Contrast-enhanced ultrasonography parameters in neural network diagnosis of liver tumors

AIM:To study the role of time-intensity curve(TIC) analysis parameters in a complex system of neural networks designed to classify liver tumors.METHODS:We prospectively included 112 patients with hepatocellular carcinoma(HCC)(n = 41),hypervascular(n = 20) and hypovascular(n = 12) liver metastases,hepatic hemangiomas(n = 16) or focal fatty changes(n = 23) who underwent contrast-enhanced ultrasonography in the Research Center of Gastroenterology and Hepatology,Craiova,Romania.We recorded full length movies of all contrast uptake phases and post-processed them offline by selecting two areas of interest(one for the tumor and one for the healthy surrounding parenchyma) and consecutive TIC analysis.The difference in maximum intensities,the time to reaching them and the aspect of the late/portal phase,as quantified by the neural network and a ratio between median intensities of the central and peripheral areas were analyzed by a feed forward back propagation multi-layer neural network which was trained to classify data into five distinct classes,corresponding to each type of liver lesion.RESULTS:The neural network had 94.45% training accuracy(95% CI:89.31%-97.21%) and 87.12% testing accuracy(95% CI:86.83%-93.17%).The automatic classification process registered 93.2% sensitivity,89.7% specificity,94.42% positive predictive value and 87.57% negative predictive value.The artificial neural networks(ANN) incorrectly classified as hemangyomas three HCC cases and two hypervascular metastases,while in turn misclassifying four liver hemangyomas as HCC(one case) and hypervascular metastases(three cases).Comparatively,human interpretation of TICs showed 94.1% sensitivity,90.7% specificity,95.11% positive predictive value and 88.89% negative predictive value.The accuracy and specificity of the ANN diagnosis system was similar to that of human interpretation of the TICs(P = 0.225 and P = 0.451,respectively).Hepatocellular carcinoma cases showed contrast uptake during the arterial phase followed by wash-out in the portal and first seconds of the late phases.For the hypovascular metastases did not show significant contrast uptake during the arterial phase,which resulted in negative differences between the maximum intensities.We registered wash-out in the late phase for most of the hypervascular metastases.Liver hemangiomas had contrast uptake in the arterial phase without agent wash-out in the portallate phases.The focal fatty changes did not show any differences from surrounding liver parenchyma,resulting in similar TIC patterns and extracted parameters.CONCLUSION:Neural network analysis of contrastenhanced ultrasonography-obtained TICs seems a promising field of development for future techniques,providing fast and reliable diagnostic aid for the clinician.

Comment on“Prognostic value of preoperative enhanced computed tomography as a quantitative imaging biomarker in pancreatic cancer”

Pancreatic ductal adenocarcinoma(PDAC)is one of the most lethal malignancies because of its high invasiveness and metastatic potential.Computed tomography(CT)is often used as a preliminary diagnostic tool for pancreatic cancer,and it is increasingly used to predict treatment response and disease stage.Recently,a study published in World Journal of Gastroenterology reported that quantitative analysis of preoperative enhanced CT data can be used to predict postoperative overall survival in patients with PDAC.A tumor relative enhancement ratio of≤0.7 indicates a higher tumor stage and poor prognosis.

Real-time monitoring of tumor vascular disruption induced by radiofrequency assisted gadofullerene

The anti-vascular therapy has been extensively studied for high performance tumor therapy by suppressing the tumor angiogenesis or cutting off the existing tumor vasculature. We have previously reported a novel anti-tumor treatment technique using radiofrequency （RF）-assisted ga- dofullerene nanocrystals （GFNCs） to selectively disrupt the tumor vasculature. In this work, we further revealed the changes on morphology and functionality of the tumor vas-culature during the high-performance RF-assisted GFNCs treatment in vivo. Here, a dearly evident mechanism of this technique in tumor vascular disruption was elucidated. Based on the H22 tumor bearing mice with dorsal skin flap chamber （DSFC） mode] and the dynamic contrast enhanced magnetic resonance imaging （DCE-MRI） technique, it was revealed that the GFNCs would selectively inset in the gaps of tumor vas-culature due to the innately incomplete structures and unique microenvironment of tumor vasculature,＇ and they damaged the surrounding endothelia cells excited by the RF to induce a phase transition accompanying with size expansion. Soon afterwards, the blood flow of the tumor blood vessels was permanently shut off, causing the entire tumor vascular net- work to collapse within 24 h after the treatment. The RF-as- sistant GFNCs technique was proved to aim at the tumor vasculatnre precisely, and was harmless to the normal vascu- lature. The current studies provide a rational explanation on the high efficiency anticancer activity of the RF-assisted GFNCs treatment, suggesting a novel technique with potent clinical application.

Bioorthogonal Prodrug–Antibody Conjugates for On-Target and On-Demand Chemotherapy

Current antibody–drug conjugates(ADCs)suffer from low tissue penetration and significant side effects,largely due to the permanent linkage and/or premature release of cytotoxic payloads.Herein,we developed a prodrug–antibody conjugate(ProADC)strategy by conjugating a bioorthogonal-activatable prodrug with an antibody that allowed on-target release and on-demand activation of cytotoxic drugs at a tumor site.The bioorthogonal-caged prodrug exhibited an enhanced permeability into and on-demand activation within cancer cells,while the pH-sensitive ADC linker allowed on-target release of the anticancer agent.Together,the ProADCs showed enhanced tumor penetration and alleviated side effects for use as an on-target and on-demand chemotherapy agents.