Search results for "CT scans"
showing 5 items of 5 documents
Diagnosis of pre-sarcopenia from a single selectional crosscut at C3 region, using CT scans before radiotherapy
2019
espanolProposito: el proposito de este estudio fue diagnosticar la presarcopenia en pacientes con cancer que no disponen de imagenes por tomografia computarizada (TC) a nivel abdominal mediante un metodo novedoso basado en cortes a nivel cervical. Material y metodos: se analizaron y se compararon mediante unidades la masa muscular y la masa muscular esqueletica en 37 pacientes con cancer de pulmon y neoplasias del aparato digestivo superior que incluian cortes en la TC de planificacion a nivel de C3 y L3. La presarcopenia se identifico de acuerdo con los puntos de corte establecidos actualmente: ≤ 41 cm2/m2 para mujeres, ≤ 43 cm2/m2 en hombres con un IMC ≤ 25 kg/m2 y ≤ 53 cm2/m2 en hombres …
Machine learning classification for COVID19 patients performed on small datasets of CT scans.
2022
In this work we evaluated the possibility of carrying out classifications of the outcome of patients with COVID19 disease through machine learning (ML) techniques working on small datasets of computed tomography (CT) images. In fact, one of the most common problems for medical artificial intelligence (AI) applications is the limited availability of annotated clinical data for model training. In the framework of the artificial intelligence in medicine (AIM) project funded by INFN, we analyzed datasets of CT scans of 79 subjects combined with clinical data containing information relating to positive outcome (no need for intensive care) or poor prognosis (admission into intensive care unit and…
Automatische Berechnung des Milzvolumens aus Spiral-CT-Daten mit Hilfe neuronaler Netze und „Fuzzy Logik”∗
2000
PURPOSE To assess spleen segmentation and volumentry in spiral CT scans with and without pathological changes of splenic tissue. METHODS The image analysis software HYBRIKON is based on region growing, self-organized neural nets, and fuzzy-anatomic rules. The neural nets were trained with spiral CT data from 10 patients, not used in the following evaluation on spiral CT scans from 19 patients. An experienced radiologist verified the results. The true positive and false positive areas were compared in terms to the areas marked by the radiologist. The results were compared with a standard thresholding method. RESULTS The neural nets achieved a higher accuracy than the thresholding method. Cor…
Les crânes déformés de Saint-Etienne (Beaune, Côte d'Or, Ve-VIe siècles). Données archéologiques et anthropologiques
1995
The sector of the Saint-Étienne necropolis (Beaune), reveals the existence of two clearly separated zones which are characterized by different funeral and cultural practices: tomb architecture, archaeological material and artificially deformed crania. This seems to provide evidence of two distinct groups. A preliminary morpho-metrical study of four skulls and the examination of several CT scans of three of them, allow us to confirm the presence of artificial antero-posterior cranial deformations.
Spiral-CT und 3 D-Rekonstruktion des Tracheobronchialbaumes zur Auswahl geeigneter Doppellumentuben vor Einzellungenbeatmung
1997
Purpose To assess the potential of 3-D spiral CT in the selection of adequate double-lumen tubes (DLT) for one-lung-ventilation. Materials and methods 3-D spiral CT of eight different DLTs was performed with standardized acquisition parameters: section thickness 4 mm, table speed 6 mm/s, increment 3 mm and standardised thresholds, window settings and magnification zoom. The accuracy was confirmed by measuring 3-D objects on screen and original DLTs by vernier caliper. 3-D spiral CT was performed in 20 patients preoperatively with slice thickness 4-8 mm, pitch 1-1.5, increment 4-8 mm. To select the adequate DLT size the 3-D reconstructions of the patient's tracheobronchial tree and of the DL…