RESUMO
OBJECTIVE: To provide an improved method for the identification and analysis of brain tumors in MRI scans using a semi-automated computational approach, that has the potential to provide a more objective, precise and quantitatively rigorous analysis, compared to human visual analysis. BACKGROUND: Self-Organizing Maps (SOM) is an unsupervised, exploratory data analysis tool, which can automatically domain an image into selfsimilar regions or clusters, based on measures of similarity. It can be used to perform image-domain of brain tissue on MR images, without prior knowledge. DESIGN/METHODS: We used SOM to analyze T1, T2 and FLAIR acquisitions from two MRI machines in our service from 14 patients with brain tumors confirmed by biopsies--three lymphomas, six glioblastomas, one meningioma, one ganglioglioma, two oligoastrocytomas and one astrocytoma. The SOM software was used to analyze the data from the three image acquisitions from each patient and generated a self-organized map for each containing 25 clusters. RESULTS: Damaged tissue was separated from the normal tissue using the SOM technique. Furthermore, in some cases it allowed to separate different areas from within the tumor--like edema/peritumoral infiltration and necrosis. In lesions with less precise boundaries in FLAIR, the estimated damaged tissue area in the resulting map appears bigger. CONCLUSIONS: Our results showed that SOM has the potential to be a powerful MR imaging analysis technique for the assessment of brain tumors.
Assuntos
Neoplasias Encefálicas/patologia , Glioblastoma/patologia , Glioma/patologia , Processamento de Imagem Assistida por Computador , Imageamento por Ressonância Magnética , Adulto , Idoso , Idoso de 80 Anos ou mais , Neoplasias Encefálicas/classificação , Feminino , Humanos , Masculino , Neoplasias Meníngeas/patologia , Meningioma/patologia , Pessoa de Meia-Idade , Curva ROCRESUMO
Twenty-three south-Swedish public supply wells were studied to assess pesticide pollution of regional groundwater resources. Relations between pesticide occurrence, hydrogeology, and land use were analyzed using Kohonen's Self-Organizing Maps approach. Pesticides are demonstrated to be substantially present in regional groundwater, with detections in 18 wells. Concentrations above the drinking water threshold are confirmed for nine wells. Observations indicate considerable urban influence, and lagged effects of past, less restricted use. Modern, oxic waters from shallow, unconfined, unconsolidated or fracture-type bedrock aquifers appear particularly vulnerable. Least affected waters appear primarily associated with deeper wells, anoxic conditions, and more confined sediment aquifers lacking urban influence. Comprehensive, standardized monitoring of pesticides in groundwater need to be implemented nationwide to enable sound assessments of pollution status and trends, and to develop sound groundwater management plans in accordance with the Water Framework Directive. Further, existing water protection areas and associated regulations need to be reassessed.