New method of sentinel node detection using a combination of contrast-enhanced ultrasound and dye guidance: an animal study

Omoto, Kiyoka; Hozumi, Yasuo; Nihei, Yoshito; Omoto, Yoko; Mizunuma, Hirobumi; Nagai, Hideo; Koibuchi, Harumi; Fujii, Yasutomo; Taniguchi, Nobuyuki; Itoh, Kouichi

doi:10.1007/s10396-005-0098-z

Cited by 7 publications

(2 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Once the model was developed (trained), it was deployed on one node to make prediction on an external testing set. The number of computing node here determines the number of queries per second the model can support 59 . During the model development, the model automatically distributes the images of the developmental cohort to 80% training, 10% validation, and 10% testing from which the internal validation metrics were reported as precision (positive predictive value [PPV]) and recall (sensitivity).…”

Section: Methodsmentioning

confidence: 99%

Characterizing Sentinel Lymph Node Status in Breast Cancer Patients Using a Deep-Learning Model Compared With Radiologists' Analysis of Grayscale Ultrasound and Lymphosonography

Machado,

Tahmasebi,

Fallon

et al. 2024

Ultrasound Quarterly

View full text Add to dashboard Cite

The objective of the study was to use a deep learning model to differentiate between benign and malignant sentinel lymph nodes (SLNs) in patients with breast cancer compared to radiologists' assessments. Seventy-nine women with breast cancer were enrolled and underwent lymphosonography and contrast-enhanced ultrasound (CEUS) examination after subcutaneous injection of ultrasound contrast agent around their tumor to identify SLNs. Google AutoML was used to develop image classification model. Grayscale and CEUS images acquired during the ultrasound examination were uploaded with a data distribution of 80% for training/20% for testing. The performance metric used was area under precision/recall curve (AuPRC). In addition, 3 radiologists assessed SLNs as normal or abnormal based on a clinical established classification. Two-hundred seventeen SLNs were divided in 2 for model development; model 1 included all SLNs and model 2 had an equal number of benign and malignant SLNs. Validation results model 1 AuPRC 0.84 (grayscale)/0.91 (CEUS) and model 2 AuPRC 0.91 (grayscale)/0.87 (CEUS). The comparison between artificial intelligence (AI) and readers' showed statistical significant differences between all models and ultrasound modes; model 1 grayscale AI versus readers, P = 0.047, and model 1 CEUS AI versus readers, P < 0.001. Model 2 r grayscale AI versus readers, P = 0.032, and model 2 CEUS AI versus readers, P = 0.041. The interreader agreement overall result showed κ values of 0.20 for grayscale and 0.17 for CEUS. In conclusion, AutoML showed improved diagnostic performance in balance volume datasets. Radiologist performance was not influenced by the dataset’s distribution.

show abstract

Section: Methodsmentioning

confidence: 99%

Characterizing Sentinel Lymph Node Status in Breast Cancer Patients Using a Deep-Learning Model Compared With Radiologists' Analysis of Grayscale Ultrasound and Lymphosonography

Machado,

Tahmasebi,

Fallon

et al. 2024

Ultrasound Quarterly

View full text Add to dashboard Cite

show abstract

“…After a local massage, the agent will be taken up by lymphatic channels and finally will reach the SLN, which can be imaged by low mechanical index (MI) US. So far, several contrast agents have been used in the studies, including 25% albumin solution ( 21 , 22 ) , hydroxyethylated starch ( 23 ) , SonoVue ® ( 24 – 26 ) , Sonazoid ® ( 17 , 18 ) , and Definity ® ( 27 ) .…”

Section: Introductionmentioning

confidence: 99%

Contrast enhanced ultrasound of sentinel lymph nodes

et al. 2013

View full text Add to dashboard Cite

Sentinel lymph nodes are the first lymph nodes in the region that receive lymphatic drainage from a primary tumor. The detection or exclusion of sentinel lymph node micrometastases is critical in the staging of cancer, especially breast cancer and melanoma because it directly affects patient's prognosis and surgical management. Currently, intraoperative sentinel lymph node biopsies using blue dye and radioisotopes are the method of choice for the detection of sentinel lymph node with high identification rate. In contrast, conventional ultrasound is not capable of detecting sentinel lymph nodes in most cases. Contrast enhanced ultrasound with contrast specific imaging modes has been used for the evaluation and diagnostic work-up of peripherally located suspected lymphadenopathy. The method allows for real-time analysis of all vascular phases and the visualization of intranodal focal “avascular” areas that represent necrosis or deposits of neoplastic cells. In recent years, a number of animal and human studies showed that contrast enhanced ultrasound can be also used for the detection of sentinel lymph node, and may become a potential application in clinical routine. Several contrast agents have been used in those studies, including albumin solution, hydroxyethylated starch, SonoVue®, Sonazoid® and Definity®. This review summarizes the current knowledge about the use of ultrasound techniques in detection and evaluation of sentinel lymph node.

show abstract

Sentinel lymph node identification using contrast-enhanced ultrasound in breast cancer: review of the literature

2023

View full text Add to dashboard Cite

Before breast cancer surgery, sentinel lymph node (SLN) identification and biopsy using blue dye, radioisotope (RI) with a gamma probe, or a combination of the two are mainly performed. The dye-guided method requires skilled technique to make an incision in the skin and identify SLNs without damaging the lymphatic vessels. In addition, dye-induced anaphylactic shock has been reported. To use the γ-probe-guided method, the facility must be able to handle RI. However, to overcome the drawbacks of these methods, Omoto et al. developed a new identification modality using contrast-enhanced ultrasound with an ultrasound contrast agent (UCA) in 2002. Since then, many basic experiments and clinical studies using various UCA have been reported. In particular, a number of studies in SLN detection using Sonazoid have been reported and are herein reviewed.

show abstract

New method of sentinel node detection using a combination of contrast-enhanced ultrasound and dye guidance: an animal study

Abstract: These results suggest that this combination of contrast-enhanced ultrasound-guided and dye-guided methods warrants use as a quick, simple procedure for detecting sentinel lymph nodes.

Cited by 7 publications

References 21 publications

Characterizing Sentinel Lymph Node Status in Breast Cancer Patients Using a Deep-Learning Model Compared With Radiologists' Analysis of Grayscale Ultrasound and Lymphosonography

Characterizing Sentinel Lymph Node Status in Breast Cancer Patients Using a Deep-Learning Model Compared With Radiologists' Analysis of Grayscale Ultrasound and Lymphosonography

Contrast enhanced ultrasound of sentinel lymph nodes

Sentinel lymph node identification using contrast-enhanced ultrasound in breast cancer: review of the literature

Contact Info

Product

Resources

About