Tumor Detection in Automated Breast Ultrasound Using 3-D CNN and Prioritized Candidate Aggregation.

Automated whole breast ultrasound (ABUS) has been widely used as a screening modality for examination of breast abnormalities. Reviewing hundreds of slices produced by ABUS, however, is time consuming. Therefore, in this paper, a fast and effective computer-aided detection system based on 3-D convolutional neural networks (CNNs) and prioritized candidate aggregation is proposed to accelerate this reviewing. First, an efficient sliding window method is used to extract volumes of interest (VOIs). Then, each VOI is estimated the tumor probability with a 3-D CNN, and VOIs with higher estimated probability are selected as tumor candidates. Since the candidates may overlap each other, a novel scheme is designed to aggregate the overlapped candidates. During the aggregation, candidates are prioritized based on estimated tumor probability to alleviate over-aggregation issue. The relationship between the sizes of VOI and target tumor is optimally exploited to effectively perform each stage of our detection algorithm. On evaluation with a test set of 171 tumors, our method achieved sensitivities of 95% (162/171), 90% (154/171), 85% (145/171), and 80% (137/171) with 14.03, 6.92, 4.91, and 3.62 false positives per patient (with six passes), respectively. In summary, our method is more general and much faster than preliminary works and demonstrates promising results.

Whole-Breast Ultrasound for Breast Screening and Archiving.

The incidence of breast cancer is increasing worldwide, reinforcing the importance of breast screening. Conventional hand-held ultrasound (HHUS) for breast screening is efficient and relatively easy to perform; however, it lacks systematic recording and localization. This study investigated an electromagnetic tracking-based whole-breast ultrasound (WBUS) system to facilitate the use of HHUS for breast screening. One-hundred nine breast masses were collected, and the detection of suspicious breast lesions was compared between the WBUS system, HHUS and a commercial automated breast ultrasound (ABUS) system. The positioning error between WBUS and ABUS (1.39 ± 0.68 cm) was significantly smaller than that between HHUS and ABUS (1.62 ± 0.91 cm, p = 0.014) and HHUS and WBUS (1.63 ± 0.9 cm, p = 0.024). WBUS is a practical clinical tool for breast screening that can be used instead of the often unavailable and costly ABUS.

Multi-dimensional tumor detection in automated whole breast ultrasound using topographic watershed.

Automated whole breast ultrasound (ABUS) is becoming a popular screening modality for whole breast examination. Compared to conventional handheld ultrasound, ABUS achieves operator-independent and is feasible for mass screening. However, reviewing hundreds of slices in an ABUS image volume is time-consuming. A computer-aided detection (CADe) system based on watershed transform was proposed in this study to accelerate the reviewing. The watershed transform was applied to gather similar tissues around local minima to be homogeneous regions. The likelihoods of being tumors of the regions were estimated using the quantitative morphology, intensity, and texture features in the 2-D/3-D false positive reduction (FPR). The collected database comprised 68 benign and 65 malignant tumors. As a result, the proposed system achieved sensitivities of 100% (133/133), 90% (121/133), and 80% (107/133) with FPs/pass of 9.44, 5.42, and 3.33, respectively. The figure of merit of the combination of three feature sets is 0.46 which is significantly better than that of other feature sets ( [Formula: see text]). In summary, the proposed CADe system based on the multi-dimensional FPR using the integrated feature set is promising in detecting tumors in ABUS images.

Tumor detection in automated breast ultrasound images using quantitative tissue clustering.

PURPOSE: A computer-aided detection (CADe) system based on quantitative tissue clustering algorithm was proposed to identify potential tumors in automated breast ultrasound (ABUS) images. METHODS: Our three-dimensional (3D) ABUS images database included 148 biopsy-verified lesions (size 0.4-7.9 cm; mean 1.76 cm). An ABUS volume was comprised of 229-282 slices of two-dimensional (2D) images. For tumor detection, the fast 3D mean shift method was used to remove the speckle noise and the segment tissues with similar properties. The hypoechogenic regions, i.e., the tumor candidates, were extracted using fuzzy c-means clustering. Seven features related to echogenicity and morphology were quantified and used to predict the likelihood of identifying a tumor and filtering out the false-positive (FP) regions. RESULTS: The sensitivity of the proposed CADe system achieved 89.19% (132/148) with 2.00 FPs per volume. For the volumes without lesion, the FP rate was 1.27. The sensitivity was 92.50% (74/80) for malignant tumors and 85.29% (58/68) for benign tumors. CONCLUSIONS: The proposed CADe system provides an automatic and quantitative procedure for tumor detection in ABUS images. Further studies are needed to reduce the FP rate of the CADe algorithm.

Image-quality figure evaluator based on contrast-detail phantom in radiography.

BACKGROUND: In radiology, it is significantly important to produce adequate diagnostic information while minimally affecting the patient with the lowest amount of dose. A contrast-detail phantom is generally used to study the quality of image and the amount of radiation dose for digital X-ray imaging systems. To evaluate the quality of a phantom image, radiologists are traditionally required to manually indicate the location of the holes in each square in the phantom image. Then, the image quality figure (IQF) of the image can be evaluated. However, evaluation by the human eye is subjective as well as time-consuming, and it differs from person to person. METHODS: In this paper, an image processing-based IQF evaluator is proposed to automatically measure the quality of a phantom image. Nine phantom images, each consisting of 2382 × 2212 pixels, were used as test images and were provided by Taichung Hospital, Department of Health, Executive Yuan, Taiwan, Republic of China. The IP-IQF evaluator separates the phantom image into squares and then stretches the contrast of each square to the range 0-255. After that, it splits each square into 3 × 3 equal-sized regions, and recognizes the pattern of the square based on the features computed by mean-difference gradient operation and run length enhancer. Furthermore, a genetic algorithm-based parameter values-detecting algorithm is presented to compute the optimal values of the parameters used in the IP-IQF evaluator. RESULTS: The experimental results demonstrate that CoCIQ and the IP-IQF evaluator can efficiently measure the IQF of a phantom image. The IP-IQF evaluator is more effective than a radiologist and CoCIQ in evaluating the IQF of a phantom image. CONCLUSIONS: The proposed IQF evaluator is more sensitive than not only the observation of radiologists but also the computer program CoCIQ. Moreover, a genetic algorithm is provided to compute the most suitable values of the parameters used in the IQF evaluator.