Improving Accuracy and Efficiency with Concurrent Use of Artificial Intelligence for Digital Breast Tomosynthesis.

PURPOSE: To evaluate the use of artificial intelligence (AI) to shorten digital breast tomosynthesis (DBT) reading time while maintaining or improving accuracy. MATERIALS AND METHODS: A deep learning AI system was developed to identify suspicious soft-tissue and calcified lesions in DBT images. A reader study compared the performance of 24 radiologists (13 of whom were breast subspecialists) reading 260 DBT examinations (including 65 cancer cases) both with and without AI. Readings occurred in two sessions separated by at least 4 weeks. Area under the receiver operating characteristic curve (AUC), reading time, sensitivity, specificity, and recall rate were evaluated with statistical methods for multireader, multicase studies. RESULTS: Radiologist performance for the detection of malignant lesions, measured by mean AUC, increased 0.057 with the use of AI (95% confidence interval [CI]: 0.028, 0.087; P < .01), from 0.795 without AI to 0.852 with AI. Reading time decreased 52.7% (95% CI: 41.8%, 61.5%; P < .01), from 64.1 seconds without to 30.4 seconds with AI. Sensitivity increased from 77.0% without AI to 85.0% with AI (8.0%; 95% CI: 2.6%, 13.4%; P < .01), specificity increased from 62.7% without to 69.6% with AI (6.9%; 95% CI: 3.0%, 10.8%; noninferiority P < .01), and recall rate for noncancers decreased from 38.0% without to 30.9% with AI (7.2%; 95% CI: 3.1%, 11.2%; noninferiority P < .01). CONCLUSION: The concurrent use of an accurate DBT AI system was found to improve cancer detection efficacy in a reader study that demonstrated increases in AUC, sensitivity, and specificity and a reduction in recall rate and reading time.© RSNA, 2019See also the commentary by Hsu and Hoyt in this issue.

Clinical value of prostate segmentation and volume determination on MRI in benign prostatic hyperplasia.

Benign prostatic hyperplasia (BPH) is a nonmalignant pathological enlargement of the prostate, which occurs primarily in the transitional zone. BPH is highly prevalent and is a major cause of lower urinary tract symptoms in aging males, although there is no direct relationship between prostate volume and symptom severity. The progression of BPH can be quantified by measuring the volumes of the whole prostate and its zones, based on image segmentation on magnetic resonance imaging. Prostate volume determination via segmentation is a useful measure for patients undergoing therapy for BPH. However, prostate segmentation is not widely used due to the excessive time required for even experts to manually map the margins of the prostate. Here, we review and compare new methods of prostate volume segmentation using both manual and automated methods, including the ellipsoid formula, manual planimetry, and semiautomated and fully automated segmentation approaches. We highlight the utility of prostate segmentation in the clinical context of assessing BPH.

Fully automated prostate segmentation on MRI: comparison with manual segmentation methods and specimen volumes.

OBJECTIVE: The objective of our study was to compare calculated prostate volumes derived from tridimensional MR measurements (ellipsoid formula), manual segmentation, and a fully automated segmentation system as validated by actual prostatectomy specimens. MATERIALS AND METHODS: Ninety-eight consecutive patients (median age, 60.6 years; median prostate-specific antigen [PSA] value, 6.85 ng/mL) underwent triplane T2-weighted MRI on a 3-T magnet with an endorectal coil while undergoing diagnostic workup for prostate cancer. Prostate volume estimates were determined using the formula for ellipsoid volume based on tridimensional measurements, manual segmentation of triplane MRI, and automated segmentation based on normalized gradient fields cross-correlation and graph-search refinement. Estimates of prostate volume based on ellipsoid volume, manual segmentation, and automated segmentation were compared with prostatectomy specimen volumes. Prostate volume estimates were compared using the Pearson correlation coefficient and linear regression analysis. The Dice similarity coefficient was used to quantify spatial agreement between manual segmentation and automated segmentation. RESULTS: The Pearson correlation coefficient revealed strong positive correlation between prostatectomy specimen volume and prostate volume estimates derived from manual segmentation (R = 0.89-0.91, p < 0.0001) and automated segmentation (R = 0.88-0.91, p < 0.0001). No difference was observed between manual segmentation and automated segmentation. Mean partial and full Dice similarity coefficients of 0.92 and 0.89, respectively, were achieved for axial automated segmentation. CONCLUSION: Prostate volume estimates obtained with a fully automated 3D segmentation tool based on normalized gradient fields cross-correlation and graph-search refinement can yield highly accurate prostate volume estimates in a clinically relevant time of 10 seconds. This tool will assist in developing a broad range of applications including routine prostate volume estimations, image registration, biopsy guidance, and decision support systems.

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.

Effect of computer-aided detection for CT colonography in a multireader, multicase trial.

PURPOSE: To assess the effect of using computer-aided detection (CAD) in second-read mode on readers' accuracy in interpreting computed tomographic (CT) colonographic images. MATERIALS AND METHODS: The contributing institutions performed the examinations under approval of their local institutional review board, with waiver of informed consent, for this HIPAA-compliant study. A cohort of 100 colonoscopy-proved cases was used: In 52 patients with findings positive for polyps, 74 polyps of 6 mm or larger were observed in 65 colonic segments; in 48 patients with findings negative for polyps, no polyps were found. Nineteen blinded readers interpreted each case at two different times, with and without the assistance of a commercial CAD system. The effect of CAD was assessed in segment-level and patient-level receiver operating characteristic (ROC) curve analyses. RESULTS: Thirteen (68%) of 19 readers demonstrated higher accuracy with CAD, as measured with the segment-level area under the ROC curve (AUC). The readers' average segment-level AUC with CAD (0.758) was significantly greater (P = .015) than the average AUC in the unassisted read (0.737). Readers' per-segment, per-patient, and per-polyp sensitivity for all polyps of 6 mm or larger was higher (P < .011, .007, .005, respectively) for readings with CAD compared with unassisted readings (0.517 versus 0.465, 0.521 versus 0.466, and 0.477 versus 0.422, respectively). Sensitivity for patients with at least one large polyp of 10 mm or larger was also higher (P < .047) with CAD than without (0.777 versus 0.743). Average reader sensitivity also improved with CAD by more than 0.08 for small adenomas. Use of CAD reduced specificity of readers by 0.025 (P = .05). CONCLUSION: Use of CAD resulted in a significant improvement in overall reader performance. CAD improves reader sensitivity when measured per segment, per patient, and per polyp for small polyps and adenomas and also reduces specificity by a small amount.

Registration of prone and supine CT colonography scans using correlation optimized warping and canonical correlation analysis.

PURPOSE: In computed tomographic colonography (CTC), a patient will be scanned twice-Once supine and once prone-to improve the sensitivity for polyp detection. To assist radiologists in CTC reading, in this paper we propose an automated method for colon registration from supine and prone CTC scans. METHODS: We propose a new colon centerline registration method for prone and supine CTC scans using correlation optimized warping (COW) and canonical correlation analysis (CCA) based on the anatomical structure of the colon. Four anatomical salient points on the colon are first automatically distinguished. Then correlation optimized warping is applied to the segments defined by the anatomical landmarks to improve the global registration based on local correlation of segments. The COW method was modified by embedding canonical correlation analysis to allow multiple features along the colon centerline to be used in our implementation. RESULTS: We tested the COW algorithm on a CTC data set of 39 patients with 39 polyps (19 training and 20 test cases) to verify the effectiveness of the proposed COW registration method. Experimental results on the test set show that the COW method significantly reduces the average estimation error in a polyp location between supine and prone scans by 67.6%, from 46.27 +/- 52.97 to 14.98 mm +/- 11.41 mm, compared to the normalized distance along the colon centerline algorithm (p < 0.01). CONCLUSIONS: The proposed COW algorithm is more accurate for the colon centerline registration compared to the normalized distance along the colon centerline method and the dynamic time warping method. Comparison results showed that the feature combination of z-coordinate and curvature achieved lowest registration error compared to the other feature combinations used by COW. The proposed method is tolerant to centerline errors because anatomical landmarks help prevent the propagation of errors across the entire colon centerline.

Medical image registration with partial data.

We have developed a general-purpose registration algorithm for medical images and volumes. The transformation between images is modeled as locally affine but globally smooth, and explicitly accounts for local and global variations in image intensities. An explicit model of missing data is also incorporated, allowing us to simultaneously segment and register images with partial or missing data. The algorithm is built upon a differential multiscale framework and incorporates the expectation maximization algorithm. We show that this approach is highly effective in registering a range of synthetic and clinical medical images.

Symmetric curvature patterns for colonic polyp detection.

A novel approach for generating a set of features derived from properties of patterns of curvature is introduced as a part of a computer aided colonic polyp detection system. The resulting sensitivity was 84% with 4.8 false positives per volume on an independent test set of 72 patients (56 polyps). When used in conjunction with other features, it allowed the detection system to reach an overall sensitivity of 94% with a false positive rate of 4.3 per volume.

Elastic registration in the presence of intensity variations.

We have developed a general-purpose registration algorithm for medical images and volumes. This method models the transformation between images as locally affine but globally smooth. The model also explicitly accounts for local and global variations in image intensities. This approach is built upon a differential multiscale framework, allowing us to capture both large- and small-scale transformations. We show that this approach is highly effective across a broad range of synthetic and clinical medical images.