Severity Assessment and Progression Prediction of COVID-19 Patients Based on the LesionEncoder Framework and Chest CT

Automatic severity assessment and progression prediction can facilitate admission, triage, and referral of COVID-19 patients. This study aims to explore the potential use of lung lesion features in the management of COVID-19, based on the assumption that lesion features may carry important diagnostic and prognostic information for quantifying infection severity and forecasting disease progression. A novel LesionEncoder framework is proposed to detect lesions in chest CT scans and to encode lesion features for automatic severity assessment and progression prediction. The LesionEncoder framework consists of a U-Net module for detecting lesions and extracting features from individual CT slices, and a recurrent neural network (RNN) module for learning the relationship between feature vectors and collectively classifying the sequence of feature vectors. Chest CT scans of two cohorts of COVID-19 patients from two hospitals in China were used for training and testing the proposed framework. When applied to assessing severity, this framework outperformed baseline methods achieving a sensitivity of 0.818, specificity of 0.952, accuracy of 0.940, and AUC of 0.903. It also outperformed the other tested methods in disease progression prediction with a sensitivity of 0.667, specificity of 0.838, accuracy of 0.829, and AUC of 0.736. The LesionEncoder framework demonstrates a strong potential for clinical application in current COVID-19 management, particularly in automatic severity assessment of COVID-19 patients. This framework also has a potential for other lesion-focused medical image analyses.

Ultrabright Plasmonic-Fluor Nanolabel-Enabled Detection of a Urinary ER Stress Biomarker in Autosomal Dominant Tubulointerstitial Kidney Disease

Autosomal dominant tubulointerstitial kidney disease (ADTKD)-uromodulin (UMOD) is the most common non-polycystic genetic kidney disease, but it remains unrecognized due to its clinical heterogeneity and lack of screening test. Moreover, clinical feature being a poor predictor of the disease outcome further highlights the need for development of mechanistic biomarkers in ADTKD. However, low abundant urinary proteins secreted by thick ascending limb (TAL) cells, where UMOD is synthesized, have posed a challenge on detection of biomarkers in ADTKD-UMOD. In the CRISPR/Cas9-generated murine model and patients with ADTKD-UMOD, we find that immunoglobulin heavy chain-binding protein (BiP), an ER chaperone, was exclusively upregulated by mutant UMOD in TAL and easily detected by Western blot in the urine at an early stage of disease. However, even the most sensitive ELISA failed to detect urinary BiP in affected individuals. We therefore developed an ultrasensitive, plasmon-enhanced fluorescence-linked immunosorbent assay (p-FLISA) to quantify urinary BiP concentration by harnessing the newly invented ultrabright fluorescent nanoconstruct, termed "plasmonic fluor" (Nat Biomed Eng 2020). p-FLISA demonstrated that urinary BiP excretion was significantly elevated in ADTKD-UMOD patients compared with unaffected controls, which may have potential utility in risk stratification, disease activity monitoring, disease progression prediction, and guidance of ER-targeted therapies in ADTKD.

Progression prediction model for solid tumors with clinical and immunological parameters.

2539 Background: The immune system has well-known relation to tumor progression. Numerous immune-related parameters exist, but only a minor part could be used as biomarkers, especially dynamic ones. We trained a progression prediction model based on clinical features and peripheral immune system assessments. Methods: Patients with immunogenic (melanoma, 295, kidney cancer, 81), non-immunogenic (soft tissue sarcoma, 47, colorectal cancer, 26) and multiple primary tumors (29) with immunologic assessments before treatment (23.5%), on therapy (58.3), and in follow-up after the treatment (18.2%) were randomly divided in 7:3 ratio to the training and test groups. Counts of lymphocytes, T-, B, NK cells, cytotoxic lymphocytes, T-helpers were used as immunologic parameters. Age, sex, disease, stage, therapy, mutational status, last response on treatment, disease and therapy duration, previous treatments were used as clinical ones. The model was trained to predict disease progression in the next three months using “Catboost” gradient boosting. We used ROC AUC to test model performance and Yoden’s index for optimal cutoff calculation. We also studied the influence of model prediction on overall survival (OS) and time to progression (TTP) on the test dataset using the Kaplan-Meyer method and Cox regression. Results: We used 1682 assessments of immune parameters (immune status, IS) done in 354 patients (average 5 per patient) to train the model and 616 IS in 124 patients for validation. All IS of one patient were in the same group. The ROC AUC value of the model was 0.801. The model prediction of progression increased the probability of progressive disease from 37.5 to 62% and decreased the response rate from 37,5% to 8.4% (p = 0.016). The model prediction did not add information over known prognostic factors for OS in the multifactorial model but was an independent prognostic factor for TTP (HR 2.204, p = 0.011). False-positive results separate the group of patients with poor prognosis (OS 16 months, TTP 6 months) among patients with clinical benefit from patients with favorable prognosis (OS 61 months, TTP 18 months, p < 0.001), who had a truly negative model prediction. The possibility of prognosis improvement with therapy change was an essential factor for OS and TTP prediction (р < 0.001). The model was useful in predicting higher OS in patients with disease progression (p = 0.033) and shorter response duration in patients with clinical benefit (р = 0.03). Conclusions: Our progression prediction model provides clinically useful information and can be used for decision making in several clinical situations. Its utility should be tested in a prospective trial.

A Novel Bayesian Framework For Multi-State Disease Progression Of Lung Cancer

CT screening has been commonly used to identify and diagnose lung cancer in its early stages. CT has been shown in clinical studies to reduce lung cancer mortality by 20% as compared to plain chest radiography; however, existing CT screening services face obstacles such as high over diagnosis rates, high costs, and elevated radiation exposure.The study develops computer and deep learning models for predictive lung cancer diagnosis and disease progression prediction in an effort to solve these difficulties. Using a symmetric chain code method and a machine learning system, a novel lung segmentation approach was first developed. The lung nodules connected to the lung wall are included in this process, which minimises over-segmentation error. Finally, to predict the inter disease progression of lung cancer, a Bayesian method was coupled with a prolonged Markov model.The resultant model calculates specific lung cancer state transition data, which can be used to make customised screening recommendations. Extensive trials and results have shown the efficacy of these approaches, paving the way for current CT screening systems to be optimised and improved.

Micro Optical Coherence Tomography for Coronary Imaging

Intravascular optical coherence tomography (IVOCT) that produces images with 10 μm resolution has emerged as a significant technology for evaluating coronary architectural morphology. Yet, many features that are relevant to coronary plaque pathogenesis can only be seen at the cellular level. This issue has motivated the development of a next-generation form of OCT imaging that offers higher resolution. One such technology that we review here is termed micro-OCT (μOCT) that enables the assessment of the cellular and subcellular morphology of human coronary atherosclerotic plaques. This chapter reviews recent advances and ongoing works regarding μOCT in the field of cardiology. This new technology has the potential to provide researchers and clinicians with a tool to better understand the natural history of coronary atherosclerosis, increase plaque progression prediction capabilities, and better assess the vessel healing process after revascularization therapy.