Artificial intelligence for imaging-based COVID-19 detection: Systematic review comparing added value of AI versus human readers

Kriza, Christine; Amenta, Valeria; Zenié, Alexandre; Panidis, Dimitrios; Chassaigne, Hubert; Urban, Patricia; Holzwarth, Uwe; Sauer, Aisha V.; Reina, Vittorio; Griesinger, Claudius Benedict

doi:10.1016/j.ejrad.2021.110028

Cited by 14 publications

(4 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, these have their shortcomings. For starters, most of these reviews only studied the literature pertaining to using ML in diagnostic imaging [9][10][11][12][13][14][15].…”

Section: Introductionmentioning

confidence: 99%

Harnessing Machine Learning in Early COVID-19 Detection and Prognosis: A Comprehensive Systematic Review

Dabbagh¹,

Jamal²,

Masud³

et al. 2023

Cureus

View full text Add to dashboard Cite

During the early phase of the COVID-19 pandemic, reverse transcriptase-polymerase chain reaction (RT-PCR) testing faced limitations, prompting the exploration of machine learning (ML) alternatives for diagnosis and prognosis. Providing a comprehensive appraisal of such decision support systems and their use in COVID-19 management can aid the medical community in making informed decisions during the risk assessment of their patients, especially in low-resource settings. Therefore, the objective of this study was to systematically review the studies that predicted the diagnosis of COVID-19 or the severity of the disease using ML. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA), we conducted a literature search of MEDLINE (OVID), Scopus, EMBASE, and IEEE Xplore from January 1 to June 31, 2020. The outcomes were COVID-19 diagnosis or prognostic measures such as death, need for mechanical ventilation, admission, and acute respiratory distress syndrome. We included peer-reviewed observational studies, clinical trials, research letters, case series, and reports. We extracted data about the study's country, setting, sample size, data source, dataset, diagnostic or prognostic outcomes, prediction measures, type of ML model, and measures of diagnostic accuracy. Bias was assessed using the Prediction model Risk Of Bias ASsessment Tool (PROBAST). This study was registered in the International Prospective Register of Systematic Reviews (PROSPERO), with the number CRD42020197109. The final records included for data extraction were 66. Forty-three (64%) studies used secondary data. The majority of studies were from Chinese authors (30%). Most of the literature (79%) relied on chest imaging for prediction, while the remainder used various laboratory indicators, including hematological, biochemical, and immunological markers. Thirteen studies explored predicting COVID-19 severity, while the rest predicted diagnosis. Seventy percent of the articles used deep learning models, while 30% used traditional ML algorithms. Most studies reported high sensitivity, specificity, and accuracy for the ML models (exceeding 90%). The overall concern about the risk of bias was "unclear" in 56% of the studies. This was mainly due to concerns about selection bias. ML may help identify COVID-19 patients in the early phase of the pandemic, particularly in the context of chest imaging. Although these studies reflect that these ML models exhibit high accuracy, the novelty of these models and the biases in dataset selection make using them as a replacement for the clinicians' cognitive decision-making questionable. Continued research is needed to enhance the robustness and reliability of ML systems in COVID-19 diagnosis and prognosis.

show abstract

“…However, these have their shortcomings. For starters, most of these reviews only studied the literature pertaining to using ML in diagnostic imaging [9][10][11][12][13][14][15].…”

Section: Introductionmentioning

confidence: 99%

Harnessing Machine Learning in Early COVID-19 Detection and Prognosis: A Comprehensive Systematic Review

Dabbagh¹,

Jamal²,

Masud³

et al. 2023

Cureus

View full text Add to dashboard Cite

show abstract

“…AI is a very powerful technology in radiographic image interpretation [ 14 , 15 , 16 ]. Using AI in radiology practices is beneficial in healthcare [ 17 ].…”

Section: Introductionmentioning

confidence: 99%

Classification of Cervical Spine Fracture and Dislocation Using Refined Pre-Trained Deep Model and Saliency Map

et al. 2023

View full text Add to dashboard Cite

Cervical spine (CS) fractures or dislocations are medical emergencies that may lead to more serious consequences, such as significant functional disability, permanent paralysis, or even death. Therefore, diagnosing CS injuries should be conducted urgently without any delay. This paper proposes an accurate computer-aided-diagnosis system based on deep learning (AlexNet and GoogleNet) for classifying CS injuries as fractures or dislocations. The proposed system aims to support physicians in diagnosing CS injuries, especially in emergency services. We trained the model on a dataset containing 2009 X-ray images (530 CS dislocation, 772 CS fractures, and 707 normal images). The results show 99.56%, 99.33%, 99.67%, and 99.33% for accuracy, sensitivity, specificity, and precision, respectively. Finally, the saliency map has been used to measure the spatial support of a specific class inside an image. This work targets both research and clinical purposes. The designed software could be installed on the imaging devices where the CS images are captured. Then, the captured CS image is used as an input image where the designed code makes a clinical decision in emergencies.

show abstract

“…Indeed, the segmentation of HRCT images, which means the manual delineation and quantification of the pathological lung regions from the imaging data, was revealed to be a challenging and time-consuming task, not only for this reason, but also due to the high number of cases to report, the magnitude of the imaging data, and the similarity of COVID-19 patterns with other types of pneumonia [8]. A modern solution to this challenge is the integration of automated segmentation using Artificial Intelligence (AI), specifically methods based on Deep Learning (DL) [4,9] and Convolutional Neural Networks (CNNs) [10][11][12].…”

Section: Introductionmentioning

confidence: 99%

Enhancing COVID-19 CT Image Segmentation: A Comparative Study of Attention and Recurrence in UNet Models

Buongiorno,

Del Corso,

Germanese

et al. 2023

J. Imaging

View full text Add to dashboard Cite

Imaging plays a key role in the clinical management of Coronavirus disease 2019 (COVID-19) as the imaging findings reflect the pathological process in the lungs. The visual analysis of High-Resolution Computed Tomography of the chest allows for the differentiation of parenchymal abnormalities of COVID-19, which are crucial to be detected and quantified in order to obtain an accurate disease stratification and prognosis. However, visual assessment and quantification represent a time-consuming task for radiologists. In this regard, tools for semi-automatic segmentation, such as those based on Convolutional Neural Networks, can facilitate the detection of pathological lesions by delineating their contour. In this work, we compared four state-of-the-art Convolutional Neural Networks based on the encoder–decoder paradigm for the binary segmentation of COVID-19 infections after training and testing them on 90 HRCT volumetric scans of patients diagnosed with COVID-19 collected from the database of the Pisa University Hospital. More precisely, we started from a basic model, the well-known UNet, then we added an attention mechanism to obtain an Attention-UNet, and finally we employed a recurrence paradigm to create a Recurrent–Residual UNet (R2-UNet). In the latter case, we also added attention gates to the decoding path of an R2-UNet, thus designing an R2-Attention UNet so as to make the feature representation and accumulation more effective. We compared them to gain understanding of both the cognitive mechanism that can lead a neural model to the best performance for this task and the good compromise between the amount of data, time, and computational resources required. We set up a five-fold cross-validation and assessed the strengths and limitations of these models by evaluating the performances in terms of Dice score, Precision, and Recall defined both on 2D images and on the entire 3D volume. From the results of the analysis, it can be concluded that Attention-UNet outperforms the other models by achieving the best performance of 81.93%, in terms of 2D Dice score, on the test set. Additionally, we conducted statistical analysis to assess the performance differences among the models. Our findings suggest that integrating the recurrence mechanism within the UNet architecture leads to a decline in the model’s effectiveness for our particular application.

show abstract

Artificial intelligence for imaging-based COVID-19 detection: Systematic review comparing added value of AI versus human readers

Cited by 14 publications

References 35 publications

Harnessing Machine Learning in Early COVID-19 Detection and Prognosis: A Comprehensive Systematic Review

Harnessing Machine Learning in Early COVID-19 Detection and Prognosis: A Comprehensive Systematic Review

Classification of Cervical Spine Fracture and Dislocation Using Refined Pre-Trained Deep Model and Saliency Map

Enhancing COVID-19 CT Image Segmentation: A Comparative Study of Attention and Recurrence in UNet Models

Contact Info

Product

Resources

About