Artificial Intelligence for context-aware surgical guidance in complex robot-assisted oncological procedures: An exploratory feasibility study

Abstract

Background: Complex oncological procedures pose various surgical challenges including dissection in distinct tissue planes and preservation of vulnerable anatomical structures throughout different surgical phases. In rectal surgery, a violation of dissection planes increases the risk of local recurrence and autonomous nerve damage resulting in incontinence and sexual dysfunction. While deep learning-based identification of target structures has been described in basic laparoscopic procedures, feasibility of artificial intelligence-based guidance has not yet been investigated in complex abdominal surgery. Methods: A dataset of 57 robot-assisted rectal resection (RARR) videos was split into a pre-training dataset of 24 temporally non-annotated videos and a training dataset of 33 temporally annotated videos. Based on phase annotations and pixel-wise annotations of randomly selected image frames, convolutional neural networks were trained to distinguish surgical phases and phase-specifically segment anatomical structures and tissue planes. To evaluate model performance, F1 score, Intersection-over-Union (IoU), precision, recall, and specificity were determined. Results: We demonstrate that both temporal (average F1 score for surgical phase recognition: 0.78) and spatial features of complex surgeries can be identified using machine learning-based image analysis. Based on analysis of a total of 8797 images with pixel-wise target structure segmentations, mean IoUs for segmentation of anatomical target structures range from 0.09 to 0.82 and from 0.05 to 0.32 for dissection planes and dissection lines throughout different phases of RARR in our analysis. Conclusions: Image-based recognition is a promising technique for surgical guidance in complex surgical procedures. Future research should investigate clinical applicability, usability, and therapeutic impact of a respective guidance system.

The Dresden Surgical Anatomy Dataset for Abdominal Organ Segmentation in Surgical Data Science

“…On the one hand, it can be used as a source of further image material in combination with other, already existing datasets. On the other hand, it can be used to create organ detection algorithms working either with weak labels or with semantic segmentation masks, for example as a basis for further development of assistance applications 17 . Proposed training-validation-test splits as well as results of detailed segmentation studies are reported in a separate publication 18 .…”

Artificial Intelligence in Colorectal Cancer Surgery: Present and Future Perspectives

“…Given that incomplete TME is directly associated with local tumor recurrence and reduced overall survival, TME represents a crucial step in rectal cancer treatment [ 51 , 52 , 53 ]. In a recent study [ 54 ], supervised machine learning models were used to identify various anatomical structures throughout different phases of robot-assisted rectal resection and to recognize resection planes during TME ( Figure 2 ). In this monocentric study, detections were most reliable for larger anatomical structures such as Gerota’s fascia or the mesocolon with mean F1 scores of 0.78 and 0.71, respectively, the mean F1 score for detection of the dissection plane (“angel’s hair”) during TME was 0.32, while the exact dissection line could be predicted in few images (mean F1 score: 0.05).…”

Machines with vision for intraoperative guidance during gastrointestinal cancer surgery

“…The same principle can be applied to oncologic resections. For example, models implemented by two independent groups have attempted to use DL, CNN, and segmentation to identify the total mesorectal excision (TME) plane of dissection during rectal cancer resections (23,24). This is particularly important given the difficulty of staying in the correct plane of dissection during rectal surgery.…”