We propose a method for fast, accurate and robust localization of several organs in medical images. We generalize global-to-local cascades of regression forests [1] to multiple organs. A first regressor encodes global relationships between organs. Subsequent regressors refine the localization of each organ locally and independently for improved accuracy. We introduce confidence maps, which incorporate information about both the regression vote distribution and the organ shape through probabilistic atlases. They are used within the cascade itself, to better select the test voxels for the second set of regressors, and to provide richer information than the classical bounding boxes thanks to the shape prior. We demonstrate the robustness and accuracy of our approach through a quantitative evaluation on a large database of 130 CT volumes.
To develop a deep learning model for detecting brain abnormalities on MRI.
Materials and Methods:In this retrospective study, a deep learning approach using T2-weighted fluid attenuated inversion recovery (FLAIR) images was developed to classify brain MRI as "likely normal" or "likely abnormal." A convolutional neural network model was trained on a large heterogeneous dataset collected from two different continents and covering a broad panel of pathologies including neoplasms, hemorrhage, infarcts, and others. Three datasets were used. Dataset A consisted of 2839 patients, Dataset B consisted of 6442 patients, and Dataset C consisted of 1489 patients and was only used for testing. Dataset A and B were split into training, validation and test sets. A total of three models were trained: Model A (using only Dataset A), Model B (using only Dataset B), and Model A+B (using training datasets from A and B). All three models were tested on subsets from Dataset A, Dataset B and Dataset C separately. The evaluation was performed using annotations based on the images as well as labels based on the radiologic reports.
Liver segmentation in 3D CT images is a fundamental step for surgery planning and follow-up. Robustness, automation and speed are required to fulfill this task efficiently. We propose a fully-automatic workflow for liver segmentation built on state-of-the-art algorithmic components to meet these requirements. The liver is first localized using regression forests. A liver probability map is computed, followed by a global-to-local segmentation strategy using a template deformation framework. We evaluate our method on the SLIVER07 reference database and confirm its state-of-the-art results on a large, varied database of 268 CT volumes. This extensive validation demonstrates the robustness of our approach to variable fields of view, liver contrast, shape and pathologies. Our framework is an attractive tradeoff between robustness, accuracy (mean distance to ground truth of 1.7mm) and computational speed (46s). We also emphasize the genericity and relative simplicity of our framework, which requires very limited liver-specific tuning.
Non-contrast head CT (NCCT) is extremely insensitive for early (< 3–6 h) acute infarct identification. We developed a deep learning model that detects and delineates suspected early acute infarcts on NCCT, using diffusion MRI as ground truth (3566 NCCT/MRI training patient pairs). The model substantially outperformed 3 expert neuroradiologists on a test set of 150 CT scans of patients who were potential candidates for thrombectomy (60 stroke-negative, 90 stroke-positive middle cerebral artery territory only infarcts), with sensitivity 96% (specificity 72%) for the model versus 61–66% (specificity 90–92%) for the experts; model infarct volume estimates also strongly correlated with those of diffusion MRI (r2 > 0.98). When this 150 CT test set was expanded to include a total of 364 CT scans with a more heterogeneous distribution of infarct locations (94 stroke-negative, 270 stroke-positive mixed territory infarcts), model sensitivity was 97%, specificity 99%, for detection of infarcts larger than the 70 mL volume threshold used for patient selection in several major randomized controlled trials of thrombectomy treatment.
Stroke is a leading cause of death and disability. The ability to quickly identify the presence of acute infarct and quantify the volume on magnetic resonance imaging (MRI) has important treatment implications. We developed a machine learning model that used the apparent diffusion coefficient and diffusion weighted imaging series. It was trained on 6,657 MRI studies from Massachusetts General Hospital (MGH; Boston, USA). All studies were labelled positive or negative for infarct (classification annotation) with 377 having the region of interest outlined (segmentation annotation). The different annotation types facilitated training on more studies while not requiring the extensive time to manually segment every study. We initially validated the model on studies sequestered from the training set. We then tested the model on studies from three clinical scenarios: consecutive stroke team activations for 6-months at MGH, consecutive stroke team activations for 6-months at a hospital that did not provide training data (Brigham and Women’s Hospital [BWH]; Boston, USA), and an international site (Diagnósticos da América SA [DASA]; Brazil). The model results were compared to radiologist ground truth interpretations. The model performed better when trained on classification and segmentation annotations (area under the receiver operating curve [AUROC] 0.995 [95% CI 0.992–0.998] and median Dice coefficient for segmentation overlap of 0.797 [IQR 0.642–0.861]) compared to segmentation annotations alone (AUROC 0.982 [95% CI 0.972–0.990] and Dice coefficient 0.776 [IQR 0.584–0.857]). The model accurately identified infarcts for MGH stroke team activations (AUROC 0.964 [95% CI 0.943–0.982], 381 studies), BWH stroke team activations (AUROC 0.981 [95% CI 0.966–0.993], 247 studies), and at DASA (AUROC 0.998 [95% CI 0.993–1.000], 171 studies). The model accurately segmented infarcts with Pearson correlation comparing model output and ground truth volumes between 0.968 and 0.986 for the three scenarios. Acute infarct can be accurately detected and segmented on MRI in real-world clinical scenarios using a machine learning model.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.