Your browser doesn't support javascript.
loading
Show: 20 | 50 | 100
Results 1 - 4 de 4
Filter
Add more filters










Database
Language
Publication year range
1.
Comput Med Imaging Graph ; 116: 102401, 2024 May 22.
Article in English | MEDLINE | ID: mdl-38795690

ABSTRACT

Metastatic brain cancer is a condition characterized by the migration of cancer cells to the brain from extracranial sites. Notably, metastatic brain tumors surpass primary brain tumors in prevalence by a significant factor, they exhibit an aggressive growth potential and have the capacity to spread across diverse cerebral locations simultaneously. Magnetic resonance imaging (MRI) scans of individuals afflicted with metastatic brain tumors unveil a wide spectrum of characteristics. These lesions vary in size and quantity, spanning from tiny nodules to substantial masses captured within MRI. Patients may present with a limited number of lesions or an extensive burden of hundreds of them. Moreover, longitudinal studies may depict surgical resection cavities, as well as areas of necrosis or edema. Thus, the manual analysis of such MRI scans is difficult, user-dependent and cost-inefficient, and - importantly - it lacks reproducibility. We address these challenges and propose a pipeline for detecting and analyzing brain metastases in longitudinal studies, which benefits from an ensemble of various deep learning architectures originally designed for different downstream tasks (detection and segmentation). The experiments, performed over 275 multi-modal MRI scans of 87 patients acquired in 53 sites, coupled with rigorously validated manual annotations, revealed that our pipeline, built upon open-source tools to ensure its reproducibility, offers high-quality detection, and allows for precisely tracking the disease progression. To objectively quantify the generalizability of models, we introduce a new data stratification approach that accommodates the heterogeneity of the dataset and is used to elaborate training-test splits in a data-robust manner, alongside a new set of quality metrics to objectively assess algorithms. Our system provides a fully automatic and quantitative approach that may support physicians in a laborious process of disease progression tracking and evaluation of treatment efficacy.

2.
Comput Biol Med ; 154: 106603, 2023 03.
Article in English | MEDLINE | ID: mdl-36738710

ABSTRACT

Tumor burden assessment by magnetic resonance imaging (MRI) is central to the evaluation of treatment response for glioblastoma. This assessment is, however, complex to perform and associated with high variability due to the high heterogeneity and complexity of the disease. In this work, we tackle this issue and propose a deep learning pipeline for the fully automated end-to-end analysis of glioblastoma patients. Our approach simultaneously identifies tumor sub-regions, including the enhancing tumor, peritumoral edema and surgical cavity in the first step, and then calculates the volumetric and bidimensional measurements that follow the current Response Assessment in Neuro-Oncology (RANO) criteria. Also, we introduce a rigorous manual annotation process which was followed to delineate the tumor sub-regions by the human experts, and to capture their segmentation confidences that are later used while training deep learning models. The results of our extensive experimental study performed over 760 pre-operative and 504 post-operative adult patients with glioma obtained from the public database (acquired at 19 sites in years 2021-2020) and from a clinical treatment trial (47 and 69 sites for pre-/post-operative patients, 2009-2011) and backed up with thorough quantitative, qualitative and statistical analysis revealed that our pipeline performs accurate segmentation of pre- and post-operative MRIs in a fraction of the manual delineation time (up to 20 times faster than humans). Volumetric measurements were in strong agreement with experts with the Intraclass Correlation Coefficient (ICC): 0.959, 0.703, 0.960 for ET, ED, and cavity. Similarly, automated RANO compared favorably with experienced readers (ICC: 0.681 and 0.866) producing consistent and accurate results. Additionally, we showed that RANO measurements are not always sufficient to quantify tumor burden. The high performance of the automated tumor burden measurement highlights the potential of the tool for considerably improving and simplifying radiological evaluation of glioblastoma in clinical trials and clinical practice.


Subject(s)
Brain Neoplasms , Deep Learning , Glioblastoma , Adult , Humans , Glioblastoma/diagnostic imaging , Glioblastoma/surgery , Glioblastoma/pathology , Brain Neoplasms/diagnostic imaging , Brain Neoplasms/surgery , Tumor Burden , Magnetic Resonance Imaging/methods
3.
Pol J Radiol ; 76(1): 25-9, 2011 Jan.
Article in English | MEDLINE | ID: mdl-22802813

ABSTRACT

BACKGROUND: Breast cancer is the most common malignant neoplasm and the most common cause of death among women. The core needle biopsy is becoming a universal practice in diagnosing breast lesions suspected of malignancy. Unfortunately, breast core needle biopsies also bear the risk of having false-negative results. MATERIAL/METHODS: 988 core needle breast biopsies were performed at the Maria Sklodowska-Curie Memorial Cancer Center and Institute of Oncology, Gliwice Branch, between 01 March 2006 and 29 February 2008. Malignant lesions were diagnosed in 426/988 (43.12%) cases, atypical hyperplasia in 69/988 (6.98%), and benign lesions in 493/988 (49.90%) cases. RESULTS: Twenty-two out of 988 biopsies (2.23%) were found to be false negative. Histopathological assessment of tissue specimens was repeated in these cases. In 14/22 (64%) cases, the previous diagnosis of a benign lesion was changed. In 8/22 (36%) cases, the diagnosis of a benign lesion was confirmed. False-negative rate was calculated at 2.2%. The rate of false-negative diagnoses resulting from a radiological mistake was estimated at 36%. The rate of false-negative diagnoses, resulting from histopathological assessment, was 64%. False-negative results caused by a radiological error comprised 1.5% of all histopathologically diagnosed cancers and atypias (sensitivity of 98.5%). There were no false-positive results in our material - the specificity of the method was 100%. CONCLUSIONS: Histopathological interpretation is a substantial cause of false-negative results of breast core needle biopsy. Thus, in case of a radiological-histopathological divergence, histopathological analysis of biopsy specimens should be repeated. The main radiological causes of false-negative results of breast core needle biopsy are as follows: sampling from an inappropriate site and histopathological non-homogeneity of cancer infiltration.

4.
Acta Neurochir Suppl ; 106: 187-90, 2010.
Article in English | MEDLINE | ID: mdl-19812946

ABSTRACT

OBJECTIVE: The aim of the study was to evaluate the incidence of postirradiation imaging changes after stereotactic radiosurgery for arteriovenous malformations (AVM) and cerebral cavernous malformations (CCM). MATERIAL AND METHODS: A group of 85 patients treated for arteriovenous malformations (62 patients, 73%) and cavernomas (23 patients, 27%) between October 2001 and December 2005 was analyzed. All patients were treated with stereotactic radiosurgery with doses ranging from 8-28 Gy. After the irradiation, magnetic resonance imaging (MRI) or computed tomography (CT) was performed at 6 to 12-month intervals to assess the effects of the treatment. The mean follow-up time for the whole group was 27.3 months; AVM group -- 26 months; CCM group -- 30.9 months. All the imaging data were carefully reviewed to identify the radiological symptoms of postradiosurgical damage. T2 or FLAIR hyperintensity, T1-hypointensity and contrast enhancement on MRI and the presence of hypodense areas and contrast enhancement on CT examinations were assessed. RESULTS: Imaging abnormalities were found in 28 (33%) patients. The symptoms of postradiosurgical damage were observed in 21 (33.9%) patients in the AVM group and 7 (30.4%) patients in the CCM group. Radiological symptoms of radiation necrosis associated with neurological deterioration were identified in two patients with cavernomas, while no radiation necrosis was found in the AVM group. Patients in whom radiological signs of focal brain edema or gliosis existed were asymptomatic. CONCLUSIONS: Radiological symptoms of postradiosurgical damage affected about one third of the irradiated patients, typically without any clinical manifestations. Patients irradiated for CCMs seem to be more prone to develop symptomatic postradiosurgical necrosis; this observation, however, requires further investigation.


Subject(s)
Arteriovenous Malformations/pathology , Arteriovenous Malformations/surgery , Brain/pathology , Radiosurgery/adverse effects , Adolescent , Arteriovenous Malformations/classification , Humans , Incidence , Longitudinal Studies , Magnetic Resonance Imaging/methods , Male , Retrospective Studies , Tomography, X-Ray Computed/methods
SELECTION OF CITATIONS
SEARCH DETAIL
...