Application of Artificial Neural Network Models in Segmentation and Classification of Nodules in Breast Ultrasound Digital Images

Marcomini, Karem D.; Carneiro, Adriana Munhoz; Schiabel, Homero

doi:10.1155/2016/7987212

Cited by 20 publications

(11 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some studies need to preprocess images before extracting features. [13,15] But it was not required in this study. In those studies, preprocessing images was supposed to reduce the noise in the images and thus to improve the accuracy.…”

Section: Discussionmentioning

confidence: 99%

Detection and classification the breast tumors using mask R-CNN on sonograms

et al. 2019

View full text Add to dashboard Cite

Breast cancer is one of the most harmful diseases for women with the highest morbidity. An efficient way to decrease its mortality is to diagnose cancer earlier by screening. Clinically, the best approach of screening for Asian women is ultrasound images combined with biopsies. However, biopsy is invasive and it gets incomprehensive information of the lesion. The aim of this study is to build a model for automatic detection, segmentation, and classification of breast lesions with ultrasound images. Based on deep learning, a technique using Mask regions with convolutional neural network was developed for lesion detection and differentiation between benign and malignant. The mean average precision was 0.75 for the detection and segmentation. The overall accuracy of benign/malignant classification was 85%. The proposed method provides a comprehensive and noninvasive way to detect and classify breast lesions.

show abstract

Section: Discussionmentioning

confidence: 99%

Detection and classification the breast tumors using mask R-CNN on sonograms

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Usage of neural network was also reported in the work carried out by Marcomini et al [20]. The authors have used self-organizing map along with multiple segmentation process assisting in better classification process.…”

Section: Related Workmentioning

confidence: 87%

Novel Mechanism of Classifying the Brain Tumor for Identifying its Critical State

S¹,

Sadashivappa²,

D³

2018

ijacsa

View full text Add to dashboard Cite

Classification of brain tumor is one of the most challenging tasks in the clinical and radiological research. Upon investigating the existing research contribution, we find that still there is wide open scope of addressing classification problem pertaining to brain tumor. Therefore, this manuscript presents a simple mechanism of classifying the brain tumor in order to categorize its state of criticality. The proposed system applies a multi-level preprocessing to enhance the input image followed by image thresholding for feature extraction and decomposition using wavelet transform. The extracted features are further subjected to process of dimensional reduction that maintains a balance between good number of enriched feature and less size of redundant feature using statistical approach. Further, a supervised learning approach is implemented that further optimizes the classification process. The study outcome is further benchmarked with different process of classification to show the efficient computational environment of proposed system.

show abstract

“…Based on the dataset of 144 phantom images and 123 clinical images, the model achieved an accuracy of 90% to simulators and 81% to clinical trials. 19 Yap et al proposed an end-to-end deep learning approach using fully convolutional networks (FCNs). Based on two datasets of 113 malignant and 356 benign lesions, 89.6% of the benign lesions and 60.6% of the malignant lesions were successfully segmented and correctly recognized.…”

Section: Target Detection Methods Based On Deep Learningmentioning

confidence: 99%

Ultrasonic Diagnosis of Breast Nodules Using Modified Faster R-CNN

Zhang

Lin

et al. 2019

Ultrason Imaging

View full text Add to dashboard Cite

Breast cancer has become the biggest threat to female health. Ultrasonic diagnosis of breast cancer based on artificial intelligence is basically a classification of benign and malignant tumors, which does not meet clinical demand. Besides, the current target detection method performs poorly in detecting small lesions, while it is clinically required to detect nodules below 2 mm. The objective of this study is to (a) propose a diagnostic method based on Breast Imaging Reporting and Data System (BI-RADS) and (b) increase its detectability of small lesions. We modified the framework of Faster R-CNN (Faster Region-based Convolutional Neural Network) by introducing multi-scale feature extraction and multi-resolution candidate bound extraction into the network. Then, it was trained using 852 images of BI-RADS C2, 739 images of C3, and 1662 images of malignancy (BI-RADS 4a/4b/4c/5/6). We compared our model with unmodified Faster R-CNN and YOLO v3 (You Only Look Once v3). The mean average precision (mAP) is significantly increased to 0.913, while its average detection speed is slightly declined to 4.11 FPS (frames per second). Meanwhile, its detectivity of small lesions is effectively improved. Moreover, we also tentatively applied our model on video sequences and got satisfactory results. We modified Faster R-CNN and trained it partly based on BI-RADS. Its detectability of lesions, as well as small nodules, was significantly improved. In view of wide coverage of dataset and satisfactory test results, our method can basically meet clinical needs.

show abstract

Application of Artificial Neural Network Models in Segmentation and Classification of Nodules in Breast Ultrasound Digital Images

Cited by 20 publications

References 18 publications

Detection and classification the breast tumors using mask R-CNN on sonograms

Detection and classification the breast tumors using mask R-CNN on sonograms

Novel Mechanism of Classifying the Brain Tumor for Identifying its Critical State

Ultrasonic Diagnosis of Breast Nodules Using Modified Faster R-CNN

Contact Info

Product

Resources

About