Rapid Artificial Intelligence Solutions in a Pandemic - The COVID-19-20 Lung CT Lesion Segmentation Challenge

External validation, radiological evaluation, and development of deep learning automatic lung segmentation in contrast-enhanced chest CT

OBJECTIVES

There is a need for CT pulmonary angiography (CTPA) lung segmentation models. Clinical translation requires radiological evaluation of model outputs, understanding of limitations, and identification of failure points. This multicentre study aims to develop an accurate CTPA lung segmentation model, with evaluation of outputs in two diverse patient cohorts with pulmonary hypertension (PH) and interstitial lung disease (ILD).

METHODS

This retrospective study develops an nnU-Net-based segmentation model using data from two specialist centres (UK and USA). Model was trained (n = 37), tested (n = 12), and clinically evaluated (n = 176) on a diverse 'real-world' cohort of 225 PH patients with volumetric CTPAs. Dice score coefficient (DSC) and normalised surface distance (NSD) were used for testing. Clinical evaluation of outputs was performed by two radiologists who assessed clinical significance of errors. External validation was performed on heterogenous contrast and non-contrast scans from 28 ILD patients.

RESULTS

A total of 225 PH and 28 ILD patients with diverse demographic and clinical characteristics were evaluated. Mean accuracy, DSC, and NSD scores were 0.998 (95% CI 0.9976, 0.9989), 0.990 (0.9840, 0.9962), and 0.983 (0.9686, 0.9972) respectively. There were no segmentation failures. On radiological review, 82% and 71% of internal and external cases respectively had no errors. Eighteen percent and 25% respectively had clinically insignificant errors. Peripheral atelectasis and consolidation were common causes for suboptimal segmentation. One external case (0.5%) with patulous oesophagus had a clinically significant error.

CONCLUSION

State-of-the-art CTPA lung segmentation model provides accurate outputs with minimal clinical errors on evaluation across two diverse cohorts with PH and ILD.

CLINICAL RELEVANCE

Clinical translation of artificial intelligence models requires radiological review and understanding of model limitations. This study develops an externally validated state-of-the-art model with robust radiological review. Intended clinical use is in techniques such as lung volume or parenchymal disease quantification.

KEY POINTS

• Accurate, externally validated CT pulmonary angiography (CTPA) lung segmentation model tested in two large heterogeneous clinical cohorts (pulmonary hypertension and interstitial lung disease). • No segmentation failures and robust review of model outputs by radiologists found 1 (0.5%) clinically significant segmentation error. • Intended clinical use of this model is a necessary step in techniques such as lung volume, parenchymal disease quantification, or pulmonary vessel analysis.

An ML prediction model based on clinical parameters and automated CT scan features for COVID-19 patients

Outcome prediction for individual patient groups is of paramount importance in terms of selection of appropriate therapeutic options, risk communication to patients and families, and allocating resource through optimum triage. This has become even more necessary in the context of the current COVID-19 pandemic. Widening the spectrum of predictor variables by including radiological parameters alongside the usually utilized demographic, clinical and biochemical ones can facilitate building a comprehensive prediction model. Automation has the potential to build such models with applications to time-critical environments so that a clinician will be able to utilize the model outcomes in real-time decision making at bedside. We show that amalgamation of computed tomogram (CT) data with clinical parameters (CP) in generating a Machine Learning model from 302 COVID-19 patients presenting to an acute care hospital in India could prognosticate the need for invasive mechanical ventilation. Models developed from CP alone, CP and radiologist derived CT severity score and CP with automated lesion-to-lung ratio had AUC of 0.87 (95% CI 0.85–0.88), 0.89 (95% CI 0.87–0.91), and 0.91 (95% CI 0.89–0.93), respectively. We show that an operating point on the ROC can be chosen to aid clinicians in risk characterization according to the resource availability and ethical considerations. This approach can be deployed in more general settings, with appropriate calibrations, to predict outcomes of severe COVID-19 patients effectively.

Survey of Supervised Learning for Medical Image Processing

Medical image interpretation is an essential task for the correct diagnosis of many diseases. Pathologists, radiologists, physicians, and researchers rely heavily on medical images to perform diagnoses and develop new treatments. However, manual medical image analysis is tedious and time consuming, making it necessary to identify accurate automated methods. Deep learning—especially supervised deep learning—shows impressive performance in the classification, detection, and segmentation of medical images and has proven comparable in ability to humans. This survey aims to help researchers and practitioners of medical image analysis understand the key concepts and algorithms of supervised learning techniques. Specifically, this survey explains the performance metrics of supervised learning methods; summarizes the available medical datasets; studies the state-of-the-art supervised learning architectures for medical imaging processing, including convolutional neural networks (CNNs) and their corresponding algorithms, region-based CNNs and their variants, fully convolutional networks (FCN) and U-Net architecture; and discusses the trends and challenges in the application of supervised learning methods to medical image analysis. Supervised learning requires large labeled datasets to learn and achieve good performance, and data augmentation, transfer learning, and dropout techniques have widely been employed in medical image processing to overcome the lack of such datasets.

Root-knot nematodes (Meloidogyne spp.) a threat to agriculture in Mexico: biology, current control strategies, and perspectives

Root-knot nematodes (RKN) are sedentary parasites of the roots of plants and are considered some of the most damaging pests in agriculture. Since RKN target the root vascular system, they provoke host nutrient deprivation and defective water transport, causing above-ground symptoms of growth stunting, wilting, chlorosis, and reduced crop yields. In Mexico RKN infestations are primarily dealt with by treating with synthetic chemically based nematicides that are preferred by farmers over available bioproducts. However, due to environmental and human health concerns chemical control is increasingly restricted. Biological control of RKNs can help reduce the use of chemical nematicides as it is achieved with antagonistic organisms, mainly bacteria, fungi, other nematodes, or consortia of diverse microorganisms, which control nematodes directly by predation and parasitism at different stages: eggs, juveniles, or adults; or indirectly by the action of toxic diffusible inhibitory metabolites. The need to increase agricultural production and reduce negative environmental impact creates an opportunity for optimizing biological control agents to suppress nematode populations, but this endeavour remains challenging as researchers around the world try to understand diverse control mechanisms, nematode and microbe life cycles, ecology, metabolite production, predatory behaviours, molecular and biochemical interactions, in order to generate attractive products with the approval of local regulatory bodies. Here, we provide a brief review of the biology of the genus Meloidogyne, biological control strategies, and a comparison between chemical and bioproducts in the Mexican market, and guidelines emitted by national agencies to ensure safety and effectiveness of new developments.

Evaluation of AI-Based Segmentation Tools for COVID-19 Lung Lesions on Conventional and Ultra-low Dose CT Scans

A reliable diagnosis and accurate monitoring are pivotal steps for treatment and prevention of COVID-19. Chest computed tomography (CT) has been considered a crucial diagnostic imaging technique for the injury assessment of the viral pneumonia. Furthermore, the automatization of the segmentation methods for lung alterations helps to speed up the diagnosis and lighten radiologists' workload. Considering the assiduous pathology monitoring, ultra-low dose (ULD) chest CT protocols have been implemented to drastically reduce the radiation burden. Unfortunately, the available AI technologies have not been trained on ULD-CT data and validated and their applicability deserves careful evaluation. Therefore, this work aims to compare the results of available AI tools (BCUnet, CORADS AI, NVIDIA CLARA Train SDK and CT Pneumonia Analysis) on a dataset of 73 CT examinations acquired both with conventional dose (CD) and ULD protocols. COVID-19 volume percentage, resulting from each tool, was statistically compared. This study demonstrated high comparability of the results on CD-CT and ULD-CT data among the four AI tools, with high correlation between the results obtained on both protocols (R > .68, P < .001, for all AI tools).

Exploiting Shared Knowledge From Non-COVID Lesions for Annotation-Efficient COVID-19 CT Lung Infection Segmentation

The novel Coronavirus disease (COVID-19) is a highly contagious virus and has spread all over the world, posing an extremely serious threat to all countries. Automatic lung infection segmentation from computed tomography (CT) plays an important role in the quantitative analysis of COVID-19. However, the major challenge lies in the inadequacy of annotated COVID-19 datasets. Currently, there are several public non-COVID lung lesion segmentation datasets, providing the potential for generalizing useful information to the related COVID-19 segmentation task. In this paper, we propose a novel relation-driven collaborative learning model to exploit shared knowledge from non-COVID lesions for annotation-efficient COVID-19 CT lung infection segmentation. The model consists of a general encoder to capture general lung lesion features based on multiple non-COVID lesions, and a target encoder to focus on task-specific features based on COVID-19 infections. We develop a collaborative learning scheme to regularize feature-level relation consistency of given input and encourage the model to learn more general and discriminative representation of COVID-19 infections. Extensive experiments demonstrate that trained with limited COVID-19 data, exploiting shared knowledge from non-COVID lesions can further improve state-of-the-art performance with up to 3.0% in dice similarity coefficient and 4.2% in normalized surface dice. In addition, experimental results on large scale 2D dataset with CT slices show that our method significantly outperforms cutting-edge segmentation methods metrics. Our method promotes new insights into annotation-efficient deep learning and illustrates strong potential for real-world applications in the global fight against COVID-19 in the absence of sufficient high-quality annotations.

Customized Efficient Neural Network for COVID-19 Infected Region Identification in CT Images

BACKGROUND

In the field of biomedical imaging, radiomics is a promising approach that aims to provide quantitative features from images. It is highly dependent on accurate identification and delineation of the volume of interest to avoid mistakes in the implementation of the texture-based prediction model. In this context, we present a customized deep learning approach aimed at addressing the real-time, and fully automated identification and segmentation of COVID-19 infected regions in computed tomography images.

METHODS

In a previous study, we adopted ENET, originally used for image segmentation tasks in self-driving cars, for whole parenchyma segmentation in patients with idiopathic pulmonary fibrosis which has several similarities to COVID-19 disease. To automatically identify and segment COVID-19 infected areas, a customized ENET, namely C-ENET, was implemented and its performance compared to the original ENET and some state-of-the-art deep learning architectures.

RESULTS

The experimental results demonstrate the effectiveness of our approach. Considering the performance obtained in terms of similarity of the result of the segmentation to the gold standard (dice similarity coefficient ~75%), our proposed methodology can be used for the identification and delineation of COVID-19 infected areas without any supervision of a radiologist, in order to obtain a volume of interest independent from the user.

CONCLUSIONS

We demonstrated that the proposed customized deep learning model can be applied to rapidly identify, and segment COVID-19 infected regions to subsequently extract useful information for assessing disease severity through radiomics analyses.