Detection and severity quantification of pulmonary embolism with 3D CT data using an automated deep learning-based artificial solution

PURPOSE

The purpose of this study was to propose a deep learning-based approach to detect pulmonary embolism and quantify its severity using the Qanadli score and the right-to-left ventricle diameter (RV/LV) ratio on three-dimensional (3D) computed tomography pulmonary angiography (CTPA) examinations with limited annotations.

MATERIALS AND METHODS

Using a database of 3D CTPA examinations of 1268 patients with image-level annotations, and two other public datasets of CTPA examinations from 91 (CAD-PE) and 35 (FUME-PE) patients with pixel-level annotations, a pipeline consisting of: (i), detecting blood clots; (ii), performing PE-positive versus negative classification; (iii), estimating the Qanadli score; and (iv), predicting RV/LV diameter ratio was followed. The method was evaluated on a test set including 378 patients. The performance of PE classification and severity quantification was quantitatively assessed using an area under the curve (AUC) analysis for PE classification and a coefficient of determination (R²) for the Qanadli score and the RV/LV diameter ratio.

RESULTS

Quantitative evaluation led to an overall AUC of 0.870 (95% confidence interval [CI]: 0.850-0.900) for PE classification task on the training set and an AUC of 0.852 (95% CI: 0.810-0.890) on the test set. Regression analysis yielded R² value of 0.717 (95% CI: 0.668-0.760) and of 0.723 (95% CI: 0.668-0.766) for the Qanadli score and the RV/LV diameter ratio estimation, respectively on the test set.

CONCLUSION

This study shows the feasibility of utilizing AI-based assistance tools in detecting blood clots and estimating PE severity scores with 3D CTPA examinations. This is achieved by leveraging blood clots and cardiac segmentations. Further studies are needed to assess the effectiveness of these tools in clinical practice.

Comparison of the performance of conventional and spectral-based tagged stool cleansing algorithms at CT colonography

OBJECTIVES

To compare the performance of conventional versus spectral-based electronic stool cleansing for iodine-tagged CT colonography (CTC) using a dual-layer spectral detector scanner.

METHODS

We retrospectively evaluated iodine contrast stool-tagged CTC scans of 30 consecutive patients (mean age: 69 ± 8 years) undergoing colorectal cancer screening obtained on a dual-layer spectral detector CT scanner. One reader identified locations of electronic cleansing artifacts (n = 229) on conventional and spectral cleansed images. Three additional independent readers evaluated these locations using a conventional cleansing algorithm (Intellispace Portal) and two experimental spectral cleansing algorithms (i.e., fully transparent and translucent tagged stool). For each cleansed image set, readers recorded the severity of over- and under-cleansing artifacts on a 5-point Likert scale (0 = none to 4 = severe) and readability compared to uncleansed images. Wilcoxon's signed-rank tests were used to assess artifact severity, type, and readability (worse, unchanged, or better).

RESULTS

Compared with conventional cleansing (66% score ≥ 2), the severity of overall cleansing artifacts was lower in transparent (60% score ≥ 2, p = 0.011) and translucent (50% score ≥ 2, p < 0.001) spectral cleansing. Under-cleansing artifact severity was lower in transparent (49% score ≥ 2, p < 0.001) and translucent (39% score ≥ 2, p < 0.001) spectral cleansing compared with conventional cleansing (60% score ≥ 2). Over-cleansing artifact severity was worse in transparent (17% score ≥ 2, p < 0.001) and translucent (14% score ≥ 2, p = 0.023) spectral cleansing compared with conventional cleansing (9% score ≥ 2). Overall readability was significantly improved in transparent (p < 0.001) and translucent (p < 0.001) spectral cleansing compared with conventional cleansing.

CONCLUSIONS

Spectral cleansing provided more robust electronic stool cleansing of iodine-tagged stool at CTC than conventional cleansing.

KEY POINTS

• Spectral-based electronic cleansing of tagged stool at CT colonography provides higher quality images with less perception of artifacts than does conventional cleansing. • Spectral-based electronic cleansing could potentially advance minimally cathartic approach for CT colonography. Further clinical trials are warranted.

Towards radiologist-level cancer risk assessment in CT lung screening using deep learning

PURPOSE

Lung cancer is the leading cause of cancer mortality in the US, responsible for more deaths than breast, prostate, colon and pancreas cancer combined and large population studies have indicated that low-dose computed tomography (CT) screening of the chest can significantly reduce this death rate. Recently, the usefulness of Deep Learning (DL) models for lung cancer risk assessment has been demonstrated. However, in many cases model performances are evaluated on small/medium size test sets, thus not providing strong model generalization and stability guarantees which are necessary for clinical adoption. In this work, our goal is to contribute towards clinical adoption by investigating a deep learning framework on larger and heterogeneous datasets while also comparing to state-of-the-art models.

METHODS

Three low-dose CT lung cancer screening datasets were used: National Lung Screening Trial (NLST, n = 3410), Lahey Hospital and Medical Center (LHMC, n = 3154) data, Kaggle competition data (from both stages, n = 1397 + 505) and the University of Chicago data (UCM, a subset of NLST, annotated by radiologists, n = 132). At the first stage, our framework employs a nodule detector; while in the second stage, we use both the image context around the nodules and nodule features as inputs to a neural network that estimates the malignancy risk for the entire CT scan. We trained our algorithm on a part of the NLST dataset, and validated it on the other datasets. Special care was taken to ensure there was no patient overlap between the train and validation sets.

RESULTS AND CONCLUSIONS

The proposed deep learning model is shown to: (a) generalize well across all three data sets, achieving AUC between 86% to 94%, with our external test-set (LHMC) being at least twice as large compared to other works; (b) have better performance than the widely accepted PanCan Risk Model, achieving 6 and 9% better AUC score in our two test sets; (c) have improved performance compared to the state-of-the-art represented by the winners of the Kaggle Data Science Bowl 2017 competition on lung cancer screening; (d) have comparable performance to radiologists in estimating cancer risk at a patient level.

A radial structure tensor and its use for shape-encoding medical visualization of tubular and nodular structures

The concept of curvature and shape-based rendering is beneficial for medical visualization of CT and MRI image volumes. Color-coding of local shape properties derived from the analysis of the local Hessian can implicitly highlight tubular structures such as vessels and airways, and guide the attention to potentially malignant nodular structures such as tumors, enlarged lymph nodes, or aneurysms. For some clinical applications, however, the evaluation of the Hessian matrix does not yield satisfactory renderings, in particular for hollow structures such as airways, and densely embedded low contrast structures such as lymph nodes. Therefore, as a complement to Hessian-based shape-encoding rendering, this paper introduces a combination of an efficient sparse radial gradient sampling scheme in conjunction with a novel representation, the radial structure tensor (RST). As an extension of the well-known general structure tensor, which has only positive definite eigenvalues, the radial structure tensor correlates position and direction of the gradient vectors in a local neighborhood, and thus yields positive and negative eigenvalues which can be used to discriminate between different shapes. As Hessian-based rendering, also RST-based rendering is ideally suited for GPU implementation. Feedback from clinicians indicates that shape-encoding rendering can be an effective image navigation tool to aid diagnostic workflow and quality assurance.

Extraction of airways from CT (EXACT'09)

This paper describes a framework for establishing a reference airway tree segmentation, which was used to quantitatively evaluate fifteen different airway tree extraction algorithms in a standardized manner. Because of the sheer difficulty involved in manually constructing a complete reference standard from scratch, we propose to construct the reference using results from all algorithms that are to be evaluated. We start by subdividing each segmented airway tree into its individual branch segments. Each branch segment is then visually scored by trained observers to determine whether or not it is a correctly segmented part of the airway tree. Finally, the reference airway trees are constructed by taking the union of all correctly extracted branch segments. Fifteen airway tree extraction algorithms from different research groups are evaluated on a diverse set of twenty chest computed tomography (CT) scans of subjects ranging from healthy volunteers to patients with severe pathologies, scanned at different sites, with different CT scanner brands, models, and scanning protocols. Three performance measures covering different aspects of segmentation quality were computed for all participating algorithms. Results from the evaluation showed that no single algorithm could extract more than an average of 74% of the total length of all branches in the reference standard, indicating substantial differences between the algorithms. A fusion scheme that obtained superior results is presented, demonstrating that there is complementary information provided by the different algorithms and there is still room for further improvements in airway segmentation algorithms.

Aspects of computer-aided detection (CAD) and volumetry of pulmonary nodules using multislice CT

With the superb spatial resolution of modern multislice CT scanners and their ability to complete a thoracic scan within one breath-hold, software algorithms for computer-aided detection (CAD) of pulmonary nodules are now reaching high sensitivity levels at moderate false positive rates. A number of pilot studies have shown that CAD modules can successfully find overlooked pulmonary nodules and serve as a powerful tool for diagnostic quality assurance. Equally important are tools for fast and accurate three-dimensional volume measurement of detected nodules. These allow monitoring of nodule growth between follow-up examinations for differential diagnosis and response to oncological therapy. Owing to decreasing partial volume effect, nodule volumetry is more accurate with high resolution CT data. Several studies have shown the feasibility and robustness of automated matching of corresponding nodule pairs between follow-up examinations. Fast and automated growth rate monitoring with only few reader interactions also adds to diagnostic quality assurance.

Multiscale contrast enhancement for radiographies: Laplacian Pyramid versus fast wavelet transform

Contrast enhancement of radiographies based on a multiscale decomposition of the images recently has proven to be a far more versatile and efficient method than regular unsharp-masking techniques, while containing these as a subset. In this paper, we compare the performance of two multiscale-methods, namely the Laplacian Pyramid and the fast wavelet transform (FWT). We find that enhancement based on the FWT suffers from one serious drawback-the introduction of visible artifacts when large structures are enhanced strongly. By contrast, the Laplacian Pyramid allows a smooth enhancement of large structures, such that visible artifacts can be avoided. Only for the enhancement of very small details, for denoising applications or compression of images, the FWT may have some advantages over the Laplacian Pyramid.