Three-dimensional automatic artificial intelligence driven augmented-reality selective biopsy during nerve-sparing robot-assisted radical prostatectomy: A feasibility and accuracy study

Checcucci, Enrico; Piana, Alberto; Volpi, G.; Piazzolla, Pietro; Cillis, Sabrina De; Piramide, Federico; Gatti, Cecilia; Stura, Ilaria; Bollito, Enrico; Massa, Federica; Dio, M. Di; Fiori, Cristian; Porpiglia, Francesco

doi:10.1016/j.ajur.2023.08.001

Cited by 10 publications

(6 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The use of this technology is currently pushing informatics over its limits, and the employment of AI could potentially revolutionize healthcare and consequently urological care [ 24 , 25 , 26 ]. We then decided to explore AI algorithms for organs and for 3DVM automatic recognitions [ 27 , 28 ]. Currently, a fully automatic superimposition is still not possible, but initial experiences showed promising results.…”

Section: Discussionmentioning

confidence: 99%

Automatic 3D Augmented-Reality Robot-Assisted Partial Nephrectomy Using Machine Learning: Our Pioneer Experience

Piana,

Amparore,

Sica

et al. 2024

Cancers

Self Cite

View full text Add to dashboard Cite

The aim of “Precision Surgery” is to reduce the impact of surgeries on patients’ global health. In this context, over the last years, the use of three-dimensional virtual models (3DVMs) of organs has allowed for intraoperative guidance, showing hidden anatomical targets, thus limiting healthy-tissue dissections and subsequent damage during an operation. In order to provide an automatic 3DVM overlapping in the surgical field, we developed and tested a new software, called “ikidney”, based on convolutional neural networks (CNNs). From January 2022 to April 2023, patients affected by organ-confined renal masses amenable to RAPN were enrolled. A bioengineer, a software developer, and a surgeon collaborated to create hyper-accurate 3D models for automatic 3D AR-guided RAPN, using CNNs. For each patient, demographic and clinical data were collected. A total of 13 patients were included in the present study. The average anchoring time was 11 (6–13) s. Unintended 3D-model automatic co-registration temporary failures happened in a static setting in one patient, while this happened in one patient in a dynamic setting. There was one failure; in this single case, an ultrasound drop-in probe was used to detect the neoplasm, and the surgery was performed under ultrasound guidance instead of AR guidance. No major intraoperative nor postoperative complications (i.e., Clavien Dindo > 2) were recorded. The employment of AI has unveiled several new scenarios in clinical practice, thanks to its ability to perform specific tasks autonomously. We employed CNNs for an automatic 3DVM overlapping during RAPN, thus improving the accuracy of the superimposition process.

show abstract

Section: Discussionmentioning

confidence: 99%

Automatic 3D Augmented-Reality Robot-Assisted Partial Nephrectomy Using Machine Learning: Our Pioneer Experience

Piana,

Amparore,

Sica

et al. 2024

Cancers

Self Cite

View full text Add to dashboard Cite

show abstract

“…And there are a number of different intraoperative techniques to reduce the risk of PSM. For example, confocal microscopy, frozen section, and augmented reality [ 50 – 53 ]. Compared to definite pathology, it was reported that confocal laser microscopy (CLM) had a calculated sensitivity, specificity, positive predictive value, and negative predictive value of 86%, 96%, 80%, and 98% respectively for the detection of PSMs [ 54 ].…”

Section: Discussionmentioning

confidence: 99%

The impact of positive surgical margin parameters and pathological stage on biochemical recurrence after radical prostatectomy: A systematic review and meta-analysis

Guo,

Zhang,

Shao

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

Background To systematically review and perform a meta-analysis on the predictive value of the primary Gleason grade (PGG) at the positive surgical margin (PSM), length of PSM, number of PSMs, and pathological stage of the primary tumor on biochemical recurrence (BCR) in patients with prostate cancer (PCa) after radical prostatectomy (RP). Methods A systematic literature search was performed using electronic databases, including PubMed, EMBASE, Cochrane Library, and Web of Science, from January 1, 2005, to October 1, 2023. The protocol was pre-registered in PROSPERO. Subgroup analyses were performed according to the different treatments and study outcomes. Pooled hazard ratios with 95% confidence intervals were extracted from multivariate analyses, and a fixed or random effect model was used to pool the estimates. Subgroup analyses were performed to explore the reasons for the heterogeneity. Results Thirty-one studies that included 50,028 patients with PCa were eligible for this meta-analysis. The results showed that, compared to PGG3, PGG4/5 was associated with a significantly increased risk of BCR. Compared with PSM ≤3 mm, PSM ≥3 mm was associated with a significantly increased risk of BCR. Compared with unifocal PSM, multifocal PSM (mF-PSM) was associated with a significantly increased risk of BCR. In addition, pT >2 was associated with a significantly increased risk of BCR compared to pT2. Notably, the findings were found to be reliable based on the sensitivity and subgroup analyses. Conclusions PGG at the PSM, length of PSM, number of PSMs, and pathological stage of the primary tumor in patients with PCa were found to be associated with a significantly increased risk of BCR. Thus, patients with these factors should be treated differently in terms of receiving adjunct treatment and more frequent monitoring. Large-scale, well-designed prospective studies with longer follow-up periods are needed to validate the efficacy of these risk factors and their effects on patient responses to adjuvant and salvage therapies and other oncological outcomes.

show abstract

“…Furthermore, depth estimation using camera motion and 3D structural environment mapping have been successfully integrated with AI algorithms. Finally, AI technology was integrated with 3D augmented reality (AR) image-guided surgery, allowing for automatic overlapping of the images in a specific phase of the intervention and guiding selective biopsies intraoperatively [24]. In the future, automatic overlapping during the entire procedure can be achieved.…”

Section: Discussionmentioning

confidence: 99%

Development of Bleeding Artificial Intelligence Detector (BLAIR) System for Robotic Radical Prostatectomy

Checcucci,

Piazzolla,

Marullo

et al. 2023

JCM

Self Cite

View full text Add to dashboard Cite

Background: Addressing intraoperative bleeding remains a significant challenge in the field of robotic surgery. This research endeavors to pioneer a groundbreaking solution utilizing convolutional neural networks (CNNs). The objective is to establish a system capable of forecasting instances of intraoperative bleeding during robot-assisted radical prostatectomy (RARP) and promptly notify the surgeon about bleeding risks. Methods: To achieve this, a multi-task learning (MTL) CNN was introduced, leveraging a modified version of the U-Net architecture. The aim was to categorize video input as either “absence of blood accumulation” (0) or “presence of blood accumulation” (1). To facilitate seamless interaction with the neural networks, the Bleeding Artificial Intelligence-based Detector (BLAIR) software was created using the Python Keras API and built upon the PyQT framework. A subsequent clinical assessment of BLAIR’s efficacy was performed, comparing its bleeding identification performance against that of a urologist. Various perioperative variables were also gathered. For optimal MTL-CNN training parameterization, a multi-task loss function was adopted to enhance the accuracy of event detection by taking advantage of surgical tools’ semantic segmentation. Additionally, the Multiple Correspondence Analysis (MCA) approach was employed to assess software performance. Results: The MTL-CNN demonstrated a remarkable event recognition accuracy of 90.63%. When evaluating BLAIR’s predictive ability and its capacity to pre-warn surgeons of potential bleeding incidents, the density plot highlighted a striking similarity between BLAIR and human assessments. In fact, BLAIR exhibited a faster response. Notably, the MCA analysis revealed no discernible distinction between the software and human performance in accurately identifying instances of bleeding. Conclusion: The BLAIR software proved its competence by achieving over 90% accuracy in predicting bleeding events during RARP. This accomplishment underscores the potential of AI to assist surgeons during interventions. This study exemplifies the positive impact AI applications can have on surgical procedures.

show abstract

Three-dimensional automatic artificial intelligence driven augmented-reality selective biopsy during nerve-sparing robot-assisted radical prostatectomy: A feasibility and accuracy study

Cited by 10 publications

References 32 publications

Automatic 3D Augmented-Reality Robot-Assisted Partial Nephrectomy Using Machine Learning: Our Pioneer Experience

Automatic 3D Augmented-Reality Robot-Assisted Partial Nephrectomy Using Machine Learning: Our Pioneer Experience

The impact of positive surgical margin parameters and pathological stage on biochemical recurrence after radical prostatectomy: A systematic review and meta-analysis

Development of Bleeding Artificial Intelligence Detector (BLAIR) System for Robotic Radical Prostatectomy

Contact Info

Product

Resources

About