ESTAN: Enhanced Small Tumor-Aware Network for Breast Ultrasound Image Segmentation

Background Breast ultrasound (BUS) imaging is one of the most prevalent approaches for the detection of breast cancers. Tumor segmentation of BUS images can facilitate doctors in localizing tumors and is a necessary step for computer‐aided diagnosis systems. While the majority of clinical BUS scans are normal ones without tumors, segmentation approaches such as U‐Net often predict mass regions for these images. Such false‐positive problem becomes serious if a fully automatic artificial intelligence system is used for routine screening. Methods In this study, we proposed a novel model which is more suitable for routine BUS screening. The model contains a classification branch that determines whether the image is normal or with tumors, and a segmentation branch that outlines tumors. Two branches share the same encoder network. We also built a new dataset that contains 1600 BUS images from 625 patients for training and a testing dataset with 130 images from 120 patients for testing. The dataset is the largest one with pixel‐wise masks manually segmented by experienced radiologists. Our code is available at https://github.com/szhangNJU/BUS_segmentation . Results The area under the receiver operating characteristic curve (AUC) for classifying images into normal/abnormal categories was 0.991. The dice similarity coefficient (DSC) for segmentation of mass regions was 0.898, better than the state‐of‐the‐art models. Testing on an external dataset gave a similar performance, demonstrating a good transferability of our model. Moreover, we simulated the use of the model in actual clinic practice by processing videos recorded during BUS scans; the model gave very low false‐positive predictions on normal images without sacrificing sensitivities for images with tumors. Conclusions Our model achieved better segmentation performance than the state‐of‐the‐art models and showed a good transferability on an external test set. The proposed deep learning architecture holds potential for use in fully automatic BUS health screening.

show abstract

“…Previous, Shareef et al 40 . developed an Enhanced Small Tumor‐Aware network (ESTAN) and tested it on three datasets.…”

Section: Resultsmentioning

confidence: 99%

“…Previous, Shareef et al 40 developed an Enhanced Small Tumor-Aware network (ESTAN) and tested it on three datasets. The DSCs of their model ranged from 0.78 to 0.92, TPR ranged from 0.80 to 0.91, FPR from F I G U R E 4 Segmentation performance of our model compared with Model-2 and Model-2-pos.…”

Section: Performance Of Mass Segmentationmentioning

confidence: 99%

Fully automatic tumor segmentation of breast ultrasound images with deep learning

Zhang

Liao

Wang

et al. 2022

J Applied Clin Med Phys

View full text Add to dashboard Cite

show abstract

“…In this section, we compare our proposed model with state-ofthe-art segmentation models, including U-Net [32], U-Net++ [33], DeepLabv3+ [34], ESTAN [35], Stan [38], CTG-Net [36], BO-Net [37] in the literature on both popular datasets of BUSI and UDIAT dataset. And we also compare our proposed model with state-of-the-art classification models, including Dizaj et al [41], Chowdary et al [42], Inan et al [43], Byra et al [44], Shi et al [45].…”

Section: Comparison With State-of-the-art Methodsmentioning

confidence: 99%

“…The dataset utilized in this study was obtained from the UDIAT Diagnostic Centre of the Parc Tauli Corporation, Sabadell (Spain) in 2012 using a Siemens ACUSON Sequoia C512 system 17L5 HD linear array transducer (8.5 MHz) [35]. The dataset comprises 163 images from different women, with a mean image size of 760 × 570 pixels.…”

Section: Udiat Datasetmentioning

confidence: 99%

SaTransformer: Semantic‐aware transformer for breast cancer classification and segmentation

Zhang

Hua

et al. 2023

IET Image Processing

View full text Add to dashboard Cite

Breast cancer classification and segmentation play an important role in identifying and detecting benign and malignant breast lesions. However, segmentation and classification still face many challenges: 1) The characteristics of cancer itself, such as fuzzy edges, complex backgrounds, and significant changes in size, shape, and intensity distribution make accurate segment and classification challenges. 2) Existing methods ignore the potential relationship between classification and segmentation tasks, due to the classification and segmentation being treated as two separate tasks. To overcome these challenges, in this paper, a novel Semantic‐aware transformer (SaTransformer) for breast cancer classification and segmentation is proposed. Specifically, the SaTransformer enables doing the two takes simultaneously through one unified framework. Unlike existing well‐known methods, the segmentation and classification information are semantically interactive, reinforcing each other during feature representation learning and improving the ability of feature representation learning while consuming less memory and computational complexity. The SaTransformer is validated on two publicly available breast cancer datasets – BUSI and UDIAT. Experimental results and quantitative evaluations (accuracy: 97.97%, precision: 98.20%, DSC: 86.34%) demonstrate that the SaTransformer outperforms other state‐of‐the‐art methods.

show abstract

“…For this reason, models should be designed specifically for the medical image domain, especially when segmenting a small target, as in recent studies. ESTAN [22] was an encoderdecoder model, which adopted two encoders to extract image context information at different scales and then combines that information for accurate breast tumor segmentation. Moreover, to effectively localize small tumors, it obtained feature maps from both square and large row-column-wise kernels.…”

Section: B Small Object and Lesion Detectionmentioning

confidence: 99%

PESA R-CNN: Perihematomal Edema Guided Scale Adaptive R-CNN for Hemorrhage Segmentation

Chang

Choi²

2023

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

Intracranial hemorrhage (ICH) is a type of stroke with a high mortality rate and failing to localize even minor ICH can put a patient's life at risk. However, its patterns are diverse in shapes and sizes and, sometimes, even hard to recognize its existence. Therefore, it is challenging to accurately detect and localize diverse ICH patterns. In this article, we propose a novel Perihematomal Edema Guided Scale Adaptive R-CNN (PESA R-CNN) for accurate segmentation of various size hemorrhages with the goal of minimizing missed hemorrhage regions. In our approach, we design a Center Surround Difference U-Net (CSD U-Net) to incorporate Perihematomal Edema (PHE) for more accurate Region of Interest (RoI) generation. We trained CSD U-Net to predict PHE and hemorrhage regions as targets in a weakly supervised manner and utilized its prediction results to generate RoI. By including more informative features of PHE around hemorrhage, this enhanced RoI generation allows a model to reduce the false-negative rate. Furthermore, these expanded RoIs are aligned with the Scale Adaptive RoI Align (SARA) module based on their size to prevent the loss of fine-scale information and small hemorrhage patterns. Each scale adaptively aligned RoI is processed with the corresponding separate segmentation network of Multi-Scale Segmentation Network (MSSN), which integrates the results from each scale's segmentation network. In experiments, our model shows significant improvement on dice coefficient (0.697) and Hausdorff distance (12.918), compared to all other segmentation models. It also minimizes the number of missing small hemorrhage regions and enhances overall segmentation performance on diverse ICH patterns.

show abstract

ESTAN: Enhanced Small Tumor-Aware Network for Breast Ultrasound Image Segmentation

Cited by 25 publications

References 41 publications

Fully automatic tumor segmentation of breast ultrasound images with deep learning

Fully automatic tumor segmentation of breast ultrasound images with deep learning

SaTransformer: Semantic‐aware transformer for breast cancer classification and segmentation

PESA R-CNN: Perihematomal Edema Guided Scale Adaptive R-CNN for Hemorrhage Segmentation

Contact Info

Product

Resources

About