1
|
Ribrag A, Lissavalid E, Fayard J, Djerroudi L, Ghislain MS, Ramtohul T, Tardivon A. Initial MRI findings predictive of a pathological complete response to neoadjuvant treatments in HER2-positive breast cancers. Eur J Radiol 2024; 178:111625. [PMID: 39024664 DOI: 10.1016/j.ejrad.2024.111625] [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: 03/05/2024] [Revised: 07/07/2024] [Accepted: 07/12/2024] [Indexed: 07/20/2024]
Abstract
PURPOSE This study aimed to determine if initial MRI findings could predict a pathological complete response (pCR) following neoadjuvant systemic therapy (NST) in HER2-positive breast cancers. METHODS The study retrospectively included 111 patients (Center 1, training set) and 71 patients (Center 2, validation set) with HER2-positive cancer who underwent NST. Initial clinicopathological data and MRI findings were recorded. Continuous variables were analyzed using the Mann-Whitney and Student's t-tests, while categorical variables were analyzed using the χ2 or Fisher's exact test. Univariate analysis was conducted to determine the associations between these variables and pathological complete response (pCR), defined as the absence of invasive malignant cells in the breast and lymph nodes. Interobserver reproducibility was assessed for associated non-mass enhancement (NME) parameter by analyzing 50 MR studies (intraclass correlation coefficient). RESULTS pCR was achieved in 67 patients, 51 (46 %) from Center 1 and 16 (23%) from Center 2 (p = 0.003), with significant differences between Centers 1 and 2 in tumor-infiltrating lymphocyte levels and lymphovascular invasion (p < 0.001). The initial presence of suspicious associated NME was the only significant parameter predictive of pCR (p < 0.001 for Center 1 and 0.04 for Center 2). The inter-observer reproducibility for this MRI feature was good, with an intraclass correlation coefficient of 0.872 (95 % CI: 0.73-1.00). CONCLUSION The presence of suspicious associated NME in HER2-positive cancers on the initial MRI study was predictive of achieving pCR after NST. This significant preliminary finding warrants confirmation through prospective multicenter studies.
Collapse
Affiliation(s)
- Anne Ribrag
- Department of Radiology, Institut Curie, Paris, France.
| | | | - Juliette Fayard
- Department of Radiology, Institut Curie, Saint-Cloud, France
| | | | | | | | - Anne Tardivon
- Department of Radiology, Institut Curie, Paris, France
| |
Collapse
|
2
|
Zheng L, Yang LX, Liu JY, Jiang Z, Li XW, Pu PP. Correlation and predictive value of pathological complete response and ultrasound characteristic parameters in neoadjuvant chemotherapy for breast. World J Clin Cases 2024; 12:5320-5328. [PMID: 39156092 PMCID: PMC11238688 DOI: 10.12998/wjcc.v12.i23.5320] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/10/2024] [Revised: 05/12/2024] [Accepted: 06/11/2024] [Indexed: 07/05/2024] Open
Abstract
BACKGROUND Breast cancer ranks as one of the most prevalent malignant tumors among women, significantly endangering their health and lives. While radical surgery has been a pivotal method for halting disease progression, it alone is insufficient for enhancing the quality of life for patients. AIM To investigate the correlation between ultrasound characteristic parameters of breast cancer lesions and clinical efficacy in patients undergoing neoadjuvant chemotherapy (NAC). METHODS Employing a case-control study design, this research involved 178 breast cancer patients treated with NAC at our hospital from July 2019 to June 2022. According to the Miller-Payne grading system, the pathological response, i.e. efficacy, of the NAC in the initial breast lesion after NAC was evaluated. Of these, 59 patients achieved a pathological complete response (PCR), while 119 did not (non-PCR group). Ultrasound characteristics prior to NAC were compared between these groups, and the association of various factors with NAC efficacy was analyzed using univariate and multivariate approaches. RESULTS In the PCR group, the incidence of posterior echo attenuation, lesion diameter ≥ 2.0 cm, and Alder blood flow grade ≥ II were significantly lower compared to the non-PCR group (P < 0.05). The area under the curve values for predicting NAC efficacy using posterior echo attenuation, lesion diameter, and Alder grade were 0.604, 0.603, and 0.583, respectively. Also, rates of pathological stage II, lymph node metastasis, vascular invasion, and positive Ki-67 expression were significantly lower in the PCR group (P < 0.05). Logistic regression analysis identified posterior echo attenuation, lesion diameter ≥ 2.0 cm, Alder blood flow grade ≥ II, pathological stage III, vascular invasion, and positive Ki-67 expression as independent predictors of poor response to NAC in breast cancer patients (P < 0.05). CONCLUSION While ultrasound characteristics such as posterior echo attenuation, lesion diameter ≥ 2.0 cm, and Alder blood flow grade ≥ II exhibit limited predictive value for NAC efficacy, they are significantly associated with poor response to NAC in breast cancer patients.
Collapse
Affiliation(s)
- Lei Zheng
- Department of Breast Surgery, Xingtai People's Hospital, Xingtai 054001, Hebei Province, China
| | - Li-Xian Yang
- Department of Breast Surgery, Xingtai People's Hospital, Xingtai 054001, Hebei Province, China
| | - Jing-Yi Liu
- Department of Breast Surgery, Xingtai People's Hospital, Xingtai 054001, Hebei Province, China
| | - Zhe Jiang
- Department of Medical Imaging, Xingtai People´s Hospital, Xingtai 054001, Hebei Province, China
| | - Xiao-Wei Li
- Department of Breast Surgery, Xingtai People's Hospital, Xingtai 054001, Hebei Province, China
| | - Peng-Peng Pu
- Department of Breast Surgery, Xingtai People's Hospital, Xingtai 054001, Hebei Province, China
| |
Collapse
|
3
|
Lo Gullo R, Marcus E, Huayanay J, Eskreis-Winkler S, Thakur S, Teuwen J, Pinker K. Artificial Intelligence-Enhanced Breast MRI: Applications in Breast Cancer Primary Treatment Response Assessment and Prediction. Invest Radiol 2024; 59:230-242. [PMID: 37493391 PMCID: PMC10818006 DOI: 10.1097/rli.0000000000001010] [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] [Indexed: 07/27/2023]
Abstract
ABSTRACT Primary systemic therapy (PST) is the treatment of choice in patients with locally advanced breast cancer and is nowadays also often used in patients with early-stage breast cancer. Although imaging remains pivotal to assess response to PST accurately, the use of imaging to predict response to PST has the potential to not only better prognostication but also allow the de-escalation or omission of potentially toxic treatment with undesirable adverse effects, the accelerated implementation of new targeted therapies, and the mitigation of surgical delays in selected patients. In response to the limited ability of radiologists to predict response to PST via qualitative, subjective assessments of tumors on magnetic resonance imaging (MRI), artificial intelligence-enhanced MRI with classical machine learning, and in more recent times, deep learning, have been used with promising results to predict response, both before the start of PST and in the early stages of treatment. This review provides an overview of the current applications of artificial intelligence to MRI in assessing and predicting response to PST, and discusses the challenges and limitations of their clinical implementation.
Collapse
Affiliation(s)
- Roberto Lo Gullo
- Department of Radiology, Breast Imaging Service, Memorial Sloan Kettering Cancer Center, 300 E 66 Street, New York, NY 10065, USA
| | - Eric Marcus
- AI for Oncology, Netherlands Cancer Institute, Plesmanlaan 121, 1066 CX Amsterdam, the Netherlands
| | - Jorge Huayanay
- Department of Radiology, Breast Imaging Service, Memorial Sloan Kettering Cancer Center, 300 E 66 Street, New York, NY 10065, USA
- Department of Radiology, National Institute of Neoplastic Diseases, Lima, Peru
| | - Sarah Eskreis-Winkler
- Department of Radiology, Breast Imaging Service, Memorial Sloan Kettering Cancer Center, 300 E 66 Street, New York, NY 10065, USA
| | - Sunitha Thakur
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, New York, USA
| | - Jonas Teuwen
- Department of Radiology, Breast Imaging Service, Memorial Sloan Kettering Cancer Center, 300 E 66 Street, New York, NY 10065, USA
- Department of Medical Imaging, Radboud University Medical Center, Geert Grooteplein Zuid 10, 6525 GA Nijmegen, the Netherlands
- AI for Oncology, Netherlands Cancer Institute, Plesmanlaan 121, 1066 CX Amsterdam, the Netherlands
| | - Katja Pinker
- Department of Radiology, Breast Imaging Service, Memorial Sloan Kettering Cancer Center, 300 E 66 Street, New York, NY 10065, USA
| |
Collapse
|
4
|
Zhang MQ, Liu XP, Du Y, Zha HL, Zha XM, Wang J, Liu XA, Wang SJ, Zou QG, Zhang JL, Li CY. Prediction of pathological complete response of breast cancer patients who received neoadjuvant chemotherapy with a nomogram based on clinicopathologic variables, ultrasound, and MRI. Br J Radiol 2024; 97:228-236. [PMID: 38263817 PMCID: PMC11027305 DOI: 10.1093/bjr/tqad014] [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: 03/29/2023] [Revised: 08/01/2023] [Accepted: 10/31/2023] [Indexed: 01/25/2024] Open
Abstract
OBJECTIVE To establish a nomogram for predicting the pathologic complete response (pCR) in breast cancer (BC) patients after NAC by applying magnetic resonance imaging (MRI) and ultrasound (US). METHODS A total of 607 LABC women who underwent NAC before surgery between January 2016 and June 2022 were retrospectively enrolled, and then were randomly divided into the training (n = 425) and test set (n = 182) with the ratio of 7:3. MRI and US variables were collected before and after NAC, as well as the clinicopathologic features. Univariate and multivariate logistic regression analyses were applied to confirm the potentially associated predictors of pCR. Finally, a nomogram was developed in the training set with its performance evaluated by the area under the receiver operating characteristics curve (ROC) and validated in the test set. RESULTS Of the 607 patients, 108 (25.4%) achieved pCR. Hormone receptor negativity (odds ratio [OR], 0.3; P < .001), human epidermal growth factor receptor 2 positivity (OR, 2.7; P = .001), small tumour size at post-NAC US (OR, 1.0; P = .031), tumour size reduction ≥50% at MRI (OR, 9.8; P < .001), absence of enhancement in the tumour bed at post-NAC MRI (OR, 8.1; P = .003), and the increase of ADC value after NAC (OR, 0.3; P = .035) were all significantly associated with pCR. Incorporating the above variables, the nomogram showed a satisfactory performance with an AUC of 0.884. CONCLUSION A nomogram including clinicopathologic variables and MRI and US characteristics shows preferable performance in predicting pCR. ADVANCES IN KNOWLEDGE A nomogram incorporating MRI and US with clinicopathologic variables was developed to provide a brief and concise approach in predicting pCR to assist clinicians in making treatment decisions early.
Collapse
Affiliation(s)
- Man-Qi Zhang
- Department of Ultrasound, The First Affiliated Hospital of Nanjing Medical University, Nanjing 210029, China
| | - Xin-Pei Liu
- Department of Ultrasound, The First Affiliated Hospital of Nanjing Medical University, Nanjing 210029, China
| | - Yu Du
- Department of Ultrasound, Shanghai General Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200080, China
| | - Hai-Ling Zha
- Department of Ultrasound, The First Affiliated Hospital of Nanjing Medical University, Nanjing 210029, China
| | - Xiao-Ming Zha
- Department of Breast Surgery, The First Affiliated Hospital of Nanjing Medical University, Nanjing 210029, China
| | - Jue Wang
- Department of Breast Surgery, The First Affiliated Hospital of Nanjing Medical University, Nanjing 210029, China
| | - Xiao-An Liu
- Department of Breast Surgery, The First Affiliated Hospital of Nanjing Medical University, Nanjing 210029, China
| | - Shou-Ju Wang
- Department of Radiology, The First Affiliated Hospital of Nanjing Medical University, Nanjing 210029, China
| | - Qi-Gui Zou
- Department of Radiology, The First Affiliated Hospital of Nanjing Medical University, Nanjing 210029, China
| | - Jiu-Lou Zhang
- Department of Radiology, The First Affiliated Hospital of Nanjing Medical University, Nanjing 210029, China
| | - Cui-Ying Li
- Department of Ultrasound, The First Affiliated Hospital of Nanjing Medical University, Nanjing 210029, China
| |
Collapse
|
5
|
Wang Y, Zhao M, Ma Y, Liu A, Zhu Y, Yin L, Liang Z, Qu Z, Lu H, Ma Y, Ye Z. Accuracy of Preoperative Contrast-enhanced Cone Beam Breast CT in Assessment of Residual Tumor after Neoadjuvant Chemotherapy: A Comparative Study with Breast MRI. Acad Radiol 2023; 30:1805-1815. [PMID: 36610931 DOI: 10.1016/j.acra.2022.12.027] [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: 10/26/2022] [Revised: 12/11/2022] [Accepted: 12/16/2022] [Indexed: 01/07/2023]
Abstract
RATIONALE AND OBJECTIVES To compare the accuracy of preoperative contrast-enhanced cone beam breast CT (CE-CBBCT) and MRI in assessment of residual tumor after neoadjuvant chemotherapy (NAC). MATERIALS AND METHODS Residual tumor assessments in 91 female patients were performed on preoperative CE-CBBCT and MRI images after NAC. The agreements of tumor size between imaging and pathology were tested by Intraclass Correlation Coefficient (ICC). Subgroup analyses were set according to ductal carcinoma in situ (DCIS), calcifications and molecular subtypes. Correlated-samples Wilcoxon Signed-rank test was used to analyze the difference between imaging and pathology in total and subgroups. AUC, sensitivity, specificity, PPV, and NPV were calculated to compare the performance of CE-CBBCT and MRI in predicting pathological complete response (pCR). RESULTS Comparing with pathology, the agreement on CE-CBBCT was good (ICC = 0.64, 95% CI, 0.35-0.78), whereas on MRI was moderate (ICC = 0.59, 95% CI, 0.36-0.77), and overestimation on CE-CBBCT was less than that on MRI (median (interquartile range, IQR): 0.24 [0.00, 1.31] cm vs. 0.67 [0.00, 1.81] cm; p = 0.000). In subgroup analysis, CE-CBBCT showed superior accuracy than MRI when residual DCIS (p = 0.000) and calcifications (p = 0.000) contained, as well as luminal A (p = 0.043) and luminal B (p = 0.009) breast cancer. CE-CBBCT and MRI performed comparable in predicting pCR, AUCs were 0.749 and 0.733 respectively (p > 0.05). CONCLUSION CE-CBBCT showed superior accuracy in assessment of residual tumor compared with MRI, especially when residual DCIS or calcifications contained and luminal subtype. The performance of preoperative CE-CBBCT in predicting pCR was comparable to MRI. CE-CBBCT could be an alternative method used for preoperative assessment after NAC.
Collapse
Affiliation(s)
- Yafei Wang
- Department of Radiology, Tianjin Medical University Cancer Institute & Hospital, National Clinical Research Center for Cancer, Tianjin's Clinical Research Center for Cancer, Key Laboratory of Breast Cancer Prevention and Therapy, Tianjin Medical University, Ministry of Education, Key Laboratory of Cancer Prevention and Therapy, Tianjin, China
| | - Mengran Zhao
- Department of Radiology, Tianjin Medical University Cancer Institute & Hospital, National Clinical Research Center for Cancer, Tianjin's Clinical Research Center for Cancer, Key Laboratory of Breast Cancer Prevention and Therapy, Tianjin Medical University, Ministry of Education, Key Laboratory of Cancer Prevention and Therapy, Tianjin, China
| | - Yue Ma
- Department of Radiology, Tianjin Medical University Cancer Institute & Hospital, National Clinical Research Center for Cancer, Tianjin's Clinical Research Center for Cancer, Key Laboratory of Breast Cancer Prevention and Therapy, Tianjin Medical University, Ministry of Education, Key Laboratory of Cancer Prevention and Therapy, Tianjin, China
| | - Aidi Liu
- Department of Radiology, Tianjin Medical University Cancer Institute & Hospital, National Clinical Research Center for Cancer, Tianjin's Clinical Research Center for Cancer, Key Laboratory of Breast Cancer Prevention and Therapy, Tianjin Medical University, Ministry of Education, Key Laboratory of Cancer Prevention and Therapy, Tianjin, China
| | - Yueqiang Zhu
- Department of Radiology, Tianjin Medical University Cancer Institute & Hospital, National Clinical Research Center for Cancer, Tianjin's Clinical Research Center for Cancer, Key Laboratory of Breast Cancer Prevention and Therapy, Tianjin Medical University, Ministry of Education, Key Laboratory of Cancer Prevention and Therapy, Tianjin, China
| | - Lu Yin
- Department of Radiology, Tianjin Medical University Cancer Institute & Hospital, National Clinical Research Center for Cancer, Tianjin's Clinical Research Center for Cancer, Key Laboratory of Breast Cancer Prevention and Therapy, Tianjin Medical University, Ministry of Education, Key Laboratory of Cancer Prevention and Therapy, Tianjin, China
| | - Zhiran Liang
- Department of Radiology, Tianjin Medical University Cancer Institute & Hospital, National Clinical Research Center for Cancer, Tianjin's Clinical Research Center for Cancer, Key Laboratory of Breast Cancer Prevention and Therapy, Tianjin Medical University, Ministry of Education, Key Laboratory of Cancer Prevention and Therapy, Tianjin, China
| | - Zhiye Qu
- Department of Radiology, Tianjin Medical University Cancer Institute & Hospital, National Clinical Research Center for Cancer, Tianjin's Clinical Research Center for Cancer, Key Laboratory of Breast Cancer Prevention and Therapy, Tianjin Medical University, Ministry of Education, Key Laboratory of Cancer Prevention and Therapy, Tianjin, China
| | - Hong Lu
- Department of Breast Imaging, Tianjin Medical University Cancer Institute & Hospital, National Clinical Research Center for Cancer, Tianjin's Clinical Research Center for Cancer, Key Laboratory of Breast Cancer Prevention and Therapy, Tianjin Medical University, Ministry of Education, Key Laboratory of Cancer Prevention and Therapy, Tianjin, China
| | - Ying Ma
- Department of Pancreatic Cancer, Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center for Cancer, Key Laboratory of Cancer Prevention and Therapy, Tianjin's Clinical Research Center for Cancer, Tianjin, China
| | - Zhaoxiang Ye
- Department of Radiology, Tianjin Medical University Cancer Institute & Hospital, National Clinical Research Center for Cancer, Tianjin's Clinical Research Center for Cancer, Key Laboratory of Breast Cancer Prevention and Therapy, Tianjin Medical University, Ministry of Education, Key Laboratory of Cancer Prevention and Therapy, Tianjin, China..
| |
Collapse
|
6
|
Hu Y, Mao L, Wang M, Li Z, Li M, Wang C, Ji L, Zeng H, Zhang X. New insights into breast microcalcification for poor prognosis: NACT cohort and bone metastasis evaluation cohort. J Cancer Res Clin Oncol 2023; 149:7285-7297. [PMID: 36917189 DOI: 10.1007/s00432-023-04668-4] [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: 10/05/2022] [Accepted: 02/23/2023] [Indexed: 03/15/2023]
Abstract
OBJECTIVES The study aimed to analyze the poor prognosis of microcalcification in breast cancer (BC), including the pathological complete response (pCR) to neoadjuvant chemotherapy (NACT) and the risk of bone metastases. MATERIALS AND METHODS 313 breast cancer patients received NACT to evaluate pCR and 1182 patients from a multicenter database to assess bone metastases were retrospectively included. Two groups were divided according to the presence or absence of mammography microcalcification. Clinical data, image characteristics, neoadjuvant treatment response, bone involvement, and follow-up information were recorded. The pCR and bone metastases were compared between subgroups using the Mann-Whitney and χ2 tests and logistic regression, respectively. RESULTS Mammographic microcalcification was associated with a lower pCR than uncalcified BC in the NACT cohort (20.6% vs 31.6%, P = 0.029). Univariate and multivariate analysis suggested that calcification was a risk factor for poor NACT response [OR = 1.780, 95%CI (1.065-2.974), P = 0.028], [OR = 2.352, 95%CI (1.186-4.667), P = 0.014]. Microcalcification was more likely to be necrosis on MRI than those without microcalcification (53.0% vs 31.7%, P < 0.001), multivariate analysis indicated that tumor necrosis was also a risk factor for poor NACT response [OR = 2.325, 95%CI (1.100-4.911), P = 0.027]. Age, menopausal status, breast density, mass, molecular, and pathology type were not significantly associated with non-pCR risk assessment. In a multicenter cohort of 1182 patients with pathologically confirmed BC, those with microcalcifications had a higher proportion of bone metastases compared to non-calcified BC (11.6% vs 4.9%, P < 0.001). Univariate and multivariate analysis showed that microcalcification was an independent risk factor for bone metastasis [OR = 2.550, 95%CI (1.620-4.012), P < 0.001], [OR = 2.268(1.263-4.071), P = 0.006)]. Osteolytic bone metastases predominated but there was no statistical difference between the two groups (78.9% vs 60.7%, P = 0.099). Calcified BC was mainly involved in axial bone, but was more likely to involve the whole-body bone than non-calcified BC (33.8% vs 10.7%, P = 0.021). CONCLUSION This study provides important insights into the poor prognosis of microcalcification, not only in terms of poor response to NACT but also the risk factor of bone metastases.
Collapse
Affiliation(s)
- Yangling Hu
- Department of Radiology, The First Affiliated Hospital, Sun Yat-Sen University, Guangzhou, China
| | - Lijuan Mao
- Department of Radiology, The First Affiliated Hospital, Sun Yat-Sen University, Guangzhou, China
| | - Mengyi Wang
- Department of Radiology, The First Affiliated Hospital, Sun Yat-Sen University, Guangzhou, China
| | - Zhenqiu Li
- Department of Radiology, The Panyu Fifth Hospital, Guangzhou, China
| | - Meizhi Li
- Department of Radiology, The First Affiliated Hospital, Sun Yat-Sen University, Guangzhou, China
| | - Chaoyang Wang
- Department of Radiology, The First Affiliated Hospital, Sun Yat-Sen University, Guangzhou, China
| | - Lin Ji
- Department of Radiology, The First Affiliated Hospital, Sun Yat-Sen University, Guangzhou, China
| | - Hui Zeng
- Department of Radiology, Nanfang Hospital, Southern Medical University, Guangzhou, China.
| | - Xiaoling Zhang
- Department of Radiology, The First Affiliated Hospital, Sun Yat-Sen University, Guangzhou, China.
| |
Collapse
|
7
|
Yu FH, Miao SM, Li CY, Hang J, Deng J, Ye XH, Liu Y. Pretreatment ultrasound-based deep learning radiomics model for the early prediction of pathologic response to neoadjuvant chemotherapy in breast cancer. Eur Radiol 2023; 33:5634-5644. [PMID: 36976336 DOI: 10.1007/s00330-023-09555-7] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/07/2022] [Revised: 02/09/2023] [Accepted: 02/19/2023] [Indexed: 03/29/2023]
Abstract
OBJECTIVES To investigate the predictive performance of the deep learning radiomics (DLR) model integrating pretreatment ultrasound imaging features and clinical characteristics for evaluating therapeutic response after neoadjuvant chemotherapy (NAC) in patients with breast cancer. METHODS A total of 603 patients who underwent NAC were retrospectively included between January 2018 and June 2021 from three different institutions. Four different deep convolutional neural networks (DCNNs) were trained by pretreatment ultrasound images using annotated training dataset (n = 420) and validated in a testing cohort (n = 183). Comparing the predictive performance of these models, the best one was selected for image-only model structure. Furthermore, the integrated DLR model was constructed based on the image-only model combined with independent clinical-pathologic variables. Areas under the curve (AUCs) of these models and two radiologists were compared by using the DeLong method. RESULTS As the optimal basic model, Resnet50 achieved an AUC and accuracy of 0.879 and 82.5% in the validation set. The integrated DLR model, yielding the highest classification performance in predicting response to NAC (AUC 0.962 and 0.939 in the training and validation cohort), outperformed the image-only model and the clinical model and also performed better than two radiologists' prediction (all p < 0.05). In addition, predictive efficacy of the radiologists was improved under the assistance of the DLR model significantly. CONCLUSION The pretreatment US-based DLR model could hold promise as a clinical guidance for predicting NAC response of patients with breast cancer, thereby providing benefit of timely treatment strategy adjustment to potential poor NAC responders. KEY POINTS • Multicenter retrospective study showed that deep learning radiomics (DLR) model based on pretreatment ultrasound image and clinical parameter achieved satisfactory prediction of tumor response to neoadjuvant chemotherapy (NAC) in breast cancer. • The integrated DLR model could become an effective tool to guide clinicians in identifying potential poor pathological responders before chemotherapy. • The predictive efficacy of the radiologists was improved under the assistance of the DLR model.
Collapse
Affiliation(s)
- Fei-Hong Yu
- Department of Ultrasound, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China
| | - Shu-Mei Miao
- Department of Information, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China
- Department of Medical Informatics, School of Biomedical Engineering and Informatics, Nanjing Medical University, Nanjing, China
| | - Cui-Ying Li
- Department of Ultrasound, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China
| | - Jing Hang
- Department of Ultrasound, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China
| | - Jing Deng
- Department of Ultrasound, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China
| | - Xin-Hua Ye
- Department of Ultrasound, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China
| | - Yun Liu
- Department of Information, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China.
- Department of Medical Informatics, School of Biomedical Engineering and Informatics, Nanjing Medical University, Nanjing, China.
| |
Collapse
|
8
|
Panico C, Ferrara F, Woitek R, D’Angelo A, Di Paola V, Bufi E, Conti M, Palma S, Cicero SL, Cimino G, Belli P, Manfredi R. Staging Breast Cancer with MRI, the T. A Key Role in the Neoadjuvant Setting. Cancers (Basel) 2022; 14:cancers14235786. [PMID: 36497265 PMCID: PMC9739275 DOI: 10.3390/cancers14235786] [Citation(s) in RCA: 8] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/16/2022] [Revised: 11/15/2022] [Accepted: 11/17/2022] [Indexed: 11/27/2022] Open
Abstract
Breast cancer (BC) is the most common cancer among women worldwide. Neoadjuvant chemotherapy (NACT) indications have expanded from inoperable locally advanced to early-stage breast cancer. Achieving a pathological complete response (pCR) has been proven to be an excellent prognostic marker leading to better disease-free survival (DFS) and overall survival (OS). Although diagnostic accuracy of MRI has been shown repeatedly to be superior to conventional methods in assessing the extent of breast disease there are still controversies regarding the indication of MRI in this setting. We intended to review the complex literature concerning the tumor size in staging, response and surgical planning in patients with early breast cancer receiving NACT, in order to clarify the role of MRI. Morphological and functional MRI techniques are making headway in the assessment of the tumor size in the staging, residual tumor assessment and prediction of response. Radiomics and radiogenomics MRI applications in the setting of the prediction of response to NACT in breast cancer are continuously increasing. Tailored therapy strategies allow considerations of treatment de-escalation in excellent responders and avoiding or at least postponing breast surgery in selected patients.
Collapse
Affiliation(s)
- Camilla Panico
- Department of Bioimaging, Radiation Oncology and Hematology, UOC of Radiologia, Fondazione Policlinico Universitario A. Gemelli IRCSS, Largo A. Gemelli 8, 00168 Rome, Italy
- Correspondence:
| | - Francesca Ferrara
- Institute of Radiology, Catholic University of the Sacred Heart, Largo A. Gemelli 8, 00168 Rome, Italy
| | - Ramona Woitek
- Medical Image Analysis and AI (MIAAI), Danube Private University, 3500 Krems, Austria
- Department of Radiology, University of Cambridge, Cambridge CB2 0QQ, UK
- Cancer Research UK Cambridge Centre, Cambridge CB2 0RE, UK
| | - Anna D’Angelo
- Department of Bioimaging, Radiation Oncology and Hematology, UOC of Radiologia, Fondazione Policlinico Universitario A. Gemelli IRCSS, Largo A. Gemelli 8, 00168 Rome, Italy
| | - Valerio Di Paola
- Department of Bioimaging, Radiation Oncology and Hematology, UOC of Radiologia, Fondazione Policlinico Universitario A. Gemelli IRCSS, Largo A. Gemelli 8, 00168 Rome, Italy
| | - Enida Bufi
- Department of Bioimaging, Radiation Oncology and Hematology, UOC of Radiologia, Fondazione Policlinico Universitario A. Gemelli IRCSS, Largo A. Gemelli 8, 00168 Rome, Italy
| | - Marco Conti
- Department of Bioimaging, Radiation Oncology and Hematology, UOC of Radiologia, Fondazione Policlinico Universitario A. Gemelli IRCSS, Largo A. Gemelli 8, 00168 Rome, Italy
| | - Simone Palma
- Institute of Radiology, Catholic University of the Sacred Heart, Largo A. Gemelli 8, 00168 Rome, Italy
| | - Stefano Lo Cicero
- Institute of Radiology, Catholic University of the Sacred Heart, Largo A. Gemelli 8, 00168 Rome, Italy
| | - Giovanni Cimino
- Institute of Radiology, Catholic University of the Sacred Heart, Largo A. Gemelli 8, 00168 Rome, Italy
| | - Paolo Belli
- Department of Bioimaging, Radiation Oncology and Hematology, UOC of Radiologia, Fondazione Policlinico Universitario A. Gemelli IRCSS, Largo A. Gemelli 8, 00168 Rome, Italy
- Institute of Radiology, Catholic University of the Sacred Heart, Largo A. Gemelli 8, 00168 Rome, Italy
| | - Riccardo Manfredi
- Department of Bioimaging, Radiation Oncology and Hematology, UOC of Radiologia, Fondazione Policlinico Universitario A. Gemelli IRCSS, Largo A. Gemelli 8, 00168 Rome, Italy
- Institute of Radiology, Catholic University of the Sacred Heart, Largo A. Gemelli 8, 00168 Rome, Italy
| |
Collapse
|