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/m2, 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<InlineEquation ID="IEq1"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="13058_2025_1981_Article_IEq1.gif" Format="GIF" Height="13" Rendition="HTML" Resolution="72" Type="Linedraw" Width="18" /> </InlineMediaObject> <EquationSource Format="TEX">\(\:\:\pm\:\:\)</EquationSource> </InlineEquation>5.28 and 0.818<InlineEquation ID="IEq2"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="13058_2025_1981_Article_IEq2.gif" Format="GIF" Height="13" Rendition="HTML" Resolution="72" Type="Linedraw" Width="18" /> </InlineMediaObject> <EquationSource Format="TEX">\(\:\:\pm\:\:\)</EquationSource> </InlineEquation>6.96, while the HDs were 9.80<InlineEquation ID="IEq3"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="13058_2025_1981_Article_IEq3.gif" Format="GIF" Height="13" Rendition="HTML" Resolution="72" Type="Linedraw" Width="18" /> </InlineMediaObject> <EquationSource Format="TEX">\(\:\:\pm\:\:\)</EquationSource> </InlineEquation>2.57 and 10.32<InlineEquation ID="IEq4"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="13058_2025_1981_Article_IEq4.gif" Format="GIF" Height="13" Rendition="HTML" Resolution="72" Type="Linedraw" Width="18" /> </InlineMediaObject> <EquationSource Format="TEX">\(\:\:\pm\:\:\)</EquationSource> </InlineEquation>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.

Development of a deep learning-based model for guiding a dissection during robotic breast surgery

期刊论文
出版模式：

开放获取
发表日期：

2025年3月10日

查看全文

Jeea Lee,
Sungwon Ham,
Namkug Kim,
Hyung Seok Park

摘要

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/m², 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 \(\:\:\pm\:\:\) 5.28 and 0.818 \(\:\:\pm\:\:\) 6.96, while the HDs were 9.80 \(\:\:\pm\:\:\) 2.57 and 10.32 \(\:\:\pm\:\:\) 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.