Disease Progression Detection via Deep Sequence Learning of Successive Radiographic Scans

Abstract

The highly rapid spread of the current pandemic has quickly overwhelmed hospitals all over the world and motivated extensive research to address a wide range of emerging problems. The unforeseen influx of COVID-19 patients to hospitals has made it inevitable to deploy a rapid and accurate triage system, monitor progression, and predict patients at higher risk of deterioration in order to make informed decisions regarding hospital resource management. Disease detection in radiographic scans, severity estimation, and progression and prognosis prediction have been extensively studied with the help of end-to-end methods based on deep learning. The majority of recent works have utilized a single scan to determine severity or predict progression of the disease. In this paper, we present a method based on deep sequence learning to predict improvement or deterioration in successive chest X-ray scans and build a mathematical model to determine individual patient disease progression profile using successive scans. A deep convolutional neural network pretrained on a diverse lung disease dataset was used as a feature extractor to generate the sequences. We devised three strategies for sequence modeling in order to obtain both fine-grained and coarse-grained features and construct sequences of different lengths. We also devised a strategy to quantify positive or negative change in successive scans, which was then combined with age-related risk factors to construct disease progression profile for COVID-19 patients. The age-related risk factors allowed us to model rapid deterioration and slower recovery in older patients. Experiments conducted on two large datasets showed that the proposed method could accurately predict disease progression. With the best feature extractor, the proposed method was able to achieve AUC of 0.98 with the features obtained from radiographs. Furthermore, the proposed patient profiling method accurately estimated the health profile of patients.

Deep learning techniques for detection and prediction of pandemic diseases: a systematic literature review

“… [ 37 ] Proposed ensemble learning techniques for detecting pneumoconiosis disease in CXRs using multiple deep learning models Chest X-ray radiographs (CXRs) Deep ensemble learning NA The ensemble framework outperformed others, achieving an accuracy of 91.50% in the automated detection of pneumoconiosis. Although, the ensemble learning techniques shown an improved performance but there is need for potential techniques to help radiologists in the primary screening of pandemic [ 8 ] A deep sequence learning-based technique to forecast improvement or worsening in subsequent chest X-ray scans using those scans was proposed A lung disease and OVID chest X-ray datasets were used DCNNs NA Among DCNNs feature extractors used, ChexNet (DenseNet121) PT outperformed others with Precision, recall, F-measure and AUC of 0.921, 0.918, 0.920, and 0.92 respectively The accuracy of the prediction was not reported and other state-of-the-art metrics reported might be improved when optimization techniques or feature selection algorithm is introduced [ 44 ] The goal was to develop an uncertainty-aware CNN model for prediction of COVID-19 COVID19CXr, X-ray image, and Kaggle datasets UA-ConvNet EfficientNet-B3 model and Monte Carlo (MC) dropout The suggested UA-ConvNet model achieves sensitivity of 98.15% and G-mean of 98.02% (with a Confidence Interval of 97.99–98.07). The method demonstrated its superiority over the currently used techniques for identifying COVID-19 instances from CXR images.…”

radioGWAS links radiome to genome to discover driver genes with somatic mutations for heterogeneous tumor image phenotype in pancreatic cancer

“…For each gene, we also calculated the number of individuals carrying variants in any given gene. The top-ranked genes are KRAS (22), TP53 (17), KMT2C (17), LRP1B (14), FGFR2 (13), RGPD3 (11), EWSR1 (10), and RGPD4 (10) (Supplementary Table S2).…”

“…This degree of heterogeneity has previously been underestimated or understated in the literature and in studies that undertake the discovery of biomarkers related to disease progression. It is also reflected by the results of population-based DNA sequencing and RNA expression studies to date, in that no consistent pattern of mutations or RNA expression profiles have yet been defined that accurately predict biological aspects of disease progression 11 , 12 .…”

Prognosis Prediction in COVID-19 Patients through Deep Feature Space Reasoning

“…Since the COVID-19 pandemic in late 2019 and early 2020, it has been found that chest radiography imaging can be effectively used to observe and summarize lung abnormalities, including ground glass opacities and their distribution in both lungs. Extensive studies on CXR imaging have shown their potential for severity assessment on the basis of lung involvement in the infection, disease progression detection [ 6 ], and prognosis prediction. However, in the case of COVID-19, the novelty of the disease makes it more challenging even for the expert radiologists to confidently interpret the findings, particularly on CXRs [ 12 , 13 , 14 ].…”

“…Though CT represents 3D volumetric data, CXRs provide many advantages, such as quick triaging, availability, accessibility, and portability. In recent years, CXRs have been used extensively by researchers to develop deep-learning methods for COVID-19 detection [ 5 ], progression detection [ 6 ], severity estimation [ 7 ], and prognosis prediction [ 8 ]. Most studies focus on training end-to-end deep learning models to predict COVID-19 progression or outcomes from CXRs [ 9 , 10 , 11 ].…”