Pulmonary Embolism Risk Stratification from CTPA and Medical Records: Vascular Graphs Are Not All You Need

Risk stratification for pulmonary embolism (PE) is critical for clinical decision-making. Stratification guidelines are based on patient medical records, parameters measured from computed tomography pulmonary angiography (CTPA), and blood tests. However, blood tests are often missing in routine practice. This work studies whether state-of-the-art models can accurately classify risk stratification from only medical records and biomarkers extracted from CTPA images. We benchmark different approaches to combine medical records and cardiac biomarkers with rich pulmonary vascular information; we add vascular biomarkers to tabular models and apply graph neural networks (GNNs) on the vascular tree's intrinsic graph representation. We use a private dataset (n=353) with uniquely complete data for PE risk stratification. Our results show that, among global features, medical records and cardiac biomarkers are the most significant predictors, while vascular biomarkers do not further improve stratification. Even more surprising, even GNNs on vascular graphs fail to outperform strong tabular baseline on global features. We consider hypotheses, on both models and data, that could explain this suboptimal performance. Our investigation suggests that, counter-intuitively, vascular graphs might hold no discriminative information for PE risk stratification. Code is available from https://github.com/creatis-myriad/GENESIS.

A Patient-Specific Pulmonary Arterial Tree Digital Twin to Extract Pulmonary Embolism Biomarkers

Pulmonary embolism, the obstruction of a pulmonary artery by a blood clot, is one of the leading causes of acute cardiovascular syndrome. In clinical practice, therapeutic decisions after diagnosis via computed tomography pulmonary angiography rely on risk stratification, which categorizes 30-day mortality risk into three categories. This stratification depends on the right-to-left ventricular diameter ratio and blood levels of two cardiac enzymes. However, blood biomarkers are not always available in emergency settings, and manual calculation of established severity scores - such as Qanadli and Mastora - is time-consuming and rarely performed in clinical routine practice. This study introduces an automated pipeline that models a directed graph representation of the pulmonary arterial tree, labeling its hierarchical structure and characterizing pulmonary embolism. The pipeline derives image-based biomarkers, including local artery-level features (morphological information, hierarchical position, clot volume, and resulting obstruction) and global patient-level biomarkers such as automatically calculated severity scores (Qanadli and Mastora) and the total embolic volume distribution by lobes and hierarchical levels. Using artificial-intelligence-generated binary masks of arteries, emboli, lungs, and lobes, it creates a patient digital twin of the arterial structure. Validation of the pipeline through comparison to an existing pipeline, anatomical expectations, and manual severity score calculations demonstrates the pipeline's ability to automatically generate anatomically accurate digital twins and severity scores with strong agreement. This supports the potential of these image-derived biomarkers to automatically provide rapid, precise information on thrombotic burden and spatial clot distribution.

Alteration of skeletal muscle energy metabolism assessed by 31P MRS in clinical routine, part 1: Advanced Quality Control pipeline

Background: Implementing a standardized 31P-MRS dynamic acquisition protocol to evaluate skeletal muscle energy metabolism and monitor muscle fatigability1,2, while being compatible with various longitudinal clinical studies on diversified patient cohorts, requires a high level of technicality and expertise. Furthermore, processing data to obtain reliable results also demands a great degree of expertise from the operator. In this two-part article, we present an advanced quality control approach for data acquired using a dynamic 31P-MRS protocol. The aim is to provide decision support to the operator in order to assist in data processing and obtain reliable results based on objective criteria. We present first in part one, an advanced data quality control (QC) approach of a dynamic 31P-MRS protocol. Part two is an impact study demonstrating the added value of the QC approach to explore clinical results derived from two patient populations with significant fatigue: COVID19 and multiple sclerosis (MS). Experimental: 31P-MRS was performed on a 3T clinical MRI in 175 subjects from clinical and healthy control populations conducted in a University Hospital. An advanced data QC Score (QCS) was developed using multiple objective criteria. The criteria were based on current recommendations from the literature enriched by new proposals based on clinical experience. The QCS was designed to indicate valid and corrupt data and guide necessary objective data editing to extract as much valid physiological data as possible. Dynamic acquisitions using an MR-compatible ergometer ran over a rest(40s), exercise(2min), and a recovery phase(6min). Results: Using QCS enabled rapid identification of subjects with data anomalies allowing the user to correct the data series or reject them partially or entirely as well as identify fully valid datasets. Overall, the use of the QCS resulted in the automatic classification of 45% of the subjects including 58 participants that had data with no criterion violation and 21 participants with violations that resulted in the rejection of all dynamic data. The remaining datasets were inspected manually with guidance allowing acceptance of full datasets from an additional 80 participants and recovery phase data from an additional 16 subjects. Overall, more anomalies occurred with patient data (35% of datasets) compared to healthy controls (15% of datasets). Conclusion: This paper describes typical difficulties encountered during the dynamic acquisition of 31P-MRS. Based on these observations, a standardized data quality control pipeline was created and implemented in both healthy and patient populations. The QC scoring ensures a standardized data rejection procedure and rigorous objective analysis of dynamic 31P-MRS data obtained from patients. The contribution of this methodology contributes to efforts made to standardize the practices of the 31P-MRS that has been underway for a decade, with the ultimate goal of making it an empowered tool for clinical research.

Alteration of skeletal muscle energy metabolism assessed by 31P MRS in clinical routine, part 2: Clinical application

Background: In this second part of a two-part paper, we intend to demonstrate the impact of the previously proposed advanced quality control pipeline. To understand its benefit and challenge the proposed methodology in a real scenario, we chose to compare the outcome when applying it to the analysis of two patient populations with a significant but highly different types of fatigue: COVID19 and multiple sclerosis (MS). Experimental: 31P-MRS was performed on a 3T clinical MRI, in 19 COVID19 patients, 38 MS patients, and 40 matched healthy controls. Dynamic acquisitions using an MR-compatible ergometer ran over a rest(40s), exercise(2min), and a recovery phase(6min). Long and short TR acquisitions were also made at rest for T1 correction. The advanced data quality control pipeline presented in part 1 is applied to the selected patient cohorts to investigate its impact on clinical outcomes. We first used power and sample size analysis to estimate objectively the impact of adding QCS. Then, comparisons between patients and healthy control groups using validated QCS were performed using unpaired T-tests or Mann-Whitney tests (p<0.05).Results: The application of the QCS resulted in increased statistical power, changed the values of several outcome measures, and reduced variability (SD). A significant difference was found between the T1PCr and T1Pi of MS patients and healthy controls. Furthermore, the use of a fixed correction factor led to systematically higher estimated concentrations of PCr and Pi than when using individually corrected factors. We observed significant differences between the two patient populations and healthy controls for resting [PCr] -- MS only, [Pi], [ADP], [H2PO4-] and pH -- COVID19 only, and post-exercise [PCr],[Pi] and [H2PO4-] - MS only. The dynamic indicators $\tau$PCr, $\tau$Pi, ViPCr and Vmax were reduced for COVID19 and MS patients compared to controls. Conclusion: Our results show that QCS in dynamic 31P-MRS studies results in smaller data variability and therefore impacts study sample size and power. Although QCS resulted in discarded data and therefore reduced the acceptable data and subject numbers, this rigorous and unbiased approach allowed for proper assessment of muscle metabolites and metabolism in patient populations. The outcomes include an increased metabolite T1, which directly affect the T1 correction factor applied to the amplitudes of the metabolite, and a prolonged $\tau$PCr indicating reduced muscle oxidative capacity for patients with MS and COVID19.

Validation of apparent intra-and extra-myocellular lipid content indicator using spiral spectroscopic imaging at 3T

This work presents a fast and simple method based on spiral MRSI for mapping the IMCL and EMCL apparent content, which is a challenging task and it compares this indicator to classical quantification results in muscles of interest.

Disentangled representations: towards interpretation of sex determination from hip bone

By highlighting the regions of the input image that contribute the most to the decision, saliency maps have become a popular method to make neural networks interpretable. In medical imaging, they are particularly well-suited to explain neural networks in the context of abnormality localization. However, from our experiments, they are less suited to classification problems where the features that allow to distinguish between the different classes are spatially correlated, scattered and definitely non-trivial. In this paper we thus propose a new paradigm for better interpretability. To this end we provide the user with relevant and easily interpretable information so that he can form his own opinion. We use Disentangled Variational Auto-Encoders which latent representation is divided into two components: the non-interpretable part and the disentangled part. The latter accounts for the categorical variables explicitly representing the different classes of interest. In addition to providing the class of a given input sample, such a model offers the possibility to transform the sample from a given class to a sample of another class, by modifying the value of the categorical variables in the latent representation. This paves the way to easier interpretation of class differences. We illustrate the relevance of this approach in the context of automatic sex determination from hip bones in forensic medicine. The features encoded by the model, that distinguish the different classes were found to be consistent with expert knowledge.