Publications by authors named "Gianluca Brugnara"
Background: This study aimed to explore the potential of the Advanced Data Analytics (ADA) package of GPT-4 to autonomously develop machine learning models (MLMs) for predicting glioma molecular types using radiomics from MRI.
Methods: Radiomic features were extracted from preoperative MRI of = 615 newly diagnosed glioma patients to predict glioma molecular types (IDH-wildtype vs IDH-mutant 1p19q-codeleted vs IDH-mutant 1p19q-non-codeleted) with a multiclass ML approach. Specifically, ADA was used to autonomously develop an ML pipeline and benchmark performance against an established handcrafted model using various MRI normalization methods (N4, Zscore, and WhiteStripe).
Objectives: Chemical exchange saturation transfer (CEST) imaging has emerged as a promising imaging biomarker, but its reliability for clinical practice remains uncertain. This study aimed to investigate the robustness of CEST parameters in healthy volunteers and patients with brain tumours.
Methods: A total of n = 52 healthy volunteers and n = 52 patients with histologically confirmed glioma underwent two consecutive 3-T MRI scans separated by a 1-min break.
Article Synopsis
- AI models usually struggle when applied to new datasets after being developed, leading to lower performance.
- This study explored the use of a data augmentation method through generative adversarial networks (GAN) to create synthetic patient images, aiming to enhance the AI model's ability to generalize across different datasets.
- Results showed that models using synthetic data achieved much better performance on external tests compared to those that did not, indicating that this approach could be beneficial in other medical imaging tasks as well.*
Article Synopsis
- Scientists are creating a smart computer program called CTA-DEFACE to hide faces in CT angiography images to keep people's data safe.
- They tested their program using images from different places and it worked really well, making faces much harder to recognize.
- The program is available for everyone to use online, and it's better at hiding faces than other similar programs.
Article Synopsis
- This study explored the use of shape radiomic features and tumor volume to classify IDH-wildtype gliomas and their relation to overall survival.
- A total of 436 patients' preoperative MR imaging data was analyzed, leading to the identification of two distinct tumor clusters with significantly different survival outcomes (Cluster 1: median OS 23.8 months, Cluster 2: median OS 11.4 months).
- The findings suggest that incorporating shape-radiomics along with tumor volume improves survival predictions for high-grade gliomas compared to using tumor volume alone.
Article Synopsis
- This study introduces a new way to classify patients with a type of brain cancer called IDH-wildtype glioblastomas by looking at how much of the tumor is removed during surgery.
- It involves 622 patients from one hospital and another 536 patients from three different hospitals, all of whom received standard cancer treatments and had tests to check their tumor characteristics.
- The new classification model shows that younger patients with certain tumor features have a better chance of living longer after surgery, compared to older patients or those with less successful surgeries.
Background: This study investigates the influence of diffusion-weighted Magnetic Resonance Imaging (DWI-MRI) on radiomic-based prediction of glioma types according to molecular status and assesses the impact of DWI intensity normalization on model generalizability.
Methods: Radiomic features, compliant with image biomarker standardization initiative standards, were extracted from preoperative MRI of 549 patients with diffuse glioma, known IDH, and 1p19q-status. Anatomical sequences (T1, T1c, T2, FLAIR) underwent N4-Bias Field Correction (N4) and WhiteStripe normalization (N4/WS).
Article Synopsis
- MRI scans take a long time to get, especially in places with fewer resources, so researchers want to make it faster using a special computer program called a deep convolutional neural network (dCNN).
- They studied information from a lot of patients with a type of brain cancer called glioblastoma to help train the dCNN to create better MRI images quickly by using less data.
- Their tests showed that the dCNN-created images were very similar to the original ones, and it worked well when looking at important cancer details in the scans.
Objective: Anorexia nervosa (AN) and obesity are weight-related disorders with imbalances in energy homeostasis that may be due to hormonal dysregulation. Given the importance of the hypothalamus in hormonal regulation, we aimed to identify morphometric alterations to hypothalamic subregions linked to these conditions and their connection to appetite-regulating hormones.
Methods: Structural magnetic resonance imaging (MRI) was obtained from 78 patients with AN, 27 individuals with obesity and 100 normal-weight healthy controls.
Purpose To develop a fully automated device- and sequence-independent convolutional neural network (CNN) for reliable and high-throughput labeling of heterogeneous, unstructured MRI data. Materials and Methods Retrospective, multicentric brain MRI data (2179 patients with glioblastoma, 8544 examinations, 63 327 sequences) from 249 hospitals and 29 scanner types were used to develop a network based on ResNet-18 architecture to differentiate nine MRI sequence types, including T1-weighted, postcontrast T1-weighted, T2-weighted, fluid-attenuated inversion recovery, susceptibility-weighted, apparent diffusion coefficient, diffusion-weighted (low and high value), and gradient-recalled echo T2*-weighted and dynamic susceptibility contrast-related images. The two-dimensional-midsection images from each sequence were allocated to training or validation (approximately 80%) and testing (approximately 20%) using a stratified split to ensure balanced groups across institutions, patients, and MRI sequence types.
View Article and Find Full Text PDFArticle Synopsis
- The study investigates how different MRI intensity normalization techniques affect radiomic models' ability to predict molecular glioma subtypes using data from patients with newly diagnosed gliomas.
- Four normalization methods were tested on MRI data from 615 patients, with the findings indicating that N4 followed by WhiteStripe and z-score normalization significantly enhanced the models' performance on external datasets, compared to no normalization and N4 alone.
- The results emphasize the importance of MRI data normalization in ensuring that radiomic models can be reliably applied to different patient populations, with the best-performing methods achieving robust generalizability across diverse datasets.
Swift diagnosis and treatment play a decisive role in the clinical outcome of patients with acute ischemic stroke (AIS), and computer-aided diagnosis (CAD) systems can accelerate the underlying diagnostic processes. Here, we developed an artificial neural network (ANN) which allows automated detection of abnormal vessel findings without any a-priori restrictions and in <2 minutes. Pseudo-prospective external validation was performed in consecutive patients with suspected AIS from 4 different hospitals during a 6-month timeframe and demonstrated high sensitivity (≥87%) and negative predictive value (≥93%).
View Article and Find Full Text PDFObjective: Multiple variables beyond the extent of recanalization can impact the clinical outcome after acute ischemic stroke due to large vessel occlusions. Here, we assessed the influence of small vessel disease and cortical atrophy on clinical outcome using native cranial computed tomography (NCCT) in a large single-center cohort.
Methods: A total of 1103 consecutive patients who underwent endovascular treatment (EVT) due to occlusion of the middle cerebral artery territory were included.
The translation of AI-generated brain metastases (BM) segmentation into clinical practice relies heavily on diverse, high-quality annotated medical imaging datasets. The BraTS-METS 2023 challenge has gained momentum for testing and benchmarking algorithms using rigorously annotated internationally compiled real-world datasets. This study presents the results of the segmentation challenge and characterizes the challenging cases that impacted the performance of the winning algorithms.
View Article and Find Full Text PDFBackground: Pseudoprogression (PsPD) is a major diagnostic challenge in the follow-up of patients with glioblastoma (GB) after chemoradiotherapy (CRT). Conventional imaging signs and parameters derived from diffusion and perfusion-MRI have yet to prove their reliability in clinical practice for an accurate differential diagnosis. Here, we tested these parameters and combined them with radiomic features (RFs), clinical data, and MGMT promoter methylation status using machine- and deep-learning (DL) models to distinguish PsPD from Progressive disease.
View Article and Find Full Text PDFGlioblastoma, the most common and aggressive primary brain tumor type, is considered an immunologically "cold" tumor with sparse infiltration by adaptive immune cells. Immunosuppressive tumor-associated myeloid cells are drivers of tumor progression. Therefore, targeting and reprogramming intratumoral myeloid cells is an appealing therapeutic strategy.
View Article and Find Full Text PDFArticle Synopsis
- Machine learning can work well, but it often struggles to make accurate predictions on new data, which is called out-of-sample generalizability.
- To solve this problem, researchers are using a method called Federated ML that allows computers to share information about how well they're learning without actually sharing the data itself.
- In a big study with 71 locations around the world, scientists created a model to help detect brain tumors more accurately, showing a significant improvement compared to older methods and hoping to help with rare illnesses and data sharing in healthcare.
Background: Quantitative and automated volumetric evaluation of early ischemic changes on non-contrast CT (NCCT) has recently been proposed as a new tool to improve prognostic performance in patients undergoing endovascular therapy (EVT) for acute ischemic stroke (AIS). We aimed to test its clinical value compared with the Alberta Stroke Program Early CT Score (ASPECTS) in a large single-institutional patient cohort.
Methods: A total of 1103 patients with AIS due to large vessel occlusion in the M1 or proximal M2 segments who underwent NCCT and EVT between January 2013 and November 2019 were retrospectively enrolled.
Background: Reliable detection and precise volumetric quantification of brain metastases (BM) on MRI are essential for guiding treatment decisions. Here we evaluate the potential of artificial neural networks (ANN) for automated detection and quantification of BM.
Methods: A consecutive series of 308 patients with BM was used for developing an ANN (with a 4:1 split for training/testing) for automated volumetric assessment of contrast-enhancing tumors (CE) and non-enhancing FLAIR signal abnormality including edema (NEE).
Background: To assess whether artificial intelligence (AI)-based decision support allows more reproducible and standardized assessment of treatment response on MRI in neuro-oncology as compared to manual 2-dimensional measurements of tumor burden using the Response Assessment in Neuro-Oncology (RANO) criteria.
Methods: A series of 30 patients (15 lower-grade gliomas, 15 glioblastoma) with availability of consecutive MRI scans was selected. The time to progression (TTP) on MRI was separately evaluated for each patient by 15 investigators over two rounds.
Background: Magnetic resonance imaging is essential for monitoring people with multiple sclerosis, but the diagnostic value of gadolinium contrast administration in spine magnetic resonance imaging is unclear.
Objective: To assess the diagnostic value of gadolinium contrast administration in spine magnetic resonance imaging follow-up examinations and identify imaging markers correlating with lesion enhancement.
Methods: A total of 65 multiple sclerosis patients with at least 2 spinal magnetic resonance imaging follow-up examinations were included.
Background: Gadolinium-based contrast agents (GBCAs) are widely used to enhance tissue contrast during MRI scans and play a crucial role in the management of patients with cancer. However, studies have shown gadolinium deposition in the brain after repeated GBCA administration with yet unknown clinical significance. We aimed to assess the feasibility and diagnostic value of synthetic post-contrast T1-weighted MRI generated from pre-contrast MRI sequences through deep convolutional neural networks (dCNN) for tumour response assessment in neuro-oncology.
View Article and Find Full Text PDFBackground: We studied the effects of endovascular treatment (EVT) and the impact of the extent of recanalization on cerebral perfusion and oxygenation parameters in patients with acute ischemic stroke (AIS) and large vessel occlusion (LVO).
Methods: Forty-seven patients with anterior LVO underwent computed tomography perfusion (CTP) before and immediately after EVT. The entire ischemic region (T >6 s) was segmented before intervention, and tissue perfusion (time-to-maximum (T), time-to-peak (TTP), mean transit time (MTT), cerebral blood volume (CBV), cerebral blood flow (CBF)) and oxygenation (coefficient of variation (COV), capillary transit time heterogeneity (CTH), metabolic rate of oxygen (CMRO), oxygen extraction fraction (OEF)) parameters were quantified from the segmented area at baseline and the corresponding area immediately after intervention, as well as within the ischemic core and penumbra.