1
|
Chen S, Bennett DL, Colditz GA, Jiang S. Pectoral muscle removal in mammogram images: A novel approach for improved accuracy and efficiency. Cancer Causes Control 2024; 35:185-191. [PMID: 37676616 PMCID: PMC10764470 DOI: 10.1007/s10552-023-01781-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/01/2023] [Accepted: 08/21/2023] [Indexed: 09/08/2023]
Abstract
PURPOSE Accurate pectoral muscle removal is critical in mammographic breast density estimation and many other computer-aided algorithms. We propose a novel approach to remove pectoral muscles form mediolateral oblique (MLO) view mammograms and compare accuracy and computational efficiency with existing method (Libra). METHODS A pectoral muscle identification pipeline was developed. The image is first binarized to enhance contrast and then the Canny algorithm was applied for edge detection. Robust interpolation is used to smooth out the pectoral muscle region. Accuracy and computational speed of pectoral muscle identification was assessed using 951 women (1,902 MLO mammograms) from the Joanne Knight Breast Health Cohort at Washington University School of Medicine. RESULTS Our proposed algorithm exhibits lower mean error of 12.22% in comparison to Libra's estimated error of 20.44%. This 40% gain in accuracy was statistically significant (p < 0.001). The computational time for the proposed algorithm is 5.4 times faster when compared to Libra (5.1 s for proposed vs. 27.7 s for Libra per mammogram). CONCLUSION We present a novel approach for pectoral muscle removal in mammogram images that demonstrates significant improvement in accuracy and efficiency compared to existing method. Our findings have important implications for the development of computer-aided systems and other automated tools in this field.
Collapse
Affiliation(s)
- Simin Chen
- Division of Public Health Sciences, Department of Surgery, Washington University School of Medicine, 660 South Euclid Avenue, St. Louis, MO, MSC 8100-0094-02, USA
| | - Debbie L Bennett
- Department of Radiology, Washington University School of Medicine, St. Louis, MO, USA
| | - Graham A Colditz
- Division of Public Health Sciences, Department of Surgery, Washington University School of Medicine, 660 South Euclid Avenue, St. Louis, MO, MSC 8100-0094-02, USA.
- Alvin J. Siteman Cancer Center, Barnes-Jewish Hospital and Washington University School of Medicine, St. Louis, MO, USA.
| | - Shu Jiang
- Division of Public Health Sciences, Department of Surgery, Washington University School of Medicine, 660 South Euclid Avenue, St. Louis, MO, MSC 8100-0094-02, USA.
- Alvin J. Siteman Cancer Center, Barnes-Jewish Hospital and Washington University School of Medicine, St. Louis, MO, USA.
| |
Collapse
|
2
|
Verboom SD, Caballo M, Peters J, Gommers J, van den Oever D, Broeders MJM, Teuwen J, Sechopoulos I. Deep learning-based breast region segmentation in raw and processed digital mammograms: generalization across views and vendors. J Med Imaging (Bellingham) 2024; 11:014001. [PMID: 38162417 PMCID: PMC10753125 DOI: 10.1117/1.jmi.11.1.014001] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/14/2023] [Revised: 11/25/2023] [Accepted: 12/11/2023] [Indexed: 01/03/2024] Open
Abstract
Purpose We developed a segmentation method suited for both raw (for processing) and processed (for presentation) digital mammograms (DMs) that is designed to generalize across images acquired with systems from different vendors and across the two standard screening views. Approach A U-Net was trained to segment mammograms into background, breast, and pectoral muscle. Eight different datasets, including two previously published public sets and six sets of DMs from as many different vendors, were used, totaling 322 screen film mammograms (SFMs) and 4251 DMs (2821 raw/processed pairs and 1430 only processed) from 1077 different women. Three experiments were done: first training on all SFM and processed images, second also including all raw images in training, and finally testing vendor generalization by leaving one dataset out at a time. Results The model trained on SFM and processed mammograms achieved a good overall performance regardless of projection and vendor, with a mean (±std. dev.) dice score of 0.96 ± 0.06 for all datasets combined. When raw images were included in training, the mean (±std. dev.) dice score for the raw images was 0.95 ± 0.05 and for the processed images was 0.96 ± 0.04 . Testing on a dataset with processed DMs from a vendor that was excluded from training resulted in a difference in mean dice varying between - 0.23 to + 0.02 from that of the fully trained model. Conclusions The proposed segmentation method yields accurate overall segmentation results for both raw and processed mammograms independent of view and vendor. The code and model weights are made available.
Collapse
Affiliation(s)
- Sarah D. Verboom
- Radboud University Medical Center, Department of Medical Imaging, Nijmegen, The Netherlands
| | - Marco Caballo
- Radboud University Medical Center, Department of Medical Imaging, Nijmegen, The Netherlands
| | - Jim Peters
- Radboud University Medical Center, Department for Health Evidence, Nijmegen, The Netherlands
| | - Jessie Gommers
- Radboud University Medical Center, Department of Medical Imaging, Nijmegen, The Netherlands
| | - Daan van den Oever
- Radboud University Medical Center, Department of Medical Imaging, Nijmegen, The Netherlands
| | - Mireille J. M. Broeders
- Radboud University Medical Center, Department for Health Evidence, Nijmegen, The Netherlands
- Dutch Expert Centre for Screening (LRCB), Nijmegen, The Netherlands
| | - Jonas Teuwen
- Radboud University Medical Center, Department of Medical Imaging, Nijmegen, The Netherlands
- Netherlands Cancer Institute, Department of Radiation Oncology, Amsterdam, The Netherlands
- Memorial Sloan Kettering Cancer Center, Department of Radiology, New York, New York, United States
| | - Ioannis Sechopoulos
- Radboud University Medical Center, Department of Medical Imaging, Nijmegen, The Netherlands
- Dutch Expert Centre for Screening (LRCB), Nijmegen, The Netherlands
- University of Twente, Multi-Modality Medical Imaging, Enschede, The Netherlands
| |
Collapse
|
3
|
Lv JJ, Chen HY, Li JW, Lin KH, Chen RJ, Wang LJ, Zeng XX, Ren JC, Zhao HM. Contour extraction of medical images using an attention-based network. Biomed Signal Process Control 2023. [DOI: 10.1016/j.bspc.2023.104828] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/17/2023]
|
4
|
Bonaldi L, Pretto A, Pirri C, Uccheddu F, Fontanella CG, Stecco C. Deep Learning-Based Medical Images Segmentation of Musculoskeletal Anatomical Structures: A Survey of Bottlenecks and Strategies. Bioengineering (Basel) 2023; 10:bioengineering10020137. [PMID: 36829631 PMCID: PMC9952222 DOI: 10.3390/bioengineering10020137] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/25/2022] [Revised: 01/13/2023] [Accepted: 01/17/2023] [Indexed: 01/22/2023] Open
Abstract
By leveraging the recent development of artificial intelligence algorithms, several medical sectors have benefited from using automatic segmentation tools from bioimaging to segment anatomical structures. Segmentation of the musculoskeletal system is key for studying alterations in anatomical tissue and supporting medical interventions. The clinical use of such tools requires an understanding of the proper method for interpreting data and evaluating their performance. The current systematic review aims to present the common bottlenecks for musculoskeletal structures analysis (e.g., small sample size, data inhomogeneity) and the related strategies utilized by different authors. A search was performed using the PUBMED database with the following keywords: deep learning, musculoskeletal system, segmentation. A total of 140 articles published up until February 2022 were obtained and analyzed according to the PRISMA framework in terms of anatomical structures, bioimaging techniques, pre/post-processing operations, training/validation/testing subset creation, network architecture, loss functions, performance indicators and so on. Several common trends emerged from this survey; however, the different methods need to be compared and discussed based on each specific case study (anatomical region, medical imaging acquisition setting, study population, etc.). These findings can be used to guide clinicians (as end users) to better understand the potential benefits and limitations of these tools.
Collapse
Affiliation(s)
- Lorenza Bonaldi
- Department of Civil, Environmental and Architectural Engineering, University of Padova, Via F. Marzolo 9, 35131 Padova, Italy
| | - Andrea Pretto
- Department of Industrial Engineering, University of Padova, Via Venezia 1, 35121 Padova, Italy
| | - Carmelo Pirri
- Department of Neuroscience, University of Padova, Via A. Gabelli 65, 35121 Padova, Italy
| | - Francesca Uccheddu
- Department of Industrial Engineering, University of Padova, Via Venezia 1, 35121 Padova, Italy
- Centre for Mechanics of Biological Materials (CMBM), University of Padova, Via F. Marzolo 9, 35131 Padova, Italy
| | - Chiara Giulia Fontanella
- Department of Industrial Engineering, University of Padova, Via Venezia 1, 35121 Padova, Italy
- Centre for Mechanics of Biological Materials (CMBM), University of Padova, Via F. Marzolo 9, 35131 Padova, Italy
- Correspondence: ; Tel.: +39-049-8276754
| | - Carla Stecco
- Department of Neuroscience, University of Padova, Via A. Gabelli 65, 35121 Padova, Italy
- Centre for Mechanics of Biological Materials (CMBM), University of Padova, Via F. Marzolo 9, 35131 Padova, Italy
| |
Collapse
|
5
|
Zhao Y, Zhang J, Hu D, Qu H, Tian Y, Cui X. Application of Deep Learning in Histopathology Images of Breast Cancer: A Review. MICROMACHINES 2022; 13:2197. [PMID: 36557496 PMCID: PMC9781697 DOI: 10.3390/mi13122197] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 11/01/2022] [Revised: 12/04/2022] [Accepted: 12/09/2022] [Indexed: 06/17/2023]
Abstract
With the development of artificial intelligence technology and computer hardware functions, deep learning algorithms have become a powerful auxiliary tool for medical image analysis. This study was an attempt to use statistical methods to analyze studies related to the detection, segmentation, and classification of breast cancer in pathological images. After an analysis of 107 articles on the application of deep learning to pathological images of breast cancer, this study is divided into three directions based on the types of results they report: detection, segmentation, and classification. We introduced and analyzed models that performed well in these three directions and summarized the related work from recent years. Based on the results obtained, the significant ability of deep learning in the application of breast cancer pathological images can be recognized. Furthermore, in the classification and detection of pathological images of breast cancer, the accuracy of deep learning algorithms has surpassed that of pathologists in certain circumstances. Our study provides a comprehensive review of the development of breast cancer pathological imaging-related research and provides reliable recommendations for the structure of deep learning network models in different application scenarios.
Collapse
Affiliation(s)
- Yue Zhao
- College of Medicine and Biological Information Engineering, Northeastern University, Shenyang 110169, China
- Key Laboratory of Intelligent Computing in Medical Image, Ministry of Education, Shenyang 110169, China
- Key Laboratory of Data Analytics and Optimization for Smart Industry, Northeastern University, Shenyang 110169, China
| | - Jie Zhang
- College of Medicine and Biological Information Engineering, Northeastern University, Shenyang 110169, China
| | - Dayu Hu
- College of Medicine and Biological Information Engineering, Northeastern University, Shenyang 110169, China
| | - Hui Qu
- College of Medicine and Biological Information Engineering, Northeastern University, Shenyang 110169, China
| | - Ye Tian
- College of Medicine and Biological Information Engineering, Northeastern University, Shenyang 110169, China
| | - Xiaoyu Cui
- College of Medicine and Biological Information Engineering, Northeastern University, Shenyang 110169, China
- Key Laboratory of Intelligent Computing in Medical Image, Ministry of Education, Shenyang 110169, China
- Key Laboratory of Data Analytics and Optimization for Smart Industry, Northeastern University, Shenyang 110169, China
| |
Collapse
|
6
|
Yuan X, Xiao Y, Cai Z, Wu L. Salient object contour extraction based on pixel scales and hierarchical convolutional network. ARRAY 2022. [DOI: 10.1016/j.array.2022.100270] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/12/2022] Open
|
7
|
Multi-decoding Network with Attention Learning for Edge Detection. Neural Process Lett 2022. [DOI: 10.1007/s11063-022-11070-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/09/2022]
|
8
|
|
9
|
Rahman MA, Jha RK. Multidirectional Gabor Filter-Based Approach for Pectoral Muscle Boundary Detection. IEEE TRANSACTIONS ON RADIATION AND PLASMA MEDICAL SCIENCES 2022. [DOI: 10.1109/trpms.2021.3058157] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/24/2022]
|
10
|
Li H, Mukundan R, Boyd S. Spatial Distribution Analysis of Novel Texture Feature Descriptors for Accurate Breast Density Classification. SENSORS 2022; 22:s22072672. [PMID: 35408286 PMCID: PMC9002800 DOI: 10.3390/s22072672] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 03/04/2022] [Revised: 03/27/2022] [Accepted: 03/28/2022] [Indexed: 12/10/2022]
Abstract
Breast density has been recognised as an important biomarker that indicates the risk of developing breast cancer. Accurate classification of breast density plays a crucial role in developing a computer-aided detection (CADe) system for mammogram interpretation. This paper proposes a novel texture descriptor, namely, rotation invariant uniform local quinary patterns (RIU4-LQP), to describe texture patterns in mammograms and to improve the robustness of image features. In conventional processing schemes, image features are obtained by computing histograms from texture patterns. However, such processes ignore very important spatial information related to the texture features. This study designs a new feature vector, namely, K-spectrum, by using Baddeley's K-inhom function to characterise the spatial distribution information of feature point sets. Texture features extracted by RIU4-LQP and K-spectrum are utilised to classify mammograms into BI-RADS density categories. Three feature selection methods are employed to optimise the feature set. In our experiment, two mammogram datasets, INbreast and MIAS, are used to test the proposed methods, and comparative analyses and statistical tests between different schemes are conducted. Experimental results show that our proposed method outperforms other approaches described in the literature, with the best classification accuracy of 92.76% (INbreast) and 86.96% (MIAS).
Collapse
Affiliation(s)
- Haipeng Li
- Department of Computer Science and Software Engineering, University of Canterbury, Christchurch 8140, New Zealand;
- Correspondence:
| | - Ramakrishnan Mukundan
- Department of Computer Science and Software Engineering, University of Canterbury, Christchurch 8140, New Zealand;
| | - Shelley Boyd
- Canterbury Breastcare, St. George’s Medical Centre, Christchurch 8014, New Zealand;
| |
Collapse
|
11
|
Liu X, Xing F, Fakhri GE, Woo J. SELF-SEMANTIC CONTOUR ADAPTATION FOR CROSS MODALITY BRAIN TUMOR SEGMENTATION. PROCEEDINGS. IEEE INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING 2022; 2022:10.1109/isbi52829.2022.9761629. [PMID: 35990931 PMCID: PMC9387767 DOI: 10.1109/isbi52829.2022.9761629] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/15/2023]
Abstract
Unsupervised domain adaptation (UDA) between two significantly disparate domains to learn high-level semantic alignment is a crucial yet challenging task. To this end, in this work, we propose exploiting low-level edge information to facilitate the adaptation as a precursor task, which has a small cross-domain gap, compared with semantic segmentation. The precise contour then provides spatial information to guide the semantic adaptation. More specifically, we propose a multi-task framework to learn a contouring adaptation network along with a semantic segmentation adaptation network, which takes both magnetic resonance imaging (MRI) slice and its initial edge map as input. These two networks are jointly trained with source domain labels, and the feature and edge map level adversarial learning is carried out for cross-domain alignment. In addition, self-entropy minimization is incorporated to further enhance segmentation performance. We evaluated our framework on the BraTS2018 database for cross-modality segmentation of brain tumors, showing the validity and superiority of our approach, compared with competing methods.
Collapse
Affiliation(s)
- Xiaofeng Liu
- Dept. of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA
| | - Fangxu Xing
- Dept. of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA
| | - Georges El Fakhri
- Dept. of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA
| | - Jonghye Woo
- Dept. of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA
| |
Collapse
|
12
|
Du G, Zhan Y, Zhang Y, Guo J, Chen X, Liang J, Zhao H. Automated segmentation of the gastrocnemius and soleus in shank ultrasound images through deep residual neural network. Biomed Signal Process Control 2022. [DOI: 10.1016/j.bspc.2021.103447] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/02/2022]
|
13
|
Deep convolutional neural networks for computer-aided breast cancer diagnostic: a survey. Neural Comput Appl 2022. [DOI: 10.1007/s00521-021-06804-y] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/24/2022]
|
14
|
Xu C, Qi Y, Wang Y, Lou M, Pi J, Ma Y. ARF-Net: An Adaptive Receptive Field Network for breast mass segmentation in whole mammograms and ultrasound images. Biomed Signal Process Control 2022. [DOI: 10.1016/j.bspc.2021.103178] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/25/2022]
|
15
|
Feng Y, Liu W, Zhang X, Liu Z, Liu Y, Wang G. An Interval Iteration Based Multilevel Thresholding Algorithm for Brain MR Image Segmentation. ENTROPY 2021; 23:e23111429. [PMID: 34828127 PMCID: PMC8623348 DOI: 10.3390/e23111429] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 08/31/2021] [Revised: 10/11/2021] [Accepted: 10/26/2021] [Indexed: 11/16/2022]
Abstract
In this paper, we propose an interval iteration multilevel thresholding method (IIMT). This approach is based on the Otsu method but iteratively searches for sub-regions of the image to achieve segmentation, rather than processing the full image as a whole region. Then, a novel multilevel thresholding framework based on IIMT for brain MR image segmentation is proposed. In this framework, the original image is first decomposed using a hybrid L1 − L0 layer decomposition method to obtain the base layer. Second, we use IIMT to segment both the original image and its base layer. Finally, the two segmentation results are integrated by a fusion scheme to obtain a more refined and accurate segmentation result. Experimental results showed that our proposed algorithm is effective, and outperforms the standard Otsu-based and other optimization-based segmentation methods.
Collapse
Affiliation(s)
- Yuncong Feng
- College of Computer Science and Engineering, Changchun University of Technology, Changchun 130012, China; (Y.F.); (W.L.); (Z.L.); (Y.L.); (G.W.)
- Artificial Intelligence Research Institute, Changchun University of Technology, Changchun 130012, China
- Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun 130012, China
| | - Wanru Liu
- College of Computer Science and Engineering, Changchun University of Technology, Changchun 130012, China; (Y.F.); (W.L.); (Z.L.); (Y.L.); (G.W.)
| | - Xiaoli Zhang
- Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun 130012, China
- College of Computer Science and Technology, Jilin University, Changchun 130012, China
- Correspondence: ; Tel.: +86-150-4304-6596
| | - Zhicheng Liu
- College of Computer Science and Engineering, Changchun University of Technology, Changchun 130012, China; (Y.F.); (W.L.); (Z.L.); (Y.L.); (G.W.)
| | - Yunfei Liu
- College of Computer Science and Engineering, Changchun University of Technology, Changchun 130012, China; (Y.F.); (W.L.); (Z.L.); (Y.L.); (G.W.)
| | - Guishen Wang
- College of Computer Science and Engineering, Changchun University of Technology, Changchun 130012, China; (Y.F.); (W.L.); (Z.L.); (Y.L.); (G.W.)
- Artificial Intelligence Research Institute, Changchun University of Technology, Changchun 130012, China
| |
Collapse
|
16
|
Li H, Mukundan R, Boyd S. Novel Texture Feature Descriptors Based on Multi-Fractal Analysis and LBP for Classifying Breast Density in Mammograms. J Imaging 2021; 7:jimaging7100205. [PMID: 34677291 PMCID: PMC8540831 DOI: 10.3390/jimaging7100205] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/29/2021] [Revised: 09/26/2021] [Accepted: 10/01/2021] [Indexed: 11/16/2022] Open
Abstract
This paper investigates the usefulness of multi-fractal analysis and local binary patterns (LBP) as texture descriptors for classifying mammogram images into different breast density categories. Multi-fractal analysis is also used in the pre-processing step to segment the region of interest (ROI). We use four multi-fractal measures and the LBP method to extract texture features, and to compare their classification performance in experiments. In addition, a feature descriptor combining multi-fractal features and multi-resolution LBP (MLBP) features is proposed and evaluated in this study to improve classification accuracy. An autoencoder network and principal component analysis (PCA) are used for reducing feature redundancy in the classification model. A full field digital mammogram (FFDM) dataset, INBreast, which contains 409 mammogram images, is used in our experiment. BI-RADS density labels given by radiologists are used as the ground truth to evaluate the classification results using the proposed methods. Experimental results show that the proposed feature descriptor based on multi-fractal features and LBP result in higher classification accuracy than using individual texture feature sets.
Collapse
Affiliation(s)
- Haipeng Li
- Department of Computer Science and Software Engineering, University of Canterbury, Christchurch 8140, New Zealand;
- Correspondence:
| | - Ramakrishnan Mukundan
- Department of Computer Science and Software Engineering, University of Canterbury, Christchurch 8140, New Zealand;
| | - Shelley Boyd
- Canterbury Breastcare, St. George’s Medical Centre, Christchurch 8014, New Zealand;
| |
Collapse
|
17
|
Single-Input Multi-Output U-Net for Automated 2D Foetal Brain Segmentation of MR Images. J Imaging 2021; 7:jimaging7100200. [PMID: 34677286 PMCID: PMC8536962 DOI: 10.3390/jimaging7100200] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/30/2021] [Revised: 09/14/2021] [Accepted: 09/26/2021] [Indexed: 11/16/2022] Open
Abstract
In this work, we develop the Single-Input Multi-Output U-Net (SIMOU-Net), a hybrid network for foetal brain segmentation inspired by the original U-Net fused with the holistically nested edge detection (HED) network. The SIMOU-Net is similar to the original U-Net but it has a deeper architecture and takes account of the features extracted from each side output. It acts similar to an ensemble neural network, however, instead of averaging the outputs from several independently trained models, which is computationally expensive, our approach combines outputs from a single network to reduce the variance of predications and generalization errors. Experimental results using 200 normal foetal brains consisting of over 11,500 2D images produced Dice and Jaccard coefficients of 94.2 ± 5.9% and 88.7 ± 6.9%, respectively. We further tested the proposed network on 54 abnormal cases (over 3500 images) and achieved Dice and Jaccard coefficients of 91.2 ± 6.8% and 85.7 ± 6.6%, respectively.
Collapse
|
18
|
Pawar SD, Sharma KK, Sapate SG, Yadav GY. Segmentation of pectoral muscle from digital mammograms with depth-first search algorithm towards breast density classification. Biocybern Biomed Eng 2021. [DOI: 10.1016/j.bbe.2021.08.005] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/15/2023]
|
19
|
Shen Y, Wu N, Phang J, Park J, Liu K, Tyagi S, Heacock L, Kim SG, Moy L, Cho K, Geras KJ. An interpretable classifier for high-resolution breast cancer screening images utilizing weakly supervised localization. Med Image Anal 2021; 68:101908. [PMID: 33383334 PMCID: PMC7828643 DOI: 10.1016/j.media.2020.101908] [Citation(s) in RCA: 52] [Impact Index Per Article: 17.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/18/2020] [Revised: 11/12/2020] [Accepted: 11/13/2020] [Indexed: 12/12/2022]
Abstract
Medical images differ from natural images in significantly higher resolutions and smaller regions of interest. Because of these differences, neural network architectures that work well for natural images might not be applicable to medical image analysis. In this work, we propose a novel neural network model to address these unique properties of medical images. This model first uses a low-capacity, yet memory-efficient, network on the whole image to identify the most informative regions. It then applies another higher-capacity network to collect details from chosen regions. Finally, it employs a fusion module that aggregates global and local information to make a prediction. While existing methods often require lesion segmentation during training, our model is trained with only image-level labels and can generate pixel-level saliency maps indicating possible malignant findings. We apply the model to screening mammography interpretation: predicting the presence or absence of benign and malignant lesions. On the NYU Breast Cancer Screening Dataset, our model outperforms (AUC = 0.93) ResNet-34 and Faster R-CNN in classifying breasts with malignant findings. On the CBIS-DDSM dataset, our model achieves performance (AUC = 0.858) on par with state-of-the-art approaches. Compared to ResNet-34, our model is 4.1x faster for inference while using 78.4% less GPU memory. Furthermore, we demonstrate, in a reader study, that our model surpasses radiologist-level AUC by a margin of 0.11.
Collapse
Affiliation(s)
- Yiqiu Shen
- Center for Data Science, New York University, 60 5th Ave, New York, NY 10011, USA
| | - Nan Wu
- Center for Data Science, New York University, 60 5th Ave, New York, NY 10011, USA
| | - Jason Phang
- Center for Data Science, New York University, 60 5th Ave, New York, NY 10011, USA
| | - Jungkyu Park
- Department of Radiology, NYU School of Medicine, 530 1st Ave, New York, NY 10016, USA
| | - Kangning Liu
- Center for Data Science, New York University, 60 5th Ave, New York, NY 10011, USA
| | - Sudarshini Tyagi
- Department of Computer Science, Courant Institute of Mathematical Sciences, New York University, 251 Mercer St, New York, NY 10012, USA
| | - Laura Heacock
- Department of Radiology, NYU School of Medicine, 530 1st Ave, New York, NY 10016, USA; Perlmutter Cancer Center, NYU Langone Health, 160 E 34th St, New York, NY 10016, USA
| | - S Gene Kim
- Department of Radiology, NYU School of Medicine, 530 1st Ave, New York, NY 10016, USA; Center for Advanced Imaging Innovation and Research, NYU Langone Health, 660 1st Ave, New York, NY 10016, USA; Perlmutter Cancer Center, NYU Langone Health, 160 E 34th St, New York, NY 10016, USA
| | - Linda Moy
- Department of Radiology, NYU School of Medicine, 530 1st Ave, New York, NY 10016, USA; Center for Advanced Imaging Innovation and Research, NYU Langone Health, 660 1st Ave, New York, NY 10016, USA; Perlmutter Cancer Center, NYU Langone Health, 160 E 34th St, New York, NY 10016, USA
| | - Kyunghyun Cho
- Center for Data Science, New York University, 60 5th Ave, New York, NY 10011, USA; Department of Computer Science, Courant Institute of Mathematical Sciences, New York University, 251 Mercer St, New York, NY 10012, USA
| | - Krzysztof J Geras
- Center for Data Science, New York University, 60 5th Ave, New York, NY 10011, USA; Department of Radiology, NYU School of Medicine, 530 1st Ave, New York, NY 10016, USA; Center for Advanced Imaging Innovation and Research, NYU Langone Health, 660 1st Ave, New York, NY 10016, USA.
| |
Collapse
|
20
|
Africano G, Arponen O, Sassi A, Rinta-Kiikka I, Laaperi AL, Pertuz S. A New Benchmark and Method for the Evaluation of Chest Wall Detection in Digital Mammography .. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2020; 2020:1132-1135. [PMID: 33018186 DOI: 10.1109/embc44109.2020.9175960] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/07/2022]
Abstract
CAD systems have shown good potential for improving breast cancer diagnosis and anomaly detection in mammograms. A basic enabling step for the utilization of CAD systems in mammographic analysis is the correct identification of the breast region. Therefore, several methods to segment the pectoral muscle in the medio-lateral oblique (MLO) mammographic view have been proposed in the literature. However, currently it is difficult to perform and objective comparison between different chest wall (CW) detection methods since they are often evaluated with different evaluation procedures, datasets and the implementations of the methods are not publicly available. For this reason, we propose a methodology to evaluate and compare the performance of CW detection methods using a publicly available dataset (INbreast). We also propose a new intensity-based method for automatic CW detection. We then utilize the proposed evaluation methodology to compare the performance of our CW detection algorithm with a state-of-the-art CW detection method. The performance was measured in terms of the Dice's coefficient similarity, the area error and mean contour distance. The proposed method achieves yielded the best results in all the performance measures.
Collapse
|
21
|
Rampun A, Morrow PJ, Scotney BW, Wang H. Breast density classification in mammograms: An investigation of encoding techniques in binary-based local patterns. Comput Biol Med 2020; 122:103842. [DOI: 10.1016/j.compbiomed.2020.103842] [Citation(s) in RCA: 13] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/26/2020] [Revised: 06/02/2020] [Accepted: 06/02/2020] [Indexed: 12/01/2022]
|
22
|
Sharif MI, Li JP, Naz J, Rashid I. A comprehensive review on multi-organs tumor detection based on machine learning. Pattern Recognit Lett 2020. [DOI: 10.1016/j.patrec.2019.12.006] [Citation(s) in RCA: 17] [Impact Index Per Article: 4.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/05/2023]
|