves were generated using the Kaplan-Meier method, and differences in survival between groups were compared using the log-rank test.</p><p><strong>Results: </strong>A total of 87 NB patients [median age: 40 (20-56) months; 48 girls and 39 boys] were evaluated. Logistic regression analyses revealed that MTV (>133.3 cm³) was an independent predictor of MYCN gain. During the follow-up period of 22 (2-70) months, 21 patients died and 37 patients experienced disease recurrence or progression. Cox proportional hazards regression analyses showed that MTV, in combination with PHOX2B, was an independent prognostic factor for EFS and OS in NB patients with MYCN-gain. Patients with high MTV exhibited significantly shorter EFS and OS compared to those with low MTV.</p><p><strong>Conclusion: </strong>The volumetric parameter MTV derived from ¹⁸F-FDG PET/CT imaging can predict MYCN gain in NB patients and provide valuable prognostic information for patients with MYCN-gain NB.</p>","PeriodicalId":7126,"journal":{"name":"Abdominal Radiology","volume":" ","pages":""},"PeriodicalIF":2.3,"publicationDate":"2025-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143960267","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Correction to: Pictorial review of multiparametric MRI in bladder urothelial carcinoma with variant histology: pearls and pitfalls.","authors":"Yuki Arita, Sungmin Woo, Lisa Ruby, Thomas C Kwee, Keisuke Shigeta, Ryo Ueda, Sunny Nalavenkata, Hiromi Edo, Kosuke Miyai, Jeeban Das, Pamela I Causa Andrieu, Hebert Alberto Vargas","doi":"10.1007/s00261-025-04923-x","DOIUrl":"https://doi.org/10.1007/s00261-025-04923-x","url":null,"abstract":"","PeriodicalId":7126,"journal":{"name":"Abdominal Radiology","volume":" ","pages":""},"PeriodicalIF":2.3,"publicationDate":"2025-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143958349","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Diagnostic accuracy of iodine quantification and material density imaging with rapid Kilovoltage-switching DECT for small hyperattenuating renal lesions.","authors":"Shanigarn Thiravit, Adisa Moleesaide, Rathachai Kaewlai, Chayanit Limsakol, Arjin Maneegarn, Arissa Phothisirisakulwong, Phakphoom Thiravit","doi":"10.1007/s00261-025-04964-2","DOIUrl":"https://doi.org/10.1007/s00261-025-04964-2","url":null,"abstract":"<p><strong>Objectives: </strong>To assess accuracy of MDI and iodine quantification in distinguishing enhancing renal masses from hyperattenuating cysts, compared with conventional attenuation measurements, given that differentiation between these entities can influence follow-up imaging strategies and surgical decision-making, and to investigate the optimal threshold of iodine concentration using rapid kilovoltage-switching DECT (rsDECT).</p><p><strong>Materials and methods: </strong>Retrospective study enrolled 126 renal lesions 1-4 cm in size with 10-70 attenuation on pre-contrast CT in patients who underwent rsDECT during the portovenous phase. Two reading sessions (true unenhanced (TUE) + post-contrast (PC) + MDI images versus MDI only images) for the visual assessment of renal mass enhancement were done (with at least 1-month time gap). Measurement of attenuation and iodine concentration within each renal lesion was recorded. Diagnostic accuracies and a threshold of each quantitative parameters were evaluated. Final diagnosis of renal lesions was based on pathological or imaging criteria.</p><p><strong>Results: </strong>Accuracy of MDI images were 90.5% with TUE + PC + MDI and 88.9% with MDI only. AUC of VUE HU, TUE HU, PC HU, PC VUE HU, PC-TUE HU, absolute and normalized iodine concentration were 0.87, 0.82, 0.96, 0.95, 0.96, 0.97 and 0.95 (all p < 0.001). The optimal absolute iodine concentration threshold was 1.6 mg I/mL, with 91% sensitivity and 92% specificity. This threshold outperformed 0.5 mg I/mL showing 100% sensitivity, 29% specificity) and 2.0 mg I/mL showing 71% sensitivity, 97% specificity.</p><p><strong>Conclusion: </strong>In characterization of a small (< 4 cm) hyperattenuating renal lesion identified on abdominal CT, post processing MDI with iodine quantification has better or comparable accuracy to attenuation measurement and the specificity of iodine concentration using rsDECT improves with a threshold higher than 0.5 mg I/mL. This could enhance diagnostic workflows for renal lesion assessment using MDI and offer the potential to omit TUE scanning, thereby reducing patient radiation exposure.</p>","PeriodicalId":7126,"journal":{"name":"Abdominal Radiology","volume":" ","pages":""},"PeriodicalIF":2.3,"publicationDate":"2025-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143961309","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"External validation of an RSNA 2023 Abdominal Trauma AI Challenge high performing machine learning model in the detection and grading of splenic injuries on CT.","authors":"Anish Kirpalani, Théo Viel, Zixuan Hu, Hui Ming Lin, Sebastiaan Hermans, David Gomez, Robert Moreland, Shobhit Mathur, Aaditeya Jhaveri, Matthew Wu, Paraskevi A Vlachou, Monica Tafur, Ervin Sejdić, Errol Colak","doi":"10.1007/s00261-025-04910-2","DOIUrl":"https://doi.org/10.1007/s00261-025-04910-2","url":null,"abstract":"<p><strong>Purpose: </strong>This study aims to validate the performance of an award-winning machine learning (ML) model from the Radiological Society of North America (RSNA) 2023 Abdominal Trauma AI Challenge in detecting splenic injuries on CT scans using a large, geographically and temporally distinct external dataset.</p><p><strong>Method: </strong>A single-center retrospective study was conducted using an external dataset comprising 1216 CT scans (608 positive and 608 negative for splenic injuries). The ML model, trained on the RSNA Abdominal Traumatic Injury CT (RATIC) dataset, employs a multi-component pipeline including 2D MaxVit, 2.5D CoatNet with LSTM for study-level predictions. Model performance was evaluated using sensitivity, specificity, PPV, NPV, accuracy, F1 score, and AUC.</p><p><strong>Results: </strong>The ML model achieved an AUC of 0.931 (95% CI: 0.917, 0.945) for binary classification of splenic injuries, with an accuracy of 0.849 (95% CI: 0.827, 0.868), sensitivity of 0.747 (95% CI: 0.711, 0.780), and specificity of 0.951 (95% CI: 0.930, 0.965). For high-grade splenic injuries, the model achieved an AUC of 0.950 (95% CI: 0.932, 0.968), accuracy of 0.928 (95% CI: 0.912, 0.941), sensitivity of 0.719 (95% CI: 0.643, 0.784), and specificity of 0.958 (95% CI: 0.944, 0.968).</p><p><strong>Conclusion: </strong>The ML model shows strong, reliable performance and generalizability in detecting and grading splenic injuries on CT scans. This supports its potential clinical application, particularly for quick and accurate diagnosis in splenic trauma patients, and highlights the value of RSNA AI challenges in advancing clinical research and applications in medical imaging.</p>","PeriodicalId":7126,"journal":{"name":"Abdominal Radiology","volume":" ","pages":""},"PeriodicalIF":2.3,"publicationDate":"2025-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143959708","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Computer-aided diagnosis tool utilizing a deep learning model for preoperative T-staging of rectal cancer based on three-dimensional endorectal ultrasound.","authors":"Xiaoyin Liu, Ruifei Zhang, Junzhao Chen, Si Qin, Limei Chen, Hang Yi, Xiaowen Liu, Guanbin Li, Guangjian Liu","doi":"10.1007/s00261-025-04966-0","DOIUrl":"https://doi.org/10.1007/s00261-025-04966-0","url":null,"abstract":"<p><strong>Background: </strong>The prognosis and treatment outcomes for patients with rectal cancer are critically dependent on an accurate and comprehensive preoperative evaluation.Three-dimensional endorectal ultrasound (3D-ERUS) has demonstrated high accuracy in the T staging of rectal cancer. Thus, we aimed to develop a computer-aided diagnosis (CAD) tool using a deep learning model for the preoperative T-staging of rectal cancer with 3D-ERUS.</p><p><strong>Methods: </strong>We retrospectively analyzed the data of 216 rectal cancer patients who underwent 3D-ERUS. The patients were randomly assigned to a training cohort (n = 156) or a testing cohort (n = 60). Radiologists interpreted the 3D-ERUS images of the testing cohort with and without the CAD tool. The diagnostic performance of the CAD tool and its impact on the radiologists' interpretations were evaluated.</p><p><strong>Results: </strong>The CAD tool demonstrated high diagnostic efficacy for rectal cancer tumors of all T stages, with the best diagnostic performance achieved for T1-stage tumors (AUC, 0.85; 95% CI, 0.73-0.93). With assistance from the CAD tool, the AUC for T1 tumors improved from 0.76 (95% CI, 0.63-0.86) to 0.80 (95% CI, 0.68-0.94) (P = 0.020) for junior radiologist 2. For junior radiologist 1, the AUC improved from 0.61 (95% CI, 0.48-0.73) to 0.79 (95% CI, 0.66-0.88) (P = 0.013) for T2 tumors and from 0.73 (95% CI, 0.60-0.84) to 0.84 (95% CI, 0.72-0.92) (P = 0.038) for T3 tumors. The diagnostic consistency (κ value) also improved from 0.31 to 0.64 (P = 0.005) for the junior radiologists and from 0.52 to 0.66 (P = 0.005) for the senior radiologists.</p><p><strong>Conclusion: </strong>A CAD tool utilizing a deep learning model based on 3D-ERUS images showed strong performance in T staging rectal cancer. This tool could improve the performance of and consistency between radiologists in preoperatively assessing rectal cancer patients.</p>","PeriodicalId":7126,"journal":{"name":"Abdominal Radiology","volume":" ","pages":""},"PeriodicalIF":2.3,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143951847","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}