Synthesis and quality assessment of combined time-series and static medical data using a real-world time-series generative adversarial network.

This study addresses challenges related to privacy issues in utilizing medical data, particularly the protection of personal information. To overcome this obstacle, the research focuses on data synthesis using real-world time-series generative adversarial networks (RTSGAN). A total of 53,005 data were synthesized using the dataset of 15,799 patients with colorectal cancer. The results of the quantitative evaluation of the synthetic data's quality are as follows: the Hellinger distance ranged from 0 to 0.25; the train on synthetic, test on real (TSTR) and train on real, test on synthetic (TRTS) results showed an average area under the curve of 0.99 and 0.98; a propensity mean squared error was 0.223. The synthetic and real data were similar in the qualitative methods including t-SNE and histogram analyses. The application of synthetic data in predicting five-year survival in colorectal cancer patients demonstrates comparable performance to models based on real data. This study employs distance to closest records and membership inference test to assess potential privacy exposure, revealing minimal risk. This study demonstrated that it is feasible to synthesize medical data, including time-series data, using the RTSGAN, and the synthetic data can be evaluated to accurately reflect the characteristics of real data through quantitative and qualitative methods as well as by utilizing real-world artificial intelligence models.

Gastrointestinal tract perforation after radiofrequency ablation for hepatic tumor: Incidence and risk factors.

OBJECTIVE: We analyzed the incidence and mortality rate of gastrointestinal (GI) tract perforation after radiofrequency ablation (RFA) for hepatic tumors and assess its risk factors. METHODS: This retrospective cohort study included 4799 patients with malignant tumors who underwent RFA (n = 7206). Sixty-nine cases of thermal injury to the GI tract were identified via a search of the electronic medical record system using index terms and divided into two groups according to the thermal injury with (n = 8) or without (n = 61) GI tract perforation based on follow-up CT reports. The risk factors for GI tract perforation were identified via multivariable logistic regression analysis using clinical, technical, and follow-up CT findings. RESULTS: The incidence of thermal injury to the GI tract and GI tract perforation was 0.96 % (69/7206) and 0.11 % (8/7206), respectively. The type of adjacent GI tract and history of diabetes mellitus differed significantly between the two groups (p < 0.05). The index tumor being located around the small intestine was the only significant risk factor for GI tract perforation after ablation (Odds ratio, 22.69; 95 % confidence interval, 2.59-198.34; p = 0.005 [reference standard, stomach]). All perforations were not identified on CT images immediately after RFA. The median time to detection was 20 days (range, 3-41 days). Two patients (25 %, 2/8) died due to perforation-related complications. CONCLUSION: GI tract perforation after RFA for hepatic tumors is rare; however, it is associated with high mortality. Thus, careful follow-up is required after RFA if the index tumor is located around the small intestine.

2023 Survey on User Experience of Artificial Intelligence Software in Radiology by the Korean Society of Radiology.

OBJECTIVE: In Korea, radiology has been positioned towards the early adoption of artificial intelligence-based software as medical devices (AI-SaMDs); however, little is known about the current usage, implementation, and future needs of AI-SaMDs. We surveyed the current trends and expectations for AI-SaMDs among members of the Korean Society of Radiology (KSR). MATERIALS AND METHODS: An anonymous and voluntary online survey was open to all KSR members between April 17 and May 15, 2023. The survey was focused on the experiences of using AI-SaMDs, patterns of usage, levels of satisfaction, and expectations regarding the use of AI-SaMDs, including the roles of the industry, government, and KSR regarding the clinical use of AI-SaMDs. RESULTS: Among the 370 respondents (response rate: 7.7% [370/4792]; 340 board-certified radiologists; 210 from academic institutions), 60.3% (223/370) had experience using AI-SaMDs. The two most common use-case of AI-SaMDs among the respondents were lesion detection (82.1%, 183/223), lesion diagnosis/classification (55.2%, 123/223), with the target imaging modalities being plain radiography (62.3%, 139/223), CT (42.6%, 95/223), mammography (29.1%, 65/223), and MRI (28.7%, 64/223). Most users were satisfied with AI-SaMDs (67.6% [115/170, for improvement of patient management] to 85.1% [189/222, for performance]). Regarding the expansion of clinical applications, most respondents expressed a preference for AI-SaMDs to assist in detection/diagnosis (77.0%, 285/370) and to perform automated measurement/quantification (63.5%, 235/370). Most respondents indicated that future development of AI-SaMDs should focus on improving practice efficiency (81.9%, 303/370) and quality (71.4%, 264/370). Overall, 91.9% of the respondents (340/370) agreed that there is a need for education or guidelines driven by the KSR regarding the use of AI-SaMDs. CONCLUSION: The penetration rate of AI-SaMDs in clinical practice and the corresponding satisfaction levels were high among members of the KSR. Most AI-SaMDs have been used for lesion detection, diagnosis, and classification. Most respondents requested KSR-driven education or guidelines on the use of AI-SaMDs.

Value of Sonazoid-enhanced ultrasonography in characterizing indeterminate focal liver lesions on gadoxetic acid-enhanced liver MRI in patients without risk factors for hepatocellular carcinoma.

PURPOSE: To evaluate the added value of contrast-enhanced ultrasonography (CEUS) using Sonazoid in characterizing focal liver lesions (FLLs) with indeterminate findings on gadoxetic acid-enhanced liver MRI in patients without risk factors for hepatocellular carcinoma (HCC). METHODS: Patients who underwent CEUS using Sonazoid for characterizing indeterminate FLLs on gadoxetic acid-enhanced liver MRI were. The indeterminate FLLs were classified according to the degree of malignancy on a 5-point scale on MRI and combined MRI and CEUS. The final diagnosis was made either pathologically or based on more than one-year follow-up. The diagnostic performance was assessed using a receiver operating characteristic (ROC) curve analysis, and the net reclassification improvement (NRI) was calculated. RESULTS: A total of 97 patients (mean age, 49 years ± 16, 41 men, 80 benign and 17 malignant lesions) were included. When CEUS was added to MRI, the area under the ROC curve increased, but the difference was not statistically significant (0.87 [95% confidence interval {CI}, 0.77-0.98] for MRI vs 0.93 [95% CI, 0.87-0.99] for CEUS added to MRI, P = 0.296). The overall NRI was 0.473 (95% CI, 0.100-0.845; P = 0.013): 33.8% (27/80) of benign lesions and 41.2% (7/17) of malignant lesions were appropriately reclassified, whereas 10.0% (8/80) of benign lesions and 17.6% (3/17) of malignant lesions were incorrectly reclassified. CONCLUSIONS: Although performing CEUS with Sonazoid did not significantly improve the overall diagnostic performance in characterizing indeterminate FLLs on gadoxetic acid-enhanced liver MRI in patients without risk factors for HCC, it may increase radiologist's confidence in classifying FLLs.

Using GPT-4 for LI-RADS feature extraction and categorization with multilingual free-text reports.

BACKGROUND AND AIMS: The Liver Imaging Reporting and Data System (LI-RADS) offers a standardized approach for imaging hepatocellular carcinoma. However, the diverse styles and structures of radiology reports complicate automatic data extraction. Large language models hold the potential for structured data extraction from free-text reports. Our objective was to evaluate the performance of Generative Pre-trained Transformer (GPT)-4 in extracting LI-RADS features and categories from free-text liver magnetic resonance imaging (MRI) reports. METHODS: Three radiologists generated 160 fictitious free-text liver MRI reports written in Korean and English, simulating real-world practice. Of these, 20 were used for prompt engineering, and 140 formed the internal test cohort. Seventy-two genuine reports, authored by 17 radiologists were collected and de-identified for the external test cohort. LI-RADS features were extracted using GPT-4, with a Python script calculating categories. Accuracies in each test cohort were compared. RESULTS: On the external test, the accuracy for the extraction of major LI-RADS features, which encompass size, nonrim arterial phase hyperenhancement, nonperipheral 'washout', enhancing 'capsule' and threshold growth, ranged from .92 to .99. For the rest of the LI-RADS features, the accuracy ranged from .86 to .97. For the LI-RADS category, the model showed an accuracy of .85 (95% CI: .76, .93). CONCLUSIONS: GPT-4 shows promise in extracting LI-RADS features, yet further refinement of its prompting strategy and advancements in its neural network architecture are crucial for reliable use in processing complex real-world MRI reports.

LI-RADS category is associated with treatment outcomes of small single HCC: surgical resection vs. radiofrequency ablation.

OBJECTIVES: To assess whether the Liver Imaging Reporting and Data System (LI-RADS) category is associated with the treatment outcomes of small single hepatocellular carcinoma (HCC) after surgical resection (SR) and radiofrequency ablation (RFA). METHODS: This retrospective study included 357 patients who underwent SR (n = 209) or RFA (n = 148) for a single HCC of ≤ 3 cm between 2014 and 2016. LI-RADS categories were assigned. Overall survival (OS), recurrence-free survival (RFS), and local tumor progression (LTP) rates after treatment were compared according to the LI-RADS category (LR-4/5 vs. LR-M) before and after propensity score matching (PSM). Prognostic factors for treatment outcomes were assessed. RESULTS: In total, 357 patients (mean age, 59 years; men, 272) with 357 HCCs (294 LR-4/5 and 63 LR-M) were included. After PSM (n = 78 in each treatment group), there were 10 and 11 LR-M HCCs in the SR and RFA group, respectively. There were no significant differences in OS or RFS. However, SR provided a lower 5-year LTP rate than RFA (1.4% vs. 14.9%, p = 0.001). SR provided a lower 5-year LTP rate than RFA for LR-M HCCs (0% vs. 34.4%, p = 0.062) and LR-4/5 HCCs (1.5% vs. 12.0%, p = 0.008). The LI-RADS category was the sole risk factor associated with poor OS (hazard ratio [HR] 3.79, p = 0.004), RFS (HR 2.12; p = 0.001), and LTP (HR 2.89; p = 0.032). CONCLUSION: LI-RADS classification is associated with the treatment outcome of HCC, supporting favorable outcomes of SR over RFA for LTP, especially for HCCs categorized as LR-M. CLINICAL RELEVANCE STATEMENT: Liver Imaging Reporting and Data System category has a potential prognostic role, supporting favorable outcomes of surgical resection over radiofrequency ablation for local tumor progression, especially for hepatocellular carcinoma categorized as LR-M. KEY POINTS: • SR provided a lower 5-year LTP rate than RFA for HCCs categorized as LR-M (0% vs. 34.4%, p = 0.062) and HCCs categorized as LR-4/5 (1.5% vs. 12.0%, p = 0.008). • There is a steeply increased risk of LTP within 1 year after RFA for LR-M HCCs, compared to SR. • The LI-RADS category was the sole risk factor associated with poor OS (HR 3.79, p = 0.004), RFS (HR 2.12; p = 0.001), and LTP (HR 2.89; p = 0.032) in patients with HCC of ≤ 3 cm treated with SR or RFA.

Comparison of an Endoscopic Scoring System and the Simplified Magnetic Resonance Index of Activity in Patients with Small Bowel Crohn's Disease.

Background/Aims: The newly derived simplified magnetic resonance index of activity (MARIAs) has not been verified in comparison to balloon-assisted enteroscopy (BAE) for patients with small bowel Crohn's disease (CD). We studied the correlation of MARIAs with simple endoscopic scores for CD (SES-CD) of the ileum based on magnetic resonance enterography (MRE) and BAE in patients with small bowel CD. Methods: Fifty patients with small bowel CD who underwent BAE and MRE concurrently within 3 months from September 2020 to June 2021 were enrolled in the study. The primary outcome was the correlation between the active score of ileal SES-CD (ileal SES-CDa)/ileal SES-CD and MARIAs based on BAE and MRE. The cutoff value for MARIAs identifying endoscopically active/severe disease, defined as ileal SES-CDa/ileal SES-CD of 5/7 or more, was analyzed. Results: Ileal SES-CDa/ileal SES-CD and MARIAs showed strong associations (R=0.76, p<0.001; R=0.78, p<0.001). The area under the receiver operating characteristic curve of MARIAs for ileal SES-CDa ≥5 and ileal SES-CD ≥7 was 0.92 (95% confidence interval, 0.88 to 0.97) and 0.92 (95% confidence interval, 0.87 to 0.97). The cutoff value of MARIAs for detecting active/severe disease was 3. A MARIAs index value of ≥3 identified ileal SES-CDa ≥5 with a sensitivity of 85% and specificity of 87% and detected ileal SES-CD ≥7 with a sensitivity of 87% and specificity of 86%. Conclusions: This study validated the applicability of MARIAs compared to BAE-based ileal SES-CDa/SES-CD.

Treatment Outcomes of Percutaneous Radiofrequency Ablation for Hepatocellular Carcinomas: Effects of the Electrode Type and Placement Method.

OBJECTIVE: To investigate the association among the electrode placement method, electrode type, and local tumor progression (LTP) following percutaneous radiofrequency ablation (RFA) for small hepatocellular carcinomas (HCCs) and to assess the risk factors for LTP. MATERIALS AND METHODS: In this retrospective study, we enrolled 211 patients, including 150 males and 61 females, who had undergone ultrasound-guided RFA for a single HCC < 3 cm. Patients were divided into four combination groups of the electrode type and placement method: 1) tumor-puncturing with an internally cooled tip (ICT), 2) tumor-puncturing with an internally cooled wet tip (ICWT), 3) no-touch with ICT, and 4) no-touch with ICWT. Univariable and multivariable Cox proportional-hazards regression analyses were performed to evaluate the risk factors for LTP. The major RFA-related complications were assessed. RESULTS: Overall, 83, 34, 80, and 14 patients were included in the ICT, ICWT, no-touch with ICT, and no-touch with ICWT groups, respectively. The cumulative LTP rates differed significantly among the four groups. Compared to tumor puncturing with ICT, tumor puncturing with ICWT was associated with a lower LTP risk (adjusted hazard ratio [aHR] = 0.11, 95% confidence interval [CI] = 0-0.88, P = 0.034). However, the cumulative LTP rate did not differ significantly between tumor-puncturing with ICT and no-touch RFA with ICT (aHR = 0.34, 95% CI = 0.03-1.62, P = 0.188) or ICWT (aHR = 0.28, 95% CI = 0-2.28, P = 0.294). An insufficient ablative margin was a risk factor for LTP (aHR = 6.13, 95% CI = 1.41-22.49, P = 0.019). The major complication rates were 1.2%, 0%, 2.5%, and 21.4% in the ICT, ICWT, no-touch with ICT, and no-touch with ICWT groups, respectively. CONCLUSION: ICWT was associated with a lower LTP rate compared to ICT when performing tumor-puncturing RFA. An insufficient ablation margin was a risk factor for LTP.

[Imaging Techniques and Differential Diagnosis for Inflammatory Bowel Disease]. / 염증성 장질환의 영상기법 및 감별진단.

The two main types of inflammatory bowel disease (IBD) are Crohn's disease and ulcerative colitis. Currently, when IBD is suspected, CT enterography is widely used as an initial imaging test because it can evaluate both the bowel wall and the outside of the bowel, helping to differentiate IBD from other diseases. When IBD is suspected, it is necessary to distinguish between Crohn's disease and ulcerative colitis. In most cases this is not difficult; however, in some cases, it is difficult and such cases are called IBD-unclassified. CT findings are often non-specific for ulcerative colitis, making it difficult to differentiate it from other diseases using imaging alone. In contrast, characteristic CT findings for Crohn's disease are often helpful in diagnosis, although diseases, such as tuberculous enteritis can mimic Crohn's disease. Recently, mutations in the gene encoding a prostaglandin transporter called SLCO2A1 have been discovered as the cause of the disease in some patients with multiple ulcers and strictures, similar to Crohn's disease. Therefore, genetic testing is being used to make a differential diagnosis.

Erratum: Korean Practice Guidelines for Gastric Cancer 2022: An Evidence-based, Multidisciplinary Approach.

This corrects the article on p. 3 in vol. 23, PMID: 36750993.

Rescue therapy for local tumor progression after radiofrequency ablation of small hepatocellular carcinoma: a comparison between repeated ablation and transcatheter arterial chemoembolization.

OBJECTIVE: To compare the therapeutic outcomes of repeated radiofrequency ablation (RFA) and transcatheter arterial chemoembolization (TACE) as rescue therapy for the treatment of local tumor progression (LTP) after initial RFA for hepatocellular carcinoma (HCC). METHODS: This retrospective study evaluated 44 patients who had LTP as initial tumor recurrence after RFA and underwent repeated RFA (n = 23) or TACE (n = 21) for local disease control. Local disease control and overall survival rates were evaluated using the Kaplan-Meier method. A Cox proportional-hazards regression model was used to identify the independent prognostic factors. The local disease control rate after the first rescue therapy and the number of rescue therapies applied until the last follow-up were also evaluated. RESULTS: Local disease control after rescue therapy for LTP was significantly higher with repeated RFA than with TACE (p < 0.001). Treatment type was a significant factor for local disease control (p < 0.001). The overall survival rates after rescue therapy were not significantly different between the two treatments (p = 0.900). The local disease control rate after the first rescue therapy was significantly higher with RFA than with TACE (78.3% vs 23.8%, p < 0.001). The total number of rescue therapies applied was significantly higher in the TACE group than that in the repeated RFA group (median 3 vs 1, p < 0.001). CONCLUSION: Repeated RFA as rescue therapy for LTP after initial RFA for HCC was more efficient and had significantly better local disease control than TACE. ADVANCES IN KNOWLEDGE: Even if LTP occurs after initial RFA, it should not be considered a failure of RFA, and repeated RFA should be performed over TACE if possible for more effective local disease control.

Evaluation of liver metastasis in patients with breast cancer: Comparison of single-phase abdominopelvic CT and multi-phase liver CT.

PURPOSE: To compare the usefulness of multi-phase liver CT and single-phase abdominopelvic CT (APCT) in evaluating liver metastasis in newly diagnosed breast cancer patients. METHODS: In this retrospective study, a total of 7621 newly diagnosed breast cancer patients (mean age, 49.7 years ± 10.1; 7598 women) who underwent single-phase APCT (n = 5536) or multi-phase liver CT (n = 2085) for staging workup between January 2016 and June 2019 were included. The staging CTs were categorized as having no metastasis, probable metastasis, or indeterminate lesions. MRI referral rate (proportion of patients underwent additional liver MRI), negative MRI rate (patients without true hepatic metastasis / patients underwent liver MRI), true positive CT rate (patients with true metastasis / patients categorized as probable metastasis), true metastasis rate among CT indeterminate (patients with true metastasis / patients categorized as indeterminate lesions), and overall liver metastasis rate were compared between the two groups. Further, the radiation dose was recorded for every patient. RESULTS: The proportions of having no metastasis and indeterminate lesions on the results of CT interpretation were significantly different between the two groups (P = 0.006). However, the MRI referral rate, negative MR rate, true positive CT rate, true metastasis rate among CT indeterminate, and overall liver metastasis rate were not significantly different between the two groups. Radiation dose of multi-phase CT was three times higher than that of single-phase CT. CONCLUSION: Multi-phase liver CT has little benefit over single-phase APCT in assessing liver metastasis in patients with breast cancer.

Korean Practice Guidelines for Gastric Cancer 2022: An Evidence-based, Multidisciplinary Approach.

Gastric cancer is one of the most common cancers in Korea and the world. Since 2004, this is the 4th gastric cancer guideline published in Korea which is the revised version of previous evidence-based approach in 2018. Current guideline is a collaborative work of the interdisciplinary working group including experts in the field of gastric surgery, gastroenterology, endoscopy, medical oncology, abdominal radiology, pathology, nuclear medicine, radiation oncology and guideline development methodology. Total of 33 key questions were updated or proposed after a collaborative review by the working group and 40 statements were developed according to the systematic review using the MEDLINE, Embase, Cochrane Library and KoreaMed database. The level of evidence and the grading of recommendations were categorized according to the Grading of Recommendations, Assessment, Development and Evaluation proposition. Evidence level, benefit, harm, and clinical applicability was considered as the significant factors for recommendation. The working group reviewed recommendations and discussed for consensus. In the earlier part, general consideration discusses screening, diagnosis and staging of endoscopy, pathology, radiology, and nuclear medicine. Flowchart is depicted with statements which is supported by meta-analysis and references. Since clinical trial and systematic review was not suitable for postoperative oncologic and nutritional follow-up, working group agreed to conduct a nationwide survey investigating the clinical practice of all tertiary or general hospitals in Korea. The purpose of this survey was to provide baseline information on follow up. Herein we present a multidisciplinary-evidence based gastric cancer guideline.

Risk Group Stratification for Recurrence-Free Survival and Early Tumor Recurrence after Radiofrequency Ablation for Hepatocellular Carcinoma.

PURPOSE: Although the prognosis after radiofrequency ablation (RFA) for hepatocellular carcinoma (HCC) may vary according to different risk levels, there is no standardized follow-up protocol according to each patient's risk. This study aimed to stratify patients according to their risk of recurrence-free survival (RFS) and early (≤2 years) tumor recurrence (ETR) after RFA for HCC based on predictive models and nomograms and to compare the survival times of the risk groups derived from the models. METHODS: Patients who underwent RFA for a single HCC (≤3 cm) between January 2012 and March 2014 (n = 152) were retrospectively reviewed. Patients were classified into low-, intermediate-, and high-risk groups based on the total nomogram points for RFS and ETR, respectively, and compared for each outcome. Restricted mean survival times (RMSTs) in the three risk groups were evaluated for both RFS and ETR to quantitatively evaluate the difference in survival times. RESULTS: Predictive models for RFS and ETR were constructed with c-indices of 0.704 and 0.730, respectively. The high- and intermediate-risk groups for RFS had an 8.5-fold and 2.9-fold higher risk of events than the low-risk group (both p < 0.001), respectively. The high- and intermediate-risk groups for ETR had a 17.7-fold and 7.0-fold higher risk than the low-risk group (both p < 0.001), respectively. The RMST in the high-risk group was significantly lower than that in the other two groups 9 months after RFA, and that in the intermediate-risk group became lower than that in the low-risk group after 21 months with RFS and 24 months with ETR. CONCLUSION: Our predictive models were able to stratify patients into three groups according to their risk of RFS and ETR after RFA for HCC. Differences in RMSTs may be used to establish different follow-up protocols for the three risk groups.

Added Value of Pelvic CT after Treatment of HCC.

Background In patients with hepatocellular carcinoma (HCC) who undergo follow-up with CT after treatment, the benefit of routinely including pelvic coverage is not well substantiated. Purpose To investigate the added value of pelvic coverage at follow-up liver CT in detecting pelvic metastasis or incidental tumors in patients treated for HCC. Materials and Methods This retrospective study included patients who were diagnosed with HCC between January 2016 and December 2017 and followed up with liver CT after treatment. Cumulative rates of extrahepatic metastasis, isolated pelvic metastasis, and incidental pelvic tumor were estimated by using the Kaplan-Meier method. Cox proportional hazard models were used to identify risk factors for extrahepatic and isolated pelvic metastases. Radiation dose from pelvic coverage was also calculated. Results A total of 1122 patients (mean age, 60 years ± 10 [SD]; 896 men) were included. The cumulative rates at 3 years of extrahepatic metastasis, isolated pelvic metastasis, and incidental pelvic tumor were 14.4%, 1.4%, and 0.5%, respectively. At adjusted analysis, protein induced by vitamin K absence or antagonist-II (P = .001), size of the largest tumor (P = .02), T stage (P = .008), and initial treatment method (P < .001) were associated with extrahepatic metastasis. Only T stage was associated with isolated pelvic metastasis (P = .01). Because of pelvic coverage, the radiation dose increased by 29% and 39% in liver CT with and without contrast enhancement, respectively, compared with CT scans without pelvic coverage. Conclusion The incidence of isolated pelvic metastasis or incidental pelvic tumor was low in patients treated for hepatocellular carcinoma. © RSNA, 2023.

Percutaneous radiofrequency ablation of hepatocellular carcinoma in a recent cohort at a tertiary cancer center: incidence and factors associated with major complications and unexpected hospitalization events.

PURPOSE: This study aimed to assess the incidence of and factors associated with major complications, delayed discharge, and emergency room (ER) visits or readmission after percutaneous radiofrequency ablation (RFA) for single hepatocellular carcinoma (HCC) <3 cm in a recent cohort at a tertiary cancer center. METHODS: A total of 188 patients with treatment-naïve single HCCs <3 cm who underwent RFA between January 2018 and April 2021 were included in the analysis. Univariable and multivariable logistic regression analyses were performed to identify the factors associated with major complications, delayed discharge, and ER visits or readmission. Local tumor progression (LTP) and overall survival were estimated using the Kaplan-Meier method and Cox proportional-hazards regression analysis. RESULTS: Major complications occurred in 3.2% (6/188) of the patients. The longest diameter of the ablation zone was significantly larger in patients with major complications (P=0.023). Delayed discharge occurred in 5.8% (9/188) of the patients, for which albumin-bilirubin grade 3 was identified as an important determinant. No variables other than major complications were significantly associated with ER visits or readmission, which occurred in 7.0% (13/188) of the patients. Major complications, delayed discharge, and ER visits or readmission were not substantially related to the post-treatment outcomes of LTP and overall survival. CONCLUSION: This study confirmed RFA as a highly safe procedure for single HCCs <3 cm, despite the rapidly changing RFA techniques in the most recent cohort. A large ablation zone and poor liver function were predictors of major complications and delayed discharge, respectively.

Prediction of oxygen requirement in patients with COVID-19 using a pre-trained chest radiograph xAI model: efficient development of auditable risk prediction models via a fine-tuning approach.

Risk prediction requires comprehensive integration of clinical information and concurrent radiological findings. We present an upgraded chest radiograph (CXR) explainable artificial intelligence (xAI) model, which was trained on 241,723 well-annotated CXRs obtained prior to the onset of the COVID-19 pandemic. Mean area under the receiver operating characteristic curve (AUROC) for detection of 20 radiographic features was 0.955 (95% CI 0.938-0.955) on PA view and 0.909 (95% CI 0.890-0.925) on AP view. Coexistent and correlated radiographic findings are displayed in an interpretation table, and calibrated classifier confidence is displayed on an AI scoreboard. Retrieval of similar feature patches and comparable CXRs from a Model-Derived Atlas provides justification for model predictions. To demonstrate the feasibility of a fine-tuning approach for efficient and scalable development of xAI risk prediction models, we applied our CXR xAI model, in combination with clinical information, to predict oxygen requirement in COVID-19 patients. Prediction accuracy for high flow oxygen (HFO) and mechanical ventilation (MV) was 0.953 and 0.934 at 24 h and 0.932 and 0.836 at 72 h from the time of emergency department (ED) admission, respectively. Our CXR xAI model is auditable and captures key pathophysiological manifestations of cardiorespiratory diseases and cardiothoracic comorbidities. This model can be efficiently and broadly applied via a fine-tuning approach to provide fully automated risk and outcome predictions in various clinical scenarios in real-world practice.

Percutaneous radiofrequency ablation of solitary hepatic metastases from colorectal cancer: risk factors of local tumor progression-free survival and overall survival.

PURPOSE: This study aimed to evaluate local tumor progression-free survival (LTPFS) and overall survival (OS) after percutaneous radiofrequency ablation (RFA) for solitary colorectal liver metastases (CLM) <3 cm and to identify the risk factors associated with poor LTPFS and OS after percutaneous RFA. METHODS: This study screened 219 patients who underwent percutaneous RFA for CLM between January 2013 and November 2020. Of these, 92 patients with a single CLM <3 cm were included. LTPFS and OS were calculated using the Kaplan-Meier method, and the differences between curves were compared using the log-rank test. Risk factors for LTPFS and OS were assessed using Cox proportional-hazard regression models. RESULTS: Technical efficacy was achieved in the first (n=91) or second (n=1) RFA sessions. During the follow-up (median, 20.0 months), cumulative LTPFS rates at 1, 3, and 5 years were 92.4%, 83.4%, and 76.5%, respectively. During the follow-up (median, 27.8 months), the corresponding OS rates were 97.5%, 81.3%, and 74.8%, respectively. In multivariable Cox regression analyses, the group with both tumor-puncturing RFA and a T4 stage primary tumor (hazard ratio, 3.3; 95% confidence interval, 1.1 to 10.2; P=0.037) had poor LTPFS. In the univariable analysis, no factors were significantly associated with poor OS. CONCLUSION: Both LTPFS and OS were promising after percutaneous RFA for a single CLM <3 cm. The group with both tumor-puncturing RFA and a T4 stage primary tumor showed poor LTPFS. No risk factors were identified for poor OS.