ABSTRACT
Predictive artificial intelligence (AI) systems based on deep learning have been shown to achieve expert-level identification of diseases in multiple medical imaging settings, but can make errors in cases accurately diagnosed by clinicians and vice versa. We developed Complementarity-Driven Deferral to Clinical Workflow (CoDoC), a system that can learn to decide between the opinion of a predictive AI model and a clinical workflow. CoDoC enhances accuracy relative to clinician-only or AI-only baselines in clinical workflows that screen for breast cancer or tuberculosis (TB). For breast cancer screening, compared to double reading with arbitration in a screening program in the UK, CoDoC reduced false positives by 25% at the same false-negative rate, while achieving a 66% reduction in clinician workload. For TB triaging, compared to standalone AI and clinical workflows, CoDoC achieved a 5-15% reduction in false positives at the same false-negative rate for three of five commercially available predictive AI systems. To facilitate the deployment of CoDoC in novel futuristic clinical settings, we present results showing that CoDoC's performance gains are sustained across several axes of variation (imaging modality, clinical setting and predictive AI system) and discuss the limitations of our evaluation and where further validation would be needed. We provide an open-source implementation to encourage further research and application.
Subject(s)
Artificial Intelligence , Triage , Reproducibility of Results , Workflow , HumansABSTRACT
The microscopic assessment of tissue samples is instrumental for the diagnosis and staging of cancer, and thus guides therapy. However, these assessments demonstrate considerable variability and many regions of the world lack access to trained pathologists. Though artificial intelligence (AI) promises to improve the access and quality of healthcare, the costs of image digitization in pathology and difficulties in deploying AI solutions remain as barriers to real-world use. Here we propose a cost-effective solution: the augmented reality microscope (ARM). The ARM overlays AI-based information onto the current view of the sample in real time, enabling seamless integration of AI into routine workflows. We demonstrate the utility of ARM in the detection of metastatic breast cancer and the identification of prostate cancer, with latency compatible with real-time use. We anticipate that the ARM will remove barriers towards the use of AI designed to improve the accuracy and efficiency of cancer diagnosis.
Subject(s)
Artificial Intelligence , Breast Neoplasms/diagnosis , Neoplasms/diagnosis , Prostatic Neoplasms/diagnosis , Breast Neoplasms/pathology , Female , Humans , Male , Microscopy/methods , Neoplasm Staging , Neoplasms/pathology , Prostatic Neoplasms/pathologyABSTRACT
CONTEXT.: Nodal metastasis of a primary tumor influences therapy decisions for a variety of cancers. Histologic identification of tumor cells in lymph nodes can be laborious and error-prone, especially for small tumor foci. OBJECTIVE.: To evaluate the application and clinical implementation of a state-of-the-art deep learning-based artificial intelligence algorithm (LYmph Node Assistant or LYNA) for detection of metastatic breast cancer in sentinel lymph node biopsies. DESIGN.: Whole slide images were obtained from hematoxylin-eosin-stained lymph nodes from 399 patients (publicly available Camelyon16 challenge dataset). LYNA was developed by using 270 slides and evaluated on the remaining 129 slides. We compared the findings to those obtained from an independent laboratory (108 slides from 20 patients/86 blocks) using a different scanner to measure reproducibility. RESULTS.: LYNA achieved a slide-level area under the receiver operating characteristic (AUC) of 99% and a tumor-level sensitivity of 91% at 1 false positive per patient on the Camelyon16 evaluation dataset. We also identified 2 "normal" slides that contained micrometastases. When applied to our second dataset, LYNA achieved an AUC of 99.6%. LYNA was not affected by common histology artifacts such as overfixation, poor staining, and air bubbles. CONCLUSIONS.: Artificial intelligence algorithms can exhaustively evaluate every tissue patch on a slide, achieving higher tumor-level sensitivity than, and comparable slide-level performance to, pathologists. These techniques may improve the pathologist's productivity and reduce the number of false negatives associated with morphologic detection of tumor cells. We provide a framework to aid practicing pathologists in assessing such algorithms for adoption into their workflow (akin to how a pathologist assesses immunohistochemistry results).
Subject(s)
Breast Neoplasms/pathology , Deep Learning , Image Interpretation, Computer-Assisted/methods , Lymphatic Metastasis/diagnosis , Pathology, Clinical/methods , Female , Humans , Pathologists , Sentinel Lymph Node BiopsyABSTRACT
BACKGROUND: Digital pathology enables remote access or consults and powerful image analysis algorithms. However, the slide digitization process can create artifacts such as out-of-focus (OOF). OOF is often only detected on careful review, potentially causing rescanning, and workflow delays. Although scan time operator screening for whole-slide OOF is feasible, manual screening for OOF affecting only parts of a slide is impractical. METHODS: We developed a convolutional neural network (ConvFocus) to exhaustively localize and quantify the severity of OOF regions on digitized slides. ConvFocus was developed using our refined semi-synthetic OOF data generation process and evaluated using seven slides spanning three different tissue and three different stain types, each of which were digitized using two different whole-slide scanner models ConvFocus's predictions were compared with pathologist-annotated focus quality grades across 514 distinct regions representing 37,700 35 µm × 35 µm image patches, and 21 digitized "z-stack" WSIs that contain known OOF patterns. RESULTS: When compared to pathologist-graded focus quality, ConvFocus achieved Spearman rank coefficients of 0.81 and 0.94 on two scanners and reproduced the expected OOF patterns from z-stack scanning. We also evaluated the impact of OOF on the accuracy of a state-of-the-art metastatic breast cancer detector and saw a consistent decrease in performance with increasing OOF. CONCLUSIONS: Comprehensive whole-slide OOF categorization could enable rescans before pathologist review, potentially reducing the impact of digitization focus issues on the clinical workflow. We show that the algorithm trained on our semi-synthetic OOF data generalizes well to real OOF regions across tissue types, stains, and scanners. Finally, quantitative OOF maps can flag regions that might otherwise be misclassified by image analysis algorithms, preventing OOF-induced errors.
ABSTRACT
The diversity in appearance of diseased lung tissue makes automatic segmentation of lungs from CT with severe pathologies challenging. To overcome this challenge, we rely on contextual constraints from neighboring anatomies to detect and segment lung tissue across a variety of pathologies. We propose an algorithm that combines statistical learning with these anatomical constraints to seek a segmentation of the lung consistent with adjacent structures, such as the heart, liver, spleen, and ribs. We demonstrate that our algorithm reduces the number of failed detections and increases the accuracy of the segmentation on unseen test cases with severe pathologies.
Subject(s)
Anatomic Landmarks/diagnostic imaging , Imaging, Three-Dimensional/methods , Lung Diseases/diagnostic imaging , Lung/diagnostic imaging , Pattern Recognition, Automated/methods , Radiographic Image Interpretation, Computer-Assisted/methods , Tomography, X-Ray Computed/methods , Algorithms , Humans , Radiographic Image Enhancement/methods , Reproducibility of Results , Sensitivity and SpecificityABSTRACT
The automatic delineation of the boundaries of organs and other anatomical structures is a key component of many medical image processing systems. In this paper we present a generic learning approach based on a novel space of segmentation features, which can be trained to predict the overlap error and Dice coefficient of an arbitrary organ segmentation without knowing the ground truth delineation. We show the regressor to be much stronger a predictor of these error metrics than the responses of probabilistic boosting classifiers trained on the segmentation boundary. The presented approach not only allows us to build reliable confidence measures and fidelity checks, but also to rank several segmentation hypotheses against each other during online usage of the segmentation algorithm in clinical practice.
Subject(s)
Lung/pathology , Algorithms , Computer Simulation , False Positive Reactions , Humans , Image Processing, Computer-Assisted , Models, Statistical , Pattern Recognition, Automated/methods , Probability , Reproducibility of ResultsABSTRACT
In this paper, we present a novel method by incorporating information theory into the learning-based approach for automatic and accurate pelvic organ segmentation (including the prostate, bladder and rectum). We target 3D CT volumes that are generated using different scanning protocols (e.g., contrast and non-contrast, with and without implant in the prostate, various resolution and position), and the volumes come from largely diverse sources (e.g., diseased in different organs). Three key ingredients are combined to solve this challenging segmentation problem. First, marginal space learning (MSL) is applied to efficiently and effectively localize the multiple organs in the largely diverse CT volumes. Second, learning techniques, steerable features, are applied for robust boundary detection. This enables handling of highly heterogeneous texture pattern. Third, a novel information theoretic scheme is incorporated into the boundary inference process. The incorporation of the Jensen-Shannon divergence further drives the mesh to the best fit of the image, thus improves the segmentation performance. The proposed approach is tested on a challenging dataset containing 188 volumes from diverse sources. Our approach not only produces excellent segmentation accuracy, but also runs about eighty times faster than previous state-of-the-art solutions. The proposed method can be applied to CT images to provide visual guidance to physicians during the computer-aided diagnosis, treatment planning and image-guided radiotherapy to treat cancers in pelvic region.
Subject(s)
Algorithms , Artificial Intelligence , Imaging, Three-Dimensional/methods , Pattern Recognition, Automated/methods , Radiographic Image Interpretation, Computer-Assisted/methods , Tomography, X-Ray Computed/methods , Viscera/diagnostic imaging , Humans , Radiographic Image Enhancement/methods , Reproducibility of Results , Sensitivity and SpecificityABSTRACT
We present a novel generic segmentation system for the fully automatic multi-organ segmentation from CT medical images. Thereby we combine the advantages of learning-based approaches on point cloud-based shape representation, such a speed, robustness, point correspondences, with those of PDE-optimization-based level set approaches, such as high accuracy and the straightforward prevention of segment overlaps. In a benchmark on 10-100 annotated datasets for the liver, the lungs, and the kidneys we show that the proposed system yields segmentation accuracies of 1.17-2.89 mm average surface errors. Thereby the level set segmentation (which is initialized by the learning-based segmentations) contributes with an 20%-40% increase in accuracy.
Subject(s)
Imaging, Three-Dimensional/methods , Pattern Recognition, Automated/methods , Tomography, X-Ray Computed/methods , Algorithms , Artificial Intelligence , Databases, Factual , Humans , Kidney/pathology , Learning , Liver/pathology , Lung/pathology , Models, Anatomic , Models, Statistical , Principal Component Analysis , Reproducibility of Results , SoftwareABSTRACT
Simple algorithms for segmenting healthy lung parenchyma in CT are unable to deal with high density tissue common in pulmonary diseases. To overcome this problem, we propose a multi-stage learning-based approach that combines anatomical information to predict an initialization of a statistical shape model of the lungs. The initialization first detects the carina of the trachea, and uses this to detect a set of automatically selected stable landmarks on regions near the lung (e.g., ribs, spine). These landmarks are used to align the shape model, which is then refined through boundary detection to obtain fine-grained segmentation. Robustness is obtained through hierarchical use of discriminative classifiers that are trained on a range of manually annotated data of diseased and healthy lungs. We demonstrate fast detection (35s per volume on average) and segmentation of 2 mm accuracy on challenging data.
Subject(s)
Cone-Beam Computed Tomography/methods , Lung Neoplasms/diagnostic imaging , Lung Neoplasms/diagnosis , Lung/diagnostic imaging , Algorithms , Diagnostic Imaging/methods , Humans , Learning , Lung/pathology , Lung Neoplasms/pathology , Models, Statistical , Pattern Recognition, Automated/methods , Radiographic Image Interpretation, Computer-Assisted/methods , SoftwareABSTRACT
Organ segmentation is a challenging problem on which recent progress has been made by incorporation of local image statistics that model the heterogeneity of structures outside of an organ of interest. However, most of these methods rely on landmark based segmentation, which has certain drawbacks. We propose to perform organ segmentation with a novel level set algorithm that incorporates local statistics via a highly efficient point tracking mechanism. Specifically, we compile statistics on these tracked points to allow for a local intensity profile outside of the contour and to allow for a local surface area penalty, which allows us to capture fine detail where it is expected. The local intensity and curvature models are learned through landmarks automatically embedded on the surface of the training shapes. We use Parzen windows to model the internal organ intensities as one distribution since this is sufficient for most organs. In addition, since the method is based on level sets, we are able to naturally take advantage of recent work on global shape regularization. We show state-of-the-art results on the challenging problems of liver and kidney segmentation.
Subject(s)
Algorithms , Kidney/diagnostic imaging , Liver/diagnostic imaging , Pattern Recognition, Automated/methods , Radiographic Image Interpretation, Computer-Assisted/methods , Subtraction Technique , Tomography, X-Ray Computed/methods , Humans , Radiographic Image Enhancement/methods , Sensitivity and SpecificityABSTRACT
We present a new segmentation approach for the myocardium in gated and non-gated perfusion SPECT images. To this end, we represent the epi- and endocardium by separate signed distance functions and couple them by a soft constraint to give explicit control over the wall thickness. By an explicit modeling of the basal plane, the volume of the blood pool as well as the myocardium are determinable. Furthermore, prior shape information is incorporated by applying a kernel density estimation on a number of expert segmentations in a low-dimensional PCA subspace. Thereby, information along the time axis is fully taken into account by employing 4-dimensional embedding functions.
Subject(s)
Artificial Intelligence , Gated Blood-Pool Imaging/methods , Heart Ventricles/diagnostic imaging , Image Interpretation, Computer-Assisted/methods , Pattern Recognition, Automated/methods , Tomography, Emission-Computed, Single-Photon/methods , Ventricular Dysfunction, Left/diagnostic imaging , Algorithms , Image Enhancement/methods , Reproducibility of Results , Sensitivity and SpecificityABSTRACT
We develop a 4D (3D plus time) statistical shape model for implicit level set based shape representations. To this end, we represent hand segmented training sequences of the left ventricle by respective 4-dimensional embedding functions and approximate these by a principal component analysis. In contrast to recent 4D models on explicit shape representations, the implicit shape model developed in this work does not require the computation of point correspondences which is known to be quite challenging, especially in higher dimensions. Experimental results on the segmentation of SPECT sequences of the left myocardium confirm that the 4D shape model outperforms respective 3D models, because it takes into account a statistical model of the temporal shape evolution.
Subject(s)
Heart Ventricles/diagnostic imaging , Image Enhancement/methods , Image Interpretation, Computer-Assisted/methods , Imaging, Three-Dimensional/methods , Pattern Recognition, Automated/methods , Tomography, Emission-Computed, Single-Photon/methods , Ventricular Dysfunction, Left/diagnostic imaging , Algorithms , Artificial Intelligence , Computer Simulation , Electrocardiography/methods , Humans , Models, Cardiovascular , Reproducibility of Results , Sensitivity and Specificity , Subtraction Technique , Time FactorsABSTRACT
We present an approach to parallel variational optical-flow computation by using an arbitrary partition of the image plane and iteratively solving related local variational problems associated with each subdomain. The approach is particularly suited for implementations on PC clusters because interprocess communication is minimized by restricting the exchange of data to a lower dimensional interface. Our mathematical formulation supports various generalizations to linear/nonlinear convex variational approaches, three-dimensional image sequences, spatiotemporal regularization, and unstructured geometries and triangulations. Results concerning the effects of interface preconditioning, as well as runtime and communication volume measurements on a PC cluster, are presented. Our approach provides a major step toward real-time two-dimensional image processing using off-the-shelf PC hardware and facilitates the efficient application of variational approaches to large-scale image processing problems.
Subject(s)
Algorithms , Image Enhancement/methods , Image Interpretation, Computer-Assisted/methods , Information Storage and Retrieval/methods , Pattern Recognition, Automated/methods , Imaging, Three-Dimensional/methods , Numerical Analysis, Computer-Assisted , Signal Processing, Computer-Assisted , Subtraction TechniqueABSTRACT
This paper investigates the usefulness of bidirectional multigrid methods for variational optical flow computations. Although these numerical schemes are among the fastest methods for solving equation systems, they are rarely applied in the field of computer vision. We demonstrate how to employ those numerical methods for the treatment of variational optical flow formulations and show that the efficiency of this approach even allows for real-time performance on standard PCs. As a representative for variational optic flow methods, we consider the recently introduced combined local-global method. It can be considered as a noise-robust generalization of the Horn and Schunck technique. We present a decoupled, as well as a coupled, version of the classical Gauss-Seidel solver, and we develop several multgrid implementations based on a discretization coarse grid approximation. In contrast, with standard bidirectional multigrid algorithms, we take advantage of intergrid transfer operators that allow for nondyadic grid hierarchies. As a consequence, no restrictions concerning the image size or the number of traversed levels have to be imposed. In the experimental section, we juxtapose the developed multigrid schemes and demonstrate their superior performance when compared to unidirectional multgrid methods and nonhierachical solvers. For the well-known 316 x 252 Yosemite sequence, we succeeded in computing the complete set of dense flow fields in three quarters of a second on a 3.06-GHz Pentium4 PC. This corresponds to a frame rate of 18 flow fields per second which outperforms the widely-used Gauss-Seidel method by almost three orders of magnitude.