ABSTRACT
Knowledge of the 10B microdistribution is of great relevance in BNCT studies. Since 10B concentration assesment through neutron autoradiography depends on the correct quantification of tracks in a nuclear track detector, image acquisition and processing conditions should be controlled and verified, in order to obtain accurate results to be applied in the frame of BNCT. With this aim, an image verification process was proposed, based on parameters extracted from the quantified nuclear tracks. Track characterization was performed by selecting a set of morphological and pixel-intensity uniformity parameters from the quantified objects (area, diameter, roundness, aspect ratio, heterogeneity and clumpiness). Their distributions were studied, leading to the observation of varying behaviours in images generated by different samples and acquisition conditions. The distributions corresponding to samples coming from the BNC reaction showed similar attributes in each analyzed parameter, proving to be robust to the experimental process, but sensitive to light and focus conditions. Considering those observations, a manual feature extraction was performed as a pre-processing step. A Support Vector Machine (SVM) and a fully dense Neural Network (NN) were optimized, trained, and tested. The final performance metrics were similar for both models: 93%-93% for the SVM, vs 94%-95% for the NN in accuracy and precision respectively. Based on the distribution of the predicted class probabilities, the latter had a better capacity to reject inadequate images, so the NN was selected to perform the image verification step prior to quantification. The trained NN was able to correctly classify the images regardless of their track density. The exhaustive characterization of the nuclear tracks provided new knowledge related to the autoradiographic images generation. The inclusion of machine learning in the analysis workflow proves to optimize the boron determination process and paves the way for further applications in the field of boron imaging.
Subject(s)
Boron Neutron Capture Therapy , Boron , Autoradiography , Boron/analysis , Boron Neutron Capture Therapy/methods , Neutrons , Machine LearningABSTRACT
The SPECC1L protein plays a role in adherens junctions involved in cell adhesion, actin cytoskeleton organization, microtubule stabilization, spindle organization and cytokinesis. It modulates PI3K-AKT signaling and controls cranial neural crest cell delamination during facial morphogenesis. SPECC1L causative variants were first identified in individuals with oblique facial clefts. Recently, causative variants in SPECC1L were reported in a pedigree reported in 1988 as atypical Opitz GBBB syndrome. Six families with SPECC1L variants have been reported thus far. We report here eight further pedigrees with SPECC1L variants, including a three-generation family, and a further individual of a previously published family. We discuss the nosology of Teebi and GBBB, and the syndromes related to SPECC1L variants. Although the phenotype of individuals with SPECC1L mutations shows overlap with Opitz syndrome in its craniofacial anomalies, the canonical laryngeal malformations and male genital anomalies are not observed. Instead, individuals with SPECCL1 variants have branchial fistulae, omphalocele, diaphragmatic hernias, and uterus didelphis. We also point to the clinical overlap of SPECC1L syndrome with mild Baraitser-Winter craniofrontofacial syndrome: they share similar dysmorphic features (wide, short nose with a large tip, cleft lip and palate, blepharoptosis, retrognathia, and craniosynostosis), although intellectual disability, neuronal migration defect, and muscular problems remain largely specific to Baraitser-Winter syndrome. In conclusion, we suggest that patients with pathogenic variants in SPECC1L should not be described as "dominant (or type 2) Opitz GBBB syndrome", and instead should be referred to as "SPECC1L syndrome" as both disorders show distinctive, non overlapping developmental anomalies beyond facial communalities.