RESUMEN
Objective.The field of radiotherapy is highly marked by the lack of datasets even with the availability of public datasets. Our study uses a very limited dataset to provide insights on essential parameters needed to automatically and accurately segment individual bones on planning CT images of head and neck cancer patients.Approach.The study was conducted using 30 planning CT images of real patients acquired from 5 different cohorts. 15 cases from 4 cohorts were randomly selected as training and validation datasets while the remaining were used as test datasets. Four experimental sets were formulated to explore parameters such as background patch reduction, class-dependent augmentation and incorporation of a weight map on the loss function.Main results.Our best experimental scenario resulted in a mean Dice score of 0.93 ± 0.06 for other bones (skull, mandible, scapulae, clavicles, humeri and hyoid), 0.93 ± 0.02 for ribs and 0.88 ± 0.03 for vertebrae on 7 test cases from the same cohorts as the training datasets. We compared our proposed solution approach to a retrained nnU-Net and obtained comparable results for vertebral bones while outperforming in the correct identification of the left and right instances of ribs, scapulae, humeri and clavicles. Furthermore, we evaluated the generalization capability of our proposed model on a new cohort and the mean Dice score yielded 0.96 ± 0.10 for other bones, 0.95 ± 0.07 for ribs and 0.81 ± 0.19 for vertebrae on 8 test cases.Significance.With these insights, we are challenging the utilization of an automatic and accurate bone segmentation tool into the clinical routine of radiotherapy despite the limited training datasets.
Asunto(s)
Neoplasias de Cabeza y Cuello , Tomografía Computarizada por Rayos X , Humanos , Tomografía Computarizada por Rayos X/métodos , Planificación de la Radioterapia Asistida por Computador/métodos , Columna Vertebral , Cráneo , Procesamiento de Imagen Asistido por Computador/métodosRESUMEN
CaM kinase II (CaMKII) has been suggested to drive pathological cardiac remodeling and heart failure. However, the evidence provided so far is based on inhibitory strategies using chemical compounds and peptides that also exert off-target effects and followed exclusively preventive strategies. Therefore, the aim of this study was to investigate whether specific CaMKII inhibition after the onset of cardiac stress delays or reverses maladaptive cardiac remodeling and dysfunction. Combined genetic deletion of the two redundant CaMKII genes δ and γ was induced after the onset of overt heart failure as the result of pathological pressure overload induced by transverse aortic constriction (TAC). We used two different strategies to engineer an inducible cardiomyocyte-specific CaMKIIδ/CaMKIIγ double knockout mouse model (DKO): one model bases on tamoxifen-inducible mER/Cre/mER expression under control of the cardiac-specific αMHC promoter; the other strategy bases on overexpression of Cre recombinase via cardiac-specific gene transfer through adeno-associated virus (AAV9) under control of the cardiac-specific myosin light chain promoter. Both models led to a substantial deletion of CaMKII in failing hearts. To approximate the clinical situation, CaMKII deletion was induced 3 weeks after TAC surgery. In both models of DKO, the progression of cardiac dysfunction and interstitial fibrosis could be slowed down as compared to control animals. Taken together, we show for the first time that "therapeutic" CaMKII deletion after cardiac damage is sufficient to attenuate maladaptive cardiac remodeling and to reverse signs of heart failure. These data suggest that CaMKII inhibition is a promising therapeutic approach to combat heart failure.