Search bioRxiv⌕ Search
Home/Archive/bioRxiv

bioRxiv · 10.1101/2022.12.27.522072

DeepMPS: Development and validation of a deep learning model for whole slide image base prognostic prediction of low grade Lung adenocarcinoma patients

Jagjampi, A.·Khadirnaikar, S.·Malik, P. S.·Jain, D.·MB, N.·Shukla, S.
View original source ↗Export metadata ↓

Abstract

Lung adenocarcinoma (LUAD) is one of the most common cancers, and patients prognostication is crucial for treatment decisions. Histopathological images are the most generally accessible clinical information, however they have not been employed in clinical settings for prognosis. In this study, we used WSIs and clinical data from TCGA (training and testing) and East Asian Cohort (EAS, Validation) to develop and validate DL-based prognosticator. To circumvent the need for manual ROI generation, WSIs from these patients were divided into smaller patches and scored. DeepMPS prediction model was built using the top scoring 226,383 patches. The DeepMPS model showed a C-index of 0.638 in the TCGA training cohort. The univariate and multivariate cox regression analysis identified DeepMPS as an independent predictor of survival (HR: 9.48, p-value: <0.0001) in the training cohort. The training cohort of patients was separated into low and high-risk groups at various points. Kaplan-Meier analysis showed the highest difference in survival of low and high-risk patients at the 75th percentile (HR: 3.58, 95% CI: 2.57-5.00, p-value: <0.0001). At the same cut-off as the training samples, TCGA testing cohort patients demonstrated a significant difference in survival when split into low and high-risk patients (HR: 2.30, 95% CI: 1.11-4.82, p-value: 0.044). The DeepMPS model was validated in the EAS cohort patients. DeepMPS risk score significantly segregated EAS patients into low and high-risk groups at the same cut-off point as the training cohort (HR: 2.09, 95% CI: 1.11-3.97, p-value: 0.008). In multivariate Cox regression analysis, the DeepMPS score outperformed the stage in survival prediction. We also compared the DeepMPS model with the previously developed DL-based model to show that it was the best predictor of survival with the highest C-index. In conclusion, we developed a robust DL-based prognostic model which can predict the LUAD outcome without manual intervention using histopathological images. Author SummaryRight from the initial step of cancer diagnosis, histopathological images are the widely relied source of information for therapeutic decision making. Though these images carry a substantial amount of information, their use remains restricted to determining the grade of the tumor by pathologists. The advent of computational techniques has given rise to the ability to capture vital information besides the grade of the tumor, which humans might not be able to quantify visually. To this end, this work proposes a deep learning based model, Deep Multi-Modal Prognosis System (DeepMPS), to predict the prognosis of the patients based on the histopathological images to provide additional information to the pathologist which will aid in clinical decision making. DeepMPS predicts a risk score associated with each individual based on histopathological images and clinical factors. The risk score obtained from the proposed system is an independent predictor of survival. As the proposed system is independent of the manual region-of-interest (RoI) generation, it will ease the pathologists workload.

Explore related subjects

pathologyPreprint

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Jagjampi, A., Khadirnaikar, S., Malik, P. S., Jain, D., MB, N., Shukla, S.. 2022-12-30. DeepMPS: Development and validation of a deep learning model for whole slide image base prognostic prediction of low grade Lung adenocarcinoma patients. https://doi.org/10.1101/2022.12.27.522072

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related preprints

bioRxiv2026

NAE1-Dependent Protein Neddylation Preserves Endothelial Identity and Vascular Integrity

Background: Endothelial dysfunction is a central driver of cardiovascular and inflammatory diseases, yet the post-translational mechanisms that preserve endothelial homeostasis remain incompletely understood. Protein neddylation, the covalent conjugation of a ubiquitin-like modifier, regulates diverse cellular processes, yet its physiological role in the vascular endothelium remains unknown. This study investigated whether protein neddylation is required to preserve endothelial identity and vascular homeostasis. Methods: We generated tamoxifen-inducible endothelial-specific Nae1 knockout mice to inhibit neddylation and combined bulk RNA sequencing, single-cell and single-nucleus transcriptomics, quantitative proteomics, biochemical analyses, and gain- and loss-of-function approaches to define the role of endothelial neddylation in vascular homeostasis and inflammatory injury. Results: Endothelial-specific Nae1 deletion caused rapid mortality associated with vascular leakage, platelet accumulation, inflammation, and multi-organ injury. Multi-omics analyses demonstrated profound loss of endothelial identity, characterized by suppression of core endothelial programs and activation of inflammatory, procoagulant, and pyroptotic pathways. Single-cell analyses revealed progressive endothelial dysfunction culminating in depletion of the endothelial population and remodeling of the vascular niche. Mechanistically, endothelial neddylation deficiency activated gasdermin D (GSDMD)- and gasdermin E (GSDME)-dependent pyroptosis, whereas dual inhibition of GSDMD and GSDME markedly attenuated inflammatory transcriptomic remodeling, vascular injury, hepatocyte death, immune cell infiltration, and platelet accumulation. Translational analyses demonstrated reduced endothelial neddylation in experimental endotoxemia and decreased expression of neddylation pathway components in human atherosclerosis and COVID-19 datasets. Conversely, restoration of endothelial neddylation partially reversed inflammatory endothelial transcriptomic reprogramming in vivo. Conclusions: NAE1-dependent protein neddylation is an essential regulator of endothelial identity and vascular integrity. Loss of endothelial neddylation promotes gasdermin-dependent pyroptosis and thrombo-inflammatory vascular injury, whereas restoration of the neddylation pathway mitigates inflammatory endothelial dysfunction. These findings identify endothelial neddylation as a fundamental mechanism maintaining vascular homeostasis and a potential therapeutic target for cardiovascular and inflammatory diseases.

pathology↗
bioRxiv2024

COVID-19 during pregnancy alters circulating extracellular vesicle cargo and their effects on trophoblast

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection and resulting coronavirus disease (COVID-19) causes placental dysfunction, which increases the risk of adverse pregnancy outcomes. While abnormal placental pathology resulting from COVID-19 is common, direct infection of the placenta is rare. This suggests that pathophysiology associated with maternal COVID-19, rather than direct placental infection, is responsible for placental dysfunction and alteration of the placental transcriptome. We hypothesized that maternal circulating extracellular vesicles (EVs), altered by COVID-19 during pregnancy, contribute to placental dysfunction. To examine this hypothesis, we characterized maternal circulating EVs from pregnancies complicated by COVID-19 and tested their effects on trophoblast cell physiology in vitro. We found that the gestational timing of COVID-19 is a major determinant of circulating EV function and cargo. In vitro trophoblast exposure to EVs isolated from patients with an active infection at the time of delivery, but not EVs isolated from Controls, altered key trophoblast functions including hormone production and invasion. Thus, circulating EVs from participants with an active infection, both symptomatic and asymptomatic cases, can disrupt vital trophoblast functions. EV cargo differed between participants with COVID-19 and Controls, which may contribute to the disruption of the placental transcriptome and morphology. Our findings show that COVID-19 can have effects throughout pregnancy on circulating EVs and circulating EVs are likely to participate in placental dysfunction induced by COVID-19.

pathology↗
bioRxiv2024

Human iPSC-derived Committed Cardiac Progenitors Generate Cardiac Tissue Grafts in a Swine Ischemic Cardiomyopathy Model without Triggering Ventricular Arrhythmias

BackgroundIntramyocardial injection of human pluripotent stem cell-derived cardiomyocytes following a myocardial infarction (MI) improves cardiac function in large animal models, but associated ventricular arrhythmias are major safety concern. We hypothesized that transendocardial injection of human induced pluripotent stem cell (hiPSC)-derived committed cardiac progenitor cells (CCPs), combined with cardiac fibroblast-derived extracellular matrix (cECM) to enhance cell retention, will generate cardiac tissue grafts improving contractility without triggering ventricular arrhythmias. MethodshiPSCs were differentiated using bioreactors and small molecules to produce committed cardiac progenitor cells (CCPs). MI was created using a coronary artery balloon occlusion and reperfusion model in Yucatan mini pigs. Four weeks later, epicardial needle injections of CCPs+cECM were performed in a small initial feasibility cohort (n=6), and then transendocardial injections of CCPs+cECM (n=14), CCPs alone (n=14), cECM alone (n=4) or vehicle control (n=13) into the peri-infarct region in a randomized cohort. Arrhythmias were evaluated using implanted event recorders. Magnetic resonance imaging (MRI) and invasive pressure-volume assessment were used to evaluate left ventricular anatomic and functional performance. Detailed histology was performed to detect and characterize human grafts. ResultsA scalable biomanufacturing protocol was developed generating CCPs which can efficiently differentiate into cardiomyocytes or endothelial cells in vitro. Intramyocardial delivery of CCPs to post-MI porcine hearts resulted in engraftment and differentiation of CCPs to form ventricular cardiomyocyte rich grafts. There was no significant difference in cardiac MRI-based measured cardiac volumes or function between control, CCP and CCP+cECM groups; however, pressure-volume analysis showed an improvement in dobutamine-stimulated functional reserve in CCP and CCP+cECM groups. Delivery of CCPs did not result in tumors or ventricular arrhythmias. ConclusionsTransendocardial delivery of CCPs with or without cECM into post-MI porcine hearts resulted in comparable human cardiomyocyte grafts which did not improve resting LV function but did improve stress-induced contractile reserve without triggering ventricular arrhythmias.

pathology↗