Fully Automated Detection and Segmentation Pipeline for the Bone Marrow of the Lytic Bone of Multiple Myeloma Patients
Abstract
Monitoring the changes in bone marrow during therapy for multiple myeloma patients is a crucial task. Osteolytic lesions can cause deformation of the bones, affecting the robustness of traditional segmentation tools. A two-model deep learning analysis is explored in this study. A detection model reduces pixel imbalances between the background and the bone marrow pixels, achieving a mAP of 0.878±0.005. A residual U-Net segments the bone marrow, yielding a DSC of 0.856±0.003. The proposed deep learning-based segmentation pipeline allows accurate and fast annotation of the bone marrow in multiple myeloma patients.
Ensemble of Heterogeneous Machine Learning Models with Multiple Inputs for Multi Omics Analysis
Abstract
Multiple myeloma is a plasma cell neoplasm with genetic complexity that originates in pre-malignant stages due to genomic alterations, leading to malignant plasma cell proliferation. The completeness of data is significantly affecting multi-omics studies since the more sources included in the analysis, the more likely it is for key data to be missing. In this study, an ensemble meta-model that uses transfer learning from multiple single-source models was developed to assess the progression of multiple myeloma by leveraging radiocytogenetics. The proposed meta-model achieved the highest performance with an AUC of 0.75±0.07 and a SP of 0.84±0.02 among other single-source and radiocytogenetic models.
Clinical and Genomic-Based Decision Support System to Define the Optimal Timing of Allogeneic Hematopoietic Stem Cell Transplantation in Patients with Myelodysplastic Syndromes
Abstract
Allogeneic hematopoietic stem cell transplantation (HSCT) is the only potentially curative treatment for patients with myelodysplastic syndromes (MDS). Several issues must be considered when evaluating the benefits and risks of HSCT for patients with MDS, with the timing of transplantation during the disease course being a crucial question. Recently the integration of genomic screening (by Molecular International Prognostic Scoring System, IPSS-M) into patient’s assessment has resulted into a significant improvement in predicting clinical outcomes with respect to the conventional prognostic score (Revised IPSS, IPSS-R), including better stratification of post-HSCT outcome.
Here, we aimed to develop and validate a Decision Support System to define the optimal timing of HSCT in MDS patients based on clinical and genomic information as provided by IPSS-M vs conventional IPSS-R.
Clinical Text Reports to Stratify Patients Affected with Myeloid Neoplasms Using Natural Language Processing
Abstract
The availability of multimodal patient data, such as demographics, clinical, imaging, treatment, quality of life, outcomes and wearables data, as well as genome sequencing, have paved the way for the development of multimodal clinical solutions that introduce personalized or precision medicine. The clinical report is an information layer that contains relevant information about the disease in addition to the patient’s point of view. Natural language processing (NLP) is a branch of artificial intelligence (AI) and its pre-trained language models are the key technology for extracting value from this data layer.
Synthetic Histopathological Images Generation with Artificial Intelligence to Accelerate Research and Improve Clinical Outcomes in Hematology
Abstract
Hematological malignancies are rare and complex diseases and as a consequence, multimodal data (ranging from clinical and genomic information to images) are required to improve diagnosis, prognosis and personalized treatments. However, collecting all these layers of information is challenging, in particular when collecting cytological and histological images from the bone marrow (BM) reproducing disease morphologic features. Synthetic data generation by Artificial Intelligence (AI) can circumvent these issues by generating images conditioned from textual inputs (i.e. reports from pathologists), which are widely available and contain many useful clinical information. This technology can enrich data with synthetic images, thus boosting translational research and improving the performances of precision medicine strategies based on multimodal information.
Combining Gene Mutation with Transcriptomic Data Improves Outcome Prediction in Myelodysplastic Syndromes
Abstract
Myelodysplastic syndromes (MDS) are myeloid neoplasms characterized by peripheral blood cytopenias and risk of progression to acute myeloid leukemia (AML). Disease management is challenged by heterogeneity in clinical courses and survival probability. Recently, the genomic screening integration (by Molecular International Prognostic Scoring System, IPSS-M) into patient’s assessment has resulted into a significant improvement in predicting clinical outcomes compared to the conventional prognostic score (Revised IPSS, IPSS-R). Many of the consequences of genetic and cytogenetic alterations will affect gene expression by means of transcriptional and epigenetic instability and altered microenviromental signaling. The aim of this project conducted by GenoMed4All and Synthema EU consortia is to link genomic information with transcriptomic data for possibly improving the prediction of clinical outcomes in MDS patients.
Data-Driven Harmonization of 2022 Who and ICC Classifications of Myelodysplastic Syndromes/ Neoplasms (MDS): A Study By the International Consortium for MDS (icMDS)
Abstract
The inclusion of gene mutations and chromosomal abnormalities in the 2022 WHO and ICC Classifications of MDS has enhanced diagnostic precision and is expected to improve clinical decision-making process. Although these two systems share similarities, clinically relevant discrepancies still exist and potentially cause inconsistency in their adoption in a clinical setting. In this study on behalf of the International Consortium for MDS (icMDS), we adopted a data-driven approach to provide a harmonization roadmap between the 2022 WHO and ICC classification for MDS. A modified Delphi Process consensus approach is currently ongoing among icMDS experts to finalize a harmonized MDS classification scheme.
Federated learning for causal inference using deep generative disentangled models
Abstract
In the context of decentralized and privacy-constrained healthcare data settings, we introduce an innovative approach to estimate individual treatment effects (ITE) via federated learning. Emphasizing the critical importance of data privacy in healthcare, especially when drawing on data from various global hospitals, we address challenges arising from data scarcity and specific treatment assignment criteria influenced by the availability of the medication of interest. Our methodology uses federated learning applied to neural network-based generative causal inference models to bridge the gap between decentralized and centralized ITE estimation on a benchmark dataset.
Scalable and Portable Federated Learning Simulation Engine
Abstract
Federated learning (FL) is one of the most promising approaches to ensure privacy in the application of data-driven techniques to sensitive information. However, the implementation of such approaches in a production environment is still an important challenge. In this paper, we present a scalable, portable, hardware-independent, model-agnostic FL Simulation Engine (FLSE) with the aim of easing the job of researchers who want to train FL models to be deployed in production environments. The FLSE offers a tool that can be used both standalone or embedded within a larger architecture, it can be deployed seamlessly and allows concurrent, scalable, and highly available V&V assessment support for FL models. The tool allows researchers to understand the behaviour, in terms of metric performance, of their proposed models in production scenarios, allowing a boost in trustworthiness towards ethical AI.
Opportunities and Challenges of Synthetic Data Generation in Oncology
Abstract
Widespread interest in artificial intelligence (AI) in health care has focused mainly on deductive systems that analyze available real-world data to discover patterns not otherwise visible. Generative adversarial network, a new type of inductive AI, has recently evolved to generate high-fidelity virtual synthetic data (SD) trained on relatively limited real-world information. The AI system is fed with a collection of real data, and it learns to generate new augmented data while maintaining the general characteristics of the original data set. The use of SD to enhance clinical research and protect patient privacy has drawn a lot of interest in medicine and in the complex field of oncology. This article summarizes the main characteristics of this innovative technology and critically discusses how it can be used to accelerate data access for secondary purposes, providing an overview of the opportunities and challenges of SD generation for clinical cancer research and health care.