Artificial intelligence (AI) has a multitude of applications in cancer research and oncology. However, the training of AI systems is impeded by the limited availability of large datasets due to data protection requirements and other regulatory obstacles. Federated and swarm learning represent possible solutions to this problem by collaboratively training AI models while avoiding data transfer. However, in these decentralized methods, weight updates are still transferred to the aggregation server for merging the models. This leaves the possibility for a breach of data privacy, for example by model inversion or membership inference attacks by untrusted servers. Somewhat-homomorphically-encrypted federated learning (SHEFL) is a solution to this problem because only encrypted weights are transferred, and model updates are performed in the encrypted space. Here, we demonstrate the first successful implementation of SHEFL in a range of clinically relevant tasks in cancer image analysis on multicentric datasets in radiology and histopathology. We show that SHEFL enables the training of AI models which outperform locally trained models and perform on par with models which are centrally trained. In the future, SHEFL can enable multiple institutions to co-train AI models without forsaking data governance and without ever transmitting any decryptable data to untrusted servers.
An artificial intelligence system trained with structured chest radiography reports provided clinically useful support for non-radiologist physicians. Background Supine chest radiography for bedridden patients in intensive care units (ICUs) is one of the most frequently ordered imaging studies worldwide. Purpose To evaluate the diagnostic perform...
Background and Aims: While transarterial chemoembolization (TACE) represents a standard of therapy for intermediate-stage hepatocellular carcinoma (HCC) and is also routinely performed in patients with liver metastases, it is still debated which patients represent the ideal candidates for TACE therapy in terms of overall survival. Sarcopenia, the degenerative loss of skeletal muscle mass and strength, has been associated with an adverse outcome for various malignancies, but its role in the context of TACE has largely remained unknown. Here, we evaluated the role of sarcopenia on the outcome of patients undergoing TACE for primary and secondary liver cancer. Methods: The patients’ psoas muscle size was measured on axial computed tomography (CT) scans and normalized for the patients’ height squared. This value was referred to as the psoas muscle index (PMI). The PMI was correlated with clinical and laboratory markers. Results: While pre-interventional sarcopenia had no impact on the direct tumor response to TACE, sarcopenic patients with a pre-interventional PMI below our ideal cut-off value of 13.39 mm/m2 had a significantly impaired long-term outcome with a median overall survival of 491 days compared to 1291 days for patients with a high PMI. This finding was confirmed by uni- and multivariate Cox-regression analyses. Moreover, a progressive rapid decline in muscle mass after TACE was a predictor for an unfavorable prognosis. Conclusion: Our data suggest that sarcopenia represents a previously unrecognized prognostic factor for patients undergoing TACE therapy which might yield important information on the patients’ post-interventional outcome and should therefore be implemented into clinical stratification algorithms.
While surgical resection represents the standard potentially curative therapy for liver cancer, transarterial chemoembolization (TACE) has evolved as a standard therapy for intermediate-stage hepatocellular carcinoma (HCC) as well as liver metastases. However, it is still not fully understood which patients particularly benefit from TACE. Cytokines represent a broad category of signaling molecules that might reflect concomitant inflammation as an adverse prognostic factor. Here, we evaluated the role of interleukin (IL)-6, IL-8, and CC-chemokine ligand (CCL)22 as biomarkers in the context of TACE treatment. Cytokine serum levels were analyzed by multiplex immunoassay in 54 patients (HCC: n = 44, liver metastases: n = 10) undergoing TACE as well as 51 healthy controls. Patients with primary and secondary liver cancer showed significantly elevated levels of IL-6 and IL-8 but not CCL22 compared to healthy controls. Interestingly, low pre-interventional levels of IL-6 and IL-8 were predictors for an objective response after TACE in binary logistic regression. In contrast, patients with high pre-interventional IL-6 and IL-8 serum levels not only poorly responded to TACE but had a significantly impaired overall survival. Serum levels of IL-6 and IL-8 represent promising biomarkers for patients undergoing TACE and might help to pre-interventionally identify patients who particularly benefit from TACE regarding objective treatment response and overall survival.
21 January 2016 in CardioVascular and Interventional Radiology
Background: Only limited evidence has been available to date on the accuracy of systematic low-dose chest computed tomography (LDCT) use in the diagnosis of COVID-19 in patients with non-specific clinical symptoms. Methods: The COVID-19 Imaging Registry Study Aachen (COVID-19-Bildgebungs-Register Aachen, COBRA) collects data on imaging in patients with COVID-19. Two of the COBRA partner hospitals (RWTH Aachen University Hospital and Dueren Hospital) systematically perform reverse transcriptase polymerase chain reaction (RT-PCR) from nasopharyngeal swabs as well as LDCT in all patients presenting with manifestations that are compatible with COVID-19. In accordance with the COV-RADS protocol, the LDCT scans were prospectively evaluated before the RT-PCR findings were available in order to categorize the likelihood of COVID-19. Results: From 18 March to 5 May 2020, 191 patients with COVID-19 manifestations (117 male, age 65 +/- 16 years) underwent RT-PCR testing and LDCT. The mean time from the submission of the sample to the availability of the RT-PCR findings was 491 minutes (interquartile range [IQR: 276-1066]), while that from the performance of the CT to the availability of its findings was 9 minutes (IQR: 6-11). A diagnosis of COVID-19 was made in 75/191 patients (39%). The LDCT was positive in 71 of these 75 patients and negative in 106 of the 116 patients without COVID-19, corresponding to 94.7% sensitivity (95% confidence interval [86.9: 98.5]). 91.4% specificity [84.7; 95.8]. positive and negative predictive values of 87.7% [78.5; 93.9] and 96.4% [91.1; 98.6], respectively, and an AUC (area under the curve) of 0.959 [0.930; 0.988]. The initial RT-PCR test results were falsely negative in six patients, yielding a sensitivity of 92.0% [83.4; 97.0]: these six patients had positive LDCT findings. 47.4% of the LDCTs that were negative for COVID-19 (55/116) exhibited pathological pulmonary changes. including infiltrates, that were correctly distinguished from SARS-CoV-2 related changes. Conclusion: In patients with symptoms compatible with COVID-19, LDCT can esablish the diagnosis of COVID-19 with comparable sensitivity to RT-PCR testing. In addition, it offers a high specificity for distinguishing COVID-19 from other diseases associated with the same or similar clinical symptoms. We propose the systematic use of LDCT in addition to RT-PCR testing because it helps correct false-negative RT-PCR results, because its results are available much faster than those of RT-PCR-testing, and because it provides additional diagnostic information useful for treatment planning regardless of the type of the infectious agent.