1
|
Ashoor M, Khorshidi A. Improving signal-to-noise ratio by maximal convolution of longitudinal and transverse magnetization components in MRI: application to the breast cancer detection. Med Biol Eng Comput 2024; 62:941-954. [PMID: 38100039 DOI: 10.1007/s11517-023-02994-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/28/2023] [Accepted: 12/07/2023] [Indexed: 02/22/2024]
Abstract
PURPOSE The extraction of information from images provided by medical imaging systems may be employed to obtain the specific objectives in the various fields. The quantity of signal to noise ratio (SNR) plays a crucial role in displaying the image details. The higher the SNR value, the more the information is available. METHODS In this study, a new function has been formulated using the appropriate suggestions on convolutional combination of the longitudinal and transverse magnetization components related to the relaxation times of T1 and T2 in MRI, where by introducing the distinct index on the maximum value of this function, the new maps are constructed toward the best SNR. Proposed functions were analytically simulated using Matlab software and evaluated with respect to various relaxation times. This proposed method can be applied to any medical images. For instance, the T1- and T2-weighted images of the breast indicated in the reference [35] were selected for modelling and construction of the full width at x maximum (FWxM) map at the different values of x-parameter from 0.01 to 0.955 at 0.035 and 0.015 intervals. The range of x-parameter is between zero and one. To determine the maximum value of the derived SNR, these intervals have been first chosen arbitrarily. However, the smaller this interval, the more precise the value of the x-parameter at which the signal to noise is maximum. RESULTS The results showed that at an index value of x = 0.325, the new map of FWxM (0.325) will be constructed with a maximum derived SNR of 22.7 compared to the SNR values of T1- and T2-maps by 14.53 and 17.47, respectively. CONCLUSION By convolving two orthogonal magnetization vectors, the qualified images with higher new SNR were created, which included the image with the best SNR. In other words, to optimize the adoption of MRI technique and enable the possibility of wider use, an optimal and cost-effective examination has been suggested. Our proposal aims to shorten the MRI examination to further reduce interpretation times while maintaining primary sensitivity. SIGNIFICANCE Our findings may help to quantitatively identify the primary sources of each type of solid and sequential cancer.
Collapse
Affiliation(s)
- Mansour Ashoor
- Radiation Applications Research School, Nuclear Science and Technology Research Institute, Tehran, Iran
| | - Abdollah Khorshidi
- Radiation Applications Research School, Nuclear Science and Technology Research Institute, Tehran, Iran.
| |
Collapse
|
2
|
Zhang L, Cui H, Liu B, Zhang C, Horn B. Backpropagation Neural Network for Processing of Missing Data in Breast Cancer Detection. Ing Rech Biomed 2021. [DOI: 10.1016/j.irbm.2021.06.010] [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]
|
3
|
Gao P, Kong X, Song Y, Song Y, Fang Y, Ouyang H, Wang J. Recent Progress for the Techniques of MRI-Guided Breast Interventions and their applications on Surgical Strategy. J Cancer 2020; 11:4671-4682. [PMID: 32626513 PMCID: PMC7330700 DOI: 10.7150/jca.46329] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/25/2020] [Accepted: 05/09/2020] [Indexed: 01/20/2023] Open
Abstract
With a high sensitivity of breast lesions, MRI can detect suspicious lesions which are occult in traditional breast examination equipment. However, the lower and variable specificity of MRI makes the MRI-guided intervention, including biopsies and localizations, necessary before surgery, especially for patients who need the treatment of breast-conserving surgery (BCS). MRI techniques and patient preparation should be first carefully considered before the intervention to avoid lengthening the procedure time and compromising targeting accuracy. Doctors and radiologists need to reconfirm the target of the lesion and be very familiar with the process approach and equipment techniques involving the computer-aided diagnosis (CAD) tools and the biopsy system and follow a correct way. The basic steps of MRI-guided biopsy and localization are nearly the same regardless of the vendor or platform, and this article systematically introduces detailed methods and techniques of MRI-guided intervention. The two interventions both face different challenging situations during procedures with solutions given in the article. Post-operative statistics show that the complications of MRI-guided intervention are infrequent and mild, and MRI-guided biopsy provides the pathological information for the subsequent surgical decisions and MRI-guided localization fully prepared for follow-up surgical biopsy. New techniques for MRI-guided intervention are also elaborated in the article, which leads to future development. In a word, MRI-guided intervention is a safe, accurate, and effective technique with a low complication rate and successful MRI-guided intervention is truly teamwork with efforts from patients to surgeons, radiologists, MRI technologists, and nurses.
Collapse
Affiliation(s)
- Peng Gao
- Department of Breast Surgical Oncology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, 100021, China
| | - Xiangyi Kong
- Department of Breast Surgical Oncology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, 100021, China
| | - Ying Song
- Department of Diagnostic Radiology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, 100021, China
| | - Yan Song
- Department of Pathology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, 100021, China
| | - Yi Fang
- Department of Breast Surgical Oncology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, 100021, China
| | - Han Ouyang
- Department of Diagnostic Radiology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, 100021, China
| | - Jing Wang
- Department of Breast Surgical Oncology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, 100021, China
| |
Collapse
|
4
|
Chhetri A, Li X, Rispoli JV. Current and Emerging Magnetic Resonance-Based Techniques for Breast Cancer. Front Med (Lausanne) 2020; 7:175. [PMID: 32478083 PMCID: PMC7235971 DOI: 10.3389/fmed.2020.00175] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/15/2019] [Accepted: 04/15/2020] [Indexed: 01/10/2023] Open
Abstract
Breast cancer is the most commonly diagnosed cancer among women worldwide, and early detection remains a principal factor for improved patient outcomes and reduced mortality. Clinically, magnetic resonance imaging (MRI) techniques are routinely used in determining benign and malignant tumor phenotypes and for monitoring treatment outcomes. Static MRI techniques enable superior structural contrast between adipose and fibroglandular tissues, while dynamic MRI techniques can elucidate functional characteristics of malignant tumors. The preferred clinical procedure-dynamic contrast-enhanced MRI-illuminates the hypervascularity of breast tumors through a gadolinium-based contrast agent; however, accumulation of the potentially toxic contrast agent remains a major limitation of the technique, propelling MRI research toward finding an alternative, noninvasive method. Three such techniques are magnetic resonance spectroscopy, chemical exchange saturation transfer, and non-contrast diffusion weighted imaging. These methods shed light on underlying chemical composition, provide snapshots of tissue metabolism, and more pronouncedly characterize microstructural heterogeneity. This review article outlines the present state of clinical MRI for breast cancer and examines several research techniques that demonstrate capacity for clinical translation. Ultimately, multi-parametric MRI-incorporating one or more of these emerging methods-presently holds the best potential to afford improved specificity and deliver excellent accuracy to clinics for the prediction, detection, and monitoring of breast cancer.
Collapse
Affiliation(s)
- Apekshya Chhetri
- Magnetic Resonance Biomedical Engineering Laboratory, Weldon School of Biomedical Engineering, Purdue University, West Lafayette, IN, United States
- Basic Medical Sciences, College of Veterinary Medicine, Purdue University, West Lafayette, IN, United States
| | - Xin Li
- Magnetic Resonance Biomedical Engineering Laboratory, Weldon School of Biomedical Engineering, Purdue University, West Lafayette, IN, United States
| | - Joseph V. Rispoli
- Magnetic Resonance Biomedical Engineering Laboratory, Weldon School of Biomedical Engineering, Purdue University, West Lafayette, IN, United States
- Center for Cancer Research, Purdue University, West Lafayette, IN, United States
- School of Electrical & Computer Engineering, Purdue University, West Lafayette, IN, United States
| |
Collapse
|
5
|
Automatic Breast and Fibroglandular Tissue Segmentation in Breast MRI Using Deep Learning by a Fully-Convolutional Residual Neural Network U-Net. Acad Radiol 2019; 26:1526-1535. [PMID: 30713130 DOI: 10.1016/j.acra.2019.01.012] [Citation(s) in RCA: 48] [Impact Index Per Article: 9.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/22/2018] [Revised: 01/03/2019] [Accepted: 01/13/2019] [Indexed: 12/17/2022]
Abstract
RATIONALE AND OBJECTIVES Breast segmentation using the U-net architecture was implemented and tested in independent validation datasets to quantify fibroglandular tissue volume in breast MRI. MATERIALS AND METHODS Two datasets were used. The training set was MRI of 286 patients with unilateral breast cancer. The segmentation was done on the contralateral normal breasts. The ground truth for the breast and fibroglandular tissue (FGT) was obtained by using a template-based segmentation method. The U-net deep learning algorithm was implemented to analyze the training set, and the final model was obtained using 10-fold cross-validation. The independent validation set was MRI of 28 normal volunteers acquired using four different MR scanners. Dice Similarity Coefficient (DSC), voxel-based accuracy, and Pearson's correlation were used to evaluate the performance. RESULTS For the 10-fold cross-validation in the initial training set of 286 patients, the DSC range was 0.83-0.98 (mean 0.95 ± 0.02) for breast and 0.73-0.97 (mean 0.91 ± 0.03) for FGT; and the accuracy range was 0.92-0.99 (mean 0.98 ± 0.01) for breast and 0.87-0.99 (mean 0.97 ± 0.01) for FGT. For the entire 224 testing breasts of the 28 normal volunteers in the validation datasets, the mean DSC was 0.86 ± 0.05 for breast, 0.83 ± 0.06 for FGT; and the mean accuracy was 0.94 ± 0.03 for breast and 0.93 ± 0.04 for FGT. The testing results for MRI acquired using four different scanners were comparable. CONCLUSION Deep learning based on the U-net algorithm can achieve accurate segmentation results for the breast and FGT on MRI. It may provide a reliable and efficient method to process large number of MR images for quantitative analysis of breast density.
Collapse
|
6
|
Zhao WJ, Fu LR, Huang ZM, Zhu JQ, Ma BY. Effectiveness evaluation of computer-aided diagnosis system for the diagnosis of thyroid nodules on ultrasound: A systematic review and meta-analysis. Medicine (Baltimore) 2019; 98:e16379. [PMID: 31393347 PMCID: PMC6709241 DOI: 10.1097/md.0000000000016379] [Citation(s) in RCA: 32] [Impact Index Per Article: 6.4] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 02/05/2023] Open
Abstract
BACKGROUND More and more automated efficient ultrasound image analysis techniques, such as ultrasound-based computer-aided diagnosis system (CAD), were developed to obtain accurate, reproducible, and more objective diagnosis results for thyroid nodules. So far, whether the diagnostic performance of existing CAD systems can reach the diagnostic level of experienced radiologists is still controversial. The aim of the meta-analysis was to evaluate the accuracy of CAD for thyroid nodules' diagnosis by reviewing current literatures and summarizing the research status. METHODS A detailed literature search on PubMed, Embase, and Cochrane Libraries for articles published until December 2018 was carried out. The diagnostic performances of CAD systems vs radiologist were evaluated by meta-analysis. We determined the sensitivity and the specificity across studies, calculated positive and negative likelihood ratios and constructed summary receiver-operating characteristic (SROC) curves. Meta-analysis of studies was performed using a mixed-effect, hierarchical logistic regression model. RESULTS Five studies with 536 patients and 723 thyroid nodules were included in this meta-analysis. The pooled sensitivity, specificity, positive likelihood ratio, negative likelihood ratio, and diagnostic odds ratio (DOR) for CAD system were 0.87 (95% confidence interval [CI], 0.73-0.94), 0.79 (95% CI 0.63-0.89), 4.1 (95% CI 2.5-6.9), 0.17 (95% CI 0.09-0.32), and 25 (95% CI 15-42), respectively. The SROC curve indicated that the area under the curve was 0.90 (95% CI 0.87-0.92). The pooled sensitivity, specificity, positive likelihood ratio, negative likelihood ratio, and DOR for experienced radiologists were 0.82 (95% CI 0.69-0.91), 0.83 (95% CI 0.76-0.89), 4.9 (95% CI 3.4-7.0), 0.22 (95% CI 0.12-0.38), and 23 (95% CI 11-46), respectively. The SROC curve indicated that the area under the curve was 0.96 (95% CI 0.94-0.97). CONCLUSION The sensitivity of the CAD system in the diagnosis of thyroid nodules was similar to that of experienced radiologists. However, the CAD system had lower specificity and DOR than experienced radiologists. The CAD system may play the potential role as a decision-making assistant alongside radiologists in the thyroid nodules' diagnosis. Future technical improvements would be helpful to increase the accuracy as well as diagnostic efficiency.
Collapse
Affiliation(s)
- Wan-Jun Zhao
- Department of Thyroid & Parathyroid Surgery, West China Hospital
| | - Lin-Ru Fu
- West China School of Medicine, Sichuan University, Sichuan
| | - Zhi-Mian Huang
- Business College, New York University in Shanghai, Shanghai
| | - Jing-Qiang Zhu
- Department of Thyroid & Parathyroid Surgery, West China Hospital
| | - Bu-Yun Ma
- Department of Ultrasonography, West China Hospital, Sichuan University, Sichuan, China
| |
Collapse
|
7
|
Sindi R, Sá Dos Reis C, Bennett C, Stevenson G, Sun Z. Quantitative Measurements of Breast Density Using Magnetic Resonance Imaging: A Systematic Review and Meta-Analysis. J Clin Med 2019; 8:jcm8050745. [PMID: 31137728 PMCID: PMC6571752 DOI: 10.3390/jcm8050745] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/13/2019] [Accepted: 05/22/2019] [Indexed: 02/06/2023] Open
Abstract
Breast density, a measure of dense fibroglandular tissue relative to non-dense fatty tissue, is confirmed as an independent risk factor of breast cancer. Although there has been an increasing interest in the quantitative assessment of breast density, no research has investigated the optimal technical approach of breast MRI in this aspect. Therefore, we performed a systematic review and meta-analysis to analyze the current studies on quantitative assessment of breast density using MRI and to determine the most appropriate technical/operational protocol. Databases (PubMed, EMBASE, ScienceDirect, and Web of Science) were searched systematically for eligible studies. Single arm meta-analysis was conducted to determine quantitative values of MRI in breast density assessments. Combined means with their 95% confidence interval (CI) were calculated using a fixed-effect model. In addition, subgroup meta-analyses were performed with stratification by breast density segmentation/measurement method. Furthermore, alternative groupings based on statistical similarities were identified via a cluster analysis employing study means and standard deviations in a Nearest Neighbor/Single Linkage. A total of 38 studies matched the inclusion criteria for this systematic review. Twenty-one of these studies were judged to be eligible for meta-analysis. The results indicated, generally, high levels of heterogeneity between study means within groups and high levels of heterogeneity between study variances within groups. The studies in two main clusters identified by the cluster analysis were also subjected to meta-analyses. The review confirmed high levels of heterogeneity within the breast density studies, considered to be due mainly to the applications of MR breast-imaging protocols and the use of breast density segmentation/measurement methods. Further research should be performed to determine the most appropriate protocol and method for quantifying breast density using MRI.
Collapse
Affiliation(s)
- Rooa Sindi
- Discipline of Medical Radiation Sciences, School of Molecular and Life Sciences, Curtin University, Perth, Western Australia 6845, Australia.
| | - Cláudia Sá Dos Reis
- Discipline of Medical Radiation Sciences, School of Molecular and Life Sciences, Curtin University, Perth, Western Australia 6845, Australia.
- School of Health Sciences (HESAV), University of Applied Sciences and Arts Western Switzerland (HES-SO), Av. de Beaumont 21, 1011 Lausanne, Switzerland.
- CISP-Centro de Investigação em Saúde Pública, Escola Nacional de Saúde Pública, Universidade NOVA de Lisboa, 1600-560 Lisboa, Portugal.
| | - Colleen Bennett
- Discipline of Medical Radiation Sciences, School of Molecular and Life Sciences, Curtin University, Perth, Western Australia 6845, Australia.
| | | | - Zhonghua Sun
- Discipline of Medical Radiation Sciences, School of Molecular and Life Sciences, Curtin University, Perth, Western Australia 6845, Australia.
| |
Collapse
|
8
|
Fashandi H, Kuling G, Lu Y, Wu H, Martel AL. An investigation of the effect of fat suppression and dimensionality on the accuracy of breast MRI segmentation using U-nets. Med Phys 2019; 46:1230-1244. [PMID: 30609062 DOI: 10.1002/mp.13375] [Citation(s) in RCA: 14] [Impact Index Per Article: 2.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/29/2018] [Revised: 10/17/2018] [Accepted: 12/11/2018] [Indexed: 01/17/2023] Open
Abstract
PURPOSE Accurate segmentation of the breast is required for breast density estimation and the assessment of background parenchymal enhancement, both of which have been shown to be related to breast cancer risk. The MRI breast segmentation task is challenging, and recent work has demonstrated that convolutional neural networks perform well for this task. In this study, we have investigated the performance of several two-dimensional (2D) U-Net and three-dimensional (3D) U-Net configurations using both fat-suppressed and nonfat-suppressed images. We have also assessed the effect of changing the number and quality of the ground truth segmentations. MATERIALS AND METHODS We designed eight studies to investigate the effect of input types and the dimensionality of the U-Net operations for the breast MRI segmentation. Our training data contained 70 whole breast volumes of T1-weighted sequences without fat suppression (WOFS) and with fat suppression (FS). For each subject, we registered the WOFS and FS volumes together before manually segmenting the breast to generate ground truth. We compared four different input types to the U-nets: WOFS, FS, MIXED (WOFS and FS images treated as separate samples), and MULTI (WOFS and FS images combined into a single multichannel image). We trained 2D U-Nets and 3D U-Nets with these data, which resulted in our eight studies (2D-WOFS, 3D-WOFS, 2D-FS, 3D-FS, 2D-MIXED, 3D-MIXED, 2D-MULTI, and 3D-MULT). For each of these studies, we performed a systematic grid search to tune the hyperparameters of the U-Nets. A separate validation set with 15 whole breast volumes was used for hyperparameter tuning. We performed Kruskal-Walis test on the results of our hyperparameter tuning and did not find a statistically significant difference in the ten top models of each study. For this reason, we chose the best model as the model with the highest mean dice similarity coefficient (DSC) value on the validation set. The reported test results are the results of the top model of each study on our test set which contained 19 whole breast volumes annotated by three readers fused with the STAPLE algorithm. We also investigated the effect of the quality of the training annotations and the number of training samples for this task. RESULTS The study with the highest average DSC result was 3D-MULTI with 0.96 ± 0.02. The second highest average is 2D WOFS (0.96 ± 0.03), and the third is 2D MULTI (0.96 ± 0.03). We performed the Kruskal-Wallis one-way ANOVA test with Dunn's multiple comparison tests using Bonferroni P-value correction on the results of the selected model of each study and found that 3D-MULTI, 2D-MULTI, 3D-WOFS, 2D-WOFS, 2D-FS, and 3D-FS were not statistically different in their distributions, which indicates that comparable results could be obtained in fat-suppressed and nonfat-suppressed volumes and that there is no significant difference between the 3D and 2D approach. Our results also suggested that the networks trained on single sequence images or multiple sequence images organized in multichannel images perform better than the models trained on a mixture of volumes from different sequences. Our investigation of the size of the training set revealed that training a U-Net in this domain only requires a modest amount of training data and results obtained with 49 and 70 training datasets were not significantly different. CONCLUSIONS To summarize, we investigated the use of 2D U-Nets and 3D U-Nets for breast volume segmentation in T1 fat-suppressed and without fat-suppressed volumes. Although our highest score was obtained in the 3D MULTI study, when we took advantage of information in both fat-suppressed and nonfat-suppressed volumes and their 3D structure, all of the methods we explored gave accurate segmentations with an average DSC on >94% demonstrating that the U-Net is a robust segmentation method for breast MRI volumes.
Collapse
Affiliation(s)
- Homa Fashandi
- Physical Sciences, Sunnybrook Research Institute, Toronto, Ontario, M4N 3M5, Canada
| | - Gregory Kuling
- Department of Medical Biophysics, University of Toronto, Toronto, Ontario, M5G 1L7, Canada
| | - Yingli Lu
- Physical Sciences, Sunnybrook Research Institute, Toronto, Ontario, M4N 3M5, Canada
| | - Hongbo Wu
- Department of Medical Biophysics, University of Toronto, Toronto, Ontario, M5G 1L7, Canada
| | - Anne L Martel
- Physical Sciences, Sunnybrook Research Institute, Toronto, Ontario, M4N 3M5, Canada.,Department of Medical Biophysics, University of Toronto, Toronto, Ontario, M5G 1L7, Canada
| |
Collapse
|
9
|
Artificial Intelligence for Breast MRI in 2008-2018: A Systematic Mapping Review. AJR Am J Roentgenol 2019; 212:280-292. [PMID: 30601029 DOI: 10.2214/ajr.18.20389] [Citation(s) in RCA: 36] [Impact Index Per Article: 7.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/22/2022]
Abstract
OBJECTIVE The purpose of this study is to review literature from the past decade on applications of artificial intelligence (AI) to breast MRI. MATERIALS AND METHODS In June 2018, a systematic search of the literature was performed to identify articles on the use of AI in breast MRI. For each article identified, the surname of the first author, year of publication, journal of publication, Web of Science Core Collection journal category, country of affiliation of the first author, study design, dataset, study aim(s), AI methods used, and, when available, diagnostic performance were recorded. RESULTS Sixty-seven studies, 58 (87%) of which had a retrospective design, were analyzed. When journal categories were considered, 36% of articles were identified as being included in the radiology and imaging journal category. Contrast-enhanced sequences were used for most AI applications (n = 50; 75%) and, on occasion, were combined with other MRI sequences (n = 8; 12%). Four main clinical aims were addressed: breast lesion classification (n = 36; 54%), image processing (n = 14; 21%), prognostic imaging (n = 9; 13%), and response to neoadjuvant therapy (n = 8; 12%). Artificial neural networks, support vector machines, and clustering were the most frequently used algorithms, accounting for 66%. The performance achieved and the most frequently used techniques were then analyzed according to specific clinical aims. Supervised learning algorithms were primarily used for lesion characterization, with the AUC value from ROC analysis ranging from 0.74 to 0.98 (median, 0.87) and with that from prognostic imaging ranging from 0.62 to 0.88 (median, 0.80), whereas unsupervised learning was mainly used for image processing purposes. CONCLUSION Interest in the application of advanced AI methods to breast MRI is growing worldwide. Although this growth is encouraging, the current performance of AI applications in breast MRI means that such applications are still far from being incorporated into clinical practice.
Collapse
|
10
|
Application of Radiomics and Decision Support Systems for Breast MR Differential Diagnosis. COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE 2018; 2018:7417126. [PMID: 30344618 PMCID: PMC6174735 DOI: 10.1155/2018/7417126] [Citation(s) in RCA: 16] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 02/28/2018] [Revised: 07/24/2018] [Accepted: 09/04/2018] [Indexed: 01/17/2023]
Abstract
Over the years, MR systems have evolved from imaging modalities to advanced computational systems producing a variety of numerical parameters that can be used for the noninvasive preoperative assessment of breast pathology. Furthermore, the combination with state-of-the-art image analysis methods provides a plethora of quantifiable imaging features, termed radiomics that increases diagnostic accuracy towards individualized therapy planning. More importantly, radiomics can now be complemented by the emerging deep learning techniques for further process automation and correlation with other clinical data which facilitate the monitoring of treatment response, as well as the prediction of patient's outcome, by means of unravelling of the complex underlying pathophysiological mechanisms which are reflected in tissue phenotype. The scope of this review is to provide applications and limitations of radiomics towards the development of clinical decision support systems for breast cancer diagnosis and prognosis.
Collapse
|
11
|
Thakran S, Chatterjee S, Singhal M, Gupta RK, Singh A. Automatic outer and inner breast tissue segmentation using multi-parametric MRI images of breast tumor patients. PLoS One 2018; 13:e0190348. [PMID: 29320532 PMCID: PMC5761869 DOI: 10.1371/journal.pone.0190348] [Citation(s) in RCA: 19] [Impact Index Per Article: 3.2] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/02/2017] [Accepted: 12/13/2017] [Indexed: 11/22/2022] Open
Abstract
The objectives of the study were to develop a framework for automatic outer and inner breast tissue segmentation using multi-parametric MRI images of the breast tumor patients; and to perform breast density and tumor tissue analysis. MRI of the breast was performed on 30 patients at 3T-MRI. T1, T2 and PD-weighted(W) images, with and without fat saturation(WWFS), and dynamic-contrast-enhanced(DCE)-MRI data were acquired. The proposed automatic segmentation approach was performed in two steps. In step-1, outer segmentation of breast tissue from rest of body parts was performed on structural images (T2-W/T1-W/PD-W without fat saturation images) using automatic landmarks detection technique based on operations like profile screening, Otsu thresholding, morphological operations and empirical observation. In step-2, inner segmentation of breast tissue into fibro-glandular(FG), fatty and tumor tissue was performed. For validation of breast tissue segmentation, manual segmentation was carried out by two radiologists and similarity coefficients(Dice and Jaccard) were computed for outer as well as inner tissues. FG density and tumor volume were also computed and analyzed. The proposed outer and inner segmentation approach worked well for all the subjects and was validated by two radiologists. The average Dice and Jaccard coefficients value for outer segmentation using T2-W images, obtained by two radiologists, were 0.977 and 0.951 respectively. These coefficient values for FG tissue were 0.915 and 0.875 respectively whereas for tumor tissue, values were 0.968 and 0.95 respectively. The volume of segmented tumor ranged over 2.1 cm3–7.08 cm3. The proposed approach provided automatic outer and inner breast tissue segmentation, which enables automatic calculations of breast tissue density and tumor volume. This is a complete framework for outer and inner breast segmentation method for all structural images.
Collapse
Affiliation(s)
- Snekha Thakran
- Centre for Biomedical Engineering, Indian Institute of Technology Delhi, New Delhi, India
| | - Subhajit Chatterjee
- Department of Computer Science and Engineering, Indian Institute of Technology Delhi, New Delhi, India
| | - Meenakshi Singhal
- Department of Radiology, Fortis Memorial Research Institute, Gurgaon, India
| | - Rakesh Kumar Gupta
- Department of Radiology, Fortis Memorial Research Institute, Gurgaon, India
| | - Anup Singh
- Centre for Biomedical Engineering, Indian Institute of Technology Delhi, New Delhi, India.,Department of Biomedical Engineering, All India Institute of Medical Sciences Delhi, New Delhi, India
| |
Collapse
|
12
|
Liu L, Li K, Qin W, Wen T, Li L, Wu J, Gu J. Automated breast tumor detection and segmentation with a novel computational framework of whole ultrasound images. Med Biol Eng Comput 2018; 56:183-199. [PMID: 29292471 DOI: 10.1007/s11517-017-1770-3] [Citation(s) in RCA: 21] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/17/2017] [Accepted: 12/13/2017] [Indexed: 01/12/2023]
Abstract
Due to the low contrast and ambiguous boundaries of the tumors in breast ultrasound (BUS) images, it is still a challenging task to automatically segment the breast tumors from the ultrasound. In this paper, we proposed a novel computational framework that can detect and segment breast lesions fully automatic in the whole ultrasound images. This framework includes several key components: pre-processing, contour initialization, and tumor segmentation. In the pre-processing step, we applied non-local low-rank (NLLR) filter to reduce the speckle noise. In contour initialization step, we cascaded a two-step Otsu-based adaptive thresholding (OBAT) algorithm with morphologic operations to effectively locate the tumor regions and initialize the tumor contours. Finally, given the initial tumor contours, the improved Chan-Vese model based on the ratio of exponentially weighted averages (CV-ROEWA) method was utilized. This pipeline was tested on a set of 61 breast ultrasound (BUS) images with diagnosed tumors. The experimental results in clinical ultrasound images prove the high accuracy and robustness of the proposed framework, indicating its potential applications in clinical practice. Graphical abstract ᅟ.
Collapse
Affiliation(s)
- Lei Liu
- Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, 518055, People's Republic of China
| | - Kai Li
- Department of Medical Ultrasonics, The Third Affiliated Hospital, Sun Yat-sen University, Guangzhou, 510630, People's Republic of China
| | - Wenjian Qin
- Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, 518055, People's Republic of China.,University of Chinese Academy of Sciences, Beijing, 100049, People's Republic of China
| | - Tiexiang Wen
- Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, 518055, People's Republic of China
| | - Ling Li
- Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, 518055, People's Republic of China
| | - Jia Wu
- Department of Radiation Oncology, Stanford University, Stanford, CA, 94305, USA.
| | - Jia Gu
- Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, 518055, People's Republic of China.
| |
Collapse
|
13
|
Doran SJ, Hipwell JH, Denholm R, Eiben B, Busana M, Hawkes DJ, Leach MO, Silva IDS. Breast MRI segmentation for density estimation: Do different methods give the same results and how much do differences matter? Med Phys 2017; 44:4573-4592. [PMID: 28477346 PMCID: PMC5697622 DOI: 10.1002/mp.12320] [Citation(s) in RCA: 17] [Impact Index Per Article: 2.4] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/20/2016] [Revised: 03/02/2017] [Accepted: 04/03/2017] [Indexed: 11/20/2022] Open
Abstract
PURPOSE To compare two methods of automatic breast segmentation with each other and with manual segmentation in a large subject cohort. To discuss the factors involved in selecting the most appropriate algorithm for automatic segmentation and, in particular, to investigate the appropriateness of overlap measures (e.g., Dice and Jaccard coefficients) as the primary determinant in algorithm selection. METHODS Two methods of breast segmentation were applied to the task of calculating MRI breast density in 200 subjects drawn from the Avon Longitudinal Study of Parents and Children, a large cohort study with an MRI component. A semiautomated, bias-corrected, fuzzy C-means (BC-FCM) method was combined with morphological operations to segment the overall breast volume from in-phase Dixon images. The method makes use of novel, problem-specific insights. The resulting segmentation mask was then applied to the corresponding Dixon water and fat images, which were combined to give Dixon MRI density values. Contemporaneously acquired T1 - and T2 -weighted image datasets were analyzed using a novel and fully automated algorithm involving image filtering, landmark identification, and explicit location of the pectoral muscle boundary. Within the region found, fat-water discrimination was performed using an Expectation Maximization-Markov Random Field technique, yielding a second independent estimate of MRI density. RESULTS Images are presented for two individual women, demonstrating how the difficulty of the problem is highly subject-specific. Dice and Jaccard coefficients comparing the semiautomated BC-FCM method, operating on Dixon source data, with expert manual segmentation are presented. The corresponding results for the method based on T1 - and T2 -weighted data are slightly lower in the individual cases shown, but scatter plots and interclass correlations for the cohort as a whole show that both methods do an excellent job in segmenting and classifying breast tissue. CONCLUSIONS Epidemiological results demonstrate that both methods of automated segmentation are suitable for the chosen application and that it is important to consider a range of factors when choosing a segmentation algorithm, rather than focus narrowly on a single metric such as the Dice coefficient.
Collapse
Affiliation(s)
- Simon J. Doran
- Division of Radiotherapy and Imaging, The Institute of Cancer ResearchCancer Research UK Cancer Imaging CentreLondonSM2 5NGUK
| | - John H. Hipwell
- Department of Medical Physics and BioengineeringUCL, Centre for Medical Image Computing (CMIC)LondonWC1E 7JEUK
| | - Rachel Denholm
- Department of Non‐Communicable Disease EpidemiologyLondon School of Hygiene & Tropical MedicineLondonWC1E 7HTUK
| | - Björn Eiben
- Department of Medical Physics and BioengineeringUCL, Centre for Medical Image Computing (CMIC)LondonWC1E 7JEUK
| | - Marta Busana
- Department of Non‐Communicable Disease EpidemiologyLondon School of Hygiene & Tropical MedicineLondonWC1E 7HTUK
| | - David J. Hawkes
- Department of Medical Physics and BioengineeringUCL, Centre for Medical Image Computing (CMIC)LondonWC1E 7JEUK
| | - Martin O. Leach
- Division of Radiotherapy and Imaging, The Institute of Cancer ResearchCancer Research UK Cancer Imaging CentreLondonSM2 5NGUK
| | - Isabel dos Santos Silva
- Department of Non‐Communicable Disease EpidemiologyLondon School of Hygiene & Tropical MedicineLondonWC1E 7HTUK
| |
Collapse
|
14
|
Rispoli JV, Wright SM, Malloy CR, McDougall MP. Automated modification and fusion of voxel models to construct body phantoms with heterogeneous breast tissue: Application to MRI simulations. ACTA ACUST UNITED AC 2017; 7:1-7. [PMID: 28798837 DOI: 10.5430/jbgc.v7n1p1] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/06/2022]
Abstract
BACKGROUND Human voxel models incorporating detailed anatomical features are vital tools for the computational evaluation of electromagnetic (EM) fields within the body. Besides whole-body human voxel models, phantoms representing smaller heterogeneous anatomical features are often employed; for example, localized breast voxel models incorporating fatty and fibroglandular tissues have been developed for a variety of EM applications including mammography simulation and dosimetry, magnetic resonance imaging (MRI), and ultra-wideband microwave imaging. However, considering wavelength effects, electromagnetic modeling of the breast at sub-microwave frequencies necessitates detailed breast phantoms in conjunction with whole-body voxel models. METHODS Heterogeneous breast phantoms are sized to fit within radiofrequency coil hardware, modified by voxel-wise extrusion, and fused to whole-body models using voxel-wise, tissue-dependent logical operators. To illustrate the utility of this method, finite-difference time-domain simulations are performed using a whole-body model integrated with a variety of available breast phantoms spanning the standard four tissue density classifications representing the majority of the population. RESULTS The software library uses a combination of voxel operations to seamlessly size, modify, and fuse eleven breast phantoms to whole-body voxel models. The software is publicly available on GitHub and is linked to the file exchange at MATLAB® Central. Simulations confirm the proportions of fatty and fibroglandular tissues in breast phantoms have significant yet predictable implications on projected power deposition in tissue. CONCLUSIONS Breast phantoms may be modified and fused to whole-body voxel models using the software presented in this work; user considerations for the open-source software and resultant phantoms are discussed. Furthermore, results indicate simulating breast models as predominantly fatty tissue can considerably underestimate the potential for tissue heating in women with substantial fibroglandular tissue.
Collapse
Affiliation(s)
- Joseph V Rispoli
- Department of Biomedical Engineering, Texas A&M University, College Station, Texas, United States of America.,Weldon School of Biomedical Engineering, Purdue University, West Lafayette, Indiana, United States of America.,School of Electrical and Computer Engineering, Purdue University, West Lafayette, Indiana, United States of America
| | - Steven M Wright
- Department of Biomedical Engineering, Texas A&M University, College Station, Texas, United States of America.,Department of Electrical & Computer Engineering, Texas A&M University, College Station, Texas, United States of America
| | - Craig R Malloy
- Advanced Imaging Research Center, University of Texas Southwestern Medical Center, Dallas, Texas, United States of America.,Department of Radiology, University of Texas Southwestern Medical Center, Dallas, Texas, United States of America
| | - Mary P McDougall
- Department of Biomedical Engineering, Texas A&M University, College Station, Texas, United States of America.,Department of Electrical & Computer Engineering, Texas A&M University, College Station, Texas, United States of America
| |
Collapse
|