Search

Deep learning (DL) has been proposed to automate image segmentation and provide accuracy, consistency, and efficiency. Accurate segmentation of lipomatous tumors (LTs) is critical for correct tumor radiomics analysis and localization. The major challenge of this task is data heterogeneity, including tumor morphological characteristics and multicenter scanning protocols. To mitigate the issue, we aimed to develop a DL-based Super Learner (SL) ensemble framework with different data correction and normalization methods. Pathologically proven LTs on pre-operative T1-weighted/proton-density MR images of 185 patients were manually segmented. The LTs were categorized by tumor locations as distal upper limb (DUL), distal lower limb (DLL), proximal upper limb (PUL), proximal lower limb (PLL), or Trunk (T) and grouped by 80%/9%/11% for training, validation and testing. Six configurations of correction/normalization were applied to data for fivefold-cross-validation trainings, resulting in 30 base learners (BLs). A SL was obtained from the BLs by optimizing SL weights. The performance was evaluated by dice-similarity-coefficient (DSC), sensitivity, specificity, and Hausdorff distance (HD95). For predictions of the BLs, the average DSC, sensitivity, and specificity from the testing data were 0.72 [Formula: see text] 0.16, 0.73 [Formula: see text] 0.168, and 0.99 [Formula: see text] 0.012, respectively, while for SL predictions were 0.80 [Formula: see text] 0.184, 0.78 [Formula: see text] 0.193, and 1.00 [Formula: see text] 0.010. The average HD95 of the BLs were 11.5 (DUL), 23.2 (DLL), 25.9 (PUL), 32.1 (PLL), and 47.9 (T) mm, whereas of SL were 1.7, 8.4, 15.9, 2.2, and 36.6 mm, respectively. The proposed method could improve the segmentation accuracy and mitigate the performance instability and data heterogeneity aiding the differential diagnosis of LTs in real clinical situations.

This present work focuses on the mapping of marbles, decorative patterns and area of the mosaics of the St. Nicola's Basilica in Bari (Italy) by their photogrammetric survey. The extraordinary importance of these mosaics is due to the stylistic uniqueness and the undisputed workmanship and to the employed materials for tesserae. These mosaics include the white and polychrome marbles, used in the Roman age and reused in medieval artistic production, and imitation stones used as substitutes during the past restorations. The digital survey was realised by the photogrammetric reconstruction of mosaics collecting a photo dataset, after the mosaics redrawing by an image processing software and finally implemented it with lithological identification marbles. It allowed to obtain a punctual mapping of materials, through which to identify original areas and restoration areas, decorative patterns, recurring geometries. The research carried out, supported by the photogrammetric reconstruction as established method for high resolution digital reproduction and mapping, not only ensures the conservation and improvement of the enjoyment of the mosaic floors of the St. Nicola's Basilica, but allows to conduct studies on materials, decorative patterns and restoration areas directly on the digitized product. [ABSTRACT FROM AUTHOR]

At Ustica island (Palermo, Italy), in the area of Casa dei Francesi, 119 fragments of obsidian artifacts were collected on the surface of an agricultural field at an altitude of 50 m asl. In the same area, until now, scientific literature reports only the presence of late Roman pottery (4th–6th centuries AD), and no evidence has appeared that it could be the site of a prehistoric settlement. The most important prehistoric settlement, the Faraglioni Village (Middle Bronze Age) is located 700 m further north, overlooking the sea. Obsidian provenance analyses, performed on the 119 samples with absolutely non-destructive techniques WD-XRF and SEM-EDS, indicate two sources areas: Lipari (93 samples, 78%) and Pantelleria (26 samples, 22%). Concerning the obsidians from the island of Pantelleria, it was possible to also establish the sub-source of Salto la Vecchia. The typological and functional analyses of the 119 obsidian fragments point out that 115 are debitages, some of which show evidence of percussion bulbs, and only 4 are tools with micro-retouching. This work focuses on the geochemical and typological characterization of the obsidian assemblage collected, the characteristics of which suggest the existence of a prehistoric settlement in the area of the Casa dei Francesi or nearby.

In the last twenty years, obsidian artefacts have been found in important and often extensive karst cavities in Southern Italy: three located in Calabria (Grotta della Monaca, and Grotta del Tesauro, in Sant’Agata di Esaro, Cosenza; Grotta Pietra Sant’Angelo in San Lorenzo Bellizzi, Cosenza), one in Puglia (Grotta di Santa Barbara in Polignano a Mare, Bari) and another in Campania (Grotta di Polla, Salerno). All these sites, that have returned a total of 151 obsidian tools, were connected to human frequentation of the underground environments that occurred during the Holocene, which can be precisely located in the vast period between the Neolithic and the Eneolithic (6th–4th millennium BC). They are mainly blades and bladelets, but also burins together with scrapers and cores, generally of small dimensions. SEM-EDS and WD-XRF absolutely non-destructive analyses carried out on these items have shown that all samples have a source area in the obsidian outcrops of the island of Lipari (Messina, Italy). These data confirm that the Aeolian island of Lipari furnished the privileged obsidian extraction outcrops for most of the Neolithic and Eneolithic archaeological sites of Southern Italy.