Diagnostic and interventional radiology最新文献

With the ongoing revolution of artificial intelligence (AI) in medicine, the impact of AI in radiology is more pronounced than ever. An increasing number of technical and clinical AI-focused studies are published each day. As these tools inevitably affect patient care and physician practices, it is crucial that radiologists become more familiar with the leading strategies and underlying principles of AI. Multimodal AI models can combine both imaging and clinical metadata and are quickly becoming a popular approach that is being integrated into the medical ecosystem. This narrative review covers major concepts of multimodal AI through the lens of recent literature. We discuss emerging frameworks, including graph neural networks, which allow for explicit learning from non-Euclidean relationships, and transformers, which allow for parallel computation that scales, highlighting existing literature and advocating for a focus on emerging architectures. We also identify key pitfalls in current studies, including issues with taxonomy, data scarcity, and bias. By informing radiologists and biomedical AI experts about existing practices and challenges, we hope to guide the next wave of imaging-based multimodal AI research.

Purpose: Although favorable results have been reported on catheter-directed sclerotherapy (CDS) for ovarian endometrioma, a thorough evaluation of its long-term efficacy is lacking. This study evaluates the long-term efficacy and safety of CDS with 99% ethanol for treatment of ovarian endometrioma.

Methods: Between January 2020 and February 2022, data from 33 consecutive patients with symptomatic ovarian endometriomas who underwent CDS were retrospectively evaluated. All patients underwent pre-procedural and 6- and 12-month post-procedural ultrasonography. To assess the effect on ovarian reserve, serum anti-Müllerian hormone (AMH) levels were measured before and after the procedure. Procedure-related complications were also assessed.

Results: The mean volume of endometriomas decreased from 80.22 ± 66.43 to 0.73 ± 1.10 mL (P < 0.001), and the mean percentage of volume reduction was 98.99% ± 1.53%. No recurrences were observed during the follow-up period. In patients whose serum AMH levels were monitored for 1 year, no significant change in AMH level before and after CDS was observed (3.07 ± 1.81 vs. 2.72 ± 2.02 ng/mL, P = 0.190). One patient complained of moderate abdominal pain after CDS, which was conservatively managed.

Conclusion: CDS remained safe and effective in treating ovarian endometrioma at the 1-year follow-up. Ovarian function after CDS was well preserved.

Clinical significance: CDS is a safe and effective treatment option for patients with ovarian endometrioma without compromising ovarian function.

Purpose: This study aims to demonstrate the performance of machine learning algorithms to distinguish clinically significant prostate cancer (csPCa) from clinically insignificant prostate cancer (ciPCa) in prostate bi-parametric magnetic resonance imaging (MRI) using radiomics features.

Methods: MRI images of patients who were diagnosed with cancer with histopathological confirmation following prostate MRI were collected retrospectively. Patients with a Gleason score of 3+3 were considered to have clinically ciPCa, and patients with a Gleason score of 3+4 and above were considered to have csPCa. Radiomics features were extracted from T2-weighted (T2W) images, apparent diffusion coefficient (ADC) images, and their corresponding Laplacian of Gaussian (LoG) filtered versions. Additionally, a third feature subset was created by combining the T2W and ADC images, enhancing the analysis with an integrated approach. Once the features were extracted, Pearson's correlation coefficient and selection were performed using wrapper-based sequential algorithms. The models were then built using support vector machine (SVM) and logistic regression (LR) machine learning algorithms. The models were validated using a five-fold cross-validation technique.

Results: This study included 77 patients, 30 with ciPCA and 47 with csPCA. From each image, four images were extracted with LoG filtering, and 111 features were obtained from each image. After feature selection, 5 features were obtained from T2W images, 5 from ADC images, and 15 from the combined dataset. In the SVM model, area under the curve (AUC) values of 0.64 for T2W, 0.86 for ADC, and 0.86 for the combined dataset were obtained in the test set. In the LR model, AUC values of 0.79 for T2W, 0.86 for ADC, and 0.85 for the combined dataset were obtained.

Conclusion: Machine learning models developed with radiomics can provide a decision support system to complement pathology results and help avoid invasive procedures such as re-biopsies or follow-up biopsies that are sometimes necessary today.

Clinical significance: This study demonstrates that machine learning models using radiomics features derived from bi-parametric MRI can discriminate csPCa from clinically insignificant PCa. These findings suggest that radiomics-based machine learning models have the potential to reduce the need for re-biopsy in cases of indeterminate pathology, assist in diagnosing pathology-radiology discordance, and support treatment decision-making in the management of PCa.

Purpose: Peripheral arterial disease (PAD) is increasingly prevalent, particularly among the aging population. Retrograde tibiopedal access (RTPA) has emerged as a useful endovascular treatment for PAD. However, there is limited research examining factors that influence the efficacy of RTPA. To investigate factors affecting the access, crossing, and recanalization success rates of RTPA for infrapopliteal PAD treatment.

Methods: A retrospective study was conducted on 720 patients who underwent endovascular treatment for PAD. Of these, 104 patients (mean age: 65.5 ± 16.2; 89 men) with 131 RTPA trials were included in the final evaluation. The disease and its duration, Rutherford score, smoking status, access site, and its occlusion status, access, crossing, and recanalization success were noted. Data were analyzed using Pearson's chi-square and Mann-Whitney U tests and multivariate logistic regression to evaluate the impact of various factors on success rates.

Results: The access success rate was 82.6%, the crossing success rate was 95.4%, and the recanalization success rate was 74%. Access success was significantly higher when the dorsal pedal artery (DPA) was the access artery compared with the posterior tibial artery (91.3% vs. 74.2%, P = 0.009). Access success was notably lower in patients with thromboangiitis obliterans compared with patients with diabetes mellitus (DM) and non-DM atherosclerosis (68.6% vs. 90.3% and 80.3%, P = 0.019). Recanalization success was higher when the puncture site was non-occluded (76.7% vs. 53.5%, P = 0.023).

Conclusion: The study suggests that RTPA is a generally effective and safe technique for infrapopliteal PAD treatment. The most favorable outcomes are observed in individuals with DM who have a non-occluded DPA at the puncture site. Recanalization success is only affected by the patency of the artery at the puncture site.

Clinical significance: These findings offer targeted guidance for clinicians and highlight areas requiring further investigation.

Purpose: This study aimed to evaluate the performance of large language models (LLMs) and multimodal LLMs in interpreting the Breast Imaging Reporting and Data System (BI-RADS) categories and providing clinical management recommendations for breast radiology in text-based and visual questions.

Methods: This cross-sectional observational study involved two steps. In the first step, we compared ten LLMs (namely ChatGPT 4o, ChatGPT 4, ChatGPT 3.5, Google Gemini 1.5 Pro, Google Gemini 1.0, Microsoft Copilot, Perplexity, Claude 3.5 Sonnet, Claude 3 Opus, and Claude 3 Opus 200K), general radiologists, and a breast radiologist using 100 text-based multiple-choice questions (MCQs) related to the BI-RADS Atlas 5^th edition. In the second step, we assessed the performance of five multimodal LLMs (ChatGPT 4o, ChatGPT 4V, Claude 3.5 Sonnet, Claude 3 Opus, and Google Gemini 1.5 Pro) in assigning BI-RADS categories and providing clinical management recommendations on 100 breast ultrasound images. The comparison of correct answers and accuracy by question types was analyzed using McNemar's and chi-squared tests. Management scores were analyzed using the Kruskal- Wallis and Wilcoxon tests.

Results: Claude 3.5 Sonnet achieved the highest accuracy in text-based MCQs (90%), followed by ChatGPT 4o (89%), outperforming all other LLMs and general radiologists (78% and 76%) (P < 0.05), except for the Claude 3 Opus models and the breast radiologist (82%) (P > 0.05). Lower-performing LLMs included Google Gemini 1.0 (61%) and ChatGPT 3.5 (60%). Performance across different categories of showed no significant variation among LLMs or radiologists (P > 0.05). For breast ultrasound images, Claude 3.5 Sonnet achieved 59% accuracy, significantly higher than other multimodal LLMs (P < 0.05). Management recommendations were evaluated using a 3-point Likert scale, with Claude 3.5 Sonnet scoring the highest (mean: 2.12 ± 0.97) (P < 0.05). Accuracy varied significantly across BI-RADS categories, except Claude 3 Opus (P < 0.05). Gemini 1.5 Pro failed to answer any BI-RADS 5 questions correctly. Similarly, ChatGPT 4V failed to answer any BI-RADS 1 questions correctly, making them the least accurate in these categories (P < 0.05).

Conclusion: Although LLMs such as Claude 3.5 Sonnet and ChatGPT 4o show promise in text-based BI-RADS assessments, their limitations in visual diagnostics suggest they should be used cautiously and under radiologists' supervision to avoid misdiagnoses.

Clinical significance: This study demonstrates that while LLMs exhibit strong capabilities in text-based BI-RADS assessments, their visual diagnostic abilities are currently limited, necessitating further development and cautious application in clinical practice.

Purpose: This study aimed to detect supratentorial cortical and subcortical morphological changes in pediatric patients with infratentorial tumors.

Methods: The study included 24 patients aged 4-18 years who were diagnosed with primary infratentorial tumors and 41 age- and gender-matched healthy controls. Synthetic magnetization-prepared rapid gradient echo images of brain magnetic resonance imaging were generated using deep learning algorithms applied to T2-axial images. The cortical thickness, surface area, volume, and local gyrification index (LGI), as well as subcortical gray matter volumes, were automatically calculated. Surface-based morphometry parameters for the patient and control groups were compared using the general linear model, and volumes between subcortical structures were compared using the t-test and Mann-Whitney U test.

Results: In the patient group, cortical thinning was observed in the left supramarginal, and cortical thickening was observed in the left caudal middle frontal (CMF), left fusiform, left lateral orbitofrontal, left lingual gyrus, right CMF, right posterior cingulate, and right superior frontal (P < 0.050). The patient group showed a volume reduction in the pars triangularis, paracentral, precentral, and supramarginal gyri of the left hemisphere (P < 0.05). A decreased surface area was observed in the bilateral superior frontal and cingulate gyri (P < 0.05). The patient group exhibited a decreased LGI in the right precentral and superior temporal gyri, left supramarginal, and posterior cingulate gyri and showed an increased volume in the bilateral caudate nucleus and hippocampus, while a volume reduction was observed in the bilateral putamen, pallidum, and amygdala (P < 0.05). The ventricular volume and tumor volume showed a positive correlation with the cortical thickness in the bilateral CMF while demonstrating a negative correlation with areas exhibiting a decreased LGI (P < 0.05).

Conclusion: Posterior fossa tumors lead to widespread morphological changes in cortical structures, with the most prominent pattern being hypogyria.

Clinical significance: This study illuminates the neurological impacts of infratentorial tumors in children, providing a foundation for future therapeutic strategies aimed at mitigating these adverse cortical and subcortical changes and improving patient outcomes.

Purpose: Systemic inflammation and body composition are associated with survival outcomes of cancer patients. This study aimed to examine the combined prognostic value of systemic inflammatory markers and body composition parameters in patients with locally advanced cervical cancer (LACC).

Methods: Patients who underwent concurrent chemoradiotherapy (CCRT) for LACC at a tertiary referral teaching hospital between January 2010 and January 2018 were enrolled. A predictive model was established based on systemic immune-inflammation index (SII) and computer tomography-derived visceral fat-to-muscle ratio (vFMR). Overall survival (OS) and progression-free survival (PFS) were assessed using the Kaplan-Meier method and Cox regression models. The model performance was assessed using discrimination, calibration, and clinical usefulness.

Results: In total, 212 patients were enrolled. The SII and vFMR were closely related, and both independently predicted survival (P < 0.05). A predictive model was established based on the above biomarkers and included three subgroups: high-risk [both high SII (>828) and high vFMR (>1.1)], middle-risk (either high SII or high vFMR), and low-risk (neither high SII nor high vFMR). The 3-year OS (PFS) rates for low-, middle-, and high-risk patients were 90.5% (86.0%), 73.9% (58.4%), and 46.8% (36.1%), respectively (P < 0.05). This model demonstrated satisfactory predictive accuracy (area under the curve values for predicting 3-year OS and PFS were 0.704 and 0.718, respectively), good fit (Hosmer-Lemeshow tests: P > 0.05), and clinical usefulness.

Conclusion: Systemic inflammatory markers combined with body composition parameters could independently predict the prognosis of patients with LACC, highlighting the utilization of commonly collected indicators in decision-making processes.

Clinical significance: The SII and vFMR, as well as their composite indices, were promising prognostic factors in patients with LACC who received definitive CCRT. Future studies are needed to explore novel therapies to improve the outcomes in high-risk patients.

Purpose: To investigate the safety and efficacy of the imaging-guided percutaneous nephrostomy (PCN) procedure in infants.

Methods: A total of 75 (50 boys; 66.7%) patients with a mean age of 121 days (range, 1-351 days) who underwent PCN over a period of 20 years were included in this retrospective study. For each patient, PCN indications, catheter size, the mean duration of catheterization, complications, and the procedure performed following nephrostomy were recorded. Technical success was determined based on the successful placement of the nephrostomy catheter within the pelvicalyceal system. Clinical success was defined as the complete resolution of hydronephrosis and improvement in renal function tests during follow-up. In patients with urinary leakage, technical and clinical success was determined based on the resolution of leakage.

Results: The technical success rate was 100%, and no procedure-related mortality was observed. In 11 patients (14.7%), bilateral PCN was performed. The most frequent indication of PCN was ureteropelvic junction obstruction (n = 41, 54.7%). Procedure-related major complications were encountered in two patients (methemoglobinemia and respiratory arrest caused by the local anesthetic agent in one patient and the development of urinoma caused by urinary leakage from the puncture site in the other). Mild urinary leakage was the only minor complication that occurred and only in one patient. Catheter-related complications were managed through replacement or revision surgery in 16 patients (21.3%).

Conclusion: Imaging-guided PCN is a feasible and effective procedure with high technical success and low major complication rates, and it is useful for protecting kidney function in infants.

Percutaneous transhepatic biliary drainage (PTBD) is commonly used in the treatment of malign and benign biliary pathologies. Certain complications after PTBD may occur, such as biliary fistula, biliary leakage, bilioma, and hematoma. The purpose of this study was to evaluate the safety and effectiveness of using a sterile gelatin sponge to seal the biliary tract after PTBD in patients with liver transplants to prevent complications. A total of 131 biliary drainages were introduced in 97 patients, and a sterile gelatin sponge was used to seal the biliary tract after removal of the biliary drainage catheter. The patients were immediately examined for complications using ultrasound and then followed up clinically unless imaging was required. Five fluid collections within the liver with a diameter <2 cm, consistent with hematoma or bilioma, were resolved spontaneously. No hematoma or bilioma required treatment, and no biliary leakage or fistula was detected. No compli¬cations related to the use of the sponge were observed. The use of a sterile gelatin sponge is a safe and effec-tive method for sealing the biliary tract to prevent complications after PTBD in patients with liver transplants.

Purpose: This study aimed to evaluate whether an artificial intelligence (AI) system can identify basal lung metastatic nodules examined using abdominopelvic computed tomography (CT) that were initially overlooked by radiologists.

Methods: We retrospectively included abdominopelvic CT images with the following inclusion criteria: a) CT images from patients with solid organ malignancies between March 1 and March 31, 2019, in a single institution; and b) abdominal CT images interpreted as negative for basal lung metastases. Reference standards for diagnosis of lung metastases were confirmed by reviewing medical records and subsequent CT images. An AI system that could automatically detect lung nodules on CT images was applied retrospectively. A radiologist reviewed the AI detection results to classify them as lesions with the possibility of metastasis or clearly benign. The performance of the initial AI results and the radiologist's review of the AI results were evaluated using patient-level and lesion-level sensitivities, false-positive rates, and the number of false-positive lesions per patient.

Results: A total of 878 patients (580 men; mean age, 63 years) were included, with overlooked basal lung metastases confirmed in 13 patients (1.5%). The AI exhibited an area under the receiver operating characteristic curve value of 0.911 for the identification of overlooked basal lung metastases. Patient- and lesion-level sensitivities of the AI system ranged from 69.2% to 92.3% and 46.2% to 92.3%, respectively. After a radiologist reviewed the AI results, the sensitivity remained unchanged. The false-positive rate and number of false-positive lesions per patient ranged from 5.8% to 27.6% and 0.1% to 0.5%, respectively. Radiologist reviews significantly reduced the false-positive rate (2.4%-12.6%; all P values < 0.001) and the number of false-positive lesions detected per patient (0.03-0.20, respectively).

Conclusion: The AI system could accurately identify basal lung metastases detected in abdominopelvic CT images that were overlooked by radiologists, suggesting its potential as a tool for radiologist interpretation.

Clinical significance: The AI system can identify missed basal lung lesions in abdominopelvic CT scans in patients with malignancy, providing feedback to radiologists, which can reduce the risk of missing basal lung metastasis.