Deep Learning-Based Segmentation of Head and Neck Organs-at-Risk with Clinical Partially Labeled Data

Radiotherapy is one of the main treatments for localized head and neck (HN) cancer. To design a personalized treatment with reduced radio-induced toxicity, accurate delineation of organs at risk (OAR) is a crucial step. Manual delineation is time- and labor-consuming, as well as observer-dependent. Deep learning (DL) based segmentation has proven to overcome some of these limitations, but requires large databases of homogeneously contoured image sets for robust training. However, these are not easily obtained from the standard clinical protocols as the OARs delineated may vary depending on the patient’s tumor site and specific treatment plan. This results in incomplete or partially labeled data. This paper presents a solution to train a robust DL-based automated segmentation tool exploiting a clinical partially labeled dataset. We propose a two-step workflow for OAR segmentation: first, we developed longitudinal OAR-specific 3D segmentation models for pseudo-contour generation, completing the missing contours for some patients; with all OAR available, we trained a multi-class 3D convolutional neural network (nnU-Net) for final OAR segmentation. Results obtained in 44 independent datasets showed superior performance of the proposed methodology for the segmentation of fifteen OARs, with an average Dice score coefficient and surface Dice similarity coefficient of 80.59% and 88.74%. We demonstrated that the model can be straightforwardly integrated into the clinical workflow for standard and adaptive radiotherapy.     

Use of Nitric Oxide Donor-Loaded Microbubble Destruction by Ultrasound in Thrombus Treatment

In the presence of a vascular thrombus, the recovery of blood flow and vascular recanalization are very important to prevent tissue damage. An alternative procedure to thrombolysis is required for patients who are unable to receive surgery or thrombolytic drugs due to other physical conditions. Recently, the performance of thrombolysis combined with microbubbles has become an attractive and effective therapeutic procedure. Indeed, in a recent study, we demonstrated that, upon exposure to ultrasound, liposomes loaded with nitric oxide release agonists conjugated to microbubbles; therefore, there is potential to release the agonist in a controlled manner into specific tissues. This means that the effect of the agonist is potentiated, decreasing interactions with other tissues, and reducing the dose required to induce nitric-oxide-dependent vasodilation. In the present study, we hypothesized that a liposome microbubble delivery system can be used as a hydrophilic agonist carrier for the nitric oxide donor spermine NONOate, to elicit femoral vasodilation and clot degradation. Therefore, we used spermine-NONOate-loaded microbubbles to evaluate the effect of ultrasound-mediated microbubble disruption (UMMD) on thromboembolic femoral artery recanalization. We prepared spermine NONOate-loaded microbubbles and tested their effect on ex vivo preparations, hypothesizing that ultrasound-induced microbubble disruption is associated with the vasorelaxation of aortic rings. Thrombolysis was demonstrated in aorta blood-flow recovery after disruption by spermine NONOate-loaded microbubbles via ultrasound application in the region where the thrombus is located. Our study provides an option for the clinical translation of NO donors to therapeutic applications.     

Um Stickstoff in organischen K?rpern nachzuweisen

Ohne Zusammenfassung     

Bemerkung zur vorstehenden Abhandlung

Ohne Zusammenfassung     

Zur Erkennung von echten und mit Glykose oder Rohrzucker gef?lschten Honigen

Ohne Zusammenfassung     

Ueber die Untersuchung der mineralischen Schmier?le

Ohne Zusammenfassung