Study on Classification Method of Indocyanine Green Lymphography Based on Deep Learning (BCRL；ICG)

Study on Classification Method of Indocyanine Green Lymphography in Diagnosing Breast Cancer-related Lymphedema Based on Deep Learning

Breast cancer related lymphedema (BCRL) is the most common complication after breast cancer surgery, which brings a heavy psychological and spiritual burden to patients. For a long time, the diagnosis and treatment of lymphedema has been a difficult point in domestic and foreign research. To a large extent, it is because most of the patients who come to see a doctor have already developed obvious lymphedema, and the internal lymphatic vessels have undergone pathological remodeling[1] Therefore, it is particularly important to detect early lymphedema and intervene in time through the use of sensitive screening tools. Indocyanine green (ICG) lymphangiography is a relatively new method, which can display superficial lymph flow in real time and quickly, and will not be affected by radioactivity [7]. In 2007, indocyanine green lymphography was used for the first time to evaluate the function of superficial lymphatic vessels. In 2011, Japanese scholars found skin reflux signs based on ICG lymphography data of 20 patients with lymphedema after breast cancer surgery, and they were roughly divided into three types according to their severity: splash, star cluster, and diffuse (Figure 1) [8]. Later, in 2016, a prospective study involving 196 people affirmed the value of ICG lymphography in the early diagnosis of lymphedema, and made the images of ICG lymphography more specific stages 0-5 [9], but The staging is still based on the three types of skin reflux symptoms found in a small sample clinical study in 2011, which is not completely applicable in actual clinical applications. In addition, when abnormal skin reflux symptoms appear on ICG lymphangiography, the pathophysiological changes that occur in the body lack research and exploration. Therefore, this research hopes to refine the image features of ICG lymphography through machine learning (deep learning), and establish a PKUPH model for diagnosing early lymphedema by staging the image features.

Study Overview

• Status: Recruiting
• Conditions: Breast Cancer Related Lymphedema; Deep Learning
• Intervention / Treatment: Other: No Intervention.

• Study Type: Observational
• Enrollment (Anticipated): 200

Contacts and Locations

• Study Contact: Name: Siyao Liu, Dr; Phone Number: +8618801229921; Email: dr.liusiyao@pku.edu.cn

Study Locations

• China
  • Beijing
    • Beijing, Beijing, China
      • Recruiting
      • Peking University People's Hospital
      • Contact: liu siyao; Phone Number: +86 18801229921; Email: doc_lsy@163.com

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Child; Adult; Older Adult
• Accepts Healthy Volunteers: Yes
• Genders Eligible for Study: Female

• Sampling Method: Probability Sample

Study Population

patients who have been admitted to the Breast Surgery Clinic due to the main complaint of upper extremity edema

Description

Inclusion Criteria:

• From October 2016 to present, about 200 patients who have been admitted to the Breast Surgery Clinic due to the main complaint of upper extremity edema, are willing to accept ICG lymphography, arm circumference measurement, drainage measurement, bioelectrical impedance measurement, main complaint scale, etc. .

Exclusion Criteria:

• Bilateral breast cancer; history of contrast agent allergy; arteriovenous thrombosis in the affected limb; regional lymph node recurrence; no informed consent; severe heart and brain diseases; primary lymphatic system disease (such as lymphatic leakage); unilateral only The limbs received ICG imaging.

Study Plan

How is the study designed?

Number of groups / cohorts

3

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
label 1; Baseline data measurement of this group of patients: arm circumference（positive） and ICG (positive).	Other: No Intervention.; No Intervention.Only learn ICG image features of different label groups
label 2; Baseline data measurement of this group of patients: arm circumference（negative） and ICG (positive).	Other: No Intervention.; No Intervention.Only learn ICG image features of different label groups
label 3; Baseline data measurement of this group of patients: arm circumference（negative） and ICG (negative).	Other: No Intervention.; No Intervention.Only learn ICG image features of different label groups

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Establish a PKUPH model for the diagnosis of lymphedema by ICG based on deep learning	Establish a PKUPH model for the diagnosis of lymphedema by ICG based on deep learning	2016-2022

Collaborators and Investigators

• Sponsor: Peking University People's Hospital
• Investigators: Principal Investigator: Shu Wang, Dr, Breast Center, Peking University People's Hospital, Beijing, China

Publications and helpful links

General Publications

• Mihara M, Hara H, Araki J, Kikuchi K, Narushima M, Yamamoto T, Iida T, Yoshimatsu H, Murai N, Mitsui K, Okitsu T, Koshima I. Indocyanine green (ICG) lymphography is superior to lymphoscintigraphy for diagnostic imaging of early lymphedema of the upper limbs. PLoS One. 2012;7(6):e38182. doi: 10.1371/journal.pone.0038182. Epub 2012 Jun 4.
• Yamamoto T, Yamamoto N, Doi K, Oshima A, Yoshimatsu H, Todokoro T, Ogata F, Mihara M, Narushima M, Iida T, Koshima I. Indocyanine green-enhanced lymphography for upper extremity lymphedema: a novel severity staging system using dermal backflow patterns. Plast Reconstr Surg. 2011 Oct;128(4):941-947. doi: 10.1097/PRS.0b013e3182268cd9.
• Beek MA, te Slaa A, van der Laan L, Mulder PG, Rutten HJ, Voogd AC, Luiten EJ, Gobardhan PD. Reliability of the Inverse Water Volumetry Method to Measure the Volume of the Upper Limb. Lymphat Res Biol. 2015 Jun;13(2):126-30. doi: 10.1089/lrb.2015.0011.
• Shi S, Lu Q, Fu MR, Ouyang Q, Liu C, Lv J, Wang Y. Psychometric properties of the Breast Cancer and Lymphedema Symptom Experience Index: The Chinese version. Eur J Oncol Nurs. 2016 Feb;20:10-6. doi: 10.1016/j.ejon.2015.05.002. Epub 2015 Jun 9.

Study record dates

Study Major Dates

• Study Start (Actual): October 1, 2016
• Primary Completion (Anticipated): October 1, 2022
• Study Completion (Anticipated): October 1, 2022

Study Registration Dates

• First Submitted: March 27, 2021
• First Submitted That Met QC Criteria: March 27, 2021
• First Posted (Actual): April 1, 2021

Study Record Updates

• Last Update Posted (Actual): April 1, 2021
• Last Update Submitted That Met QC Criteria: March 27, 2021
• Last Verified: March 1, 2021

More Information

Terms related to this study

• Additional Relevant MeSH Terms: Pathologic Processes; Skin Diseases; Neoplasms; Lymphatic Diseases; Neoplasms by Site; Postoperative Complications; Breast Diseases; Breast Neoplasms; Lymphedema; Breast Cancer Lymphedema
• Other Study ID Numbers: PKUPH202102

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO
• IPD Plan Description: there is no plan to make individual participant data (IPD) available to other researchers

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No