A5039907864- Cancer Genomics and Diagnostics
- Acute Myeloid Leukemia Research
- Radiomics and Machine Learning in Medical Imaging
- Myeloproliferative Neoplasms: Diagnosis and Treatment
- Multiple Myeloma Research and Treatments
- AI in cancer detection
- Digital Imaging for Blood Diseases
- Advanced X-ray and CT Imaging
- Genomics and Phylogenetic Studies
- Gene expression and cancer classification
- Epigenetics and DNA Methylation
- Wound Healing and Treatments
- Facial Nerve Paralysis Treatment and Research
- Diabetic Foot Ulcer Assessment and Management
- Neurological diseases and metabolism
- Pressure Ulcer Prevention and Management
- Genomics and Rare Diseases
- Protein Degradation and Inhibitors
- Prion Diseases and Protein Misfolding
- Computational Drug Discovery Methods
- Meningioma and schwannoma management
- Genomics and Chromatin Dynamics
- Amyotrophic Lateral Sclerosis Research
- Distributed and Parallel Computing Systems
- Constraint Satisfaction and Optimization
University of Bologna
1992-2024
Istituto delle Scienze Neurologiche di Bologna
2023-2024
Istituti di Ricovero e Cura a Carattere Scientifico
2022-2024
Humanitas University
2022
Leukemia and Lymphoma Society
2022
Osservatorio astronomico di Bologna
2022
Ministero della Salute
2022
Institute of Biomedical Science
2022
PURPOSE Patients with newly diagnosed multiple myeloma (NDMM) show heterogeneous outcomes, and approximately 60% of them are at intermediate-risk according to the Revised International Staging system (R-ISS), standard-of-care risk stratification model. Moreover, chromosome 1q gain/amplification (1q+) recently proved be a poor prognostic factor. In this study, we revised R-ISS by analyzing additive value each single feature, including 1q+. PATIENTS AND METHODS The European Myeloma Network,...
Synthetic data are artificial generated without including any real patient information by an algorithm trained to learn the characteristics of a source set and became widely used accelerate research in life sciences. We aimed (1) apply generative intelligence build synthetic different hematologic neoplasms; (2) develop validation framework assess fidelity privacy preservability; (3) test capability clinical/translational hematology.
The aim of the present study was to provide a comprehensive characterization whole genome DNA methylation patterns in replicative and ionizing irradiation- or doxorubicin-induced premature senescence, exhaustively exploring epigenetic modifications three different human cell types: somatic diploid skin fibroblasts bone marrow- adipose-derived mesenchymal stem cells. With CpG-wise differential analysis, signatures were identified: (a) type- treatment-specific signature; (b) type-specific...
Introduction: DNA methylation clocks presents advantageous characteristics with respect to the ambitious goal of identifying very early markers disease, based on concept that accelerated ageing is a reliable predictor in this sense. Methods: Such tools, being epigenomic based, are expected be conditioned by sex and tissue specificities, work about quantifying dependency as well from regression model size training set. Results: Our quantitative results indicate elastic-net penalization best...
Rare cancers constitute over 20% of human neoplasms, often affecting patients with unmet medical needs. The development effective classification and prognostication systems is crucial to improve the decision-making process drive innovative treatment strategies. We have created implemented MOSAIC, an artificial intelligence (AI)-based framework designed for multimodal analysis, classification, personalized prognostic assessment in rare cancers. Clinical validation was performed on...
Background Sex is a major source of diversity among patients and sex-informed approach becoming new paradigm in precision medicine.We aimed to describe sex myelodysplastic syndromes terms disease genotype, phenotype, clinical outcome.Moreover, we sought incorporate information into the decision-making process as fundamental component patient individuality. MethodsIn this multicentre, observational cohort study, retrospectively analysed 13 284 aged 18 years or older with diagnosis syndrome...
Abstract Quantitative computed tomography (QCT)-based in silico models have demonstrated improved accuracy predicting hip fractures with respect to the current gold standard, areal bone mineral density. These require that femur is segmented as a first step. This task can be challenging, and fact, it often almost fully manual, which time-consuming, operator-dependent, hard reproduce. work proposes semi-automated procedure for segmentation from CT images. The proposed based on joint...
Appropriate wound management shortens the healing times and reduces costs, benefiting patient in physical terms potentially reducing healthcare system’s economic burden. Among instrumental measurement methods, image analysis of a area is becoming one cornerstones chronic ulcer management. Our study aim to develop solid AI method based on convolutional neural network segment wounds efficiently make work physician more efficient, subsequently, lay foundations for further development in-depth...
Rectal cancer is a malignant neoplasm of the large intestine resulting from uncontrolled proliferation rectal tract. Predicting pathologic response neoadjuvant chemoradiotherapy at an MRI primary staging scan in patients affected by locally advanced (LARC) could lead to significant improvement survival and quality life patients. In this study, possibility automatizing estimation scan, using fully automated artificial intelligence-based model for segmentation consequent characterization tumor...
Benign renal tumors, such as oncocytoma (RO), can be erroneously diagnosed malignant cell carcinomas (RCC), because of their similar imaging features. Computer-aided systems leveraging radiomic features used to better discriminate benign tumors from the ones. The purpose this work was build a machine learning model distinguish RO clear RCC (ccRCC).We collected CT images 77 patients, with 30 cases (39%) and 47 ccRCC (61%). Radiomic were extracted both tumor volumes identified by clinicians...
Onco-hematological studies are increasingly adopting statistical mixture models to support the advancement of genomically-driven classification systems for blood cancer. Targeting enhanced patients stratification based on sole role molecular biology attracted much interest and contributes bring personalized medicine closer reality. In onco-hematology, Hierarchical Dirichlet Mixture Models (HDMM) have become one preferred method cluster genomics data, that include presence or absence gene...
Background: Radiomics is a field of research medicine and data science in which quantitative imaging features are extracted from medical images successively analyzed to develop models for providing diagnostic, prognostic, predictive information. The purpose this work was machine learning model predict the survival probability 85 cervical cancer patients using PET CT radiomic as predictors. Methods: Initially, were divided into two mutually exclusive sets: training set containing 80% testing...
Targeted Next Generation Sequencing is a common and powerful approach used in both clinical research settings. However, at present, large fraction of the acquired genetic information not since pathogenicity cannot be assessed for most variants. Further complicating this scenario increasingly frequent description poli/oligogenic pattern inheritance showing contribution multiple variants increasing disease risk. We present an which entire provided by target sequencing transformed into binary...
Abstract Background Current high-throughput technologies—i.e. whole genome sequencing, RNA-Seq, ChIP-Seq, etc.—generate huge amounts of data and their usage gets more widespread with each passing year. Complex analysis pipelines involving several computationally-intensive steps have to be applied on an increasing number samples. Workflow management systems allow parallelization a efficient computational power. Nevertheless, this mostly happens by assigning the available cores single or few...
Background: Acute myeloid leukemia (AML) is a heterogeneous disease in terms of clinical features, outcomes and genetics. While mutations NPM1 are usually considered as favorable prognostic marker, the vast majority patients carry several co-mutations that might influence prognosis. Therefore, better understanding NPM1mut AML mutational landscape warranted. The large cohort collected within European HARMONY Alliance provides an excellent basis for this purpose. Aims: To identify clinically...
Since 2017, targeted therapies combined with conventional intensive chemotherapy have started to improve outcome of patients acute myeloid leukemia (AML). However, even before these innovations outcomes improved, which has not yet been extensively studied. Thus, we used a large pan-European multicenter dataset the HARMONY Alliance evaluate treatment-time dependent over two decades. In 5359 AML patients, compared impact induction therapy on four consecutive 5-year calendar periods from 1997...