Development of a Deep Learning-based Model for Guiding a Dissection During Robotic Breast Surgery

Overview

Journal Breast Cancer Res

Specialty Oncology

Date 2025 Mar 11

PMID 40065440

Authors

Jeea Lee

Sungwon Ham

Namkug Kim

Hyung Seok Park

Affiliations

Soon will be listed here.

Abstract

Background: Traditional surgical education is based on observation and assistance in surgical practice. Recently introduced deep learning (DL) techniques enable the recognition of the surgical view and automatic identification of surgical landmarks. However, there was no previous studies have conducted to develop surgical guide for robotic breast surgery. To develop a DL model for guiding the dissection plane during robotic mastectomy for beginners and trainees.

Methods: Ten surgical videos of robotic mastectomy procedures were recorded. Video frames taken at 1-s intervals were converted to PNG format. The ground truth was manually delineated by two experienced surgeons using ImageJ software. The evaluation metrics were the Dice similarity coefficient (DSC) and Hausdorff distance (HD).

Results: A total of 8,834 images were extracted from ten surgical videos of robotic mastectomies performed between 2016 and 2020. Skin flap dissection during the robotic mastectomy console time was recorded. The median age and body mass index of the patients was 47.5 (38-52) years and 22.00 (19.30-29.52) kg/m, respectively, and the median console time was 32 (21-48) min. Among the 8,834 images, 428 were selected and divided into training, validation, and testing datasets at a ratio of 7:1:2. Two experts determined that the DSC of our model was 0.828[Formula: see text]5.28 and 0.818[Formula: see text]6.96, while the HDs were 9.80[Formula: see text]2.57 and 10.32[Formula: see text]1.09.

Conclusion: DL can serve as a surgical guide for beginners and trainees, and can be used as a training tool to enhance surgeons' surgical skills.

References

Giger M . Machine Learning in Medical Imaging. J Am Coll Radiol. 2018; 15(3 Pt B):512-520. DOI: 10.1016/j.jacr.2017.12.028. View

Zou K, Warfield S, Bharatha A, Tempany C, Kaus M, Haker S . Statistical validation of image segmentation quality based on a spatial overlap index. Acad Radiol. 2004; 11(2):178-89. PMC: 1415224. DOI: 10.1016/s1076-6332(03)00671-8. View

Anteby R, Horesh N, Soffer S, Zager Y, Barash Y, Amiel I . Deep learning visual analysis in laparoscopic surgery: a systematic review and diagnostic test accuracy meta-analysis. Surg Endosc. 2021; 35(4):1521-1533. DOI: 10.1007/s00464-020-08168-1. View

Unger J, Hebisch C, Phipps J, Lagarto J, Kim H, Darrow M . Real-time diagnosis and visualization of tumor margins in excised breast specimens using fluorescence lifetime imaging and machine learning. Biomed Opt Express. 2020; 11(3):1216-1230. PMC: 7075618. DOI: 10.1364/BOE.381358. View

Lee J, Jun S, Cho Y, Lee H, Kim G, Seo J . Deep Learning in Medical Imaging: General Overview. Korean J Radiol. 2017; 18(4):570-584. PMC: 5447633. DOI: 10.3348/kjr.2017.18.4.570. View

Frey J, Salibian A, Choi M, Karp N . Mastectomy Flap Thickness and Complications in Nipple-Sparing Mastectomy: Objective Evaluation using Magnetic Resonance Imaging. Plast Reconstr Surg Glob Open. 2017; 5(8):e1439. PMC: 5585433. DOI: 10.1097/GOX.0000000000001439. View

Toesca A, Peradze N, Galimberti V, Manconi A, Intra M, Gentilini O . Robotic Nipple-sparing Mastectomy and Immediate Breast Reconstruction With Implant: First Report of Surgical Technique. Ann Surg. 2017; 266(2):e28-e30. DOI: 10.1097/SLA.0000000000001397. View

De La Cruz-Ku G, Chambergo-Michilot D, Perez A, Valcarcel B, Pamen L, Linshaw D . Outcomes of robotic nipple-sparing mastectomy versus conventional nipple-sparing mastectomy in women with breast cancer: a systematic review and meta-analysis. J Robot Surg. 2023; 17(4):1493-1509. DOI: 10.1007/s11701-023-01547-5. View

Wu W, Liu H, Li L, Long Y, Wang X, Wang Z . Application of local fully Convolutional Neural Network combined with YOLO v5 algorithm in small target detection of remote sensing image. PLoS One. 2021; 16(10):e0259283. PMC: 8555847. DOI: 10.1371/journal.pone.0259283. View

10.

Aggarwal R, Sounderajah V, Martin G, Ting D, Karthikesalingam A, King D . Diagnostic accuracy of deep learning in medical imaging: a systematic review and meta-analysis. NPJ Digit Med. 2021; 4(1):65. PMC: 8027892. DOI: 10.1038/s41746-021-00438-z. View

11.

Park H, Lee J, Lai H, Park J, Ryu J, Lee J . Surgical and Oncologic Outcomes of Robotic and Conventional Nipple-Sparing Mastectomy with Immediate Reconstruction: International Multicenter Pooled Data Analysis. Ann Surg Oncol. 2022; 29(11):6646-6657. DOI: 10.1245/s10434-022-11865-x. View

12.

Xia H, Yang B, Li Y, Wang B . An Improved CenterNet Model for Insulator Defect Detection Using Aerial Imagery. Sensors (Basel). 2022; 22(8). PMC: 9031845. DOI: 10.3390/s22082850. View

13.

Ryu J, Lee J, Lee J, Ko B, Kim J, Shin H . Mastectomy with Reconstruction Including Robotic Endoscopic Surgery (MARRES): a prospective cohort study of the Korea Robot-Endoscopy Minimal Access Breast Surgery Study Group (KoREa-BSG) and Korean Breast Cancer Study Group (KBCSG). BMC Cancer. 2023; 23(1):571. PMC: 10283322. DOI: 10.1186/s12885-023-10978-0. View

14.

Nessa A, Shaikh S, Fuller M, Masannat Y, Kastora S . Postoperative complications and surgical outcomes of robotic versus conventional nipple-sparing mastectomy in breast cancer: meta-analysis. Br J Surg. 2023; 111(1). PMC: 10769157. DOI: 10.1093/bjs/znad336. View

15.

Robertson S, Rusby J, Cutress R . Determinants of optimal mastectomy skin flap thickness. Br J Surg. 2014; 101(8):899-911. DOI: 10.1002/bjs.9470. View

16.

Matsen C, Mehrara B, Eaton A, Capko D, Berg A, Stempel M . Skin Flap Necrosis After Mastectomy With Reconstruction: A Prospective Study. Ann Surg Oncol. 2015; 23(1):257-64. PMC: 4697877. DOI: 10.1245/s10434-015-4709-7. View

17.

Shen D, Wu G, Suk H . Deep Learning in Medical Image Analysis. Annu Rev Biomed Eng. 2017; 19:221-248. PMC: 5479722. DOI: 10.1146/annurev-bioeng-071516-044442. View

18.

Lee J, Park H, Lee D, Song S, Yu J, Ryu J . From cadaveric and animal studies to the clinical reality of robotic mastectomy: a feasibility report of training program. Sci Rep. 2021; 11(1):21032. PMC: 8548531. DOI: 10.1038/s41598-021-00278-7. View

19.

Lee D, Yu H, Kwon H, Kong H, Lee K, Kim H . Evaluation of Surgical Skills during Robotic Surgery by Deep Learning-Based Multiple Surgical Instrument Tracking in Training and Actual Operations. J Clin Med. 2020; 9(6). PMC: 7355689. DOI: 10.3390/jcm9061964. View