Detection and diagnosis of colitis on computed tomography using deep convolutional neural networks.

PURPOSE: Colitis refers to inflammation of the inner lining of the colon that is frequently associated with infection and allergic reactions. In this paper, we propose deep convolutional neural networks methods for lesion-level colitis detection and a support vector machine (SVM) classifier for patient-level colitis diagnosis on routine abdominal CT scans. METHODS: The recently developed Faster Region-based Convolutional Neural Network (Faster RCNN) is utilized for lesion-level colitis detection. For each 2D slice, rectangular region proposals are generated by region proposal networks (RPN). Then, each region proposal is jointly classified and refined by a softmax classifier and bounding-box regressor. Two convolutional neural networks, eight layers of ZF net and 16 layers of VGG net are compared for colitis detection. Finally, for each patient, the detections on all 2D slices are collected and a SVM classifier is applied to develop a patient-level diagnosis. We trained and evaluated our method with 80 colitis patients and 80 normal cases using 4 × 4-fold cross validation. RESULTS: For lesion-level colitis detection, with ZF net, the mean of average precisions (mAP) were 48.7% and 50.9% for RCNN and Faster RCNN, respectively. The detection system achieved sensitivities of 51.4% and 54.0% at two false positives per patient for RCNN and Faster RCNN, respectively. With VGG net, Faster RCNN increased the mAP to 56.9% and increased the sensitivity to 58.4% at two false positive per patient. For patient-level colitis diagnosis, with ZF net, the average areas under the ROC curve (AUC) were 0.978 ± 0.009 and 0.984 ± 0.008 for RCNN and Faster RCNN method, respectively. The difference was not statistically significant with P = 0.18. At the optimal operating point, the RCNN method correctly identified 90.4% (72.3/80) of the colitis patients and 94.0% (75.2/80) of normal cases. The sensitivity improved to 91.6% (73.3/80) and the specificity improved to 95.0% (76.0/80) for the Faster RCNN method. With VGG net, Faster RCNN increased the AUC to 0.986 ± 0.007 and increased the diagnosis sensitivity to 93.7% (75.0/80) and specificity was unchanged at 95.0% (76.0/80). CONCLUSION: Colitis detection and diagnosis by deep convolutional neural networks is accurate and promising for future clinical application.

Sequential Monte Carlo tracking of the marginal artery by multiple cue fusion and random forest regression.

Given the potential importance of marginal artery localization in automated registration in computed tomography colonography (CTC), we have devised a semi-automated method of marginal vessel detection employing sequential Monte Carlo tracking (also known as particle filtering tracking) by multiple cue fusion based on intensity, vesselness, organ detection, and minimum spanning tree information for poorly enhanced vessel segments. We then employed a random forest algorithm for intelligent cue fusion and decision making which achieved high sensitivity and robustness. After applying a vessel pruning procedure to the tracking results, we achieved statistically significantly improved precision compared to a baseline Hessian detection method (2.7% versus 75.2%, p<0.001). This method also showed statistically significantly improved recall rate compared to a 2-cue baseline method using fewer vessel cues (30.7% versus 67.7%, p<0.001). These results demonstrate that marginal artery localization on CTC is feasible by combining a discriminative classifier (i.e., random forest) with a sequential Monte Carlo tracking mechanism. In so doing, we present the effective application of an anatomical probability map to vessel pruning as well as a supplementary spatial coordinate system for colonic segmentation and registration when this task has been confounded by colon lumen collapse.

Feasibility of using the marginal blood vessels as reference landmarks for CT colonography.

OBJECTIVE: The purpose of this study was to show the spatial relationship of the colonic marginal blood vessels and the teniae coli on CT colonography (CTC) and the use of the marginal blood vessels for supine-prone registration of polyps and for determination of proper connectivity of collapsed colonic segments. MATERIALS AND METHODS: We manually labeled the marginal blood vessels on 15 CTC examinations. Colon segmentation, centerline extraction, teniae detection, and teniae identification were automatically performed. For assessment of their spatial relationships, the distances from the marginal blood vessels to the three teniae coli and to the colon were measured. Student t tests (paired, two-tailed) were performed to evaluate the differences among these distances. To evaluate the reliability of the marginal vessels as reference points for polyp correlation, we analyzed 20 polyps from 20 additional patients who underwent supine and prone CTC. The average difference of the circumferential polyp position on the supine and prone scans was computed. Student t tests (paired, two-tailed) were performed to evaluate the supine-prone differences of the distance. We performed a study on 10 CTC studies from 10 patients with collapsed colonic segments by manually tracing the marginal blood vessels near the collapsed regions to resolve the ambiguity of the colon path. RESULTS: The average distances (± SD) from the marginal blood vessels to the tenia mesocolica, tenia omentalis, and tenia libera were 20.1 ± 3.1 mm (95% CI, 18.5-21.6 mm), 39.5 ± 4.8 mm (37.1-42.0 mm), and 36.9 ± 4.2 mm (34.8-39.1 mm), respectively. Pairwise comparison showed that these distances to the tenia libera and tenia omentalis were significantly different from the distance to the tenia mesocolica (p < 0.001). The average distance from the marginal blood vessels to the colon wall was 15.3 ± 2.0 mm (14.2-16.3 mm). For polyp localization, the average difference of the circumferential polyp position on the supine and prone scans was 9.6 ± 9.4 mm (5.5-13.7 mm) (p = 0.15) and expressed as a percentage of the colon circumference was 3.1% ± 2.0% (2.3-4.0%) (p = 0.83). We were able to trace the marginal blood vessels for 10 collapsed colonic segments and determine the paths of the colon in these regions. CONCLUSION: The marginal blood vessels run parallel to the colon in proximity to the tenia mesocolica and enable accurate supine-prone registration of polyps and localization of the colon path in areas of collapse. Thus, the marginal blood vessels may be used as reference landmarks complementary to the colon centerline and teniae coli.

Sequential Monte Carlo tracking for marginal artery segmentation on CT angiography by multiple cue fusion.

In this work we formulate vessel segmentation on contrast-enhanced CT angiogram images as a Bayesian tracking problem. To obtain posterior probability estimation of vessel location, we employ sequential Monte Carlo tracking and propose a new vessel segmentation method by fusing multiple cues extracted from CT images. These cues include intensity, vesselness, organ detection, and bridge information for poorly enhanced segments from global path minimization. By fusing local and global information for vessel tracking, we achieved high accuracy and robustness, with significantly improved precision compared to a traditional segmentation method (p = 0.0002). Our method was applied to the segmentation of the marginal artery of the colon, a small bore vessel of potential importance for colon segmentation and CT colonography. Experimental results indicate the effectiveness of the proposed method.

Visual phrase learning and its application in computed tomographic colonography.

In this work, we propose a visual phrase learning scheme to learn an optimal visual composite of anatomical components/parts from CT colonography images for computer-aided detection. The key idea is to utilize the anatomical parts of human body from medical images and associate them with biological targets of interest (organs, cancers, lesions, etc.) for joint detection and recognition. These anatomical parts of the human body are not necessarily near each other regarding their physical locations, and they serve more like a human body navigation system for detection and recognition. To show the effectiveness of the proposed learning scheme, we applied it to two sub-problems in computed tomographic colonography: teniae detection and classification of colorectal polyp candidates. Experimental results showed its efficacy.

Matching 3-D prone and supine CT colonography scans using graphs.

In this paper, we propose a new registration method for prone and supine computed tomographic colonography scans using graph matching. We formulate 3-D colon registration as a graph matching problem and propose a new graph matching algorithm based on mean field theory. In the proposed algorithm, we solve the matching problem in an iterative way. In each step, we use mean field theory to find the matched pair of nodes with highest probability. During iterative optimization, one-to-one matching constraints are added to the system in a step-by-step approach. Prominent matching pairs found in previous iterations are used to guide subsequent mean field calculations. The proposed method was found to have the best performance with smallest standard deviation compared with two other baseline algorithms called the normalized distance along the colon centerline (NDACC) ( p = 0.17) with manual colon centerline correction and spectral matching ( p < 1e-5). A major advantage of the proposed method is that it is fully automatic and does not require defining a colon centerline for registration. For the latter NDACC method, user interaction is almost always needed for identifying the colon centerlines.

Automated teniae coli detection and identification on computed tomographic colonography.

PURPOSE: Computed tomographic colonography (CTC) is a minimally invasive technique for colonic polyps and cancer screening. Teniae coli are three bands of longitudinal smooth muscle on the colon surface. Teniae coli are important anatomically meaningful landmarks on human colon. In this paper, the authors propose an automatic teniae coli detection method for CT colonography. METHODS: The original CTC slices are first segmented and reconstructed to a 3D colon surface. Then, the 3D colon surface is unfolded using a reversible projection technique. After that the unfolded colon is projected to a 2D height map. The teniae coli are detected using the height map and then reversely projected back to the 3D colon. Since teniae are located at the junctions where the haustral folds meet, the authors apply 2D Gabor filter banks to extract features of haustral folds. The maximum response of the filter banks is then selected as the feature image. The fold centers are then identified based on local maxima and thresholding on the feature image. Connecting the fold centers yields a path of the folds. Teniae coli are extracted as lines running between the fold paths. The authors used the spatial relationship between ileocecal valve (ICV) and teniae mesocolica (TM) to identify the TM, then the teniae omentalis (TO) and the teniae libera (TL) can be identified subsequently. RESULTS: The authors tested the proposed method on 47 cases of 37 patients, 10 of the patients with both supine and prone CT scans. The proposed method yielded performance with an average normalized root mean square error (RMSE) ( ± standard deviation [95% confidence interval]) of 4.87% ( ± 2.93%, [4.05% 5.69%]). CONCLUSIONS: The proposed fully-automated teniae coli detection and identification method is accurate and promising for future clinical applications.