1
|
Yang X, Wang X, Zuo Z, Zeng W, Liu H, Zhou L, Wen Y, Long C, Tan S, Li X, Zeng Y. Radiomics-based analysis of dynamic contrast-enhanced magnetic resonance image: A prediction nomogram for lymphovascular invasion in breast cancer. Magn Reson Imaging 2024; 112:89-99. [PMID: 38971267 DOI: 10.1016/j.mri.2024.07.001] [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: 01/28/2024] [Revised: 06/11/2024] [Accepted: 07/03/2024] [Indexed: 07/08/2024]
Abstract
OBJECTIVE To develop and validate a nomogram for quantitively predicting lymphovascular invasion (LVI) of breast cancer (BC) based on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) radiomics and morphological features. METHODS We retrospectively divided 238 patients with BC into training and validation cohorts. Radiomic features from DCE-MRI were subdivided into A1 and A2, representing the first and second post-contrast images respectively. We utilized the minimal redundancy maximal relevance filter to extract radiomic features, then we employed the least absolute shrinkage and selection operator regression to screen these features and calculate individualized radiomics score (Rad score). Through the application of multivariate logistic regression, we built a prediction nomogram that integrated DCE-MRI radiomics and MR morphological features (MR-MF). The diagnostic capabilities were evaluated by comparing C-indices and calibration curves. RESULTS The diagnostic efficiency of the A1/A2 radiomics model surpassed that of the A1 and A2 alone. Furthermore, we incorporated the MR-MF (diffusion-weighted imaging rim sign, peritumoral edema) and optimized Radiomics into a hybrid nomogram. The C-indices for the training and validation cohorts were 0.868 (95% CI: 0.839-0.898) and 0.847 (95% CI: 0.787-0.907), respectively, indicating a good level of discrimination. Moreover, the calibration plots demonstrated excellent agreement in the training and validation cohorts, confirming the effectiveness of the calibration. CONCLUSION This nomogram combined MR-MF and A1/A2 Radiomics has the potential to preoperatively predict LVI in patients with BC.
Collapse
Affiliation(s)
- Xiuqi Yang
- Department of Radiology, Xiangtan Central Hospital, No. 120, Heping Road, Yuhu District, Xiangtan, Hunan 411000, China
| | - Xuefei Wang
- Breast Surgery Department, Chinese Academy of Medical Sciences and Peking Union Medical College, Peking Union Medical College and Hospital, Beijing 100000, China
| | - Zhichao Zuo
- The School of Mathematics and Computational Science, Xiangtan University, Xiangtan, Hunan 411105, China
| | - Weihua Zeng
- Department of Radiology, Xiangtan Central Hospital, No. 120, Heping Road, Yuhu District, Xiangtan, Hunan 411000, China
| | - Haibo Liu
- Department of Radiology, Xiangtan Central Hospital, No. 120, Heping Road, Yuhu District, Xiangtan, Hunan 411000, China
| | - Lu Zhou
- Department of Radiology, Xiangtan Central Hospital, No. 120, Heping Road, Yuhu District, Xiangtan, Hunan 411000, China
| | - Yizhou Wen
- Department of Radiology, Xiangtan Central Hospital, No. 120, Heping Road, Yuhu District, Xiangtan, Hunan 411000, China
| | - Chuang Long
- Department of Radiology, Xiangtan Central Hospital, No. 120, Heping Road, Yuhu District, Xiangtan, Hunan 411000, China
| | - Siying Tan
- Department of Radiology, Xiangtan Central Hospital, No. 120, Heping Road, Yuhu District, Xiangtan, Hunan 411000, China
| | - Xiong Li
- Department of Radiology, Xiangtan Central Hospital, No. 120, Heping Road, Yuhu District, Xiangtan, Hunan 411000, China.
| | - Ying Zeng
- Department of Radiology, Xiangtan Central Hospital, No. 120, Heping Road, Yuhu District, Xiangtan, Hunan 411000, China.
| |
Collapse
|
2
|
Zhang J, Yin Z, Zhang J, Song R, Cui Y, Yang X. Preoperative MRI Features Associated With Axillary Nodal Burden and Disease-Free Survival in Patients With Early-Stage Breast Cancer. Korean J Radiol 2024; 25:788-797. [PMID: 39197824 PMCID: PMC11361803 DOI: 10.3348/kjr.2024.0196] [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: 11/29/2023] [Revised: 05/20/2024] [Accepted: 06/27/2024] [Indexed: 09/01/2024] Open
Abstract
OBJECTIVE To investigate the potential association among preoperative breast MRI features, axillary nodal burden (ANB), and disease-free survival (DFS) in patients with early-stage breast cancer. MATERIALS AND METHODS We retrospectively reviewed 297 patients with early-stage breast cancer (cT1-2N0M0) who underwent preoperative MRI between December 2016 and December 2018. Based on the number of positive axillary lymph nodes (LNs) determined by postoperative pathology, the patients were divided into high nodal burden (HNB; ≥3 positive LNs) and non-HNB (<3 positive LNs) groups. Univariable and multivariable logistic regression analyses were performed to identify independent risk factors associated with ANB. Predictive efficacy was evaluated using the receiver operating characteristic (ROC) curve and area under the curve (AUC). Univariable and multivariable Cox proportional hazards regression analyses were performed to determine preoperative features associated with DFS. RESULTS We included 47 and 250 patients in the HNB and non-HNB groups, respectively. Multivariable logistic regression analysis revealed that multifocality/multicentricity (adjusted odds ratio [OR] = 3.905, 95% confidence interval [CI]: 1.685-9.051, P = 0.001) and peritumoral edema (adjusted OR = 3.734, 95% CI: 1.644-8.479, P = 0.002) were independent risk factors for HNB. Combined peritumoral edema and multifocality/multicentricity achieved an AUC of 0.760 (95% CI: 0.707-0.807) for predicting HNB, with a sensitivity and specificity of 83.0% and 63.2%, respectively. During the median follow-up period of 45 months (range, 5-61 months), 26 cases (8.75%) of breast cancer recurrence were observed. Multivariable Cox proportional hazards regression analysis indicated that younger age (adjusted hazard ratio [HR] = 3.166, 95% CI: 1.200-8.352, P = 0.021), larger tumor size (adjusted HR = 4.370, 95% CI: 1.671-11.428, P = 0.002), and multifocality/multicentricity (adjusted HR = 5.059, 95% CI: 2.166-11.818, P < 0.001) were independently associated with DFS. CONCLUSION Preoperative breast MRI features may be associated with ANB and DFS in patients with early-stage breast cancer.
Collapse
Affiliation(s)
- Junjie Zhang
- Cancer Hospital Affiliated to Shanxi Medical University/Shanxi Province Cancer Hospital/Shanxi Hospital Affiliated to Cancer Hospital, Chinese Academy of Medical Sciences, Taiyuan, China
| | - Zhi Yin
- College of Medical Imaging, Shanxi Medical University, Taiyuan, China
| | - Jianxin Zhang
- Cancer Hospital Affiliated to Shanxi Medical University/Shanxi Province Cancer Hospital/Shanxi Hospital Affiliated to Cancer Hospital, Chinese Academy of Medical Sciences, Taiyuan, China
| | - Ruirui Song
- Cancer Hospital Affiliated to Shanxi Medical University/Shanxi Province Cancer Hospital/Shanxi Hospital Affiliated to Cancer Hospital, Chinese Academy of Medical Sciences, Taiyuan, China
| | - Yanfen Cui
- Cancer Hospital Affiliated to Shanxi Medical University/Shanxi Province Cancer Hospital/Shanxi Hospital Affiliated to Cancer Hospital, Chinese Academy of Medical Sciences, Taiyuan, China.
| | - Xiaotang Yang
- Cancer Hospital Affiliated to Shanxi Medical University/Shanxi Province Cancer Hospital/Shanxi Hospital Affiliated to Cancer Hospital, Chinese Academy of Medical Sciences, Taiyuan, China.
| |
Collapse
|
3
|
Liu W, Li L, Deng J, Li W. A comprehensive approach for evaluating lymphovascular invasion in invasive breast cancer: Leveraging multimodal MRI findings, radiomics, and deep learning analysis of intra- and peritumoral regions. Comput Med Imaging Graph 2024; 116:102415. [PMID: 39032451 DOI: 10.1016/j.compmedimag.2024.102415] [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: 11/13/2023] [Revised: 07/02/2024] [Accepted: 07/03/2024] [Indexed: 07/23/2024]
Abstract
PURPOSE To evaluate lymphovascular invasion (LVI) in breast cancer by comparing the diagnostic performance of preoperative multimodal magnetic resonance imaging (MRI)-based radiomics and deep-learning (DL) models. METHODS This retrospective study included 262 patients with breast cancer-183 in the training cohort (144 LVI-negative and 39 LVI-positive cases) and 79 in the validation cohort (59 LVI-negative and 20 LVI-positive cases). Radiomics features were extracted from the intra- and peritumoral breast regions using multimodal MRI to generate gross tumor volume (GTV)_radiomics and gross tumor volume plus peritumoral volume (GPTV)_radiomics. Subsequently, DL models (GTV_DL and GPTV_DL) were constructed based on the GTV and GPTV to determine the LVI status. Finally, the most effective radiomics and DL models were integrated with imaging findings to establish a hybrid model, which was converted into a nomogram to quantify the LVI risk. RESULTS The diagnostic efficiency of GPTV_DL was superior to that of GTV_DL (areas under the curve [AUCs], 0.771 and 0.720, respectively). Similarly, GPTV_radiomics outperformed GTV_radiomics (AUC, 0.685 and 0.636, respectively). Univariate and multivariate logistic regression analyses revealed an association between imaging findings, such as MRI-axillary lymph nodes and peritumoral edema (AUC, 0.665). The hybrid model achieved the highest accuracy by combining GPTV_DL, GPTV_radiomics, and imaging findings (AUC, 0.872). CONCLUSION The diagnostic efficiency of the GPTV-derived radiomics and DL models surpassed that of the GTV-derived models. Furthermore, the hybrid model, which incorporated GPTV_DL, GPTV_radiomics, and imaging findings, demonstrated the effective determination of LVI status prior to surgery in patients with breast cancer.
Collapse
Affiliation(s)
- Wen Liu
- Department of Radiology, The Third Xiangya Hospital of Central South University, Changsha, Hunan 410013, China.
| | - Li Li
- Department of Radiology, Hunan Children's Hospital, Changsha, Hunan 410007, China.
| | - Jiao Deng
- Department of Radiology, The Third Xiangya Hospital of Central South University, Changsha, Hunan 410013, China.
| | - Wei Li
- Department of Radiology, The Third Xiangya Hospital of Central South University, Changsha, Hunan 410013, China; Cell Transplantation and Gene Therapy Institute, The Third Xiangya Hospital, Central South University, Changsha, Hunan 410013, China.
| |
Collapse
|
4
|
Zhao S, Li Y, Ning N, Liang H, Wu Y, Wu Q, Wang Z, Tian J, Yang J, Gao X, Liu A, Song Q, Zhang L. Association of peritumoral region features assessed on breast MRI and prognosis of breast cancer: a systematic review and meta-analysis. Eur Radiol 2024; 34:6108-6120. [PMID: 38334760 DOI: 10.1007/s00330-024-10612-y] [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: 07/31/2023] [Revised: 12/03/2023] [Accepted: 01/01/2024] [Indexed: 02/10/2024]
Abstract
BACKGROUND Increasing attention has been given to the peritumoral region. However, conflicting findings have been reported regarding the relationship between peritumoral region features on MRI and the prognosis of breast cancer. PURPOSE To evaluate the relationship between peritumoral region features on MRI and prognosis of breast cancer. MATERIALS AND METHODS A retrospective meta-analysis of observational studies comparing either qualitative or quantitative assessments of peritumoral MRI features on breast cancer with poor prognosis and control subjects was performed for studies published till October 2022. Pooled odds ratios (ORs) or standardized mean differences and 95% confidence intervals (CIs) were estimated by using random-effects models. The heterogeneity across the studies was measured using the statistic I2. Sensitivity analyses were conducted to test this association according to different study characteristics. RESULTS Twenty-four studies comprising 1853 breast cancers of poor prognosis and 2590 control participants were included in the analysis. Peritumoral edema was associated with non-luminal breast cancers (OR=3.56; 95%CI: 2.17, 5.83; p=.000), high expression of the Ki-67 index (OR=3.70; 95%CI: 2.41, 5.70; p =.000), high histological grade (OR=5.85; 95%CI: 3.89, 8.80; p=.000), lymph node metastasis (OR=2.83; 95%CI: 1.71, 4.67; p=.000), negative expression of HR (OR=3.15; 95%CI: 2.03, 4.88; p=.000), and lymphovascular invasion (OR=1.72; 95%CI: 1.28, 2.30; p=.000). The adjacent vessel sign was associated with greater odds of breast cancer with poor prognosis (OR=2.02; 95%CI: 1.68, 2.44; p=.000). Additionally, breast cancers with poor prognosis had higher peritumor-tumor ADC ratio (SMD=0.67; 95%CI: 0.54, 0.79; p=.000) and peritumoral ADCmean (SMD=0.29; 95%CI: 0.15, 0.42; p=.000). A peritumoral region of 2-20 mm away from the margin of the tumor is recommended. CONCLUSION The presence of peritumoral edema and adjacent vessel signs, higher peritumor-tumor ADC ratio, and peritumoral ADCmean were significantly correlated with poor prognosis of breast cancer. CLINICAL RELEVANCE STATEMENT MRI features of the peritumoral region can be used as a non-invasive index for the prognostic evaluation of invasive breast cancer. KEY POINTS • Peritumoral edema was positively associated with non-luminal breast cancer, high expression of the Ki-67 index, high histological grade, lymph node metastasis, negative expression of HR, and lymphovascular invasion. • The adjacent vessel sign was associated with greater odds of breast cancers with poor prognosis. • Breast cancers with poor prognosis had higher peritumor-tumor ADC ratio and peritumoral ADCmean.
Collapse
Affiliation(s)
- Siqi Zhao
- Department of Radiology, First Affiliated Hospital of Dalian Medical University, No 222 Zhongshan Road, Xigang District, Dalian, Liaoning, 116011, People's Republic of China
| | - Yuanfei Li
- Department of Radiology, First Affiliated Hospital of Dalian Medical University, No 222 Zhongshan Road, Xigang District, Dalian, Liaoning, 116011, People's Republic of China
| | - Ning Ning
- Department of Radiology, First Affiliated Hospital of Dalian Medical University, No 222 Zhongshan Road, Xigang District, Dalian, Liaoning, 116011, People's Republic of China
| | - Hongbing Liang
- Department of Radiology, First Affiliated Hospital of Dalian Medical University, No 222 Zhongshan Road, Xigang District, Dalian, Liaoning, 116011, People's Republic of China
| | - Yueqi Wu
- Department of Radiology, First Affiliated Hospital of Dalian Medical University, No 222 Zhongshan Road, Xigang District, Dalian, Liaoning, 116011, People's Republic of China
| | - Qi Wu
- Department of Radiology, First Affiliated Hospital of Dalian Medical University, No 222 Zhongshan Road, Xigang District, Dalian, Liaoning, 116011, People's Republic of China
| | - Zhuo Wang
- Department of Radiology, First Affiliated Hospital of Dalian Medical University, No 222 Zhongshan Road, Xigang District, Dalian, Liaoning, 116011, People's Republic of China
| | - Jiahe Tian
- Zhongshan College of Dalian Medical University, No28 Aixian Road, Gaoxin District, Dalian, Liaoning, 116085, People's Republic of China
| | - Jie Yang
- School of Public Health, Dalian Medical University, Dalian, Liaoning Province, No. 9W. Lvshun South Road, Dalian, 116044, People's Republic of China
| | - Xue Gao
- Department of Pathology, First Affiliated Hospital of Dalian Medical University, 222 Zhongshan Road, Dalian, Liaoning, 116011, People's Republic of China
| | - Ailian Liu
- Department of Radiology, First Affiliated Hospital of Dalian Medical University, No 222 Zhongshan Road, Xigang District, Dalian, Liaoning, 116011, People's Republic of China
| | - Qingwei Song
- Department of Radiology, First Affiliated Hospital of Dalian Medical University, No 222 Zhongshan Road, Xigang District, Dalian, Liaoning, 116011, People's Republic of China
| | - Lina Zhang
- Department of Radiology, First Affiliated Hospital of Dalian Medical University, No 222 Zhongshan Road, Xigang District, Dalian, Liaoning, 116011, People's Republic of China.
| |
Collapse
|
5
|
Ma Q, Lu X, Chen Q, Gong H, Lei J. Multiphases DCE-MRI Radiomics Nomogram for Preoperative Prediction of Lymphovascular Invasion in Invasive Breast Cancer. Acad Radiol 2024:S1076-6332(24)00365-9. [PMID: 39107190 DOI: 10.1016/j.acra.2024.06.007] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/15/2024] [Revised: 06/03/2024] [Accepted: 06/03/2024] [Indexed: 08/09/2024]
Abstract
RATIONALE AND OBJECTIVES Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) radiomics had been used to evaluate lymphovascular invasion (LVI) in patients with breast cancer. However, no studies had explored the associations between features from delayed phase as well as multiphases DCE-MRI and the LVI status. Thus, we aimed to develop an efficient nomogram based on multiphases DCE-MRI to predict the LVI status in invasive (IBC) breast cancer patients. MATERIALS AND METHODS A retrospective analysis was conducted on preoperative clinical, pathological, and DCE-MRI data of 173 breast cancer patients. All patients were randomly assigned into training set (n=121) and validation set (n=52) in 7:3 ratio. The clinical, pathologic, and conventional MRI characteristics were then subjected to univariate and multivariate logistic regression analysis, and the clinical risk factors with P < 0.05 in the multivariate logistic regression were used to build clinical models. Different single-phase models (early phase, peak phase, and terminal phase), as well as a multiphases model integrating radiomics features from multiple phases, were established. Furthermore, a preoperative radiomics nomogram model was constructed by combining the rad-score of the multiphases model with clinicopathologic independent risk factors. Finally, the performance of the multiphases model, clinical model, and rad-score was compared using receiver operating characteristic (ROC) curves, area under the curve (AUC) values, and decision curve analysis (DCA). The clinical utility of the rad-score was evaluated using calibration curves, and Delong test was used to compare the differences in AUC values among the different models. RESULTS The axillary lymph nodes (ALN) status and Ki-67 had been identified as clinicopathologic independent predictors and a clinical model had been constructed. Image features that were extracted from the terminal phase of the DCE-MRI exhibited notably superior predictive performances compared to features from the other single phases. Particularly, in the multiphases model, terminal phase features were identified as potentially providing more predictive information. Among the nine features that were found to be associated with LVI in the multiphase model, one was derived from the early phase, two from the peak phase, and six from the terminal phase, indicating that terminal phase features contributed significantly more information towards predicting LVI. Evaluation of the nomogram performance revealed promising results in both the training set (AUCs: clinical model vs. multiphase model vs. nomogram=0.734 vs. 0.840 vs. 0.876) and the validation set (AUCs: clinical model vs. multiphase model vs. nomogram=0.765 vs. 0.753 vs. 0.832). CONCLUSION The DCE-MRI-based radiomics model demonstrated utility in predicting LVI status, features of the terminal phase offered more valuable information particularly. The preoperative radiomics nomogram enhanced the diagnostic capability of identifying LVI status in IBC patients, and might aid clinicians in making personalized treatment decisions.
Collapse
Affiliation(s)
- Qinqin Ma
- Gansu Provincial Hospital of Traditional Chinese Medicine, Lanzhou 730000, China; The First Clinical Medicine School of Lanzhou University, Lanzhou 730000, China
| | - Xingru Lu
- Department of Radiology, the First Hospital of Lanzhou University, Lanzhou 730000, China; Intelligent Imaging Medical Engineering Research Center of Gansu Province, Lanzhou 730000, China; Accurate Image Collaborative Innovation International Science and Technology Cooperation Base of Gansu Province, Lanzhou 730000, China
| | - Qitian Chen
- The General Hospital of Gansu Province in the Chinese Armed Police Force, Lanzhou 730000, China
| | - Hengxin Gong
- The First Clinical Medicine School of Lanzhou University, Lanzhou 730000, China
| | - Junqiang Lei
- The First Clinical Medicine School of Lanzhou University, Lanzhou 730000, China; Department of Radiology, the First Hospital of Lanzhou University, Lanzhou 730000, China; Intelligent Imaging Medical Engineering Research Center of Gansu Province, Lanzhou 730000, China; Accurate Image Collaborative Innovation International Science and Technology Cooperation Base of Gansu Province, Lanzhou 730000, China.
| |
Collapse
|
6
|
Xie S, Tang W, Zhang C, Wang J, Wang M, Zhou Y. Classification of breast edema on T2-weighted imaging for predicting sentinel lymph node metastasis and biological behavior in breast cancer. Clin Radiol 2024; 79:e1003-e1009. [PMID: 38763808 DOI: 10.1016/j.crad.2024.04.014] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/31/2024] [Revised: 04/16/2024] [Accepted: 04/24/2024] [Indexed: 05/21/2024]
Abstract
OBJECTIVE To determine whether preoperative classification of breast edema on T2-weighted imaging (T2WI) is useful for predicting sentinel lymph node (SLN) metastasis and biological behavior in patients with early-stage breast cancer. METHODS This retrospective study involved 341 women with breast cancer who underwent breast MRI from January 2019 to March 2022. Breast edema was scored on a scale of 1-4 on T2WI (1, no edema; 2, peritumoral edema; 3, prepectoral edema; and 4, subcutaneous edema). A logistic regression model was employed for univariate and multivariate analyses. A clinicopathological model was established using independent influencing factors identified in the multivariate analyses, excluding breast edema score (BES). Subsequently, BES was incorporated into this model to establish a combined BES model. The AUC and Delong test were used to examine the additional predictive value of the BES. RESULTS Logistic regression analysis showed that breast edema was an independent risk factor for SLN metastasis. The combined BES model significantly improved the predictive performance of SLN metastasis compared with the clinicopathological model alone (AUC, 0.77 vs. 0.71; p=0.005). In addition, the BES was significantly positively correlated with the tumor diameter (p<0.001), histologic grade (p=0.001), Ki-67 index (p<0.001), and non-luminal subtypes (p<0.001). CONCLUSION The BES on T2WI is useful for predicting SLN metastasis. A higher grade of breast edema is associated with breast cancer aggressiveness and increases the probability of SLN metastasis.
Collapse
Affiliation(s)
- S Xie
- Departments of Radiology, Yijishan Hospital of Wannan Medical College, Wuhu 241001, Anhui, China; Departments of Radiology, Fuyang Hospital of Anhui Medical University, Fuyang 236000, Anhui, China
| | - W Tang
- Department of Radiology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei, China
| | - C Zhang
- Departments of Radiology, Yijishan Hospital of Wannan Medical College, Wuhu 241001, Anhui, China
| | - J Wang
- Departments of Radiology, Yijishan Hospital of Wannan Medical College, Wuhu 241001, Anhui, China
| | - M Wang
- Departments of Radiology, Yijishan Hospital of Wannan Medical College, Wuhu 241001, Anhui, China
| | - Y Zhou
- Departments of Radiology, Yijishan Hospital of Wannan Medical College, Wuhu 241001, Anhui, China.
| |
Collapse
|
7
|
Liang R, Li F, Yao J, Tong F, Hua M, Liu J, Shi C, Sui L, Lu H. Predictive value of MRI-based deep learning model for lymphovascular invasion status in node-negative invasive breast cancer. Sci Rep 2024; 14:16204. [PMID: 39003325 PMCID: PMC11246470 DOI: 10.1038/s41598-024-67217-0] [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: 08/18/2023] [Accepted: 07/09/2024] [Indexed: 07/15/2024] Open
Abstract
To retrospectively assess the effectiveness of deep learning (DL) model, based on breast magnetic resonance imaging (MRI), in predicting preoperative lymphovascular invasion (LVI) status in patients diagnosed with invasive breast cancer who have negative axillary lymph nodes (LNs). Data was gathered from 280 patients, including 148 with LVI-positive and 141 with LVI-negative lesions. These patients had undergone preoperative breast MRI and were histopathologically confirmed to have invasive breast cancer without axillary LN metastasis. The cohort was randomly split into training and validation groups in a 7:3 ratio. Radiomics features for each lesion were extracted from the first post-contrast dynamic contrast-enhanced (DCE)-MRI. The Least Absolute Shrinkage and Selection Operator (LASSO) regression method and logistic regression analyses were employed to identify significant radiomic features and clinicoradiological variables. These models were established using four machine learning (ML) algorithms and one DL algorithm. The predictive performance of the models (radiomics, clinicoradiological, and combination) was assessed through discrimination and compared using the DeLong test. Four clinicoradiological parameters and 10 radiomic features were selected by LASSO for model development. The Multilayer Perceptron (MLP) model, constructed using both radiomic and clinicoradiological features, demonstrated excellent performance in predicting LVI, achieving a high area under the curve (AUC) of 0.835 for validation. The DL model (MLP-radiomic) achieved the highest accuracy (AUC = 0.896), followed by DL model (MLP-combination) with an AUC of 0.835. Both DL models were significantly superior to the ML model (RF-clinical) with an AUC of 0.720. The DL model (MLP), which integrates radiomic features with clinicoradiological information, effectively aids in the preoperative determination of LVI status in patients with invasive breast cancer and negative axillary LNs. This is beneficial for making informed clinical decisions.
Collapse
Affiliation(s)
- Rong Liang
- Department of Breast Imaging, Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center for Cancer, West Huan-Hu Road, Ti Yuan Bei, Hexi District, Tianjin, 300060, People's Republic of China
- Key Laboratory of Cancer Prevention and Therapy, Tianjin's Clinical Research Center for Cancer, Key Laboratory of Breast Cancer Prevention and Therapy, Tianjin Medical University, Ministry of Education, Tianjin, People's Republic of China
| | - Fangfang Li
- Department of Breast Imaging, Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center for Cancer, West Huan-Hu Road, Ti Yuan Bei, Hexi District, Tianjin, 300060, People's Republic of China
- Key Laboratory of Cancer Prevention and Therapy, Tianjin's Clinical Research Center for Cancer, Key Laboratory of Breast Cancer Prevention and Therapy, Tianjin Medical University, Ministry of Education, Tianjin, People's Republic of China
| | - Jingyuan Yao
- Department of Physiology and Biochemistry, School of Fundamental Medicine, Shanghai University of Medicine and Health Sciences, Shanghai, People's Republic of China
| | - Fang Tong
- Department of Physiology and Biochemistry, School of Fundamental Medicine, Shanghai University of Medicine and Health Sciences, Shanghai, People's Republic of China
- Institute of Wound Prevention and Treatment, Shanghai University of Medicine and Health Sciences, Shanghai, People's Republic of China
- Shanghai University of Medicine and Health Sciences Affiliated Zhoupu Hospital, Shanghai, People's Republic of China
| | - Minghui Hua
- Department of Radiology, Chest Hospital, Tianjin University, Tianjin, People's Republic of China
| | - Junjun Liu
- Department of Breast Imaging, Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center for Cancer, West Huan-Hu Road, Ti Yuan Bei, Hexi District, Tianjin, 300060, People's Republic of China
- Key Laboratory of Cancer Prevention and Therapy, Tianjin's Clinical Research Center for Cancer, Key Laboratory of Breast Cancer Prevention and Therapy, Tianjin Medical University, Ministry of Education, Tianjin, People's Republic of China
| | - Chenlei Shi
- Department of Physiology and Biochemistry, School of Fundamental Medicine, Shanghai University of Medicine and Health Sciences, Shanghai, People's Republic of China
| | - Lewen Sui
- Department of Physiology and Biochemistry, School of Fundamental Medicine, Shanghai University of Medicine and Health Sciences, Shanghai, People's Republic of China
| | - Hong Lu
- Department of Breast Imaging, Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center for Cancer, West Huan-Hu Road, Ti Yuan Bei, Hexi District, Tianjin, 300060, People's Republic of China.
- Key Laboratory of Cancer Prevention and Therapy, Tianjin's Clinical Research Center for Cancer, Key Laboratory of Breast Cancer Prevention and Therapy, Tianjin Medical University, Ministry of Education, Tianjin, People's Republic of China.
| |
Collapse
|
8
|
Ge W, Fan X, Zeng Y, Yang X, Zhou L, Zuo Z. Exploring habitats-based spatial distributions: improving predictions of lymphovascular invasion in invasive breast cancer. Acad Radiol 2024:S1076-6332(24)00355-6. [PMID: 38876841 DOI: 10.1016/j.acra.2024.05.043] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/19/2024] [Revised: 05/12/2024] [Accepted: 05/24/2024] [Indexed: 06/16/2024]
Abstract
RATIONALE AND OBJECTIVES Accurate assessment of lymphovascular invasion (LVI) in invasive breast cancer (IBC) plays a pivotal role in tailoring personalized treatment plans. This study aimed to investigate habitats-based spatial distributions to quantitatively measure tumor heterogeneity on multiparametric magnetic resonance imaging (MRI) scans and assess their predictive capability for LVI in patients with IBC. MATERIALS AND METHODS In this retrospective cohort study, we consecutively enrolled 241 women diagnosed with IBC between July 2020 and July 2023 and who had 1.5 T/T1-weighted images, fat-suppressed T2-weighted images, and dynamic contrast-enhanced MRI. Habitats-based spatial distributions were derived from the gross tumor volume (GTV) and gross tumor volume plus peritumoral volume (GPTV). GTV_habitats and GPTV_habitats were generated through sub-region segmentation, and their performances were compared. Subsequently, a combined nomogram was developed by integrating relevant spatial distributions with the identified MR morphological characteristics. Diagnostic performance was compared using receiver operating characteristic curve analysis and decision curve analysis. Statistical significance was set at p < 0.05. RESULTS GPTV_habitats exhibited superior performance compared to GTV_habitats. Consequently, the GPTV_habitats, diffusion-weighted imaging rim signs, and peritumoral edema were integrated to formulate the combined nomogram. This combined nomogram outperformed individual MR morphological characteristics and the GPTV_habitats index, achieving area under the curve values of 0.903 (0.847 -0.959), 0.770 (0.689 -0.852), and 0.843 (0.776 -0.910) in the training set and 0.931 (0.863 -0.999), 0.747 (0.613 -0.880), and 0.849 (0.759 -0.938) in the validation set. CONCLUSION The combined nomogram incorporating the GPTV_habitats and identified MR morphological characteristics can effectively predict LVI in patients with IBC.
Collapse
Affiliation(s)
- Wu Ge
- Department of Radiology, Xiangtan Central Hospital, Xiangtan, Hunan province 411000, PR China (W.G., Y.Z., X.Y., L.Z.).
| | - Xiaohong Fan
- School of Mathematics and Computational Science, Xiangtan University, Xiangtan 411105, Hunan province, PR China (X.F., Z.Z.).
| | - Ying Zeng
- Department of Radiology, Xiangtan Central Hospital, Xiangtan, Hunan province 411000, PR China (W.G., Y.Z., X.Y., L.Z.).
| | - Xiuqi Yang
- Department of Radiology, Xiangtan Central Hospital, Xiangtan, Hunan province 411000, PR China (W.G., Y.Z., X.Y., L.Z.).
| | - Lu Zhou
- Department of Radiology, Xiangtan Central Hospital, Xiangtan, Hunan province 411000, PR China (W.G., Y.Z., X.Y., L.Z.).
| | - Zhichao Zuo
- School of Mathematics and Computational Science, Xiangtan University, Xiangtan 411105, Hunan province, PR China (X.F., Z.Z.).
| |
Collapse
|
9
|
Yang X, Fan X, Lin S, Zhou Y, Liu H, Wang X, Zuo Z, Zeng Y. Assessment of Lymphovascular Invasion in Breast Cancer Using a Combined MRI Morphological Features, Radiomics, and Deep Learning Approach Based on Dynamic Contrast-Enhanced MRI. J Magn Reson Imaging 2024; 59:2238-2249. [PMID: 37855421 DOI: 10.1002/jmri.29060] [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: 06/17/2023] [Revised: 09/05/2023] [Accepted: 09/05/2023] [Indexed: 10/20/2023] Open
Abstract
BACKGROUND Assessment of lymphovascular invasion (LVI) in breast cancer (BC) primarily relies on preoperative needle biopsy. There is an urgent need to develop a non-invasive assessment method. PURPOSE To develop an effective model to assess the LVI status in patients with BC using magnetic resonance imaging morphological features (MRI-MF), Radiomics, and deep learning (DL) approaches based on dynamic contrast-enhanced MRI (DCE-MRI). STUDY TYPE Cross-sectional retrospective cohort study. POPULATION The study included 206 BC patients, with 136 in the training set [97 LVI(-) and 39 LVI(+) cases; median age: 51.5 years] and 70 in the test set [52 LVI(-) and 18 LVI(+) cases; median age: 48 years]. FIELD STRENGTH/SEQUENCE 1.5 T/T1-weighted images, fat-suppressed T2-weighted images, diffusion-weighted imaging (DWI), and DCE-MRI. ASSESSMENT The MRI-MF model was developed with conventional MR features using logistic analyses. The Radiomic feature extraction process involved collecting data from categorized DCE-MRI datasets, specifically the first and second post-contrast images (A1 and A2). Next, a DL model was implemented to determine LVI. Finally, we established a joint diagnosis model by combining the MRI-MF, Radiomics, and DL approaches. STATISTICAL TESTS Diagnostic performance was compared using receiver operating characteristic curve analysis, confusion matrix, and decision curve analysis. RESULTS Rim sign and peritumoral edema features were used to develop the MRI-MF model, while six Radiomics signature from the A1 and A2 images were used for the Radiomics model. The joint model (MRI-MF + Radiomics + DL models) achieved the highest accuracy (area under the curve [AUC] = 0.857), being significantly superior to the MRI-MF (AUC = 0.724), Radiomics (AUC = 0.736), or DL (AUC = 0.740) model. Furthermore, it also outperformed the pairwise combination models: Radiomics + MRI-MF (AUC = 0.796), DL + MRI-MF (AUC = 0.796), or DL + Radiomics (AUC = 0.826). DATA CONCLUSION The joint model incorporating MRI-MF, Radiomics, and DL approaches can effectively determine the LVI status in patients with BC before surgery. LEVEL OF EVIDENCE 4 TECHNICAL EFFICACY: Stage 2.
Collapse
Affiliation(s)
- Xiuqi Yang
- Department of Radiology, Xiangtan Central Hospital, Xiangtan, China
| | - Xiaohong Fan
- The School of Mathematics and Computational Science, Xiangtan University, Xiangtan, China
| | - Shanyue Lin
- Department of Radiology, Affiliated Hospital of Guilin Medical University, Guilin, China
| | - Yingjun Zhou
- Department of Radiology, Xiangtan Central Hospital, Xiangtan, China
| | - Haibo Liu
- Department of Radiology, Xiangtan Central Hospital, Xiangtan, China
| | - Xuefei Wang
- Department of Breast Surgery, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
| | - Zhichao Zuo
- The School of Mathematics and Computational Science, Xiangtan University, Xiangtan, China
| | - Ying Zeng
- Department of Radiology, Xiangtan Central Hospital, Xiangtan, China
| |
Collapse
|
10
|
Li X, Luo K, Zhang N, Chen W, Li B, Lu Z, Chen Y, Wu K. Prediction of Lymphovascular invasion status in breast cancer based on magnetic resonance imaging radiomics features. Magn Reson Imaging 2024; 109:91-95. [PMID: 38467265 DOI: 10.1016/j.mri.2024.03.008] [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: 08/30/2023] [Revised: 03/07/2024] [Accepted: 03/07/2024] [Indexed: 03/13/2024]
Abstract
OBJECTIVE This study intended to investigate the feasibility and effectiveness of using clinical magnetic resonance imaging (MRI) radiomics features to predict lymphovascular invasion (LVI) status in breast cancer (BC) patients. METHODS A total of 182 BC patients were retrospectively collected and randomly divided into a training set (n = 127) and a validation set (n = 55) in a 7:3 ratio. Based on pathological examination results, the training set was further divided into LVI group (n = 60) and non-LVI group (n = 67), and the validation set was divided into LVI group (n = 24) and non-LVI group (n = 31). General data and MRI examination indicators were compared. Multivariate logistic regression was utilized to analyze MRI radiomics features and clinically relevant indicators that were significant in the baseline information of patients in training set, independent risk factors were identified, and a logistic regression model was built. The accuracy of logistic model was validated using ROC curves in training and validation sets. RESULTS Age, pathohistological classification, tumor length, tumor width, presence or absence of Magnetic Resonance Spectroscopy (MRS) cho peak, presence or absence of spicule sign, peritumoral enhancement, and peritumoral edema were statistically significant (P < 0.05) between the two groups. Multivariate logistic regression analysis presented that spicule and peritumoral edema were independent risk factors for LVI in BC patients (P < 0.05). The ROC curve illustrated that AUC of the logistic regression model in the training set was 0.807 (95%CI: 0.730-0.885) and that in the validation set was 0.837 (95%CI: 0.731-0.944). CONCLUSION Radiomics features of spicule sign and peritumoral edema were independent risk factors for LVI in BC patients. A logistic regression model based on these factors, along with age, could accurately predict LVI occurrence in BC patients, providing data support for diagnosis and modeling of LVI in BC patients.
Collapse
Affiliation(s)
- Xinhua Li
- Department of Radiology, Affiliated Hospital of Guangdong Medical University, Zhanjiang 524001, China
| | - Kangwei Luo
- Department of Breast Surgery, Affiliated Hospital of Guangdong Medical University, Zhanjiang 524001, China
| | - Na Zhang
- Department of Obstetrics and Gynecology, Affiliated Hospital of Guangdong Medical University, Zhanjiang 524001, China
| | - Wubiao Chen
- Department of Radiology, Affiliated Hospital of Guangdong Medical University, Zhanjiang 524001, China
| | - Bin Li
- Department of Radiology, Affiliated Hospital of Guangdong Medical University, Zhanjiang 524001, China
| | - Zhendong Lu
- Department of Radiology, Affiliated Hospital of Guangdong Medical University, Zhanjiang 524001, China
| | - Yixian Chen
- Department of Radiology, Affiliated Hospital of Guangdong Medical University, Zhanjiang 524001, China
| | - Kangwei Wu
- Department of Radiology, Affiliated Hospital of Guangdong Medical University, Zhanjiang 524001, China.
| |
Collapse
|
11
|
Zheng H, Jian L, Li L, Liu W, Chen W. Delta-Radiomics Based on Dynamic Contrast-Enhanced MRI for Predicting Lymphovascular Invasion in Invasive Breast Cancer. Acad Radiol 2024; 31:1762-1772. [PMID: 38092588 DOI: 10.1016/j.acra.2023.11.017] [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: 09/28/2023] [Revised: 11/07/2023] [Accepted: 11/08/2023] [Indexed: 05/12/2024]
Abstract
RATIONALE AND OBJECTIVES Treatment strategies for invasive breast cancer require accurate lymphovascular invasion (LVI) predictions. This study aimed to investigate the effectiveness of delta radiomics based on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) for assessing LVI and develop a nomogram to aid treatment decisions. MATERIALS AND METHODS Overall, 293 patients with resectable invasive breast cancer underwent preoperative DCE-MRI. Radiomic features were extracted from pre-contrast (A0), first post-contrast (A1), and subtracted images of A0 and A1. Three radiomics models were developed using several data analyses; logistic analyses were performed to identify radiological features to predict the LVI status. A hybrid model integrating both radiological features and optimal radiomics was developed. Receiver operating characteristic analysis was employed to evaluate model performance, using the area under the curve (AUC) as a quantitative metric for discriminative ability. RESULTS In the test set, the Radiomics-Delta model, with 17 radiomic features, had an AUC of 0.781 and accuracy of 0.705. Radiomics-A0, with 10 features, had an AUC of 0.619 and accuracy of 0.523, while Radiomics-A1, with 8 features, had an AUC of 0.715 and accuracy of 0.591. The hybrid model exhibited better performance, with an AUC of 0.868 and accuracy of 0.875, than the radiological and Radiomics-Delta models, with an AUC of 0.759 and 0.781, respectively, and accuracy of 0.773 and 0.705, respectively. CONCLUSION Compared to Radiomics-A0 and Radiomics-A1, Radiomics-Delta demonstrated superior performance. Moreover, the hybrid model incorporating Radiomics-Delta and radiological features exhibited excellent performance in determining the LVI status in cases of invasive breast cancer.
Collapse
Affiliation(s)
- Hong Zheng
- Department of Radiology, Hunan Cancer Hospital, The Affiliated Cancer Hospital of Xiangya School of Medicine, Central South University, Changsha, 410013, Hunan, China (H.Z., L.J.)
| | - Lian Jian
- Department of Radiology, Hunan Cancer Hospital, The Affiliated Cancer Hospital of Xiangya School of Medicine, Central South University, Changsha, 410013, Hunan, China (H.Z., L.J.)
| | - Li Li
- Department of Radiology, Hunan Children's Hospital, Changsha, 410007, Hunan, China (L.L.)
| | - Wen Liu
- Department of Radiology, The Third Xiang Ya Hospital, Central South University, Changsha, 410013, Hunan, China (W.L.)
| | - Wei Chen
- Department of Radiology, The second People's Hospital of Hunan Province, Brain Hospital of Hunan Province, Changsha, 410007, Hunan, China (W.C.).
| |
Collapse
|
12
|
Zhang D, Zhou W, Lu WW, Qin XC, Zhang XY, Wang JL, Wu J, Luo YH, Duan YY, Zhang CX. Ultrasound-Based Deep Learning Radiomics Nomogram for the Assessment of Lymphovascular Invasion in Invasive Breast Cancer: A Multicenter Study. Acad Radiol 2024:S1076-6332(24)00217-4. [PMID: 38658211 DOI: 10.1016/j.acra.2024.04.010] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/22/2024] [Revised: 03/21/2024] [Accepted: 04/08/2024] [Indexed: 04/26/2024]
Abstract
RATIONALE AND OBJECTIVES The aim of this study was to develop a deep learning radiomics nomogram (DLRN) based on B-mode ultrasound (BMUS) and color doppler flow imaging (CDFI) images for preoperative assessment of lymphovascular invasion (LVI) status in invasive breast cancer (IBC). MATERIALS AND METHODS In this multicenter, retrospective study, 832 pathologically confirmed IBC patients were recruited from eight hospitals. The samples were divided into training, internal test, and external test sets. Deep learning and handcrafted radiomics features reflecting tumor phenotypes on BMUS and CDFI images were extracted. The BMUS score and CDFI score were calculated after radiomics feature selection. Subsequently, a DLRN was developed based on the scores and independent clinic-ultrasonic risk variables. The performance of the DLRN was evaluated for calibration, discrimination, and clinical usefulness. RESULTS The DLRN predicted the LVI with accuracy, achieving an area under the receiver operating characteristic curve of 0.93 (95% CI 0.90-0.95), 0.91 (95% CI 0.87-0.95), and 0.91 (95% CI 0.86-0.94) in the training, internal test, and external test sets, respectively, with good calibration. The DLRN demonstrated superior performance compared to the clinical model and single scores across all three sets (p < 0.05). Decision curve analysis and clinical impact curve confirmed the clinical utility of the model. Furthermore, significant enhancements in net reclassification improvement (NRI) and integrated discrimination improvement (IDI) indicated that the two scores could serve as highly valuable biomarkers for assessing LVI. CONCLUSION The DLRN exhibited strong predictive value for LVI in IBC, providing valuable information for individualized treatment decisions.
Collapse
Affiliation(s)
- Di Zhang
- Department of Ultrasound, The First Affiliated Hospital of Anhui Medical University, Hefei, Anhui 230022, China (D.Z., W.Z., W.W.L., X.C.Q., Y.Y.D., C.X.Z.)
| | - Wang Zhou
- Department of Ultrasound, The First Affiliated Hospital of Anhui Medical University, Hefei, Anhui 230022, China (D.Z., W.Z., W.W.L., X.C.Q., Y.Y.D., C.X.Z.)
| | - Wen-Wu Lu
- Department of Ultrasound, The First Affiliated Hospital of Anhui Medical University, Hefei, Anhui 230022, China (D.Z., W.Z., W.W.L., X.C.Q., Y.Y.D., C.X.Z.)
| | - Xia-Chuan Qin
- Department of Ultrasound, The First Affiliated Hospital of Anhui Medical University, Hefei, Anhui 230022, China (D.Z., W.Z., W.W.L., X.C.Q., Y.Y.D., C.X.Z.); Department of Ultrasound, Beijing Anzhen Hospital Nanchong Hospital, Nanchong Central Hospital, The Second Clinical Medical College, North Sichuan Medical College (University), Nan Chong, Sichuan 637000, China (X.C.Q.)
| | - Xian-Ya Zhang
- Department of Medical Ultrasound, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei 430030, China (X.Y.Z.)
| | - Jun-Li Wang
- Department of Ultrasound, WuHu Hospital, East China Normal University (The Second People's Hospital, WuHu), Wuhu, Anhui 241001, China (J.L.W.)
| | - Jun Wu
- Department of Ultrasound, The Second Affiliated Hospital of Anhui Medical University, Hefei, Anhui 230601, China (J.W.)
| | - Yan-Hong Luo
- The Third Affiliated Hospital of Anhui Medical University, Hefei First People's Hospital, Hefei, Anhui 230061, China (Y.H.L.)
| | - Ya-Yang Duan
- Department of Ultrasound, The First Affiliated Hospital of Anhui Medical University, Hefei, Anhui 230022, China (D.Z., W.Z., W.W.L., X.C.Q., Y.Y.D., C.X.Z.)
| | - Chao-Xue Zhang
- Department of Ultrasound, The First Affiliated Hospital of Anhui Medical University, Hefei, Anhui 230022, China (D.Z., W.Z., W.W.L., X.C.Q., Y.Y.D., C.X.Z.).
| |
Collapse
|
13
|
Jiang D, Qian Q, Yang X, Zeng Y, Liu H. Machine learning based on optimal VOI of multi-sequence MR images to predict lymphovascular invasion in invasive breast cancer. Heliyon 2024; 10:e29267. [PMID: 38623213 PMCID: PMC11016709 DOI: 10.1016/j.heliyon.2024.e29267] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/08/2023] [Revised: 03/24/2024] [Accepted: 04/03/2024] [Indexed: 04/17/2024] Open
Abstract
Objectives Lymphovascular invasion serves as a crucial prognostic indicator in invasive breast cancer, influencing treatment decisions. We aimed to develop a machine learning model utilizing optimal volumes of interest extracted from multisequence magnetic resonance images to predict lymphovascular invasion in patients with invasive breast cancer. Materials and methods This study comprised 191 patients postoperatively diagnosed with invasive breast cancer through multi-sequence magnetic resonance imaging. Independent predictors were identified through univariate and multivariate logistic regression analyses, culminating in the construction of a clinical model. Radiomic features were extracted from multi-sequence magnetic resonance imaging images across various volume of interest scales (-2 mm, entire, +2 mm, +4 mm, and +6 mm). Subsequently, various radiomic models were developed using machine learning model algorithms, including logistic regression, support vector machine, k-nearest neighbor, gradient boosting machine, classification and regression tree, and random forest. A hybrid model was then formulated, amalgamating optimal radiomic and clinical models. Results The area under the curve of the clinical model was 0.757. Among the radiomic models, the most efficient diagnosis was achieved by the k-nearest neighbor-based radiomics-volume of interest (+2 mm), resulting in an area under the curve of 0.780. The hybrid model, integrating the k-nearest neighbor-based radiomics-volume of interest (+2 mm), and the clinical model surpassed the individual clinical and radiomics models, exhibiting a superior area under the curve of 0.864. Conclusion Utilizing a hybrid approach integrating clinical data and multi-sequence magnetic resonance imaging-derived radiomics models based on the multiscale tumor region volume of interest (+2 mm) proved effective in determining lymphovascular invasion status in patients with invasive breast cancer. This innovative methodology may offer valuable insights for treatment planning and disease management.
Collapse
Affiliation(s)
- Dengke Jiang
- Department of Radiology, The Second Affiliated Hospital of Hunan University of Chinese Medicine, Changsha, Hunan, 410005, China
| | - Qiuqin Qian
- Department of Radiology, The Second Affiliated Hospital of Hunan University of Chinese Medicine, Changsha, Hunan, 410005, China
| | - Xiuqi Yang
- Department of Radiology, Xiangtan Central Hospital, Xiangtan, Hunan, 411100, China
| | - Ying Zeng
- Department of Radiology, Xiangtan Central Hospital, Xiangtan, Hunan, 411100, China
| | - Haibo Liu
- Department of Radiology, Xiangtan Central Hospital, Xiangtan, Hunan, 411100, China
| |
Collapse
|
14
|
Jiang W, Meng R, Cheng Y, Wang H, Han T, Qu N, Yu T, Hou Y, Xu S. Intra- and Peritumoral Based Radiomics for Assessment of Lymphovascular Invasion in Invasive Breast Cancer. J Magn Reson Imaging 2024; 59:613-625. [PMID: 37199241 DOI: 10.1002/jmri.28776] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/08/2022] [Revised: 04/28/2023] [Accepted: 04/28/2023] [Indexed: 05/19/2023] Open
Abstract
BACKGROUND Radiomics has been applied for assessing lymphovascular invasion (LVI) in patients with breast cancer. However, associations between features from peritumoral regions and the LVI status were not investigated. PURPOSE To investigate the value of intra- and peritumoral radiomics for assessing LVI, and to develop a nomogram to assist in making treatment decisions. STUDY TYPE Retrospective. POPULATION Three hundred and sixteen patients were enrolled from two centers and divided into training (N = 165), internal validation (N = 83), and external validation (N = 68) cohorts. FIELD STRENGTH/SEQUENCE 1.5 T and 3.0 T/dynamic contrast-enhanced (DCE) and diffusion-weighted imaging (DWI). ASSESSMENT Radiomics features were extracted and selected based on intra- and peritumoral breast regions in two magnetic resonance imaging (MRI) sequences to create the multiparametric MRI combined radiomics signature (RS-DCE plus DWI). The clinical model was built with MRI-axillary lymph nodes (MRI ALN), MRI-reported peritumoral edema (MPE), and apparent diffusion coefficient (ADC). The nomogram was constructed with RS-DCE plus DWI, MRI ALN, MPE, and ADC. STATISTICAL TESTS Intra- and interclass correlation coefficient analysis, Mann-Whitney U test, and least absolute shrinkage and selection operator regression were used for feature selection. Receiver operating characteristic and decision curve analyses were applied to compare performance of the RS-DCE plus DWI, clinical model, and nomogram. RESULTS A total of 10 features were found to be associated with LVI, 3 from intra- and 7 from peritumoral areas. The nomogram showed good performance in the training (AUCs, nomogram vs. clinical model vs. RS-DCE plus DWI, 0.884 vs. 0.695 vs. 0.870), internal validation (AUCs, nomogram vs. clinical model vs. RS-DCE plus DWI, 0.813 vs. 0.695 vs. 0.794), and external validation (AUCs, nomogram vs. clinical model vs. RS-DCE plus DWI, 0.862 vs. 0.601 vs. 0.849) cohorts. DATA CONCLUSION The constructed preoperative nomogram might effectively assess LVI. LEVEL OF EVIDENCE 3 TECHNICAL EFFICACY: Stage 2.
Collapse
Affiliation(s)
- Wenyan Jiang
- Department of Scientific Research and Academic, Cancer Hospital of China Medical University, Liaoning Cancer Hospital and Institute, Shenyang, China
| | - Ruiqing Meng
- Department of Biomedical Engineering, China Medical University, Shenyang, China
| | - Yuan Cheng
- Department of Biomedical Engineering, China Medical University, Shenyang, China
| | - Haotian Wang
- Department of Radiology, Cancer Hospital of China Medical University, Liaoning Cancer Hospital and Institute, Shenyang, China
| | - Tingting Han
- Department of Radiology, Shengjing Hospital of China Medical University, Shenyang, China
| | - Ning Qu
- Department of Radiology, Shengjing Hospital of China Medical University, Shenyang, China
| | - Tao Yu
- Department of Radiology, Cancer Hospital of China Medical University, Liaoning Cancer Hospital and Institute, Shenyang, China
| | - Yang Hou
- Department of Radiology, Shengjing Hospital of China Medical University, Shenyang, China
| | - Shu Xu
- Department of Radiology, Cancer Hospital of China Medical University, Liaoning Cancer Hospital and Institute, Shenyang, China
| |
Collapse
|
15
|
Zheng H, Jian L, Li L, Liu W, Chen W. Prior Clinico-Radiological Features Informed Multi-Modal MR Images Convolution Neural Network: A novel deep learning framework for prediction of lymphovascular invasion in breast cancer. Cancer Med 2024; 13:e6932. [PMID: 38230837 PMCID: PMC10905682 DOI: 10.1002/cam4.6932] [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: 10/18/2023] [Revised: 12/14/2023] [Accepted: 01/02/2024] [Indexed: 01/18/2024] Open
Abstract
BACKGROUND Current methods utilizing preoperative magnetic resonance imaging (MRI)-based radiomics for assessing lymphovascular invasion (LVI) in patients with early-stage breast cancer lack precision, limiting the options for surgical planning. PURPOSE This study aimed to develop a sophisticated deep learning framework called "Prior Clinico-Radiological Features Informed Multi-Modal MR Images Convolutional Neural Network (PCMM-Net)" to improve the accuracy of LVI prediction in breast cancer. By incorporating multiparameter MRI and prior clinical knowledge, PCMM-Net should enhance the precision of LVI assessment. METHODS A total of 341 patients with breast cancer were randomly divided into training and validation groups at a ratio of 7:3. Imaging features were extracted from T1-weighted, T2-weighted, and contrast-enhanced T1-weighted MRI sequences. Stepwise univariate and multivariate logistic regression were employed to establish a clinico-radiological model for LVI prediction. The radiomics model was built using redundancy and the least absolute shrinkage and selection operator. Then, two deep learning frameworks were developed: the Multi-Modal MR Images Convolutional Neural Network (MM-Net), which does not consider prior radiological features, and PCMM-Net, which incorporates multiparameter MRI and prior clinical knowledge. Receiver operating characteristic curves were used, and the corresponding areas under the curves (AUCs) were calculated for evaluation. RESULTS PCMM-Net achieved the highest AUC of 0.843. The clinico-radiological features displayed the lowest AUC value of 0.743, followed by MM-Net with an AUC of 0.774, and radiomics with an AUC of 0.795. CONCLUSIONS This study introduces PCMM-Net, an innovative deep learning framework that integrates prior clinico-radiological features for accurate LVI prediction in breast cancer. PCMM-Net demonstrates excellent diagnostic performance and facilitates the application of precision medicine.
Collapse
Affiliation(s)
- Hong Zheng
- Department of Radiology, Hunan Cancer Hospital, The Affiliated Cancer Hospital of Xiangya School of MedicineCentral South UniversityChangshaHunanChina
| | - Lian Jian
- Department of Radiology, Hunan Cancer Hospital, The Affiliated Cancer Hospital of Xiangya School of MedicineCentral South UniversityChangshaHunanChina
| | - Li Li
- Department of RadiologyHunan Children's HospitalChangshaHunanChina
| | - Wen Liu
- Department of RadiologyThe Third Xiang Ya HospitalCentral South UniversityChangshaHunanChina
| | - Wei Chen
- Department of RadiologyThe Second People's Hospital of Hunan Province, Brain Hospital of Hunan ProvinceChangshaHunanChina
| |
Collapse
|
16
|
Jiang Y, Zeng Y, Zuo Z, Yang X, Liu H, Zhou Y, Fan X. Leveraging multimodal MRI-based radiomics analysis with diverse machine learning models to evaluate lymphovascular invasion in clinically node-negative breast cancer. Heliyon 2024; 10:e23916. [PMID: 38192872 PMCID: PMC10772250 DOI: 10.1016/j.heliyon.2023.e23916] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/27/2023] [Revised: 12/12/2023] [Accepted: 12/15/2023] [Indexed: 01/10/2024] Open
Abstract
Objective This study aimed to investigate and validate the effectiveness of diverse radiomics models for preoperatively differentiating lymphovascular invasion (LVI) in clinically node-negative breast cancer (BC). Methods This study included 198 patients diagnosed with clinically node-negative bc and pathologically confirmed LVI status from January 2018-July 2023. The training dataset consisted of 138 patients, while the validation dataset included 60. Radiomics features were extracted from multimodal magnetic resonance imaging obtained from T1WI, T2WI, DCE, DWI, and ADC sequences. Dimensionality reduction and feature selection techniques were applied to the extracted features. Subsequently, machine learning approaches, including logistic regression, support vector machine, classification and regression trees, k-nearest neighbors, and gradient boosting machine models (GBM), were constructed using the radiomics features. The best-performing radiomic model was selected based on its performance using the confusion matrix. Univariate and multivariable logistic regression analyses were conducted to identify variables for developing a clinical-radiological (Clin-Rad) model. Finally, a combined model incorporating both radiomics and clinical-radiological model features was created. Results A total of 6195 radiomic features were extracted from multimodal magnetic resonance imaging. After applying dimensionality reduction and feature selection, seven valuable radiomics features were identified. Among the radiomics models, the GBM model demonstrated superior predictive efficiency and robustness, achieving area under the curve values (AUC) of 0.881 (0.823,0.940) and 0.820 (0.693,0.947) in the training and validation datasets, respectively. The Clin-Rad model was developed based on the peritumoral edema and DWI rim sign. In the training dataset, it achieved an AUC of 0.767 (0.681, 0.854), while in the validation dataset, it achieved an AUC of 0.734 (0.555-0.913). The combined model, which incorporated radiomics and the Clin-Rad model, showed the highest discriminatory capability. In the training dataset, it had an AUC value of 0.936 (0.892, 0.981), and in the validation dataset, it had an AUC value of 0.876 (0.757, 0.995). Additionally, decision curve analysis of the combined model revealed its optimal clinical efficacy. Conclusion The combined model, integrating radiomics and clinical-radiological features, exhibited excellent performance in distinguishing LVI status. This non-invasive and efficient approach holds promise for aiding clinical decision-making in the context of clinically node-negative BC.
Collapse
Affiliation(s)
- Yihong Jiang
- Department of Radiology, Xiangtan Central Hospital, Xiangtan, Hunan, 411100, China
| | - Ying Zeng
- Department of Radiology, Xiangtan Central Hospital, Xiangtan, Hunan, 411100, China
| | - Zhichao Zuo
- The School of Mathematics and Computational Science, Xiangtan University, Xiangtan, Hunan, 411105, China
| | - Xiuqi Yang
- Department of Radiology, Xiangtan Central Hospital, Xiangtan, Hunan, 411100, China
| | - Haibo Liu
- Department of Radiology, Xiangtan Central Hospital, Xiangtan, Hunan, 411100, China
| | - Yingjun Zhou
- Department of Radiology, Xiangtan Central Hospital, Xiangtan, Hunan, 411100, China
| | - Xiaohong Fan
- The School of Mathematics and Computational Science, Xiangtan University, Xiangtan, Hunan, 411105, China
| |
Collapse
|
17
|
Sang L, Liu Z, Huang C, Xu J, Wang H. Multiparametric MRI-based radiomics nomogram for predicting the hormone receptor status of HER2-positive breast cancer. Clin Radiol 2024; 79:60-66. [PMID: 37838543 DOI: 10.1016/j.crad.2023.09.013] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/25/2023] [Revised: 07/28/2023] [Accepted: 09/12/2023] [Indexed: 10/16/2023]
Abstract
AIM To investigate the value of multiparametric magnetic resonance imaging (MRI)-based radiomics nomograms for predicting the hormone receptor (HR) status of HER2-positive breast cancer. MATERIALS AND METHODS Patients with HER2-positive invasive breast cancer were divided randomly into training (68 patients) and validation (30 patients) sets. All were classified as either HR-positive (HR+) or negative (HR-) at histopathology. Two radiologists outlined the three-dimensional (3D) volumetric regions of interest (VOI) on the MRI images. Features (n=1,096) were extracted from the T2-weighted imaging (WI), apparent diffusion coefficient (ADC), and dynamic contrast-enhanced (DCE) images separately. Dimensionality was reduced using feature screening. Binary radiomics prediction models were established using a logistic regression classifier and were validated in the validation set. To construct a nomogram, independent predictors were identified using multivariate logistic regression analysis. The predictive efficacy of the model was assessed using the area under the receiver operating characteristic curve (AUC). RESULTS Ten radiomics features were obtained after feature dimensionality reduction based on the merged T2WI, ADC, and DCE images. The diagnostic efficacy of the radiomics signature using the three sequences was better than that of any single sequence (training set AUC: 0.797; validation set AUC: 0.75). Using multivariate logistic regression analysis, the independent predictors for identifying HR status were combined radiomics signature and peritumoural oedema. Nomograms constructed by combining the radiomics signature and peritumoural oedema showed good discrimination in both the training and validation sets (AUC: 0.815 and 0. 805, respectively). CONCLUSION A multiparametric MRI-based nomogram incorporating the radiomics signature and peritumoural oedema can assess the HR status of HER2-positive breast cancer. The resulting model can improve diagnostic accuracy, improving patient outcomes.
Collapse
Affiliation(s)
- L Sang
- Department of Radiology, Shandong Provincial Hospital, Affiliated to Shandong First Medical University, No. 324, Jingwu Road, Huaiyin District, Jinan 250012, Shandong, China
| | - Z Liu
- Department of Radiology, Shandong Provincial Hospital, Affiliated to Shandong First Medical University, No. 324, Jingwu Road, Huaiyin District, Jinan 250012, Shandong, China
| | - C Huang
- Department of Research Collaboration, R&D Center, Beijing Deepwise & League of, PHD Technology Co. Ltd, Beijing, China
| | - J Xu
- Department of Research Collaboration, R&D Center, Beijing Deepwise & League of, PHD Technology Co. Ltd, Beijing, China
| | - H Wang
- Department of Radiology, Shandong Provincial Hospital, Affiliated to Shandong First Medical University, No. 324, Jingwu Road, Huaiyin District, Jinan 250012, Shandong, China.
| |
Collapse
|
18
|
Coşkun Bilge A, Yaltırık Bilgin E, Bulut ZM, Esen Bostancı I, Bilgin E. Preoperative Dynamic Contrast-Enhanced and Diffusion-Weighted Breast Magnetic Resonance Imaging Findings for Prediction of Lymphovascular Invasion of the Lesions in Node-Negative Invasive Breast Cancer. Can Assoc Radiol J 2023:8465371231212893. [PMID: 38095635 DOI: 10.1177/08465371231212893] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/21/2023] Open
Abstract
Purpose: Our single-center retrospective study aimed to investigate the relationship between preoperative dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) findings and apparent diffusion coefficient (ADC) values and lymphovascular invasion (LVI) status of the lesions in patients with clinically-radiologically lymph node-negative invasive breast cancer. Methods: A total of 250 breast lesions diagnosed in preoperative magnetic resonance imaging were identified. All patients were divided into 2 subgroups: LVI-negative and LVI-positive according to the pathological findings of surgical specimens. The 2 groups' DCE-MRI findings, ADC values, and histopathological results of lesions were compared. Results: LVI was detected in 100 of 250 lesions. Younger age than 45 years and larger lesion size than 20 mm were found to be associated with the presence of LVI (P < .001). High histological and nuclear grade (P = .001), HER2-enriched molecular subtype (P = .001), and Ki-67 positivity (P = .016) were significantly associated with LVI. The LVI positivity rate was significantly higher in the lesions with medium-rapid initial phase kinetic curve and washout delayed phase kinetic curve (P = .001). The presence of LVI was significantly associated with the presence of peritumoral edema, sentinel lymph node metastasis, adjacent vessel sign, and increased whole breast vascularity (P < .001). When diffusion-weighted imaging findings were evaluated, it was determined that tumoral ADC values lower than 1068 × 10-6 mm2/second (P = .002) and peritumoral-tumoral ADC ratios higher than 1.5 (P = .001) statistically increased the probability of LVI. Conclusion: The patient's age, various histopathological and DCE-MRI findings, tumoral ADC value, and peritumoral-tumoral ADC ratio may be useful in the preoperative prediction of LVI status in breast cancer lesions.
Collapse
Affiliation(s)
- Almıla Coşkun Bilge
- Department of Radiology, Dr Abdurrahman Yurtaslan Ankara Oncology Training and Research Hospital, Ankara, Turkey
| | - Ezel Yaltırık Bilgin
- Department of Radiology, Dr Abdurrahman Yurtaslan Ankara Oncology Training and Research Hospital, Ankara, Turkey
| | - Zarife Melda Bulut
- Department of Pathology, Dr Abdurrahman Yurtaslan Ankara Oncology Training and Research Hospital, Ankara, Turkey
| | - Işıl Esen Bostancı
- Department of Radiology, Dr Abdurrahman Yurtaslan Ankara Oncology Training and Research Hospital, Ankara, Turkey
| | - Erkan Bilgin
- Department of Radiology, Dr Abdurrahman Yurtaslan Ankara Oncology Training and Research Hospital, Ankara, Turkey
| |
Collapse
|
19
|
Jia W, Chen X, Wang X, Zhang J, Tang T, Shi J. The Ongoing Necessity of Sentinel Lymph Node Biopsy for cT1-2N0 Breast Cancer Patients. Breast Care (Basel) 2023; 18:473-482. [PMID: 38125916 PMCID: PMC10730101 DOI: 10.1159/000532081] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/28/2023] [Accepted: 07/19/2023] [Indexed: 12/23/2023] Open
Abstract
Background Recent clinical trials attempt to determine whether it is appropriate to omit axillary lymph node surgery in patients with cT1-2N0 breast cancer. The study aimed to investigate the true extent of axillary node disease in patients with clinically negative nodes and explore the differences between negative axillary ultrasound (AUS-cN0) and suspicious axillary ultrasound with negative fine-needle aspiration (FNA-cN0). Methods Pathologically identified T1-2 invasive breast cancer patients with clinically negative nodes were retrospectively analyzed at our center between January 2019 and December 2022. Patients who received any systematic treatment before surgery were excluded from this study. Results A total of 538 patients were enrolled in this study. 134 (24.9%) patients had pathologically positive nodes, and 404 (75.1%) patients had negative nodes. Univariate analysis revealed that tumor size, T stage, Ki67 level, and vascular invasion (VI) were strongly associated with pathological axillary lymph node positivity. In multivariate analysis, VI was the only independent risk factor for node positivity in patients with cT1-2N0 disease (OR: 3.723, confidence interval [CI]: 2.380-5.824, p < 0.001). Otherwise, pathological node positivity was not significantly different between AUS-cN0 and FNA-cN0 groups (23.4% vs. 28.8%, p = 0.193). However, the rate of high nodal burden (≥3 positive nodes) was significantly higher in FNA-cN0 group. Further investigation revealed that FNA-cN0 and VI were independently associated with a high nodal burden (OR: 2.650, CI: 1.081-6.496, p = 0.033; OR: 3.521, CI: 1.249-9.931, p = 0.017, respectively). Conclusions cT1-2 breast cancer patients with clinically negative axillary lymph nodes may have pathologically positive lymph nodes and even a high nodal burden. False negatives in AUS and AUS-guided FNA should not be ignored, and sentinel lymph node biopsy remains an ongoing necessity for cT1-2N0 breast cancer patients.
Collapse
Affiliation(s)
- Wenjun Jia
- Department of General Surgery, The Second Affiliated Hospital of Anhui Medical University, Hefei, China
| | - Xiao Chen
- Department of General Surgery, The Second Affiliated Hospital of Anhui Medical University, Hefei, China
| | - Xinyu Wang
- Department of General Surgery, The Second Affiliated Hospital of Anhui Medical University, Hefei, China
| | - Jianzhong Zhang
- Department of General Surgery, The Second Affiliated Hospital of Anhui Medical University, Hefei, China
| | - Tong Tang
- Department of General Surgery, The Second Affiliated Hospital of Anhui Medical University, Hefei, China
| | - Jianing Shi
- Department of General Surgery, The Second Affiliated Hospital of Anhui Medical University, Hefei, China
| |
Collapse
|
20
|
Wu Z, Lin Q, Song H, Chen J, Wang G, Fu G, Cui C, Su X, Li L, Bian T. Evaluation of Lymphatic Vessel Invasion Determined by D2-40 Using Preoperative MRI-Based Radiomics for Invasive Breast Cancer. Acad Radiol 2023; 30:2458-2468. [PMID: 36586760 DOI: 10.1016/j.acra.2022.11.024] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/12/2022] [Revised: 11/14/2022] [Accepted: 11/18/2022] [Indexed: 12/30/2022]
Abstract
RATIONALE AND OBJECTIVES Preoperative prediction of LVI status can facilitate personalized therapeutic planning. This study aims to investigate the efficacy of preoperative MRI-based radiomics for predicting lymphatic vessel invasion (LVI) determined by D2-40 in patients with invasive breast cancer. MATERIALS AND METHODS A total of 203 patients with pathologically confirmed invasive breast cancer, who underwent preoperative breast MRI, were retrospectively enrolled and randomly assigned to the following cohorts: training cohort (n=141) and test cohort (n=62). Then, univariate and multivariate logistic regression were performed to select independent risk factors and build a clinical model. Afterwards, least absolute shrinkage and selection operator (LASSO) logistic regression was performed to select predictive features extracted from the early and delay enhancement dynamic contrast-enhanced (DCE)-MRI images, and a radiomics signature was established. Subsequently, a nomogram model was constructed by incorporating the radiomics score and risk factors. Receiver operating characteristic curves were performed to determine the performance of various models. The efficacy of the various models was evaluated using calibration and decision curves. RESULTS Fourteen radiomics features were selected to construct the radiomics model. The size of the lymph node was identified as an independent risk factor of the clinical model. The nomogram model demonstrated the best calibration and discrimination performance in both the training and test cohorts, with an area under the curve of 0.873 (95% confidence interval [CI]: 0.807-0.923) and 0.902 (95% CI: 0.800-0.963), respectively. The decision curve illustrated that the nomogram model added more net benefits, when compared to the radiomics signature and clinical model. CONCLUSION The nomogram model based on preoperative DCE-MRI images exhibits satisfactory efficacy for the noninvasive prediction of LVI determined by D2-40 in invasive breast cancer.
Collapse
Affiliation(s)
- Zengjie Wu
- Department of Radiology, the Affiliated Hospital of Qingdao University, Shandong, China
| | - Qing Lin
- Breast Disease Center, the Affiliated Hospital of Qingdao University, No. 59 Haier Road, Qingdao 266000, Shandong, China
| | - Hongming Song
- Breast Disease Center, the Affiliated Hospital of Qingdao University, No. 59 Haier Road, Qingdao 266000, Shandong, China
| | - Jingjing Chen
- Breast Disease Center, the Affiliated Hospital of Qingdao University, No. 59 Haier Road, Qingdao 266000, Shandong, China
| | - Guanqun Wang
- Department of Pathology, the Affiliated Hospital of Qingdao University, Shandong, China
| | - Guangming Fu
- Department of Pathology, the Affiliated Hospital of Qingdao University, Shandong, China
| | - Chunxiao Cui
- Breast Disease Center, the Affiliated Hospital of Qingdao University, No. 59 Haier Road, Qingdao 266000, Shandong, China
| | - Xiaohui Su
- Breast Disease Center, the Affiliated Hospital of Qingdao University, No. 59 Haier Road, Qingdao 266000, Shandong, China
| | - Lili Li
- Breast Disease Center, the Affiliated Hospital of Qingdao University, No. 59 Haier Road, Qingdao 266000, Shandong, China
| | - Tiantian Bian
- Breast Disease Center, the Affiliated Hospital of Qingdao University, No. 59 Haier Road, Qingdao 266000, Shandong, China..
| |
Collapse
|
21
|
Şendur HN, Şendur AB. MRI-Based Radiomics May Provide More In-depth Information Regarding Lymphovascular Invasion Status in Patients with Breast Cancer. Acad Radiol 2023; 30:2710-2711. [PMID: 37684183 DOI: 10.1016/j.acra.2023.07.014] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/16/2023] [Accepted: 07/17/2023] [Indexed: 09/10/2023]
Affiliation(s)
- Halit Nahit Şendur
- Gazi University Faculty of Medicine, Department of Radiology, Mevlana Bulvarı No:29 06560 Yenimahalle, Ankara, Turkey (H.H.Ş).
| | | |
Collapse
|
22
|
Ma Q, Li Z, Li W, Chen Q, Liu X, Feng W, Lei J. MRI radiomics for the preoperative evaluation of lymphovascular invasion in breast cancer: A meta-analysis. Eur J Radiol 2023; 168:111127. [PMID: 37801997 DOI: 10.1016/j.ejrad.2023.111127] [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: 08/01/2023] [Revised: 09/08/2023] [Accepted: 09/28/2023] [Indexed: 10/08/2023]
Abstract
PURPOSE To evaluate the ability of preoperative MRI-based radiomic features in predicting lymphovascular invasion (LVI) in patients with breast cancer. METHODS PubMed, Embase, Web of Science, Cochrane Library databases, and four Chinese databases were searched to identify relevant studies published up until June 15, 2023. Two reviewers screened all papers independently for eligibility. We included diagnostic accuracy studies that used radiomics-MRI for LVI in patients with breast cancer, using histopathology as the reference standard. Quality was assessed using the Quality Assessment of Diagnostic Accuracy Studies 2 and Radiomics Quality Score. Overall diagnostic odds ratio (DOR), sensitivity, specificity and area under the curve (AUC) were calculated to assess the prediction efficacy of MRI-based radiomic features in patients with breast cancer. Spearman's correlation coefficient was calculated and subgroup analysis performed to investigate causes of heterogeneity. RESULTS Eight studies comprising 1685 female patients were included. The pooled DOR, sensitivity, specificity, and AUC of radiomics in detecting LVI were 23 [confidence interval (CI) 16,32], 0.89(0.86,0.92), 0.82 (0.78,0.86), and 0.83(0.78,0.87), respectively. The meta-analysis showed significant heterogeneity among the included studies. No threshold effect was detected. Subgroup analysis showed that more than 200 participants, radiomics with clinical factors, semiautomatic segmentation method and peritumoral or intra- and peritumoral model [DOR: 28(18,42), 26(19,37), 34(16,70), 40(10,156), respectively] could improve diagnostic performance compared with less than 200 participants, only radiomics, manual segmentation method, and tumor model [DOR: 16(7,37), 21(6,73), 20(12,32), 21(13,32), respectively], but 3.0 T MR and multiple sequences approach [DOR: 27(15,49),17(8,35)] couldn't improve diagnostic performance compared with 1.5 T and DCE radiomic features [DOR:27(7,99),25(17,37)]. CONCLUSION Our meta-analysis showed that preoperative MRI-based radiomic features performs well in predicting LVI in patients with breast cancer. This noninvasive and convenient tool may be used to facilitate preoperative identification of LVI in breast cancer.
Collapse
Affiliation(s)
- Qinqin Ma
- Lanzhou University, Lanzhou 730000, China; Intelligent Imaging Medical Engineering Research Center of Gansu Province, Lanzhou 730000, China; Accurate Image Collaborative Innovation International Science and Technology Cooperation Base of Gansu Province, Lanzhou 730000, China.
| | - Zhifan Li
- Lanzhou University, Lanzhou 730000, China; Intelligent Imaging Medical Engineering Research Center of Gansu Province, Lanzhou 730000, China; Accurate Image Collaborative Innovation International Science and Technology Cooperation Base of Gansu Province, Lanzhou 730000, China.
| | - Wenjing Li
- Lanzhou University, Lanzhou 730000, China; Intelligent Imaging Medical Engineering Research Center of Gansu Province, Lanzhou 730000, China; Accurate Image Collaborative Innovation International Science and Technology Cooperation Base of Gansu Province, Lanzhou 730000, China.
| | - Qitian Chen
- No.2 Hospital of Baiyin City, Baiyin 730900, China.
| | - Xinran Liu
- Lanzhou University, Lanzhou 730000, China; Intelligent Imaging Medical Engineering Research Center of Gansu Province, Lanzhou 730000, China; Accurate Image Collaborative Innovation International Science and Technology Cooperation Base of Gansu Province, Lanzhou 730000, China.
| | - Wen Feng
- Lanzhou University, Lanzhou 730000, China; Department of Radiology, the First Hospital of Lanzhou University, Lanzhou 730000, China; Intelligent Imaging Medical Engineering Research Center of Gansu Province, Lanzhou 730000, China; Accurate Image Collaborative Innovation International Science and Technology Cooperation Base of Gansu Province, Lanzhou 730000, China.
| | - Junqiang Lei
- Department of Radiology, the First Hospital of Lanzhou University, Lanzhou 730000, China; Intelligent Imaging Medical Engineering Research Center of Gansu Province, Lanzhou 730000, China; Accurate Image Collaborative Innovation International Science and Technology Cooperation Base of Gansu Province, Lanzhou 730000, China.
| |
Collapse
|
23
|
Xu Z, Xie Y, Wu L, Chen M, Shi Z, Cui Y, Han C, Lin H, Liu Y, Li P, Chen X, Ding Y, Liu Z. Using Machine Learning Methods to Assess Lymphovascular Invasion and Survival in Breast Cancer: Performance of Combining Preoperative Clinical and MRI Characteristics. J Magn Reson Imaging 2023; 58:1580-1589. [PMID: 36797654 DOI: 10.1002/jmri.28647] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/05/2022] [Revised: 02/01/2023] [Accepted: 02/02/2023] [Indexed: 02/18/2023] Open
Abstract
BACKGROUND Preoperative assessment of lymphovascular invasion (LVI) in invasive breast cancer (IBC) is of high clinical relevance for treatment decision-making and prognosis. PURPOSE To investigate the associations of preoperative clinical and magnetic resonance imaging (MRI) characteristics with LVI and disease-free survival (DFS) by using machine learning methods in patients with IBC. STUDY TYPE Retrospective. POPULATION Five hundred and seventy-five women (range: 24-79 years) with IBC who underwent preoperative MRI examinations at two hospitals, divided into the training (N = 386) and validation datasets (N = 189). FIELD STRENGTH/SEQUENCE Axial fat-suppressed T2-weighted turbo spin-echo sequence and dynamic contrast-enhanced with fat-suppressed T1-weighted three-dimensional gradient echo imaging. ASSESSMENT MRI characteristics (clinical T stage, breast edema score, MRI axillary lymph node status, multicentricity or multifocality, enhancement pattern, adjacent vessel sign, and increased ipsilateral vascularity) were reviewed independently by three radiologists. Logistic regression (LR), eXtreme Gradient Boosting (XGBoost), k-Nearest Neighbor (KNN), and Support Vector Machine (SVM) algorithms were used to establish the models by combing preoperative clinical and MRI characteristics for assessing LVI status in the training dataset, and the methods were further applied in the validation dataset. The LVI score was calculated using the best-performing of the four models to analyze the association with DFS. STATISTICAL TESTS Chi-squared tests, variance inflation factors, receiver operating characteristics (ROC), Kaplan-Meier curve, log-rank, Cox regression, and intraclass correlation coefficient were performed. The area under the ROC curve (AUC) and hazard ratios (HR) were calculated. A P-value <0.05 was considered statistically significant. RESULTS The model established by the XGBoost algorithm had better performance than LR, SVM, and KNN models, achieving an AUC of 0.832 (95% confidence interval [CI]: 0.789, 0.876) in the training dataset and 0.838 (95% CI: 0.775, 0.901) in the validation dataset. The LVI score established by the XGBoost model was an independent indicator of DFS (adjusted HR: 2.66, 95% CI: 1.22-5.80). DATA CONCLUSION The XGBoost model based on preoperative clinical and MRI characteristics may help to investigate the LVI status and survival in patients with IBC. LEVEL OF EVIDENCE 3 TECHNICAL EFFICACY: Stage 2.
Collapse
Affiliation(s)
- Zeyan Xu
- School of Medicine, South China University of Technology, Guangzhou, China
- Department of Radiology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
| | - Yu Xie
- Department of Radiology, The Third Affiliated Hospital of Kunming Medical University, Yunnan Cancer Hospital, Yunnan Cancer Center, Kunming, China
| | - Lei Wu
- Department of Radiology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
- Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application, Guangzhou, China
- Guangdong Cardiovascular Institute, Guangzhou, China
| | - Minglei Chen
- Department of Radiology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
- Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application, Guangzhou, China
- Shantou University Medical College, Shantou, China
| | - Zhenwei Shi
- Department of Radiology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
- Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application, Guangzhou, China
- Guangdong Cardiovascular Institute, Guangzhou, China
| | - Yanfen Cui
- Department of Radiology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
- Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application, Guangzhou, China
- Guangdong Cardiovascular Institute, Guangzhou, China
| | - Chu Han
- Department of Radiology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
- Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application, Guangzhou, China
| | - Huan Lin
- School of Medicine, South China University of Technology, Guangzhou, China
- Department of Radiology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
| | - Yu Liu
- Department of Radiology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
- Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application, Guangzhou, China
| | - Pinxiong Li
- Department of Radiology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
- Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application, Guangzhou, China
| | - Xin Chen
- Department of Radiology, Guangzhou First People's Hospital, The Second Affiliated Hospital of South China University of Technology, Guangzhou, China
| | - Yingying Ding
- Department of Radiology, The Third Affiliated Hospital of Kunming Medical University, Yunnan Cancer Hospital, Yunnan Cancer Center, Kunming, China
| | - Zaiyi Liu
- School of Medicine, South China University of Technology, Guangzhou, China
- Department of Radiology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
| |
Collapse
|
24
|
Sung P, Lee JY, Cheun JH, Choi IS, Park JH, Park JH, Kim BH, Oh S, Chu AJ, Hwang KT. Prognostic Implication of Focal Breast Edema on Preoperative Breast Magnetic Resonance Imaging in Breast Cancer Patients. J Breast Cancer 2023; 26:479-491. [PMID: 37704381 PMCID: PMC10625867 DOI: 10.4048/jbc.2023.26.e35] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/01/2023] [Revised: 07/17/2023] [Accepted: 07/29/2023] [Indexed: 09/15/2023] Open
Abstract
PURPOSE In this study, we investigated the prognostic implications of focal breast edema on preoperative breast magnetic resonance imaging (MRI) in patients with breast cancer. METHODS Data of 899 patients with breast cancer at a single institution were retrospectively analyzed. The patients were divided into an edema-positive group (EPG) and an edema-negative group (ENG) based on the presence of peritumoral, prepectoral, or subcutaneous edema. Two radiologists evaluated the presence or absence of focal edema and its subtypes on preoperative breast MRI. Clinicopathologic characteristics and survival outcomes were compared between the two groups and among the three subtypes using Pearson's χ² test, Kaplan-Meier estimator, and Cox proportional hazards model. RESULTS There were 399 (44.4%) and 500 (55.6%) patients in the EPG and ENG, respectively. The EPG showed significantly higher rates of axillary lymph node metastasis (55.6% vs. 19.2%, p < 0.001) and lymphovascular invasion (LVI) (57.9% vs. 12.6%, p < 0.001) than the ENG. Patients in the EPG showed significantly worse overall survival (OS) rate (log-rank p < 0.001; hazard ratio [HR], 4.83; 95% confidence interval [CI], 2.56-9.11) and recurrence-free survival rate (log-rank p < 0.001; HR, 3.00; 95% CI, 1.94-4.63) than those in the ENG. After adjusting for other variables, focal breast edema remained a significant factor affecting the OS rate, regardless of the edema type. Specifically, the presence of subcutaneous edema emerged as the strongest predictor for OS with the highest HR (p < 0.001; HR, 9.10; 95% CI, 3.05-27.15). CONCLUSION Focal breast edema on preoperative breast MRI implies a higher possibility of LVI and axillary lymph node metastasis, which can lead to a poor prognosis. A detailed description of focal breast edema, especially subcutaneous edema, on preoperative breast MRI may provide prognostic predictions. More intensive surveillance is required for patients with breast cancer and focal preoperative breast edema.
Collapse
Affiliation(s)
- Pamela Sung
- Department of Radiology, Seoul Metropolitan Government-Seoul National University Boramae Medical Center, Seoul, Korea
| | - Jong Yoon Lee
- Department of Radiology, Seoul Metropolitan Government-Seoul National University Boramae Medical Center, Seoul, Korea
| | - Jong-Ho Cheun
- Department of Surgery, Seoul Metropolitan Government-Seoul National University Boramae Medical Center, Seoul, Korea
| | - In Sil Choi
- Department of Internal Medicine, Seoul Metropolitan Government-Seoul National University Boramae Medical Center, Seoul, Korea
| | - Jin Hyun Park
- Department of Internal Medicine, Seoul Metropolitan Government-Seoul National University Boramae Medical Center, Seoul, Korea
| | - Jeong Hwan Park
- Department of Pathology, Seoul Metropolitan Government-Seoul National University Boramae Medical Center, Seoul, Korea
| | - Byoung Hyuck Kim
- Department of Radiation Oncology, Seoul Metropolitan Government-Seoul National University Boramae Medical Center, Seoul, Korea
| | - Sohee Oh
- Medical Research Collaborating Center, Seoul Metropolitan Government-Seoul National University Boramae Medical Center, Seoul, Korea
| | - A Jung Chu
- Department of Radiology, Seoul Metropolitan Government-Seoul National University Boramae Medical Center, Seoul, Korea.
| | - Ki-Tae Hwang
- Department of Surgery, Seoul Metropolitan Government-Seoul National University Boramae Medical Center, Seoul, Korea
- Department of Surgery, Seoul National University College of Medicine, Seoul, Korea.
| |
Collapse
|
25
|
Lee K, Jeong YJ, Choo KS, Nam SB, Kim HY, Jung YJ, Lee SJ, Joo JH, Kim JY, Kim JJ, Kim JY, Yun MS, Nam KJ. Comparison of Fused Diffusion-Weighted Imaging Using Unenhanced MRI and Abbreviated Post-Contrast-Enhanced MRI in Patients with Breast Cancer. MEDICINA (KAUNAS, LITHUANIA) 2023; 59:1563. [PMID: 37763682 PMCID: PMC10534817 DOI: 10.3390/medicina59091563] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/13/2023] [Revised: 08/25/2023] [Accepted: 08/26/2023] [Indexed: 09/29/2023]
Abstract
Background and Objectives: To determine the percentage of breast cancers detectable by fused diffusion-weighted imaging (DWI) using unenhanced magnetic resonance imaging (MRI) and abbreviated post-contrast-enhanced MRI. Materials and Methods: Between October 2016 and October 2017, 194 consecutive women (mean age, 54.2 years; age range, 28-82 years) with newly diagnosed unilateral breast cancer, who underwent preoperative 3.0 T breast MRI with DWI, were evaluated. Both fused DWI and abbreviated MRI were independently reviewed by two radiologists for the detection of index cancer (which showed the most suspicious findings in both breasts), location, lesion conspicuity, lesion type, and lesion size. Moreover, the relationship between cancer detection and histopathological results of surgical specimens was evaluated. Results: Index cancer detection rates were comparable between fused DWI and abbreviated MRI (radiologist 1: 174/194 [89.7%] vs. 184/194 [94.8%], respectively, p = 0.057; radiologist 2: 174/194 [89.7%] vs. 183/194 [94.3%], respectively, p = 0.092). In both radiologists, abbreviated MRI showed a significantly higher lesion conspicuity than fused DWI (radiologist 1: 9.37 ± 2.24 vs. 8.78 ± 3.03, respectively, p < 0.001; radiologist 2: 9.16 ± 2.32 vs. 8.39 ± 2.93, respectively, p < 0.001). The κ value for the interobserver agreement of index cancer detection was 0.67 on fused DWI and 0.85 on abbreviated MRI. For lesion conspicuity, the intraclass correlation coefficients were 0.72 on fused DWI and 0.82 on abbreviated MRI. Among the histopathological factors, tumor invasiveness was associated with cancer detection on both fused DWI (p = 0.011) and abbreviated MRI (p = 0.004, radiologist 1), lymphovascular invasion on abbreviated MRI (p = 0.032, radiologist 1), and necrosis on fused DWI (p = 0.031, radiologist 2). Conclusions: Index cancer detection was comparable between fused DWI and abbreviated MRI, although abbreviated MRI showed a significantly better lesion conspicuity.
Collapse
Affiliation(s)
- Kyeyoung Lee
- Department of Radiology, Research Institute for Convergence of Biomedical Science and Technology, Pusan National University Yangsan Hospital, Pusan National University School of Medicine, Yangsan-si 50612, Republic of Korea; (K.L.); (K.S.C.)
| | - Yeo Jin Jeong
- Department of Health Promotion Center, Pusan National University Yangsan Hospital, Yangsan-si 50612, Republic of Korea;
| | - Ki Seok Choo
- Department of Radiology, Research Institute for Convergence of Biomedical Science and Technology, Pusan National University Yangsan Hospital, Pusan National University School of Medicine, Yangsan-si 50612, Republic of Korea; (K.L.); (K.S.C.)
| | - Su Bong Nam
- Department of Plastic and Reconstructive Surgery, Research Institute for Convergence of Biomedical Science and Technology, Pusan National University Yangsan Hospital, Pusan National University School of Medicine, Yangsan-si 50612, Republic of Korea;
| | - Hyun Yul Kim
- Department of Surgery, Research Institute for Convergence of Biomedical Science and Technology, Pusan National University Yangsan Hospital, Pusan National University School of Medicine, Yangsan-si 50612, Republic of Korea; (H.Y.K.); (Y.J.J.); (S.J.L.)
| | - Youn Joo Jung
- Department of Surgery, Research Institute for Convergence of Biomedical Science and Technology, Pusan National University Yangsan Hospital, Pusan National University School of Medicine, Yangsan-si 50612, Republic of Korea; (H.Y.K.); (Y.J.J.); (S.J.L.)
| | - Seung Ju Lee
- Department of Surgery, Research Institute for Convergence of Biomedical Science and Technology, Pusan National University Yangsan Hospital, Pusan National University School of Medicine, Yangsan-si 50612, Republic of Korea; (H.Y.K.); (Y.J.J.); (S.J.L.)
| | - Ji Hyeon Joo
- Department of Radiation Oncology, Research Institute for Convergence of Biomedical Science and Technology, Pusan National University Yangsan Hospital, Pusan National University School of Medicine, Yangsan-si 50612, Republic of Korea;
| | - Jin You Kim
- Department of Radiology, Research Institute for Convergence of Biomedical Science and Technology, Pusan National University Hospital, Pusan National University School of Medicine, Busan 49241, Republic of Korea; (J.Y.K.); (J.J.K.)
| | - Jin Joo Kim
- Department of Radiology, Research Institute for Convergence of Biomedical Science and Technology, Pusan National University Hospital, Pusan National University School of Medicine, Busan 49241, Republic of Korea; (J.Y.K.); (J.J.K.)
| | - Jee Yeon Kim
- Department of Pathology, Research Institute for Convergence of Biomedical Science and Technology, Pusan National University Yangsan Hospital, Pusan National University School of Medicine, Yangsan-si 50612, Republic of Korea;
| | - Mi Sook Yun
- Division of Biostatistics, Research Institute for Convergence of Biomedical Science and Technology, Pusan National University Yangsan Hospital, Yangsan-si 50612, Republic of Korea;
| | - Kyung Jin Nam
- Department of Radiology, Research Institute for Convergence of Biomedical Science and Technology, Pusan National University Yangsan Hospital, Pusan National University School of Medicine, Yangsan-si 50612, Republic of Korea; (K.L.); (K.S.C.)
| |
Collapse
|
26
|
Zhang C, Liang Z, Feng Y, Xiong Y, Manwa C, Zhou Q. Risk Factors for Lymphovascular Invasion in Invasive Ductal Carcinoma Based on Clinical and Preoperative Breast MRI Features: a Retrospective Study. Acad Radiol 2023; 30:1620-1627. [PMID: 36414494 DOI: 10.1016/j.acra.2022.10.029] [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: 08/31/2022] [Revised: 10/10/2022] [Accepted: 10/30/2022] [Indexed: 11/21/2022]
Abstract
RATIONALE AND OBJECTIVES Lymphovascular invasion (LVI) plays an important role in the prediction of metastasis and prognosis in breast cancer (BC) patients. The present study assessed correlations between preoperative breast MRI, clinical features, and LVI in patients with invasive ductal carcinoma (IDC) and identified risk factors based on these correlation factors. MATERIALS AND METHODS Patients confirmed with IDC between 01/2012 and 12/2021 were retrospectively reviewed at our hospital. A total of 5 clinical and 14 MRI features to characterize tumours were extracted. LVI evaluated in hematoxylin and eosin sections. T-test and chi-square tests were used to compare the differences in clinical and MRI features between the LVI positive and negative groups. The associations between individual features and LVI were analysed by univariable logistic regression analysis, and risk factors for LVI were identified by multivariable logistic regression analysis based on these correlation factors. RESULTS This study included 353 patients with IDC, including 130 with positive LVI. Age, CEA, CA-153, amount of fibroglandular tissue (FGT), background parenchymal enhancement, tumour size, shape, skin thickening, nipple retraction, adjacent vessel sign, and axillary lymph node (ALN) size in the LVI positive group were significantly different from the LVI negative group (all p<0.05). Multivariate logistic regression analysis revealed that age (odds ratio OR = 1.030), CA-153 (OR = 1.018), heterogeneous FGT (OR = 2.484), shape (OR = 2.157), and ALN size (OR = 1.051) were risk factors for LVI (all p<0.05). CONCLUSION Preoperative breast MRI and clinical features correlated with LVI, age, CA-153, heterogeneous FGT, shape, and ALN size are risk factors for LVI in patients with IDC.
Collapse
Affiliation(s)
- Cici Zhang
- Department of Radiology, The Third Affiliated Hospital, Southern Medical University, Address, No. 183, West Zhongshan Avenue, TianHe District Guangzhou, GuangDong China; Department of Radiology, Guangzhou Red Cross Hospital, Guangzhou, China
| | - Zhiping Liang
- Department of Radiology, Guangzhou Red Cross Hospital, Guangzhou, China
| | - Youzhen Feng
- Medical Imaging Center, The First Affiliated Hospital of Jinan University, Guangzhou, China
| | - Yuchao Xiong
- Department of Radiology, Guangzhou Red Cross Hospital, Guangzhou, China
| | - Chan Manwa
- Department of Pediatrics, Kiang Wu Hospital, Macau, China
| | - Quan Zhou
- Department of Radiology, The Third Affiliated Hospital, Southern Medical University, Address, No. 183, West Zhongshan Avenue, TianHe District Guangzhou, GuangDong China.
| |
Collapse
|
27
|
Chen Y, Wang L, Luo R, Liu H, Zhang Y, Wang D. Focal breast edema and breast edema score on T2-weighted images provides valuable biological information for invasive breast cancer. Insights Imaging 2023; 14:73. [PMID: 37121926 PMCID: PMC10149534 DOI: 10.1186/s13244-023-01424-7] [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: 02/14/2023] [Accepted: 04/10/2023] [Indexed: 05/02/2023] Open
Abstract
BACKGROUND Various features extracted from breast MRI have the potential to serve as noninvasive biomarkers for the prediction of the biologic behavior of breast cancer. The purpose of this study was to investigate the value of focal breast edema and breast edema score (BES) on T2-weighted images in providing valuable biological information for breast cancer patients' personalized treatment. METHOD Two hundred and five lesions in 201 patients with invasive breast cancer confirmed by surgery or biopsy in Xinhua Hospital Affiliated to Shanghai Jiaotong University School of Medicine from November 2018 to October 2019 were retrospectively recruited and analyzed in this study. Focal edema and BES were evaluated at fat-suppressed T2 weighted imaging. All the lesions were divided into two groups according to the presence of focal edema. The differences in clinicopathological characteristics between the two groups and between different BES were compared. RESULTS Two hundred and five lesions in 201 patients with invasive breast cancer were retrospectively recruited and analyzed in this study. On the fat-suppressed T2WI, focal edema was detected in 102 of 205 lesions (49.8%). BES was positively correlated with tumor size (p < 0.001), histologic grade (p = 0.006), Ki-67 index (p < 0.001), and N stage (p = 0.007), and was negatively correlated with expression of ER and PR (p < 0.001). Higher BES was more likely to present in patients with non-luminal breast cancer (p < 0.001) and suggested the possibility of a higher N stage. CONCLUSIONS Focal edema on T2WI of breast MRI indicates stronger tumor invasiveness, in which non-luminal breast cancer is more inclined to present focal edema. Breast edema score, a novel and practical tool, helps guide the individualized treatment of patients with invasive breast cancer. CRITICAL RELEVANCE STATEMENT Focal edema on T2WI of breast MRI indicates stronger tumor invasiveness. Breast edema score helps guide the individualized treatment of patients with invasive breast cancer.
Collapse
Affiliation(s)
- Yanhong Chen
- Department of Radiology, Xinhua Hospital, Shanghai Jiao Tong University School of Medicine, No. 1665 Kongjiang Road, Shanghai, 200092, China
| | - Lijun Wang
- Department of Radiology, Xinhua Hospital, Shanghai Jiao Tong University School of Medicine, No. 1665 Kongjiang Road, Shanghai, 200092, China
| | - Ran Luo
- Department of Radiology, Xinhua Hospital, Shanghai Jiao Tong University School of Medicine, No. 1665 Kongjiang Road, Shanghai, 200092, China
| | - Huanhuan Liu
- Department of Radiology, Xinhua Hospital, Shanghai Jiao Tong University School of Medicine, No. 1665 Kongjiang Road, Shanghai, 200092, China
| | - Yuzhen Zhang
- Department of Radiology, Xinhua Hospital, Shanghai Jiao Tong University School of Medicine, No. 1665 Kongjiang Road, Shanghai, 200092, China.
| | - Dengbin Wang
- Department of Radiology, Xinhua Hospital, Shanghai Jiao Tong University School of Medicine, No. 1665 Kongjiang Road, Shanghai, 200092, China.
| |
Collapse
|
28
|
Lai T, Chen X, Yang Z, Huang R, Liao Y, Chen X, Dai Z. Quantitative parameters of dynamic contrast-enhanced magnetic resonance imaging to predict lymphovascular invasion and survival outcome in breast cancer. Cancer Imaging 2022; 22:61. [PMID: 36273200 PMCID: PMC9587620 DOI: 10.1186/s40644-022-00499-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/27/2022] [Revised: 08/21/2022] [Accepted: 10/10/2022] [Indexed: 02/05/2023] Open
Abstract
BACKGROUND Lymphovascular invasion (LVI) predicts a poor outcome of breast cancer (BC), but LVI can only be postoperatively diagnosed by histopathology. We aimed to determine whether quantitative parameters of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) can preoperatively predict LVI and clinical outcome of BC patients. METHODS A total of 189 consecutive BC patients who underwent multiparametric MRI scans were retrospectively evaluated. Quantitative (Ktrans, Ve, Kep) and semiquantitative DCE-MRI parameters (W- in, W- out, TTP), and clinicopathological features were compared between LVI-positive and LVI-negative groups. All variables were calculated by using univariate logistic regression analysis to determine the predictors for LVI. Multivariate logistic regression was used to build a combined-predicted model for LVI-positive status. Receiver operating characteristic (ROC) curves evaluated the diagnostic efficiency of the model and Kaplan-Meier curves showed the relationships with the clinical outcomes. Multivariate analyses with a Cox proportional hazard model were used to analyze the hazard ratio (HR) for recurrence-free survival (RFS) and overall survival (OS). RESULTS LVI-positive patients had a higher Kep value than LVI-negative patients (0.92 ± 0.30 vs. 0.81 ± 0.23, P = 0.012). N2 stage [odds ratio (OR) = 3.75, P = 0.018], N3 stage (OR = 4.28, P = 0.044), and Kep value (OR = 5.52, P = 0.016) were associated with LVI positivity. The combined-predicted LVI model that incorporated the N stage and Kep yielded an accuracy of 0.735 and a specificity of 0.801. The median RFS was significantly different between the LVI-positive and LVI-negative groups (31.5 vs. 34.0 months, P = 0.010) and between the combined-predicted LVI-positive and LVI-negative groups (31.8 vs. 32.0 months, P = 0.007). The median OS was not significantly different between the LVI-positive and LVI-negative groups (41.5 vs. 44.0 months, P = 0.270) and between the combined-predicted LVI-positive and LVI-negative groups (42.8 vs. 43.5 months, P = 0.970). LVI status (HR = 2.40), N2 (HR = 3.35), and the combined-predicted LVI model (HR = 1.61) were independently associated with disease recurrence. CONCLUSION The quantitative parameter of Kep could predict LVI. LVI status, N stage, and the combined-predicted LVI model were predictors of a poor RFS but not OS.
Collapse
Affiliation(s)
- Tianfu Lai
- Department of Radiology, Meizhou People's Hospital, 514031, Meizhou, China
| | - Xiaofeng Chen
- Department of Radiology, Meizhou People's Hospital, 514031, Meizhou, China.
- Guangdong Provincial Key Laboratory of Precision Medicine and Clinical Translational, Research of Hakka Population, 514031, Meizhou, China.
| | - Zhiqi Yang
- Department of Radiology, Meizhou People's Hospital, 514031, Meizhou, China
- Guangdong Provincial Key Laboratory of Precision Medicine and Clinical Translational, Research of Hakka Population, 514031, Meizhou, China
| | - Ruibin Huang
- Department of Radiology, First Affiliated Hospital of Shantou University Medical College, 515000, Shantou, China
| | | | - Xiangguang Chen
- Department of Radiology, Meizhou People's Hospital, 514031, Meizhou, China.
- Guangdong Provincial Key Laboratory of Precision Medicine and Clinical Translational, Research of Hakka Population, 514031, Meizhou, China.
| | - Zhuozhi Dai
- Department of Radiology, Shantou Central Hospital, 515031, Shantou, Guangdong, China.
| |
Collapse
|
29
|
Kushvaha S, Renganathan R. Presence of peritumoral edema on T2w MRI: a poor non-invasive prognostic marker in breast cancer patients. THE EGYPTIAN JOURNAL OF RADIOLOGY AND NUCLEAR MEDICINE 2022. [DOI: 10.1186/s43055-022-00900-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/10/2022] Open
Abstract
Abstract
Background
The purpose of the study was to assess the correlation between peritumoral edema (PE) seen on magnetic resonance imaging (MRI) in breast cancer and the established pathological prognostic factors like tumor histology and molecular subtype, grade, Ki67 index, lymphovascular invasion (LVI) and nodal stage. The breast MRI and pathological data of post-surgery specimen of 126 breast cancer patients over a period of 18 months were retrospectively studied. Those who received neoadjuvant therapy, had non-invasive, locally advanced, inflammatory and bilateral breast cancers were excluded. Patients were divided into two groups based on finding of peritumoral edema on T2w MRI images: Group A with PE (n = 88) and Group B without PE (n = 38). Pathological results for the two groups were analyzed and compared using Chi square test. p values of < .05 were considered as significant.
Results
Statistically significant correlation was found between the PE and molecular subtype (p value of < .01), high grade (p value of .001) and High Ki-67 index (p value of .001). No significant correlation was present for the histological type and LVI pathological nodal stage (pN).
Conclusions
We concluded that presence of PE on MRI is associated with poor pathological prognostic factors in breast cancer. It can serve as an additional non-invasive marker to assess prognosis in breast cancer patients especially in those receiving neoadjuvant therapy where the whole tumor may not be available for pathological analysis post-therapy.
Collapse
|
30
|
Feng B, Liu Z, Liu Y, Chen Y, Zhou H, Cui E, Li X, Chen X, Li R, Yu T, Zhang L, Long W. Predicting lymphovascular invasion in clinically node-negative breast cancer detected by abbreviated magnetic resonance imaging: Transfer learning vs. radiomics. Front Oncol 2022; 12:890659. [PMID: 36185309 PMCID: PMC9520481 DOI: 10.3389/fonc.2022.890659] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/06/2022] [Accepted: 08/25/2022] [Indexed: 11/13/2022] Open
Abstract
Objective To compare the performance of abbreviated breast magnetic resonance imaging (AB-MRI)-based transfer learning (TL) algorithm and radionics analysis for lymphovascular invasion (LVI) prediction in patients with clinically node-negative invasive breast cancer (IBC). Methods Between November 2017 and October 2020, 233 clinically node-negative IBCs detected by AB-MRI were retrospectively enrolled. One hundred thirty IBCs from center 1 (37 LVI-positive and 93 LVI-negative) were assigned as the training cohort and 103 from center 2 (25 LVI-positive and 78 LVI-negative) as the validation cohort. Based on AB-MRI, a TL signature (TLS) and a radiomics signature (RS) were built with the least absolute shrinkage and selection operator (LASSO) logistic regression. Their diagnostic performances were validated and compared using areas under the receiver operating curve (AUCs), net reclassification improvement (NRI), integrated discrimination improvement (IDI), decision curve analysis (DCA), and stratification analysis. A convolutional filter visualization technique was used to map the response areas of LVI on the AB-MRI. Results In the validation cohort, compared with RS, the TLS showed better capability in discriminating LVI-positive from LVI-negative lesions (AUC: 0.852 vs. 0.726, p < 0.001; IDI = 0.092, p < 0.001; NRI = 0.554, p < 0.001). The diagnostic performance of TLS was not affected by the menstrual state, molecular subtype, or contrast agent type (all p > 0.05). Moreover, DCA showed that the TLS added more net benefit than RS for clinical utility. Conclusions An AB-MRI-based TLS was superior to RS for preoperative LVI prediction in patients with clinically node-negative IBC.
Collapse
Affiliation(s)
- Bao Feng
- Department of Radiology, Jiangmen Central Hospital, Jiangmen, Guangdong, China
- School of Electronic Information and Automation, Guilin University of Aerospace Technology, Guilin, China
| | - Zhuangsheng Liu
- Department of Radiology, Jiangmen Central Hospital, Jiangmen, Guangdong, China
| | - Yu Liu
- School of Electronic Information and Automation, Guilin University of Aerospace Technology, Guilin, China
| | - Yehang Chen
- School of Electronic Information and Automation, Guilin University of Aerospace Technology, Guilin, China
| | - Haoyang Zhou
- School of Electronic Information and Automation, Guilin University of Aerospace Technology, Guilin, China
| | - Enming Cui
- Department of Radiology, Jiangmen Central Hospital, Jiangmen, Guangdong, China
| | - Xiaoping Li
- Department of Breast, Jiangmen Central Hospital, Jiangmen, Guangdong, China
| | - Xiangmeng Chen
- Department of Radiology, Jiangmen Central Hospital, Jiangmen, Guangdong, China
| | - Ronggang Li
- Department of Pathology, Jiangmen Central Hospital, Jiangmen, Guangdong, China
| | - Tianyou Yu
- School of Automation Science and Engineering, South China University of Technology, Guangzhou, China
| | - Ling Zhang
- Department of Radiology, Nanfang Hospital, Southern Medical University, Guangzhou, China
- *Correspondence: Ling Zhang, ; Wansheng Long,
| | - Wansheng Long
- Department of Radiology, Jiangmen Central Hospital, Jiangmen, Guangdong, China
- *Correspondence: Ling Zhang, ; Wansheng Long,
| |
Collapse
|
31
|
Nijiati M, Aihaiti D, Huojia A, Abulizi A, Mutailifu S, Rouzi N, Dai G, Maimaiti P. MRI-Based Radiomics for Preoperative Prediction of Lymphovascular Invasion in Patients With Invasive Breast Cancer. Front Oncol 2022; 12:876624. [PMID: 35734595 PMCID: PMC9207467 DOI: 10.3389/fonc.2022.876624] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/15/2022] [Accepted: 04/19/2022] [Indexed: 12/24/2022] Open
Abstract
Objective Preoperative identification of lymphovascular invasion (LVI) in patients with invasive breast cancer is challenging due to absence of reliable biomarkers or tools in clinical settings. We aimed to establish and validate multiparametric magnetic resonance imaging (MRI)-based radiomic models to predict the risk of lymphovascular invasion (LVI) in patients with invasive breast cancer. Methods This retrospective study included a total of 175 patients with confirmed invasive breast cancer who had known LVI status and preoperative MRI from two tertiary centers. The patients from center 1 was randomly divided into a training set (n=99) and a validation set (n = 26), while the patients from center 2 was used as a test set (n=50). A total of 1409 radiomic features were extracted from the T2-weighted imaging (T2WI), dynamic contrast-enhanced (DCE) imaging, diffusion-weighted imaging (DWI), and apparent diffusion coefficient (ADC), respectively. A three-step feature selection including SelectKBest, interclass correlation coefficients (ICC), and least absolute shrinkage and selection operator (LASSO) was performed to identify the features most associated with LVI. Subsequently, a Support Vector Machine (SVM) classifier was trained to develop single-layer radiomic models and fusion radiomic models. Model performance was evaluated and compared by the area under the curve (AUC), sensitivity, and specificity. Results Based on one feature of wavelet-HLH_gldm_GrayLevelVariance, the ADC radiomic model achieved an AUC of 0.87 (95% confidence interval [CI]: 0.80–0.94) in the training set, 0.87 (0.70-1.00) in the validation set, and 0.77 (95%CI: 0.64-0.86) in the test set. However, the combination of radiomic features derived from other MR sequences failed to yield incremental value. Conclusions ADC-based radiomic model demonstrated a favorable performance in predicting LVI prior to surgery in patients with invasive breast cancer. Such model holds the potential for improving clinical decision-making regarding treatment for breast cancer.
Collapse
Affiliation(s)
- Mayidili Nijiati
- Department of Radiology, The First People's Hospital of Kashgar, Xinjiang, China
| | - Diliaremu Aihaiti
- Department of Radiology, The First People's Hospital of Kashgar, Xinjiang, China
| | - Aisikaerjiang Huojia
- Department of Radiology, The First People's Hospital of Kashgar, Xinjiang, China
| | | | - Sailidan Mutailifu
- Department of Radiology, The First People's Hospital of Kashgar, Xinjiang, China
| | - Nueramina Rouzi
- Department of Radiology, The First People's Hospital of Kashgar, Xinjiang, China
| | - Guozhao Dai
- Department of Radiology, The First People's Hospital of Kashgar, Xinjiang, China
| | - Patiman Maimaiti
- Department of Radiology, The First People's Hospital of Kashgar, Xinjiang, China
| |
Collapse
|
32
|
Effect of peri-operative chemotherapy regimen on survival in the treatment of locally advanced oesophago-gastric adenocarcinoma - A comparison of the FLOT and 'MAGIC' regimens. Eur J Cancer 2022; 163:180-188. [PMID: 35085931 DOI: 10.1016/j.ejca.2021.12.021] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/06/2021] [Revised: 12/16/2021] [Accepted: 12/19/2021] [Indexed: 12/21/2022]
Abstract
BACKGROUND Peri-operative chemotherapy improves survival in patients with locally advanced oesophago-gastric adenocarcinoma. Two regimens with proven survival benefits are epirubicin, cisplatin plus capecitabine or fluorouracil (Medical Research Council Adjuvant Gastric Infusional Chemotherapy, MAGIC) and fluorouracil plus leucovorin, oxaliplatin, and docetaxel (FLOT). This study aimed to compare the effect of these regimens on survival (primary aim) and pathological response, surgical complications, adverse events and chemotherapy completion rates. METHODS Cohort study including 946 patients treated with FLOT (n = 257) or MAGIC (n = 689) who underwent surgical resection for oesophageal (n = 743) or gastric (n = 203) adenocarcinoma between 2002 and 2021 at St Thomas' Hospital or The Royal Marsden Hospital, London, UK. Survival analysis was performed using multivariable Cox regression, providing hazard ratios (HRs) with 95% confidence intervals (CIs) adjusted for age, sex, clinical T-stage, clinical N-stage, tumour grade and presence of signet ring cells. RESULTS Patients treated with FLOT had better overall survival (HR = 0.69, 95% CI 0.50-0.94) and disease-free survival (HR = 0.75, 95% CI 0.58-0.98) than MAGIC. Patients treated with FLOT were more likely to have a complete pathological response (9.5% FLOT versus 5.5% MAGIC, p = 0.027) and were less likely to have a positive resection margin (19.1% FLOT versus 32.2% MAGIC, p < 0.001). The stratified analysis revealed similar results for oesophageal and gastric tumours. Rates of surgical complications, chemotherapy-associated adverse events and completion were similarly distributed between treatment groups. CONCLUSIONS Patients with oesophageal or gastric adenocarcinoma treated with peri-operative FLOT had better survival and pathological response than those treated with peri-operative MAGIC. Rates of surgical complications, adverse events and chemotherapy completion were comparable.
Collapse
|
33
|
Zhang J, Wang G, Ren J, Yang Z, Li D, Cui Y, Yang X. Multiparametric MRI-based radiomics nomogram for preoperative prediction of lymphovascular invasion and clinical outcomes in patients with breast invasive ductal carcinoma. Eur Radiol 2022; 32:4079-4089. [DOI: 10.1007/s00330-021-08504-6] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/20/2021] [Revised: 12/01/2021] [Accepted: 12/04/2021] [Indexed: 12/22/2022]
|
34
|
MRI Radiomics of Breast Cancer: Machine Learning-Based Prediction of Lymphovascular Invasion Status. Acad Radiol 2022; 29 Suppl 1:S126-S134. [PMID: 34876340 DOI: 10.1016/j.acra.2021.10.026] [Citation(s) in RCA: 18] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/23/2021] [Revised: 10/19/2021] [Accepted: 10/27/2021] [Indexed: 12/27/2022]
Abstract
RATIONALE AND OBJECTIVES In patients with breast cancer (BC), lymphovascular invasion (LVI) status is considered an important prognostic factor. We aimed to develop machine learning (ML)-based radiomics models for the prediction of LVI status in patients with BC, using preoperative MRI images. MATERIALS AND METHODS This retrospective study included patients with BC with known LVI status and preoperative MRI. The dataset was split into training and unseen testing sets by stratified sampling with a 2:1 ratio. 2D and 3D radiomic features were extracted from contrast-enhanced T1 weighted images (C+T1W) and apparent diffusion coefficient (ADC) maps. The reliability of the features was assessed with two radiologists' segmentation data. Dimension reduction was done with reliability analysis, multi-collinearity analysis, removal of low-variance features, and feature selection. ML models were created with base, tuned, and boosted random forest algorithms. RESULT A total of 128 lesions (LVI-positive, 76; LVI-negative, 52) were included. The best model performance was achieved with tunning and boosting model based on 3D ADC maps and selected four radiomic features. The area under the curve and accuracy were 0.726 and 63.5% in the training data, 0.732 and 76.7% in the test data, respectively. The overall sensitivity and positive predictive values were 68% and 69.6% in the training data, 84.6% and 78.6% in the test data, respectively. CONCLUSION ML and radiomics based on 3D segmentation of ADC maps can be used to predict LVI status in BC, with satisfying performance.
Collapse
|
35
|
Park NJY, Jeong JY, Park JY, Kim HJ, Park CS, Lee J, Park HY, Jung JH, Kim WW, Chae YS, Lee SJ, Kim WH. Peritumoral edema in breast cancer at preoperative MRI: an interpretative study with histopathological review toward understanding tumor microenvironment. Sci Rep 2021; 11:12992. [PMID: 34155253 PMCID: PMC8217499 DOI: 10.1038/s41598-021-92283-z] [Citation(s) in RCA: 21] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/30/2020] [Accepted: 05/13/2021] [Indexed: 12/12/2022] Open
Abstract
Peritumoral edema (PE) of breast cancer at T2-weighted MR images is considered a poor prognostic sign and may represent the microenvironment surrounding the tumor; however, its histopathological mechanism remains unclear. The purpose of the study was to identify and describe detailed histopathological characteristics associated with PE at preoperative breast MRI in breast cancer patients. This retrospective study included breast cancer patients who had undergone preoperative MRI and surgery between January 2011 and December 2012. Two radiologists determined the presence of PE in consensus based on the signal intensity surrounding the tumor at T2-weighted images. The following detailed histopathological characteristics were reviewed by two breast pathologists using four-tiered grades; lymphovascular invasion, vessel ectasia, stromal fibrosis, growth pattern, and tumor budding. Tumor necrosis and tumor infiltrating lymphocytes were assessed using a percent scale. Baseline clinicopathological characteristics, including age and histologic grade, were collected. The associations between detailed histopathologic characteristics and PE were examined using multivariable logistic regression with odds ratio (OR) calculation. A total of 136 women (median age, 49 ± 9 years) were assessed; among them 34 (25.0%) had PE. After adjustment of baseline clinicopathological characteristics that were significantly associated with PE (age, T stage, N stage, histologic grade, and subtype, all Ps < 0.05), lymphovascular invasion (P = 0.009), vessel ectasia (P = 0.021), stromal fibrosis (P = 0.024), growth pattern (P = 0.036), and tumor necrosis (P < 0.001) were also associated with PE. In comparison with patients without PE, patients with PE were more likely to have a higher degree of lymphovascular invasion (OR, 2.9), vessel ectasia (OR, 3.3), stromal fibrosis (OR, 2.5), lesser degree of infiltrative growth pattern (OR, 0.4), and higher portion of tumor necrosis (OR, 1.4). PE of breast cancer at MRI is associated with detailed histopathological characteristics of lymphovascular invasion, vessel ectasia, stromal fibrosis, growth pattern, and tumor necrosis, suggesting a relevance for tumor microenvironment.
Collapse
Affiliation(s)
- Nora Jee-Young Park
- Department of Pathology, School of Medicine, Kyungpook National University, Kyungpook National University Chilgok Hospital, Daegu, South Korea
| | - Ji Yun Jeong
- Department of Pathology, School of Medicine, Kyungpook National University, Kyungpook National University Chilgok Hospital, Daegu, South Korea
| | - Ji Young Park
- Department of Pathology, School of Medicine, Kyungpook National University, Kyungpook National University Chilgok Hospital, Daegu, South Korea
| | - Hye Jung Kim
- Department of Radiology, School of Medicine, Kyungpook National University, Kyungpook National University Chilgok Hospital, Daegu, South Korea
| | - Chan Sub Park
- Department of Surgery, School of Medicine, Kyungpook National University, Kyungpook National University Chilgok Hospital, Daegu, South Korea
| | - Jeeyeon Lee
- Department of Surgery, School of Medicine, Kyungpook National University, Kyungpook National University Chilgok Hospital, Daegu, South Korea
| | - Ho Yong Park
- Department of Surgery, School of Medicine, Kyungpook National University, Kyungpook National University Chilgok Hospital, Daegu, South Korea
| | - Jin Hyang Jung
- Department of Surgery, School of Medicine, Kyungpook National University, Kyungpook National University Chilgok Hospital, Daegu, South Korea
| | - Wan Wook Kim
- Department of Surgery, School of Medicine, Kyungpook National University, Kyungpook National University Chilgok Hospital, Daegu, South Korea
| | - Yee Soo Chae
- Department of Oncology/Hematology, School of Medicine, Kyungpook National University, Kyungpook National University Chilgok Hospital, Daegu, South Korea
| | - Soo Jung Lee
- Department of Oncology/Hematology, School of Medicine, Kyungpook National University, Kyungpook National University Chilgok Hospital, Daegu, South Korea
| | - Won Hwa Kim
- Department of Radiology, School of Medicine, Kyungpook National University, Kyungpook National University Chilgok Hospital, Daegu, South Korea.
| |
Collapse
|
36
|
Choi BB. Dynamic contrast enhanced-MRI and diffusion-weighted image as predictors of lymphovascular invasion in node-negative invasive breast cancer. World J Surg Oncol 2021; 19:76. [PMID: 33722246 PMCID: PMC7962354 DOI: 10.1186/s12957-021-02189-3] [Citation(s) in RCA: 22] [Impact Index Per Article: 7.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/17/2020] [Accepted: 03/09/2021] [Indexed: 12/26/2022] Open
Abstract
BACKGROUND Lymphovascular invasion (LVI) is an important risk factor for prognosis of breast cancer and an unfavorable prognostic factor in node-negative invasive breast cancer patients. The purpose of this study was to evaluate the association between LVI and pre-operative features of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) and diffusion-weighted imaging (DWI) in node-negative invasive breast cancer. METHODS Data were collected retrospectively from 132 cases who had undergone pre-operative MRI and had invasive breast carcinoma confirmed on the last surgical pathology report. MRI and DWI data were analyzed for the size of tumor, mass shape, margin, internal enhancement pattern, kinetic enhancement curve, high intratumoral T2-weighted signal intensity, peritumoral edema, DWI rim sign, and apparent diffusion coefficient (ADC) values. We calculated the relationship between presence of LVI and various prognostic factors and MRI features. RESULTS Pathologic tumor size, mass margin, internal enhancement pattern, kinetic enhancement curve, DWI rim sign, and the difference between maximum and minimum ADC were significantly correlated with LVI (p < 0.05). CONCLUSIONS We suggest that DCE-MRI with DWI would assist in predicting LVI status in node-negative invasive breast cancer patients.
Collapse
Affiliation(s)
- Bo Bae Choi
- Department of Radiology, Chungnam National University Hospital, 282 Munhwa-ro, Jung-gu, Daejeon, 35015, Republic of Korea.
| |
Collapse
|
37
|
Liang T, Hu B, Du H, Zhang Y. Predictive value of T2-weighted magnetic resonance imaging for the prognosis of patients with mass-type breast cancer with peritumoral edema. Oncol Lett 2020; 20:314. [PMID: 33133250 PMCID: PMC7590426 DOI: 10.3892/ol.2020.12177] [Citation(s) in RCA: 14] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/12/2020] [Accepted: 09/11/2020] [Indexed: 12/29/2022] Open
Abstract
The aim of the present study was to investigate the role of edema surrounding breast cancer masses in the prognostic prediction of magnetic resonance imaging (MRI) T2-weighted fat suppression sequence. For this purpose, 80 patients with mass-type breast cancer underwent conventional plain breast MRI, dynamic contrast-enhanced (DCE)-MRI or diffusion-weighted MRI scan. The associations between edema around the mass on MRI T2 fat suppression sequence plain scan and tumor stage, pathological findings, immunohistochemical findings and axillary lymph node metastasis were analyzed. The results revealed the presence of edema around the mass on the MRI T2 fat suppression sequence plain scan in 35 patients. By contrast, there was no abnormal enhancement on the DCE-MRI, and the apparent diffusion coefficient value did not decrease in these areas. Compared with the remaining 45 patients, the 35 patients with peritumoral edema exhibited a higher tumor stage and a higher rate of axillary lymph node metastasis (all P<0.05). However, there was no significant difference in pathological classification or the expression of estrogen receptor, progesterone receptor and human epidermal growth factor receptor 2 (as determined by immunohistochemistry) between the two groups. In total, 12 cases of tumor shrinkage during neoadjuvant chemotherapy were accompanied by an improvement in edema. Taken together, the findings of the present study indicated that the presence of edema around the mass on the MRI T2 fat suppression sequence may predict poor prognosis in patients with mass-type breast cancer. Furthermore, the improvement of the peritumoral edema post-neoadjuvant chemotherapy may also be a predictor of a more favorable prognosis.
Collapse
Affiliation(s)
- Ting Liang
- Imaging Center, The First Affiliated Hospital of Xi'an Jiaotong University School of Medicine, Xi'an, Shaanxi 710061, P.R. China
| | - Bin Hu
- Imaging Center, The First Affiliated Hospital of Xi'an Jiaotong University School of Medicine, Xi'an, Shaanxi 710061, P.R. China
| | - Hongwen Du
- Imaging Center, The First Affiliated Hospital of Xi'an Jiaotong University School of Medicine, Xi'an, Shaanxi 710061, P.R. China
| | - Yili Zhang
- Imaging Center, The First Affiliated Hospital of Xi'an Jiaotong University School of Medicine, Xi'an, Shaanxi 710061, P.R. China
| |
Collapse
|
38
|
Okuma H, Sudah M, Kettunen T, Niukkanen A, Sutela A, Masarwah A, Kosma VM, Auvinen P, Mannermaa A, Vanninen R. Peritumor to tumor apparent diffusion coefficient ratio is associated with biologically more aggressive breast cancer features and correlates with the prognostication tools. PLoS One 2020; 15:e0235278. [PMID: 32584887 PMCID: PMC7316248 DOI: 10.1371/journal.pone.0235278] [Citation(s) in RCA: 9] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/13/2020] [Accepted: 06/12/2020] [Indexed: 12/11/2022] Open
Abstract
PURPOSE The apparent diffusion coefficient (ADC) is increasingly used to characterize breast cancer. The peritumor/tumor ADC ratio is suggested to be a reliable and generally applicable index. However, its overall prognostication value remains unclear. We aimed to evaluate the associations between the peritumor/tumor ADC ratio and histopathological biomarkers and published prognostic tools in patients with invasive breast cancer. MATERIALS AND METHODS This prospective study included 88 lesions (five bilateral) in 83 patients with primary invasive breast cancer who underwent preoperative 3.0-T magnetic resonance imaging. The lowest intratumoral mean ADC value on the slice with the largest tumor cross-sectional area was designated the tumor ADC, and the highest mean ADC value on the peritumoral breast parenchymal tissue adjacent to the tumor border was designated the peritumor ADC. The peritumor/tumor ADC ratio was then calculated. The tumor and peritumor ADC values and peritumor/tumor ADC ratios were compared with histopathological parameters using an unpaired t test, and their correlations with published prognostic tools were evaluated with Pearson's correlation coefficient. RESULTS The peritumor/tumor ADC ratio was significantly associated with tumor size (p<0.001), histological grade (p = 0.005), Ki-67 index (p = 0.006), axillary-lymph-node metastasis (p = 0.001), and lymphovascular invasion (p = 0.006), but was not associated with estrogen receptor status (p = 0.931), progesterone receptor status (p = 0.160), or human epidermal growth factor receptor 2 status (p = 0.259). The peritumor/tumor ADC ratio showed moderate positive correlations with the Nottingham Prognostic Index (r = 0.498, p<0.001) and mortality predicted using PREDICT (r = 0.436, p<0.001). CONCLUSION The peritumor/tumor ADC ratio was correlated with histopathological biomarkers in patients with invasive breast cancer, showed significant correlations with published prognostic indexes, and may provide an easily applicable imaging index for the preoperative prognostic evaluation of breast cancer.
Collapse
Affiliation(s)
- Hidemi Okuma
- Institute of Clinical Medicine, School of Medicine, Clinical Radiology, University of Eastern Finland, Kuopio, Finland
- Department of Clinical Radiology, Diagnostic Imaging Center, Kuopio University Hospital, Kuopio, Finland
- * E-mail:
| | - Mazen Sudah
- Institute of Clinical Medicine, School of Medicine, Clinical Radiology, University of Eastern Finland, Kuopio, Finland
- Department of Clinical Radiology, Diagnostic Imaging Center, Kuopio University Hospital, Kuopio, Finland
| | - Tiia Kettunen
- Institute of Clinical Medicine, School of Medicine, Oncology, University of Eastern Finland, Kuopio, Finland
- Department of Oncology, Cancer Center, Kuopio University Hospital, Kuopio, Finland
| | - Anton Niukkanen
- Institute of Clinical Medicine, School of Medicine, Clinical Radiology, University of Eastern Finland, Kuopio, Finland
- Department of Clinical Radiology, Diagnostic Imaging Center, Kuopio University Hospital, Kuopio, Finland
| | - Anna Sutela
- Institute of Clinical Medicine, School of Medicine, Clinical Radiology, University of Eastern Finland, Kuopio, Finland
- Department of Clinical Radiology, Diagnostic Imaging Center, Kuopio University Hospital, Kuopio, Finland
| | - Amro Masarwah
- Institute of Clinical Medicine, School of Medicine, Clinical Radiology, University of Eastern Finland, Kuopio, Finland
- Department of Clinical Radiology, Diagnostic Imaging Center, Kuopio University Hospital, Kuopio, Finland
| | - Veli-Matti Kosma
- Institute of Clinical Medicine, School of Medicine, Pathology and Forensic Medicine, and Translational Cancer Research Area, University of Eastern Finland, Kuopio, Finland
- Biobank of Eastern Finland, Kuopio University Hospital, Kuopio, Finland
| | - Päivi Auvinen
- Institute of Clinical Medicine, School of Medicine, Oncology, University of Eastern Finland, Kuopio, Finland
- Department of Oncology, Cancer Center, Kuopio University Hospital, Kuopio, Finland
| | - Arto Mannermaa
- Institute of Clinical Medicine, School of Medicine, Pathology and Forensic Medicine, and Translational Cancer Research Area, University of Eastern Finland, Kuopio, Finland
- Biobank of Eastern Finland, Kuopio University Hospital, Kuopio, Finland
| | - Ritva Vanninen
- Institute of Clinical Medicine, School of Medicine, Clinical Radiology, University of Eastern Finland, Kuopio, Finland
- Department of Clinical Radiology, Diagnostic Imaging Center, Kuopio University Hospital, Kuopio, Finland
| |
Collapse
|
39
|
Liu Z, Li R, Liang K, Chen J, Chen X, Li X, Li R, Zhang X, Yi L, Long W. Value of digital mammography in predicting lymphovascular invasion of breast cancer. BMC Cancer 2020; 20:274. [PMID: 32245448 PMCID: PMC7119272 DOI: 10.1186/s12885-020-6712-z] [Citation(s) in RCA: 11] [Impact Index Per Article: 2.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/14/2019] [Accepted: 03/03/2020] [Indexed: 12/15/2022] Open
Abstract
Background Lymphovascular invasion (LVI) has never been revealed by preoperative scans. It is necessary to use digital mammography in predicting LVI in patients with breast cancer preoperatively. Methods Overall 122 cases of invasive ductal carcinoma diagnosed between May 2017 and September 2018 were enrolled and assigned into the LVI positive group (n = 42) and the LVI negative group (n = 80). Independent t-test and χ2 test were performed. Results Difference in Ki-67 between the two groups was statistically significant (P = 0.012). Differences in interstitial edema (P = 0.013) and skin thickening (P = 0.000) were statistically significant between the two groups. Multiple factor analysis showed that there were three independent risk factors for LVI: interstitial edema (odds ratio [OR] = 12.610; 95% confidence interval [CI]: 1.061–149.922; P = 0.045), blurring of subcutaneous fat (OR = 0.081; 95% CI: 0.012–0.645; P = 0.017) and skin thickening (OR = 9.041; 95% CI: 2.553–32.022; P = 0.001). Conclusions Interstitial edema, blurring of subcutaneous fat, and skin thickening are independent risk factors for LVI. The specificity of LVI prediction is as high as 98.8% when the three are used together.
Collapse
Affiliation(s)
- Zhuangsheng Liu
- Department of Radiology, Jiangmen Central Hospital, Affiliated Jiangmen Hospital of Sun Yat-Sen University, No. 23 Haibang Street, Jiangmen, 529000, Guangdong, China
| | - Ruqiong Li
- Department of Radiology, Jiangmen Central Hospital, Affiliated Jiangmen Hospital of Sun Yat-Sen University, No. 23 Haibang Street, Jiangmen, 529000, Guangdong, China
| | - Keming Liang
- Department of Radiology, Jiangmen Central Hospital, Affiliated Jiangmen Hospital of Sun Yat-Sen University, No. 23 Haibang Street, Jiangmen, 529000, Guangdong, China
| | - Junhao Chen
- Department of Radiology, Jiangmen Central Hospital, Affiliated Jiangmen Hospital of Sun Yat-Sen University, No. 23 Haibang Street, Jiangmen, 529000, Guangdong, China
| | - Xiangmeng Chen
- Department of Radiology, Jiangmen Central Hospital, Affiliated Jiangmen Hospital of Sun Yat-Sen University, No. 23 Haibang Street, Jiangmen, 529000, Guangdong, China
| | - Xiaoping Li
- Department of Gastrointestinal Surgery, Jiangmen Central Hospital, Affiliated Jiangmen Hospital of Sun Yat-Sen University, Jiangmen, Guangdong, China
| | - Ronggang Li
- Department of Pathology, Jiangmen Central Hospital, Affiliated Jiangmen Hospital of Sun Yat-Sen University, Jiangmen, Guangdong, China
| | - Xin Zhang
- Department of Clinical Experimental Center, Jiangmen Central Hospital, Affiliated Jiangmen Hospital of Sun Yat-Sen University, Jiangmen, Guangdong, China
| | - Lilei Yi
- Department of Radiology, Foshan Hospital of Traditional Chinese Medicine, Foshan, Guangdong, China
| | - Wansheng Long
- Department of Radiology, Jiangmen Central Hospital, Affiliated Jiangmen Hospital of Sun Yat-Sen University, No. 23 Haibang Street, Jiangmen, 529000, Guangdong, China.
| |
Collapse
|
40
|
Hayashi Y, Satake H, Ishigaki S, Ito R, Kawamura M, Kawai H, Iwano S, Naganawa S. Kinetic volume analysis on dynamic contrast-enhanced MRI of triple-negative breast cancer: associations with survival outcomes. Br J Radiol 2020; 93:20190712. [PMID: 31821036 PMCID: PMC7055451 DOI: 10.1259/bjr.20190712] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/14/2019] [Revised: 11/06/2019] [Accepted: 11/29/2019] [Indexed: 12/31/2022] Open
Abstract
OBJECTIVE To evaluate the associations between computer-aided diagnosis (CAD)-generated kinetic volume parameters and survival in triple-negative breast cancer (TNBC) patients. METHODS 40 patients with TNBC who underwent pre-operative MRI between March 2008 and March 2014 were included. We analyzed CAD-generated parameters on dynamic contrast-enhanced MRI, visual MRI assessment, and histopathological data. Cox proportional hazards models were used to determine associations with survival outcomes. RESULTS 12 of the 40 (30.0%) patients experienced recurrence and 7 died of breast cancer after a median follow-up of 73.6 months. In multivariate analysis, higher percentage volume (%V) with more than 200% initial enhancement rate correlated with worse disease-specific survival (hazard ratio, 1.12; 95% confidence interval, 1.02-1.22; p-value, 0.014) and higher %V with more than 100% initial enhancement rate followed by persistent curve type at 30% threshold correlated with worse disease-specific survival (hazard ratio, 1.33; 95% confidence interval, 1.10-1.61; p-value, 0.004) and disease-free survival (hazard ratio, 1.27; 95% confidence interval, 1.12-1.43; p-value, 0.000). CONCLUSION CAD-generated kinetic volume parameters may correlate with survival in TNBC patients. Further study would be necessary to validate our results on larger cohorts. ADVANCES IN KNOWLEDGE CAD generated kinetic volume parameters on breast MRI can predict recurrence and survival outcome of patients in TNBC. Varying the enhancement threshold improved the predictive performance of CAD generated kinetic volume parameter.
Collapse
Affiliation(s)
- Yoko Hayashi
- Department of Radiology, Nagoya University Graduate School of Medicine, Nagoya, Japan
| | - Hiroko Satake
- Department of Radiology, Nagoya University Graduate School of Medicine, Nagoya, Japan
| | - Satoko Ishigaki
- Department of Radiology, Nagoya University Graduate School of Medicine, Nagoya, Japan
| | - Rintaro Ito
- Department of Radiology, Nagoya University Graduate School of Medicine, Nagoya, Japan
| | - Mariko Kawamura
- Department of Radiology, Nagoya University Graduate School of Medicine, Nagoya, Japan
| | - Hisashi Kawai
- Department of Radiology, Nagoya University Graduate School of Medicine, Nagoya, Japan
| | - Shingo Iwano
- Department of Radiology, Nagoya University Graduate School of Medicine, Nagoya, Japan
| | - Shinji Naganawa
- Department of Radiology, Nagoya University Graduate School of Medicine, Nagoya, Japan
| |
Collapse
|
41
|
Liu Z, Feng B, Li C, Chen Y, Chen Q, Li X, Guan J, Chen X, Cui E, Li R, Li Z, Long W. Preoperative prediction of lymphovascular invasion in invasive breast cancer with dynamic contrast-enhanced-MRI-based radiomics. J Magn Reson Imaging 2019; 50:847-857. [PMID: 30773770 DOI: 10.1002/jmri.26688] [Citation(s) in RCA: 59] [Impact Index Per Article: 11.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/28/2018] [Revised: 02/02/2019] [Accepted: 02/04/2019] [Indexed: 12/20/2022] Open
Abstract
BACKGROUND Lymphovascular invasion (LVI) status facilitates the selection of optimal therapeutic strategy for breast cancer patients, but in clinical practice LVI status is determined in pathological specimens after resection. PURPOSE To explore the use of dynamic contrast-enhanced (DCE)-magnetic resonance imaging (MRI)-based radiomics for preoperative prediction of LVI in invasive breast cancer. STUDY TYPE Prospective. POPULATION Ninety training cohort patients (22 LVI-positive and 68 LVI-negative) and 59 validation cohort patients (22 LVI-positive and 37 LVI-negative) were enrolled. FIELD STRENGTH/SEQUENCE 1.5 T and 3.0 T, T1 -weighted DCE-MRI. ASSESSMENT Axillary lymph node (ALN) status for each patient was evaluated based on MR images (defined as MRI ALN status), and DCE semiquantitative parameters of lesions were calculated. Radiomic features were extracted from the first postcontrast DCE-MRI. A radiomics signature was constructed in the training cohort with 10-fold cross-validation. The independent risk factors for LVI were identified and prediction models for LVI were developed. Their prediction performances and clinical usefulness were evaluated in the validation cohort. STATISTICAL TESTS Mann-Whitney U-test, chi-square test, kappa statistics, least absolute shrinkage and selection operator (LASSO) regression, logistic regression, receiver operating characteristic (ROC) analysis, DeLong test, and decision curve analysis (DCA). RESULTS Two radiomic features were selected to construct the radiomics signature. MRI ALN status (odds ratio, 10.452; P < 0.001) and the radiomics signature (odds ratio, 2.895; P = 0.031) were identified as independent risk factors for LVI. The value of the area under the curve (AUC) for a model combining both (0.763) was higher than that for MRI ALN status alone (0.665; P = 0.029) and similar to that for the radiomics signature (0.752; P = 0.857). DCA showed that the combined model added more net benefit than either feature alone. DATA CONCLUSION The DCE-MRI-based radiomics signature in combination with MRI ALN status was effective in predicting the LVI status of patients with invasive breast cancer before surgery. LEVEL OF EVIDENCE 1 Technical Efficacy Stage: 2 J. Magn. Reson. Imaging 2019;50:847-857.
Collapse
Affiliation(s)
- Zhuangsheng Liu
- Department of Radiology, Affiliated Jiangmen Hospital of Sun Yat-Sen University, Jiangmen, Guangdong, China
| | - Bao Feng
- Department of Radiology, Affiliated Jiangmen Hospital of Sun Yat-Sen University, Jiangmen, Guangdong, China.,School of Electronic Information and Automation, Guilin University of Aerospace Technology, Guilin, Guangxi, China
| | - Changlin Li
- School of Electronic Information and Automation, Guilin University of Aerospace Technology, Guilin, Guangxi, China
| | - Yehang Chen
- School of Electronic Information and Automation, Guilin University of Aerospace Technology, Guilin, Guangxi, China
| | - Qinxian Chen
- Department of Radiology, Affiliated Jiangmen Hospital of Sun Yat-Sen University, Jiangmen, Guangdong, China
| | - Xiaoping Li
- Department of Gastrointestinal Surgery, Affiliated Jiangmen Hospital of Sun Yat-Sen University, Jiangmen, Guangdong, China
| | - Jianhua Guan
- Department of Thyroid and Breast Surgery, Affiliated Jiangmen Hospital of Sun Yat-Sen University, Jiangmen, Guangdong, China
| | - Xiangmeng Chen
- Department of Radiology, Affiliated Jiangmen Hospital of Sun Yat-Sen University, Jiangmen, Guangdong, China
| | - Enming Cui
- Department of Radiology, Affiliated Jiangmen Hospital of Sun Yat-Sen University, Jiangmen, Guangdong, China
| | - Ronggang Li
- Department of Pathology, Affiliated Jiangmen Hospital of Sun Yat-Sen University, Jiangmen, Guangdong, China
| | - Zhi Li
- School of Electronic Information and Automation, Guilin University of Aerospace Technology, Guilin, Guangxi, China
| | - Wansheng Long
- Department of Radiology, Affiliated Jiangmen Hospital of Sun Yat-Sen University, Jiangmen, Guangdong, China
| |
Collapse
|
42
|
Relation of peritumoral, prepectoral and diffuse edema with histopathologic findings of breast cancer in preoperative 3T magnetic resonance imaging. JOURNAL OF SURGERY AND MEDICINE 2019. [DOI: 10.28982/josam.512779] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/30/2022] Open
|
43
|
Tirada N, Aujero M, Khorjekar G, Richards S, Chopra J, Dromi S, Ioffe O. Breast Cancer Tissue Markers, Genomic Profiling, and Other Prognostic Factors: A Primer for Radiologists. Radiographics 2018; 38:1902-1920. [PMID: 30312139 DOI: 10.1148/rg.2018180047] [Citation(s) in RCA: 26] [Impact Index Per Article: 4.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/12/2022]
Abstract
An understanding of prognostic factors in breast cancer is imperative for guiding patient care. Increased tumor size and more advanced nodal status are established independent prognostic factors of poor outcomes and are incorporated into the American Joint Committee on Cancer (AJCC) TNM (primary tumor, regional lymph node, distant metastasis) staging system. However, other factors including imaging findings, histologic evaluation results, and molecular findings can have a direct effect on a patient's prognosis, including risk of recurrence and relative survival. Several microarray panels for gene profiling of tumors are approved by the U.S. Food and Drug Administration and endorsed by the American Society of Clinical Oncology. This article highlights prognostic factors currently in use for individualizing and guiding breast cancer therapy and is divided into four sections. The first section addresses patient considerations, in which modifiable and nonmodifiable prognostic factors including age, race and ethnicity, and lifestyle factors are discussed. The second part is focused on imaging considerations such as multicentric and/or multifocal disease, an extensive intraductal component, and skin or chest wall involvement and their effect on treatment and prognosis. The third section is about histopathologic findings such as the grade and presence of lymphovascular invasion. Last, tumor biomarkers and tumor biology are discussed, namely hormone receptors, proliferative markers, and categorization of tumors into four recognized molecular subtypes including luminal A, luminal B, human epidermal growth factor receptor 2-enriched, and triple-negative tumors. By understanding the clinical effect of these prognostic factors, radiologists, along with a multidisciplinary team, can use these tools to achieve individualized patient care and to improve patient outcomes. ©RSNA, 2018.
Collapse
Affiliation(s)
- Nikki Tirada
- From the Department of Diagnostic Radiology and Nuclear Medicine, University of Maryland School of Medicine, 22 S Greene St, Baltimore, MD 21201
| | - Mireille Aujero
- From the Department of Diagnostic Radiology and Nuclear Medicine, University of Maryland School of Medicine, 22 S Greene St, Baltimore, MD 21201
| | - Gauri Khorjekar
- From the Department of Diagnostic Radiology and Nuclear Medicine, University of Maryland School of Medicine, 22 S Greene St, Baltimore, MD 21201
| | - Stephanie Richards
- From the Department of Diagnostic Radiology and Nuclear Medicine, University of Maryland School of Medicine, 22 S Greene St, Baltimore, MD 21201
| | - Jasleen Chopra
- From the Department of Diagnostic Radiology and Nuclear Medicine, University of Maryland School of Medicine, 22 S Greene St, Baltimore, MD 21201
| | - Sergio Dromi
- From the Department of Diagnostic Radiology and Nuclear Medicine, University of Maryland School of Medicine, 22 S Greene St, Baltimore, MD 21201
| | - Olga Ioffe
- From the Department of Diagnostic Radiology and Nuclear Medicine, University of Maryland School of Medicine, 22 S Greene St, Baltimore, MD 21201
| |
Collapse
|
44
|
Cheon H, Kim HJ, Kim TH, Ryeom HK, Lee J, Kim GC, Yuk JS, Kim WH. Invasive Breast Cancer: Prognostic Value of Peritumoral Edema Identified at Preoperative MR Imaging. Radiology 2018; 287:68-75. [DOI: 10.1148/radiol.2017171157] [Citation(s) in RCA: 57] [Impact Index Per Article: 9.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/22/2022]
Affiliation(s)
- Hyejin Cheon
- From the Department of Radiology, Kyungpook National University Medical Center, 807 Hoguk-ro, Buk-gu, Daegu 41404, Republic of Korea (H.C., H.J.K., G.C.K., W.H.K.); Department of Radiology, Kyungpook National University Hospital, Daegu, Korea (T.H.K., H.K.R., J.L.); and Department of Obstetrics and Gynecology, College of Medicine, Gyeongsang National University, Gyeongsang National University Changwon Hospital, Changwon, Korea (J.S.Y.)
| | - Hye Jung Kim
- From the Department of Radiology, Kyungpook National University Medical Center, 807 Hoguk-ro, Buk-gu, Daegu 41404, Republic of Korea (H.C., H.J.K., G.C.K., W.H.K.); Department of Radiology, Kyungpook National University Hospital, Daegu, Korea (T.H.K., H.K.R., J.L.); and Department of Obstetrics and Gynecology, College of Medicine, Gyeongsang National University, Gyeongsang National University Changwon Hospital, Changwon, Korea (J.S.Y.)
| | - Tae Hun Kim
- From the Department of Radiology, Kyungpook National University Medical Center, 807 Hoguk-ro, Buk-gu, Daegu 41404, Republic of Korea (H.C., H.J.K., G.C.K., W.H.K.); Department of Radiology, Kyungpook National University Hospital, Daegu, Korea (T.H.K., H.K.R., J.L.); and Department of Obstetrics and Gynecology, College of Medicine, Gyeongsang National University, Gyeongsang National University Changwon Hospital, Changwon, Korea (J.S.Y.)
| | - Hun-Kyu Ryeom
- From the Department of Radiology, Kyungpook National University Medical Center, 807 Hoguk-ro, Buk-gu, Daegu 41404, Republic of Korea (H.C., H.J.K., G.C.K., W.H.K.); Department of Radiology, Kyungpook National University Hospital, Daegu, Korea (T.H.K., H.K.R., J.L.); and Department of Obstetrics and Gynecology, College of Medicine, Gyeongsang National University, Gyeongsang National University Changwon Hospital, Changwon, Korea (J.S.Y.)
| | - Jongmin Lee
- From the Department of Radiology, Kyungpook National University Medical Center, 807 Hoguk-ro, Buk-gu, Daegu 41404, Republic of Korea (H.C., H.J.K., G.C.K., W.H.K.); Department of Radiology, Kyungpook National University Hospital, Daegu, Korea (T.H.K., H.K.R., J.L.); and Department of Obstetrics and Gynecology, College of Medicine, Gyeongsang National University, Gyeongsang National University Changwon Hospital, Changwon, Korea (J.S.Y.)
| | - Gab Chul Kim
- From the Department of Radiology, Kyungpook National University Medical Center, 807 Hoguk-ro, Buk-gu, Daegu 41404, Republic of Korea (H.C., H.J.K., G.C.K., W.H.K.); Department of Radiology, Kyungpook National University Hospital, Daegu, Korea (T.H.K., H.K.R., J.L.); and Department of Obstetrics and Gynecology, College of Medicine, Gyeongsang National University, Gyeongsang National University Changwon Hospital, Changwon, Korea (J.S.Y.)
| | - Jin-Sung Yuk
- From the Department of Radiology, Kyungpook National University Medical Center, 807 Hoguk-ro, Buk-gu, Daegu 41404, Republic of Korea (H.C., H.J.K., G.C.K., W.H.K.); Department of Radiology, Kyungpook National University Hospital, Daegu, Korea (T.H.K., H.K.R., J.L.); and Department of Obstetrics and Gynecology, College of Medicine, Gyeongsang National University, Gyeongsang National University Changwon Hospital, Changwon, Korea (J.S.Y.)
| | - Won Hwa Kim
- From the Department of Radiology, Kyungpook National University Medical Center, 807 Hoguk-ro, Buk-gu, Daegu 41404, Republic of Korea (H.C., H.J.K., G.C.K., W.H.K.); Department of Radiology, Kyungpook National University Hospital, Daegu, Korea (T.H.K., H.K.R., J.L.); and Department of Obstetrics and Gynecology, College of Medicine, Gyeongsang National University, Gyeongsang National University Changwon Hospital, Changwon, Korea (J.S.Y.)
| |
Collapse
|