RESUMO
Diffusion-weighted Magnetic Resonance Imaging (dMRI) is increasingly used to study the fetal brain in utero. An important computation enabled by dMRI is streamline tractography, which has unique applications such as tract-specific analysis of the brain white matter and structural connectivity assessment. However, due to the low fetal dMRI data quality and the challenging nature of tractography, existing methods tend to produce highly inaccurate results. They generate many false streamlines while failing to reconstruct the streamlines that constitute the major white matter tracts. In this paper, we advocate for anatomically constrained tractography based on an accurate segmentation of the fetal brain tissue directly in the dMRI space. We develop a deep learning method to compute the segmentation automatically. Experiments on independent test data show that this method can accurately segment the fetal brain tissue and drastically improve the tractography results. It enables the reconstruction of highly curved tracts such as optic radiations. Importantly, our method infers the tissue segmentation and streamline propagation direction from a diffusion tensor fit to the dMRI data, making it applicable to routine fetal dMRI scans. The proposed method can facilitate the study of fetal brain white matter tracts with dMRI.
Assuntos
Encéfalo , Imagem de Tensor de Difusão , Feto , Substância Branca , Humanos , Imagem de Tensor de Difusão/métodos , Encéfalo/embriologia , Encéfalo/diagnóstico por imagem , Encéfalo/anatomia & histologia , Substância Branca/diagnóstico por imagem , Substância Branca/embriologia , Substância Branca/anatomia & histologia , Feto/diagnóstico por imagem , Feto/anatomia & histologia , Feminino , Aprendizado Profundo , Gravidez , Processamento de Imagem Assistida por Computador/métodos , Imagem de Difusão por Ressonância Magnética/métodosRESUMO
There is a growing interest in using diffusion MRI to study the white matter tracts and structural connectivity of the fetal brain. Recent progress in data acquisition and processing suggests that this imaging modality has a unique role in elucidating the normal and abnormal patterns of neurodevelopment in utero. However, there have been no efforts to quantify the prevalence of crossing tracts and bottleneck regions, important issues that have been extensively researched for adult brains. In this work, we determined the brain regions with crossing tracts and bottlenecks between 23 and 36 gestational weeks. We performed probabilistic tractography on 59 fetal brain scans and extracted a set of 51 distinct white tracts, which we grouped into 10 major tract bundle groups. We analyzed the results to determine the patterns of tract crossings and bottlenecks. Our results showed that 20-25% of the white matter voxels included two or three crossing tracts. Bottlenecks were more prevalent. Between 75-80% of the voxels were characterized as bottlenecks, with more than 40% of the voxels involving four or more tracts. The results of this study highlight the challenge of fetal brain tractography and structural connectivity assessment and call for innovative image acquisition and analysis methods to mitigate these problems.
RESUMO
BACKGROUND AND PURPOSE: Molecular biomarker identification increasingly influences the treatment planning of pediatric low-grade neuroepithelial tumors (PLGNTs). We aimed to develop and validate a radiomics-based ADC signature predictive of the molecular status of PLGNTs. MATERIALS AND METHODS: In this retrospective bi-institutional study, we searched the PACS for baseline brain MRIs from children with PLGNTs. Semiautomated tumor segmentation on ADC maps was performed using the semiautomated level tracing effect tool with 3D Slicer. Clinical variables, including age, sex, and tumor location, were collected from chart review. The molecular status of tumors was derived from biopsy. Multiclass random forests were used to predict the molecular status and fine-tuned using a grid search on the validation sets. Models were evaluated using independent and unseen test sets based on the combined data, and the area under the receiver operating characteristic curve (AUC) was calculated for the prediction of 3 classes: KIAA1549-BRAF fusion, BRAF V600E mutation, and non-BRAF cohorts. Experiments were repeated 100 times using different random data splits and model initializations to ensure reproducible results. RESULTS: Two hundred ninety-nine children from the first institution and 23 children from the second institution were included (53.6% male; mean, age 8.01 years; 51.8% supratentorial; 52.2% with KIAA1549-BRAF fusion). For the 3-class prediction using radiomics features only, the average test AUC was 0.74 (95% CI, 0.73-0.75), and using clinical features only, the average test AUC was 0.67 (95% CI, 0.66-0.68). The combination of both radiomics and clinical features improved the AUC to 0.77 (95% CI, 0.75-0.77). The diagnostic performance of the per-class test AUC was higher in identifying KIAA1549-BRAF fusion tumors among the other subgroups (AUC = 0.81 for the combined radiomics and clinical features versus 0.75 and 0.74 for BRAF V600E mutation and non-BRAF, respectively). CONCLUSIONS: ADC values of tumor segmentations have differentiative signals that can be used for training machine learning classifiers for molecular biomarker identification of PLGNTs. ADC-based pretherapeutic differentiation of the BRAF status of PLGNTs has the potential to avoid invasive tumor biopsy and enable earlier initiation of targeted therapy.
Assuntos
Neoplasias Encefálicas , Imagem de Difusão por Ressonância Magnética , Aprendizado de Máquina , Neoplasias Neuroepiteliomatosas , Humanos , Criança , Feminino , Masculino , Estudos Retrospectivos , Neoplasias Neuroepiteliomatosas/diagnóstico por imagem , Neoplasias Neuroepiteliomatosas/genética , Neoplasias Encefálicas/diagnóstico por imagem , Neoplasias Encefálicas/genética , Neoplasias Encefálicas/patologia , Pré-Escolar , Adolescente , Imagem de Difusão por Ressonância Magnética/métodos , Proteínas Proto-Oncogênicas B-raf/genética , Lactente , Gradação de Tumores , Biomarcadores Tumorais/genéticaRESUMO
Diffuse hemispheric glioma (DHG), H3 G34 mutant was included in the 5th edition of the World Health Organization Classification of Tumors of the Central Nervous System recently published. Given the recent inclusion in the current classification and its rarity in adult patients, there are scarce data on clinical-radiological characteristics, survival, and outcome. The authors report the case of a 35-year-old female with DHG, H3 G34-mutant characteristics and outcomes with an unusual presentation, recurrence, and prolonged survival. In conclusion, our case report demonstrates relevant details that should be observed in patients with suspicion or confirmation of the diagnosis of DHG, H3 G34 mutant, not only in the initial presentation but also in the evolution to ensure more personalized treatment.
RESUMO
BACKGROUND: Despite colloid cyst in the third ventricle is a very usual cause of hydrocephalus, its xanthogranulomatous variant is rare. The most important differential diagnosis is the third ventricular craniopharyngioma. To the best of the authors' knowledge, there have been few cases of xanthogranulomatous variant colloid cysts reported in the English literature. CASE DESCRIPTION: A 77-year-old white woman presented with headaches, memory loss, and abnormal gait for the past 4 months. Magnetic resonance imaging revealed a solid cystic lesion measuring 3.0 cm×2.8 cm×2.9 cm located inside the anterior portion of the third ventricle causing obstructive hydrocephalus. The posterior portion of the lesion was predominantly solid and hypointense on T2 and T1, with areas of post- contrast enhancement, and the anterior portion was predominantly cystic with both hyper- and hypointense areas on T1 and T2, with no suppression on fluid-attenuated inversion recovery and no restriction to diffusion. The patient underwent a left frontal craniotomy with pterional approach, and the lesion was removed microsurgically. CONCLUSION: Xanthogranulomatous reaction is rarely described in colloid cysts, which happens as a response to desquamation of epithelial lining, subsequent lipid accumulation, and as tissue inflammatory response to intracystic hemorrhage. Microsurgical resection is the treatment of choice. As compared to the plain colloid cyst, these lesions are difficult to fully excise as the inflammatory reaction to the xanthomatous material leads to adhesions to adjacent structures; therefore, the aspiration of cystic contents without spillage is advisable to achieve maximal resection of cyst walls.
RESUMO
OBJECTIVES: To evaluate the quality assurance of mammography results at a reference institution for the diagnosis and treatment of breast cancer in southern Brazil, based on the BIRADS (Breast Imaging Reporting and Data System) 5th edition recommendations for auditing purposes. MATERIALS AND METHODS: Retrospective cohort and cross-sectional study with 4502 patients (9668 mammographies)) who underwent at least one or both breast mammographies throughout 2013 at a regional public hospital, linked to a federal public university. The results were followed until 31 December 2014, including true positives (TPs), true negatives (TNs), false positives (FPs), false negatives (FNs), positive predictive values (PPVs), negative predictive value (NPV), sensitivity and specificity, with a confidence interval of 95%. RESULTS: The study showed high quality assurance, particularly regarding sensitivity (90.22%) and specificity (92.31%). The overall positive predictive value (PPV) was 65.35%, and the negative predictive value (NPV) was 98.32%. The abnormal interpretation rate (recall rate) was 12.26%. CONCLUSIONS: The results are appropriate when compared to the values proposed by the BIRADS 5th edition. Additionally, the study provided self-reflection considering our radiological practice, which is essential for improvements and collaboration regarding breast cancer detection. It may stimulate better radiological practice performance and continuing education, despite possible infrastructure and facility limitations. MAIN MESSAGES: ⢠Accurate quality performance rates are possible despite financial and governmental limitations. ⢠Low-income institutions should develop standardised teamwork to improve radiological practice. ⢠Regular mammography audits may help to increase the quality of public health systems.