scholarly journals Transfer Learning in Polyp and Endoscopic Tool Segmentation from Colonoscopy Images

2021 ◽  
Vol 1 (1) ◽  
pp. 32-34
Author(s):  
Nefeli Panagiota Tzavara ◽  
Bjørn-Jostein Singstad
Keyword(s):  
Detection Rate ◽  
Significant Error ◽  
Data Sets ◽  
Robotic Assisted ◽  
Robotic Assisted Surgery ◽  
Test Instrument ◽  
The World ◽  
Test Sets ◽  
Image Segmentation Algorithm ◽  
Segmentation Models

Colorectal cancer is one of the deadliest and most widespread types of cancer in the world. Colonoscopy is the procedure used to detect and diagnose polyps from the colon, but today's detection rate shows a significant error rate that affects diagnosis and treatment. An automatic image segmentation algorithm may help doctors to improve the detection rate of pathological polyps in the colon. Furthermore, segmenting endoscopic tools in images taken during colonoscopy may contribute towards robotic assisted surgery. In this study, we trained and validated both pre-trained and not pre-trained segmentation models on two different data sets, containing images of polyps and endoscopic tools. Finally, we applied the models on two separate test sets and the best polyp model got a dice score 0.857 and the test instrument model got a dice score 0.948. Moreover, we found that pre-training of the models increased the performance in segmenting polyps and endoscopic tools.

scholarly journals Detailed cost of robotic-assisted surgery in the Australian public health sector: from implementation to a multi-specialty caseload

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Kate McBride ◽  
Daniel Steffens ◽  
Christina Stanislaus ◽  
Michael Solomon ◽  
Teresa Anderson ◽  
...  
Keyword(s):  
Public Sector ◽  
Health Sector ◽  
Public Hospitals ◽  
Fixed Costs ◽  
Tertiary Referral Hospital ◽  
Robotic Assisted ◽  
The Public ◽  
Robotic Assisted Surgery ◽  
Specific Implementation ◽  
Theatre Utilisation

Abstract Background A barrier to the uptake of robotic-assisted surgery (RAS) continues to be the perceived high costs. A lack of detailed costing information has made it difficult for public hospitals in particular to determine whether use of the technology is justified. This study aims to provide a detailed description of the patient episode costs and the contribution of RAS specific costs for multiple specialties in the public sector. Methods A retrospective descriptive costing review of all RAS cases undertaken at a large public tertiary referral hospital in Sydney, Australia from August 2016 to December 2018 was completed. This included RAS cases within benign gynaecology, cardiothoracic, colorectal and urology, with the total costs described utilizing various inpatient costing data, and RAS specific implementation, maintenance and consumable costs. Results Of 211 RAS patients, substantial variation was found between specialties with the overall median cost per patient being $19,269 (Interquartile range (IQR): $15,445 to $32,199). The RAS specific costs were $8828 (46%) made up of fixed costs including $4691 (24%) implementation and $2290 (12%) maintenance, both of which are volume dependent; and $1848 (10%) RAS consumable costs. This was in the context of 37% robotic theatre utilisation. Conclusions There is considerable variation across surgical specialties for the cost of RAS. It is important to highlight the different cost components and drivers associated with a RAS program including its dependence on volume and how it fits within funding systems in the public sector.

scholarly journals Robotic natural orifice specimen extraction surgery versus traditional robotic-assisted surgery (NOTR) for patients with colorectal cancer: a study protocol for a randomized controlled trial

Trials ◽  
2021 ◽  
Vol 22 (1) ◽  
Author(s):  
Rui Luo ◽  
Fangfang Zheng ◽  
Haobo Zhang ◽  
Weiquan Zhu ◽  
Penghui He ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Randomized Controlled Trial ◽  
Controlled Trial ◽  
Natural Orifice ◽  
Specimen Extraction ◽  
Natural Orifice Specimen Extraction ◽  
Robotic Assisted ◽  
Randomized Controlled ◽  
Robotic Assisted Surgery ◽  
Secondary Outcomes

Abstract Background Natural orifice specimen extraction surgery for colorectal cancer has been introduced in order to reduce the abdominal incision, demonstrating major development potential in minimally invasive surgery. We are conducting this randomized controlled trial to assess whether robotic NOSES is non-inferior to traditional robotic-assisted surgery for patients with colorectal cancer in terms of primary and secondary outcomes. Method/design Accordingly, a prospective, open-label, randomized controlled, parallel-group, multicenter, and non-inferiority trial will be conducted to discuss the safety and efficacy of robotic natural orifice extraction surgery compared to traditional robotic-assisted surgery. Here, 550 estimated participants will be enrolled to have 80% power to detect differences with a one-sided significance level of 0.025 in consideration of the non-inferiority margin of 10%. The primary outcome is the incidence of surgical complications, which will be classified using the Clavien-Dindo system. Discussion This trial is expected to reveal whether robotic NOSES is non-inferior to traditional robotic-assisted surgery, which is of great significance in regard to the development of robotic NOSES for patients with colorectal cancer in the minimally invasive era. Furthermore, robotic NOSES is expected to exhibit superiority to traditional robotic-assisted surgery in terms of both primary and secondary outcomes. Trial registration ClinicalTrials.govNCT04230772. Registered on January 15, 2020.

scholarly journals Room Size Influences Flow in Robotic-Assisted Surgery

2021 ◽  
Vol 18 (15) ◽  
pp. 7984
Author(s):  
Falisha Kanji ◽  
Tara Cohen ◽  
Myrtede Alfred ◽  
Ashley Caron ◽  
Samuel Lawton ◽  
...  
Keyword(s):  
New Technology ◽  
Surgical Robots ◽  
Physical Size ◽  
Robotic Assisted ◽  
Surgical Technology ◽  
Room Size ◽  
Robotic Assisted Surgery ◽  
Academic Hospitals ◽  
Environmental Causes ◽  
The Impact

The introduction of surgical technology into existing operating rooms (ORs) can place novel demands on staff and infrastructure. Despite the substantial physical size of the devices in robotic-assisted surgery (RAS), the workspace implications are rarely considered. This study aimed to explore the impact of OR size on the environmental causes of surgical flow disruptions (FDs) occurring during RAS. Fifty-six RAS procedures were observed at two academic hospitals between July 2019 and January 2021 across general, urologic, and gynecologic surgical specialties. A multiple regression analysis demonstrated significant effects of room size in the pre-docking phase (t = 2.170, df = 54, β = 0.017, p = 0.035) where the rate of FDs increased as room size increased, and docking phase (t = −2.488, df = 54, β = −0.017, p = 0.016) where the rate of FDs increased as room size decreased. Significant effects of site (pre-docking phase: p = 0.000 and docking phase: p = 0.000) were also demonstrated. Findings from this study demonstrate hitherto unrecognized spatial challenges involved with introducing surgical robots into the operating domain. While new technology may provide benefits towards patient safety, it is important to consider the needs of the technology prior to integration.

Robotic‐assisted surgery for rectal cancer with situs inversus totalis: A case report

2021 ◽  
Author(s):  
Shunsuke Kasai ◽  
Hitoshi Hino ◽  
Akio Shiomi ◽  
Hiroyasu Kagawa ◽  
Shoichi Manabe ◽  
...  
Keyword(s):  
Rectal Cancer ◽  
Case Report ◽  
Situs Inversus ◽  
Situs Inversus Totalis ◽  
Robotic Assisted ◽  
Robotic Assisted Surgery

Belief Movement, Uncertainty Reduction, and Rational Updating*

2021 ◽  
Author(s):  
Ned Augenblick ◽  
Matthew Rabin
Keyword(s):  
Statistical Tests ◽  
Uncertainty Reduction ◽  
The State ◽  
Data Sets ◽  
New Information ◽  
The World ◽  
Core Concepts ◽  
Market Beliefs ◽  
Over Time

Abstract When a Bayesian learns new information and changes her beliefs, she must on average become concomitantly more certain about the state of the world. Consequently, it is rare for a Bayesian to frequently shift beliefs substantially while remaining relatively uncertain, or, conversely, become very confident with relatively little belief movement. We formalize this intuition by developing specific measures of movement and uncertainty reduction given a Bayesian’s changing beliefs over time, showing that these measures are equal in expectation and creating consequent statistical tests for Bayesianess. We then show connections between these two core concepts and four common psychological biases, suggesting that the test might be particularly good at detecting these biases. We provide support for this conclusion by simulating the performance of our test and other martingale tests. Finally, we apply our test to data sets of individual, algorithmic, and market beliefs.

Sign in / Sign up

Export Citation Format

Share Document