Improving Computer-Aided Detection Using Convolutional Neural Networks and Random View Aggregation.

Automated computer-aided detection (CADe) has been an important tool in clinical practice and research. State-of-the-art methods often show high sensitivities at the cost of high false-positives (FP) per patient rates. We design a two-tiered coarse-to-fine cascade framework that first operates a candidate generation system at sensitivities  âˆ¼ 100% of but at high FP levels. By leveraging existing CADe systems, coordinates of regions or volumes of interest (ROI or VOI) are generated and function as input for a second tier, which is our focus in this study. In this second stage, we generate 2D (two-dimensional) or 2.5D views via sampling through scale transformations, random translations and rotations. These random views are used to train deep convolutional neural network (ConvNet) classifiers. In testing, the ConvNets assign class (e.g., lesion, pathology) probabilities for a new set of random views that are then averaged to compute a final per-candidate classification probability. This second tier behaves as a highly selective process to reject difficult false positives while preserving high sensitivities. The methods are evaluated on three data sets: 59 patients for sclerotic metastasis detection, 176 patients for lymph node detection, and 1,186 patients for colonic polyp detection. Experimental results show the ability of ConvNets to generalize well to different medical imaging CADe applications and scale elegantly to various data sets. Our proposed methods improve performance markedly in all cases. Sensitivities improved from 57% to 70%, 43% to 77%, and 58% to 75% at 3 FPs per patient for sclerotic metastases, lymph nodes and colonic polyps, respectively.

Open-Source Radiation Exposure Extraction Engine (RE3) with Patient-Specific Outlier Detection.

We present an open-source, picture archiving and communication system (PACS)-integrated radiation exposure extraction engine (RE3) that provides study-, series-, and slice-specific data for automated monitoring of computed tomography (CT) radiation exposure. RE3 was built using open-source components and seamlessly integrates with the PACS. RE3 calculations of dose length product (DLP) from the Digital imaging and communications in medicine (DICOM) headers showed high agreement (R (2) = 0.99) with the vendor dose pages. For study-specific outlier detection, RE3 constructs robust, automatically updating multivariable regression models to predict DLP in the context of patient gender and age, scan length, water-equivalent diameter (D w), and scanned body volume (SBV). As proof of concept, the model was trained on 811 CT chest, abdomen + pelvis (CAP) exams and 29 outliers were detected. The continuous variables used in the outlier detection model were scan length (R (2) = 0.45), D w (R (2) = 0.70), SBV (R (2) = 0.80), and age (R (2) = 0.01). The categorical variables were gender (male average 1182.7 ± 26.3 and female 1047.1 ± 26.9 mGy cm) and pediatric status (pediatric average 710.7 ± 73.6 mGy cm and adult 1134.5 ± 19.3 mGy cm).

Reliability of negative BOLD in ipsilateral sensorimotor areas during unimanual task activity.

Research using functional magnetic resonance imaging has for numerous years now reported the existence of a negative blood oxygenation level dependent (BOLD) response. Based on accumulating evidence, this negative BOLD signal appears to represent an active inhibition of cortical areas in which it is found during task activity. This particularly important with respect to motor function given that it is fairly well-established that, in younger adults, the ipsilateral sensorimotor cortex exhibits negative BOLD during unimanual movements in fMRI. This interhemispheric suppression of cortical activity may have useful implications for our understanding of both basic motor function and rehabilitation of injury or disease. However, to date, we are aware of no study that has tested the reliability of evoked negative BOLD in ipsilateral sensorimotor cortex in individuals across sessions. The current study employs a unimanual finger opposition task previously shown to evoke negative BOLD in ipsilateral sensorimotor cortex across three sessions. Reliability metrics across sessions indicates that both the magnitude and location of ipsilateral sensorimotor negative BOLD response is relatively stable over each of the three sessions. Moreover, the volume of negative BOLD in ipsilateral cortex was highly correlated with volume of positive BOLD activity in the contralateral primary motor cortex. These findings show that the negative BOLD signal can be reliably evoked in unimanual task paradigms, and that the signal dynamic could represent an active suppression of the ipsilateral sensorimotor cortex originating from the contralateral motor areas.

A new 2.5D representation for lymph node detection using random sets of deep convolutional neural network observations.

Automated Lymph Node (LN) detection is an important clinical diagnostic task but very challenging due to the low contrast of surrounding structures in Computed Tomography (CT) and to their varying sizes, poses, shapes and sparsely distributed locations. State-of-the-art studies show the performance range of 52.9% sensitivity at 3.1 false-positives per volume (FP/vol.), or 60.9% at 6.1 FP/vol. for mediastinal LN, by one-shot boosting on 3D HAAR features. In this paper, we first operate a preliminary candidate generation stage, towards -100% sensitivity at the cost of high FP levels (-40 per patient), to harvest volumes of interest (VOI). Our 2.5D approach consequently decomposes any 3D VOI by resampling 2D reformatted orthogonal views N times, via scale, random translations, and rotations with respect to the VOI centroid coordinates. These random views are then used to train a deep Convolutional Neural Network (CNN) classifier. In testing, the CNN is employed to assign LN probabilities for all N random views that can be simply averaged (as a set) to compute the final classification probability per VOI. We validate the approach on two datasets: 90 CT volumes with 388 mediastinal LNs and 86 patients with 595 abdominal LNs. We achieve sensitivities of 70%/83% at 3 FP/vol. and 84%/90% at 6 FP/vol. in mediastinum and abdomen respectively, which drastically improves over the previous state-of-the-art work.

2D view aggregation for lymph node detection using a shallow hierarchy of linear classifiers.

Enlarged lymph nodes (LNs) can provide important information for cancer diagnosis, staging, and measuring treatment reactions, making automated detection a highly sought goal. In this paper, we propose a new algorithm representation of decomposing the LN detection problem into a set of 2D object detection subtasks on sampled CT slices, largely alleviating the curse of dimensionality issue. Our 2D detection can be effectively formulated as linear classification on a single image feature type of Histogram of Oriented Gradients (HOG), covering a moderate field-of-view of 45 by 45 voxels. We exploit both max-pooling and sparse linear fusion schemes to aggregate these 2D detection scores for the final 3D LN detection. In this manner, detection is more tractable and does not need to perform perfectly at instance level (as weak hypotheses) since our aggregation process will robustly harness collective information for LN detection. Two datasets (90 patients with 389 mediastinal LNs and 86 patients with 595 abdominal LNs) are used for validation. Cross-validation demonstrates 78.0% sensitivity at 6 false positives/volume (FP/vol.) (86.1% at 10 FP/vol.) and 73.1% sensitivity at 6 FP/vol. (87.2% at 10 FP/vol.), for the mediastinal and abdominal datasets respectively. Our results compare favorably to previous state-of-the-art methods.