Preliminary Study of Ai-assisted Diagnosis Using FDG-PET/CT for Axillary Lymph Node Metastasis in Patients With Breast Cancer

Abstract Background: To improve the diagnostic accuracy of axillary lymph node (LN) metastasis in breast cancer patients using FDG-PET/CT, we constructed an artificial intelligence (AI)-assisted diagnosis system that uses deep-learning technologies.Materials and Methods: Two clinicians and the new AI system retrospectively analyzed and diagnosed 414 axillae of 407 patients with biopsy-proven breast cancer who had undergone FDG-PET/CT before a mastectomy or breast-conserving surgery with a sentinel lymph node (LN) biopsy and/or axillary LN dissection. We designed and trained a deep 3D convolutional neural network (CNN) as the AI model. The diagnoses from the clinicians were blended with the diagnoses from the AI model to improve the diagnostic accuracy.Results: Although the AI model did not outperform the clinicians, the diagnostic accuracies of the clinicians were considerably improved by collaborating with the AI model: the two clinicians' sensitivities of 59.8% and 57.4% increased to 68.6% and 64.2%, respectively, whereas the clinicians' specificities of 99.0% and 99.5% remained unchanged.Conclusions: It is expected that AI using deep-learning technologies will be useful in diagnosing axillary LN metastasis using FDG-PET/CT. Even if the diagnostic performance of AI is not better than that of clinicians, taking AI diagnoses into consideration may positively impact the overall diagnostic accuracy.

Download Full-text

Preliminary study of AI-assisted diagnosis using FDG-PET/CT for axillary lymph node metastasis in patients with breast cancer

EJNMMI Research ◽

10.1186/s13550-021-00751-4 ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Zongyao Li ◽

Kazuhiro Kitajima ◽

Kenji Hirata ◽

Ren Togo ◽

Junki Takenaka ◽

...

Keyword(s):

Breast Cancer ◽

Deep Learning ◽

Lymph Node ◽

Diagnostic Accuracy ◽

Fdg Pet ◽

Learning Technologies ◽

Axillary Lymph ◽

Pet Ct ◽

Assisted Diagnosis ◽

Fdg Pet Ct

Abstract Background To improve the diagnostic accuracy of axillary lymph node (LN) metastasis in breast cancer patients using 2-[18F]FDG-PET/CT, we constructed an artificial intelligence (AI)-assisted diagnosis system that uses deep-learning technologies. Materials and methods Two clinicians and the new AI system retrospectively analyzed and diagnosed 414 axillae of 407 patients with biopsy-proven breast cancer who had undergone 2-[18F]FDG-PET/CT before a mastectomy or breast-conserving surgery with a sentinel lymph node (LN) biopsy and/or axillary LN dissection. We designed and trained a deep 3D convolutional neural network (CNN) as the AI model. The diagnoses from the clinicians were blended with the diagnoses from the AI model to improve the diagnostic accuracy. Results Although the AI model did not outperform the clinicians, the diagnostic accuracies of the clinicians were considerably improved by collaborating with the AI model: the two clinicians' sensitivities of 59.8% and 57.4% increased to 68.6% and 64.2%, respectively, whereas the clinicians' specificities of 99.0% and 99.5% remained unchanged. Conclusions It is expected that AI using deep-learning technologies will be useful in diagnosing axillary LN metastasis using 2-[18F]FDG-PET/CT. Even if the diagnostic performance of AI is not better than that of clinicians, taking AI diagnoses into consideration may positively impact the overall diagnostic accuracy.

Download Full-text

Value of F-18 FDG PET/CT in detection and prognostication of isolated extra-axillary lymph node recurrences in postoperative breast cancer

Bio-Medical Materials and Engineering ◽

10.3233/bme-130918 ◽

2014 ◽

Vol 24 (1) ◽

pp. 1173-1184

Author(s):

Jin Kyoung Oh ◽

Yong An Chung ◽

Yeon Sil Kim ◽

Hae Myung Jeon ◽

Sung Hoon Kim ◽

...

Keyword(s):

Breast Cancer ◽

Lymph Node ◽

Fdg Pet ◽

Axillary Lymph Node ◽

Axillary Lymph ◽

Pet Ct ◽

Fdg Pet Ct

Download Full-text

Prediction of macrometastasis in axillary lymph nodes of patients with invasive breast cancer and the utility of the SUV lymph node/tumor ratio using FDG-PET/CT

World Journal of Surgical Oncology ◽

10.1186/s12957-014-0424-2 ◽

2015 ◽

Vol 13 (1) ◽

pp. 49 ◽

Cited By ~ 12

Author(s):

Manabu Futamura ◽

Takahiko Asano ◽

Kazuhiro Kobayashi ◽

Kasumi Morimitsu ◽

Masahito Nawa ◽

...

Keyword(s):

Breast Cancer ◽

Lymph Node ◽

Lymph Nodes ◽

Invasive Breast Cancer ◽

Fdg Pet ◽

Axillary Lymph Nodes ◽

Axillary Lymph ◽

Pet Ct ◽

Fdg Pet Ct

Download Full-text

Early and delayed prediction of axillary lymph node neoadjuvant response by 18F-FDG PET/CT in patients with locally advanced breast cancer

European Journal of Nuclear Medicine and Molecular Imaging ◽

10.1007/s00259-013-2657-7 ◽

2014 ◽

Vol 41 (7) ◽

pp. 1309-1318 ◽

Cited By ~ 10

Author(s):

Ana María García Vicente ◽

Ángel Soriano Castrejón ◽

Alberto León Martín ◽

Fernanda Relea Calatayud ◽

María del Mar Muñoz Sánchez ◽

...

Keyword(s):

Breast Cancer ◽

Lymph Node ◽

Fdg Pet ◽

Axillary Lymph Node ◽

Locally Advanced Breast Cancer ◽

Locally Advanced ◽

Axillary Lymph ◽

Pet Ct ◽

18F Fdg ◽

Fdg Pet Ct

Download Full-text

Efficacy of US, MRI, and F-18 FDG-PET/CT for Detecting Axillary Lymph Node Metastasis after Neoadjuvant Chemotherapy in Breast Cancer Patients

Diagnostics ◽

10.3390/diagnostics11122361 ◽

2021 ◽

Vol 11 (12) ◽

pp. 2361

Author(s):

Umit Turan ◽

Murat Aygun ◽

Berna Bozkurt Duman ◽

Aygül Polat Kelle ◽

Yeliz Cavus ◽

...

Keyword(s):

Breast Cancer ◽

Lymph Node ◽

Fdg Pet ◽

Axillary Lymph ◽

Breast Cancer Patients ◽

Node Metastasis ◽

18Fdg Pet ◽

Pet Ct ◽

Sensitivity Specificity ◽

Fdg Pet Ct

Background: The aim of this study was to investigate the efficacy of post-neoadjuvant chemotherapy (NAC) ultrasound (US), magnetic resonance imaging (MRI), and F-18fluorodeoxyglucose positron emission tomography (F-18 FDG-PET/CT) for detecting post-NAC axillary lymph node(ALN) metastasis in patients who had ALN metastasis at the time of diagnosis. Methods: This study included all breast cancer patients who received NAC for ALN metastasis; underwent axillary assessment with US, MRI, or F18FDG-PET/CT; and then were operated on in the General Surgery Clinic, Adana City Research and Training Hospital, Turkey. Patients’ data were recorded, including demographic data, clinicopathological parameters, NAC regimens, and operation types. The axillary response to chemotherapy on post-NAC US, MRI, and F-18 FDG-PET/CT was compared with the postoperative histopathological result of the ALN. Results: The study included a total of 171 female patients. The mean age of the patients was 53.28 ± 10.62 years. The post-NAC assessment revealed that the sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of US for detecting ALN metastasis were 59.42%, 82.35%, 82.00%, and 60.00%, respectively, while the same measures regarding MRI for detecting ALN metastasis were 36.67%, 77.78%, 73.33%, and 42.42%, respectively. The sensitivity, specificity, PPV, and NPV of F-18FDG-PET/CT were 47.50%, 76.67%, 73.08%, and 52.27%, respectively. The evaluation of dual combinations of these three imaging techniques showed that the specificity and PPV of the combined use of US and F-18FDG-PET/CT was 100%. Conclusions: The results showed that US has the highest sensitivity and specificity for detecting ALN metastasis after NAC. Furthermore, ALND may be preferred for these patients instead of SLNB if both examinations simultaneously indicate lymph node metastasis in the post-NAC assessment with US and F-18 FDG-PET/CT. SLNB may be preferred if these two examinations simultaneously show a complete response.

Download Full-text

Volume-based parameters on FDG-PET/CT as early predictors of disease recurrence in postmastectomy breast cancer patients with one to three positive axillary lymph nodes without adjuvant radiotherapy.

Journal of Clinical Oncology ◽

10.1200/jco.2013.31.15_suppl.1124 ◽

2013 ◽

Vol 31 (15_suppl) ◽

pp. 1124-1124

Author(s):

Naomi Nakajima ◽

Masaaki Kataoka ◽

Atsushi Nishikawa ◽

Yoshifumi Sugawara ◽

Shinya Sakai ◽

...

Keyword(s):

Breast Cancer ◽

Lymph Node ◽

Lymph Nodes ◽

Cancer Patients ◽

Fdg Pet ◽

Axillary Lymph Nodes ◽

Axillary Lymph ◽

Breast Cancer Patients ◽

Pet Ct ◽

Fdg Pet Ct

1124 Background: The indication for postmastectomy radiotherapy (PMRT) in patients with 1-3 lymph node metastases in the axilla have been controversial, despite the recommendation that PMRT should be applied. In the current study, we focused our study on volume-based parameters of pretreatment FDG-PET/CT, with the aim of investigating a measurement that could help identify high-risk populations for recurrence. Methods: We retrospectively analyzed 88 patients of breast cancer treated with modified radical mastectomy and were found to have 1-3 metastatic axillary lymph nodes between 2006 and 2010. All of them were studied with FDG-PET/CT for initial staging. We evaluated the relationship between clinicopathologic factors or PET parameters including the maximum standardized uptake value (SUVmax), metabolic tumor volume (MTV), and total lesion glycolysis (TLG) and recurrence. MTV and TLG of the primary tumor and metastatic lymph node were measured by using semi-automatically delineated volume of interest (VOI) with an isocontour threshold of 40 % of the SUVmax. The optimal cutoffs of PET parameters were determined by ROC curve analysis. Results: The median follow up duration was 39 months. Median MTV was 21.1and median TLG was 42.7. Recurrence was observed in 10 patients. The area under the ROC curve of MTV and TLG for DFS was 0.82 and 0.85, respectively. In Cox univariate analysis, estrogen receptor status (HR = 6.8, p = 0.003), triple negativity (HR = 10.4, p = 0.0008), SUVmax (HR = 71.1, p = 0.001), MTV (HR = 130.3, p < 0.0001), and TLG (HR = 234.1, p = 0.0001) were significantly related to disease free survival (DFS). The estimated 3-year DFS rates were 96.4 % for the lower MTV group (< 31.8) and 71.4% for the higher MTV group (≥ 31.8, p = 0.0005). The estimated 3-year DFS rates were 95.8 % for the lower TLG group (< 109.6) and 50.0 % for the higher TLG group (≥ 109.6, p < 0.0001). On multivariate analysis, TLG was an independent prognostic factor of DFS (HR = 8.5, p = 0.005). Conclusions: Volume-based parameters on FDG-PET/CT were significant predictors of DFS in postmastectomy breast cancer patients with 1-3 metastatic axillary lymph nodes.

Download Full-text

Lymphoscintigraphy in breast cancer patients after neoadjuvant chemotherapy

Nuklearmedizin ◽

10.3413/nukmed-0320-10-05 ◽

2011 ◽

Vol 50 (01) ◽

pp. 33-38 ◽

Cited By ~ 6

Author(s):

R. Reitsamer ◽

J. Holzmannhofer ◽

G. Rendl ◽

C. Pirich ◽

C. Kronberger ◽

...

Keyword(s):

Breast Cancer ◽

Lymph Node ◽

Neoadjuvant Chemotherapy ◽

Fdg Pet ◽

Lymphatic Mapping ◽

Axillary Lymph ◽

Breast Cancer Patients ◽

Pet Ct ◽

18F Fdg ◽

Fdg Pet Ct

SummaryThe aim of this study was to evaluate the diagnostic value of lymphatic mapping by lymphoscintigraphy in breast cancer patients undergoing neoadjuvant chemotherapy (NCTX). We assessed the association between clinicopathological factors and nonvisualized sentinel nodes during preoperative lymphoscintigraphy. As secondary aims, we analyzed whether post NCTX axillary ultrasonography and fluorine-18 fluorodeoxyglucose positron emission tomography and computed tomography (F18-FDG-PET/CT) might be useful for staging in case of nonvisualized sentinel nodes. Patients, methods: 61 patients with newly diagnosed, invasive breast cancer potentially eligible for NCTX were included in this substudy of a prospective trial on the monitoring of NCTX with 18F-FDG PET/CT. In all patients, lymphoscintigraphy was performed prior to sentinel lymph node biopsy (SLNB). 42 patients received neoadjuvant chemotherapy. 19 patients did not receive NCTX. After SLNB, mastectomy or lumpectomy (breast-conserving surgery) combined with level I and II axillary lymph node dissection were performed. Cases of nonvisualized sentinel nodes were analyzed with respect to tumour and patient characteristics and the results of ultrasonography and 18F-FDG-PET/CT before and after NCTX. Results: Lymphoscintigram successfully identified at least one sN in 55 patients (i.e. identification rate of 90%). The risk of failure to identify the sN was associated statistically with a positive clinical nodal status prior to NCTX (p = 0.021). There was no statistical difference between patients with visualized and nonvisualized sN with respect to age, tumour grade, tumour size, pathological lymph node status or tumour histology. In patients without NCTX the sN identification rate was 100% versus 86% in patients with NCTX (n.s.). The FNR of patients with NCTX was 9.1%. Post NCTX axillary ultrasonography or FDG-PET/CT did not provide accurate information about the lymph node status in case of failing lymphatic mapping. Conclusion: On the basis of our findings, SLNB can not yet be recommended as a reliable staging method in breast cancer patients undergoing neoadjuvant chemotherapy. Patients with clinically positive axillary lymph nodes have a higher chance of unsuccessful lymphatic mapping by lymphoscintigraphy. Performing SLNB before NCTX in clinically node-negative patients may identify the subset of patients in whom axillary lymph node dissection can be omitted. Post NCTX axillary ultrasonography and 18F-FDG-PET/CT can not be suggested as valid axillary staging methods in case of a failed lymphatic mapping.

Download Full-text