Predicting Breast Tumor Malignancy Using Deep ConvNeXt Radiomics and Quality-Based Score Pooling in Ultrasound Sequences
Breast cancer needs to be detected early to reduce mortality rate. Ultrasound imaging (US) could significantly enhance diagnosing cases with dense breasts. Most of the existing computer-aided diagnosis (CAD) systems employ a single ultrasound image for the breast tumor to extract features to classif...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-04-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/12/5/1053 |
| _version_ | 1797500458075422720 |
|---|---|
| author | Mohamed A. Hassanien Vivek Kumar Singh Domenec Puig Mohamed Abdel-Nasser |
| author_facet | Mohamed A. Hassanien Vivek Kumar Singh Domenec Puig Mohamed Abdel-Nasser |
| author_sort | Mohamed A. Hassanien |
| collection | DOAJ |
| description | Breast cancer needs to be detected early to reduce mortality rate. Ultrasound imaging (US) could significantly enhance diagnosing cases with dense breasts. Most of the existing computer-aided diagnosis (CAD) systems employ a single ultrasound image for the breast tumor to extract features to classify it as benign or malignant. However, the accuracy of such CAD system is limited due to the large tumor size and shape variation, irregular and ambiguous tumor boundaries, and low signal-to-noise ratio in ultrasound images due to their noisy nature and the significant similarity between normal and abnormal tissues. To handle these issues, we propose a deep-learning-based radiomics method based on breast US sequences in this paper. The proposed approach involves three main components: radiomic features extraction based on a deep learning network, so-called ConvNeXt, a malignancy score pooling mechanism, and visual interpretations. Specifically, we employ the ConvNeXt network, a deep convolutional neural network (CNN) trained using the vision transformer style. We also propose an efficient pooling mechanism to fuse the malignancy scores of each breast US sequence frame based on image-quality statistics. The ablation study and experimental results demonstrate that our method achieves competitive results compared to other CNN-based methods. |
| first_indexed | 2024-03-10T03:04:10Z |
| format | Article |
| id | doaj.art-b6da0d2228df4c268fbc8d5829c3135d |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-10T03:04:10Z |
| publishDate | 2022-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-b6da0d2228df4c268fbc8d5829c3135d2023-11-23T10:38:38ZengMDPI AGDiagnostics2075-44182022-04-01125105310.3390/diagnostics12051053Predicting Breast Tumor Malignancy Using Deep ConvNeXt Radiomics and Quality-Based Score Pooling in Ultrasound SequencesMohamed A. Hassanien0Vivek Kumar Singh1Domenec Puig2Mohamed Abdel-Nasser3Department of Computer Engineering and Mathematics, Univerity Rovira i Virgili, 43007 Tarragona, SpainPrecision Medicine Centre of Excellence, School of Medicine, Dentistry and Biomedical Sciences, Queen’s University Belfast, Belfast BT7 1NN, UKDepartment of Computer Engineering and Mathematics, Univerity Rovira i Virgili, 43007 Tarragona, SpainDepartment of Computer Engineering and Mathematics, Univerity Rovira i Virgili, 43007 Tarragona, SpainBreast cancer needs to be detected early to reduce mortality rate. Ultrasound imaging (US) could significantly enhance diagnosing cases with dense breasts. Most of the existing computer-aided diagnosis (CAD) systems employ a single ultrasound image for the breast tumor to extract features to classify it as benign or malignant. However, the accuracy of such CAD system is limited due to the large tumor size and shape variation, irregular and ambiguous tumor boundaries, and low signal-to-noise ratio in ultrasound images due to their noisy nature and the significant similarity between normal and abnormal tissues. To handle these issues, we propose a deep-learning-based radiomics method based on breast US sequences in this paper. The proposed approach involves three main components: radiomic features extraction based on a deep learning network, so-called ConvNeXt, a malignancy score pooling mechanism, and visual interpretations. Specifically, we employ the ConvNeXt network, a deep convolutional neural network (CNN) trained using the vision transformer style. We also propose an efficient pooling mechanism to fuse the malignancy scores of each breast US sequence frame based on image-quality statistics. The ablation study and experimental results demonstrate that our method achieves competitive results compared to other CNN-based methods.https://www.mdpi.com/2075-4418/12/5/1053breast cancerCAD systemultrasound sequencedeep learningtransformers |
| spellingShingle | Mohamed A. Hassanien Vivek Kumar Singh Domenec Puig Mohamed Abdel-Nasser Predicting Breast Tumor Malignancy Using Deep ConvNeXt Radiomics and Quality-Based Score Pooling in Ultrasound Sequences Diagnostics breast cancer CAD system ultrasound sequence deep learning transformers |
| title | Predicting Breast Tumor Malignancy Using Deep ConvNeXt Radiomics and Quality-Based Score Pooling in Ultrasound Sequences |
| title_full | Predicting Breast Tumor Malignancy Using Deep ConvNeXt Radiomics and Quality-Based Score Pooling in Ultrasound Sequences |
| title_fullStr | Predicting Breast Tumor Malignancy Using Deep ConvNeXt Radiomics and Quality-Based Score Pooling in Ultrasound Sequences |
| title_full_unstemmed | Predicting Breast Tumor Malignancy Using Deep ConvNeXt Radiomics and Quality-Based Score Pooling in Ultrasound Sequences |
| title_short | Predicting Breast Tumor Malignancy Using Deep ConvNeXt Radiomics and Quality-Based Score Pooling in Ultrasound Sequences |
| title_sort | predicting breast tumor malignancy using deep convnext radiomics and quality based score pooling in ultrasound sequences |
| topic | breast cancer CAD system ultrasound sequence deep learning transformers |
| url | https://www.mdpi.com/2075-4418/12/5/1053 |
| work_keys_str_mv | AT mohamedahassanien predictingbreasttumormalignancyusingdeepconvnextradiomicsandqualitybasedscorepoolinginultrasoundsequences AT vivekkumarsingh predictingbreasttumormalignancyusingdeepconvnextradiomicsandqualitybasedscorepoolinginultrasoundsequences AT domenecpuig predictingbreasttumormalignancyusingdeepconvnextradiomicsandqualitybasedscorepoolinginultrasoundsequences AT mohamedabdelnasser predictingbreasttumormalignancyusingdeepconvnextradiomicsandqualitybasedscorepoolinginultrasoundsequences |