When deep learning is not enough: artificial life as a supplementary tool for segmentation of ultrasound images of breast cancer.

Segmentation of tumors in ultrasound (US) images of the breast is a critical issue in medical imaging. Due to the poor quality of US images and the varying specifications of US machines, segmentation and classification of abnormalities present difficulties even for trained radiologists. The paper aims to introduce a novel AI-based hybrid model for US segmentation that offers high accuracy, requires relatively smaller datasets, and is capable of handling previously unseen data. The software can be used for diagnostics and the US-guided biopsies. A unique and robust hybrid approach that combines deep learning (DL) and multi-agent artificial life (AL) has been introduced. The algorithms are verified on three US datasets. The method outperforms 14 selected state-of-the-art algorithms applied to US images characterized by complex geometry and high level of noise. The paper offers an original classification of the images and tests to analyze the limits of the DL. The model has been trained and verified on 1264 ultrasound images. The images are in the JPEG and PNG formats. The age of the patients ranges from 22 to 73 years. The 14 benchmark algorithms include deformable shapes, edge linking, superpixels, machine learning, and DL methods. The tests use eight-region shape- and contour-based evaluation metrics. The proposed method (DL-AL) produces excellent results in terms of the dice coefficient (region) and the relative Hausdorff distance H3 (contour-based) as follows: the easiest image complexity level, Dice = 0.96 and H3 = 0.26; the medium complexity level, Dice = 0.91 and H3 = 0.82; and the hardest complexity level, Dice = 0.90 and H3 = 0.84. All other metrics follow the same pattern. The DL-AL outperforms the second best (Unet-based) method by 10-20%. The method has been also tested by a series of unconventional tests. The model was trained on low complexity images and applied to the entire set of images. These results are summarized below. (1) Only the low complexity images have been used for training (68% unknown images): Dice = 0.80 and H3 = 2.01. (2) The low and the medium complexity images have been used for training (51% unknown images): Dice = 0.86 and H3 = 1.32. (3) The low, medium, and hard complexity images have been used for training (35% unknown images): Dice = 0.92 and H3 = 0.76. These tests show a significant advantage of DL-AL over 30%. A video demo illustrating the algorithm is at http://tinyurl.com/mr4ah687 .

Edge-Driven Multi-Agent Reinforcement Learning: A Novel Approach to Ultrasound Breast Tumor Segmentation.

A segmentation model of the ultrasound (US) images of breast tumors based on virtual agents trained using reinforcement learning (RL) is proposed. The agents, living in the edge map, are able to avoid false boundaries, connect broken parts, and finally, accurately delineate the contour of the tumor. The agents move similarly to robots navigating in the unknown environment with the goal of maximizing the rewards. The individual agent does not know the goal of the entire population. However, since the robots communicate, the model is able to understand the global information and fit the irregular boundaries of complicated objects. Combining the RL with a neural network makes it possible to automatically learn and select the local features. In particular, the agents handle the edge leaks and artifacts typical for the US images. The proposed model outperforms 13 state-of-the-art algorithms, including selected deep learning models and their modifications.

Methods for the segmentation and classification of breast ultrasound images: a review.

PURPOSE: Breast ultrasound (BUS) is one of the imaging modalities for the diagnosis and treatment of breast cancer. However, the segmentation and classification of BUS images is a challenging task. In recent years, several methods for segmenting and classifying BUS images have been studied. These methods use BUS datasets for evaluation. In addition, semantic segmentation algorithms have gained prominence for segmenting medical images. METHODS: In this paper, we examined different methods for segmenting and classifying BUS images. Popular datasets used to evaluate BUS images and semantic segmentation algorithms were examined. Several segmentation and classification papers were selected for analysis and review. Both conventional and semantic methods for BUS segmentation were reviewed. RESULTS: Commonly used methods for BUS segmentation were depicted in a graphical representation, while other conventional methods for segmentation were equally elucidated. CONCLUSIONS: We presented a review of the segmentation and classification methods for tumours detected in BUS images. This review paper selected old and recent studies on segmenting and classifying tumours in BUS images.

Multiscale superpixel method for segmentation of breast ultrasound.

BACKGROUND: In medical diagnostics, breast ultrasound is an inexpensive and flexible imaging modality. The segmentation of breast ultrasounds to identify tumour regions is a challenging and complex task. The major problems of effective tumour identification are speckle noise, artefacts and low contrast. The gold standard for segmentation is manual processing; however, manual segmentation is a cumbersome task. To address this problem, the automatic multiscale superpixel method for the segmentation of breast ultrasounds is proposed. METHODS: The original breast ultrasound image was transformed into multiscaled images, and then, the multiscaled images were preprocessed. Next, a boundary efficient superpixel decomposition of the multiscaled images was created. Finally, the tumour region was generated by the boundary graph cut segmentation method. The proposed method was evaluated with 120 images from the Thammassat University Hospital database. The dataset consists of 30 malignant, 30 benign tumors, 60 fibroadenoma, and 60 cyst images. Popular metrics, such as the accuracy, sensitivity, specificity, Dice index, Jaccard index and Hausdorff distance, were used for the evaluation. RESULTS: The results indicate that the proposed method achieves segmentation accuracy of 97.3% for benign tumors, 94.2% for malignant, 96.4% for cysts and 96.7% for fibroadenomas. The results validate that the proposed model outperforms selected state-of-the-art segmentation methods. CONCLUSIONS: The proposed method outperforms selected state-of-the-art segmentation methods with an average segmentation accuracy of 94%.

Initialization of active contours for segmentation of breast cancer via fusion of ultrasound, Doppler, and elasticity images.

Active contours (snakes) are an efficient method for segmentation of ultrasound (US) images of breast cancer. However, the method produces inaccurate results if the seeds are initialized improperly (far from the true boundaries and close to the false boundaries). Therefore, we propose a novel initialization method based on the fusion of a conventional US image with elasticity and Doppler images. The proposed fusion method (FM) has been tested against four state-of-the-art initialization methods on 90 ultrasound images from a database collected by the Thammasat University Hospital of Thailand. The ground truth was hand-drawn by three leading radiologists of the hospital. The reference methods are: center of divergence (CoD), force field segmentation (FFS), Poisson Inverse Gradient Vector Flow (PIG), and quasi-automated initialization (QAI). A variety of numerical tests proves the advantages of the FM. For the raw US images, the percentage of correctly initialized contours is: FM-94.2%, CoD-0%, FFS-0%, PIG-26.7%, QAI-42.2%. The percentage of correctly segmented tumors is FM-84.4%, CoD-0%, FFS-0%, PIG-16.67%, QAI-22.44%. For reduced field of view US images, the percentage of correctly initialized contours is: FM-94.2%, CoD-0%, FFS-0%, PIG-65.6%, QAI-67.8%. The correctly segmented tumors are FM-88.9%, CoD-0%, FFS-0%, PIG-48.9%, QAI-44.5%. The accuracy, in terms of the average Hausdorff distance, is respectively 2.29 pixels, 33.81, 34.71, 7.7, and 8.4, whereas in terms of the Jaccard index, it is 0.9, 0.18, 0.19, 0.63, and 0.48.

Automatic initialization for active contour model in breast cancer detection utilizing conventional ultrasound and Color Doppler.

Regular examination of breasts may prevent and help to cure because breast cancer is treatable when it is detected early. Therefore, a breast cancer screening modality being sensitivity and cost-effective like ultrasonic imaging modality (US), is strongly required. In addition, the combination of a conventional US and its adjunct, Color Doppler has been proved for decreasing the rate of false-positive in breast cancer diagnosis. Thus, combination of these imaging modalities in a breast cancer segmentation would provide some benefits as well. An effective method for feature segmentation, active contour model has been widely utilized for decades. A crucial stage that affects the performance of active contour model is the initialization. This paper proposes a novel method for an automatic initialization of active contour model designed specifically for US-based imaging modalities. The method estimates an initial contour by utilizing the fusion of conventional US and Color Doppler. Examples and comparisons with three state-of-the-art automatic initialization methods are demonstrated to present the advantages of the proposed method. The evaluation results show high accuracy of initialization as well as fast convergence to features of interest.

Parameter-free optic disc detection.

The paper presents a simple, parameter-free method to detect the optic disc in retinal images. It works efficiently for blurred and noisy images with a varying ratio OD/image size. The method works equally well on images with different characteristics which often cause standard methods to fail or require a new round of training. The proposed method has been tested on 214 infant and adult retinal images and has been compared against hand-drawn ground truths generated by experts. It displays consistently high OD detection rates without any prior training or adjustment of the parameters.