Deep learning ensembles for detecting brain metastases in longitudinal multi-modal MRI studies.

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.

Deep learning automates bidimensional and volumetric tumor burden measurement from MRI in pre- and post-operative glioblastoma patients.

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.

Detecting liver cirrhosis in computed tomography scans using clinically-inspired and radiomic features.

Hepatic cirrhosis is an increasing cause of mortality in developed countries-it is the pathological sequela of chronic liver diseases, and the final liver fibrosis stage. Since cirrhosis evolves from the asymptomatic phase, it is of paramount importance to detect it as quickly as possible, because entering the symptomatic phase commonly leads to hospitalization and can be fatal. Understanding the state of the liver based on the abdominal computed tomography (CT) scans is tedious, user-dependent and lacks reproducibility. We tackle these issues and propose an end-to-end and reproducible approach for detecting cirrhosis from CT. It benefits from the introduced clinically-inspired features that reflect the patient's characteristics which are often investigated by experienced radiologists during the screening process. Such features are coupled with the radiomic ones extracted from the liver, and from the suggested region of interest which captures the liver's boundary. The rigorous experiments, performed over two heterogeneous clinical datasets (two cohorts of 241 and 32 patients) revealed that extracting radiomic features from the liver's rectified contour is pivotal to enhance the classification abilities of the supervised learners. Also, capturing clinically-inspired image features significantly improved the performance of such models, and the proposed features were consistently selected as the important ones. Finally, we showed that selecting the most discriminative features leads to the Pareto-optimal models with enhanced feature-level interpretability, as the number of features was dramatically reduced (280×) from thousands to tens.

Segmentation of abdominal organs in computed tomography using a generalized statistical shape model.

Segmentation of anatomical structures in computed tomography images remains an important stage in computer-aided diagnostics and therapy. Due to the complexity of anatomical structures in the abdominal cavity, the occurrence of anatomical variants and pathological changes of organs in computed tomography images, segmentation is still treated as a current research problem. The paper presents the segmentation method based on the generalized statistical shape model. The method was tested in the application to segmentation based on 40 cases of computed tomography with contrast: 20 cases were included in training set and 20 in the testing set. For each case, expert outlines were made for the following organs: spleen, kidney, liver, pancreas, and duodenum. The following average results of the DICE coefficient were obtained: 0.96, 093, 0.88, 0.86, 0.81. The obtained results on the developed method can be treated as a step towards a universal method of segmentation in normalized scaled images, because the method does not require the selection of new parameter values when applied to the segmentation of a diverse group of parenchymal anatomical organs.

Automatic liver segmentation in computed tomography using general-purpose shape modeling methods.

BACKGROUND: Liver segmentation in computed tomography is required in many clinical applications. The segmentation methods used can be classified according to a number of criteria. One important criterion for method selection is the shape representation of the segmented organ. The aim of the work is automatic liver segmentation using general purpose shape modeling methods. METHODS: As part of the research, methods based on shape information at various levels of advancement were used. The single atlas based segmentation method was used as the simplest shape-based method. This method is derived from a single atlas using the deformable free-form deformation of the control point curves. Subsequently, the classic and modified Active Shape Model (ASM) was used, using medium body shape models. As the most advanced and main method generalized statistical shape models, Gaussian Process Morphable Models was used, which are based on multi-dimensional Gaussian distributions of the shape deformation field. RESULTS: Mutual information and sum os square distance were used as similarity measures. The poorest results were obtained for the single atlas method. For the ASM method in 10 analyzed cases for seven test images, the Dice coefficient was above 55[Formula: see text], of which for three of them the coefficient was over 70[Formula: see text], which placed the method in second place. The best results were obtained for the method of generalized statistical distribution of the deformation field. The DICE coefficient for this method was 88.5[Formula: see text] CONCLUSIONS: This value of 88.5 [Formula: see text] Dice coefficient can be explained by the use of general-purpose shape modeling methods with a large variance of the shape of the modeled object-the liver and limitations on the size of our training data set, which was limited to 10 cases. The obtained results in presented fully automatic method are comparable with dedicated methods for liver segmentation. In addition, the deforamtion features of the model can be modeled mathematically by using various kernel functions, which allows to segment the liver on a comparable level using a smaller learning set.