International Journal of Medical Robotics and Computer Assisted Surgery最新文献

{"title":"Force/position tracking control of fracture reduction robot based on nonlinear disturbance observer and neural network","authors":"Jintao Lei,&nbsp;Zhuangzhuang Wang","doi":"10.1002/rcs.2639","DOIUrl":"10.1002/rcs.2639","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>For the fracture reduction robot, the position tracking accuracy and compliance are affected by dynamic loads from muscle stretching, uncertainties in robot dynamics models, and various internal and external disturbances.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>A control method that integrates a Radial Basis Function Neural Network (RBFNN) with Nonlinear Disturbance Observer is proposed to enhance position tracking accuracy. Additionally, an admittance control is employed for force tracking to enhance the robot's compliance, thereby improving the safety.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>Experiments are conducted on a long bone fracture model with simulated muscle forces and the results demonstrate that the position tracking error is less than ±0.2 mm, the angular displacement error is less than ±0.3°, and the maximum force tracking error is 26.28 N. This result can meet surgery requirements.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusions</h3>\u0000 \u0000 <p>The control method shows promising outcomes in enhancing the safety and accuracy of long bone fracture reduction with robotic assistance.</p>\u0000 </section>\u0000 </div>","PeriodicalId":50311,"journal":{"name":"International Journal of Medical Robotics and Computer Assisted Surgery","volume":"20 3","pages":""},"PeriodicalIF":2.5,"publicationDate":"2024-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141285546","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Radical prostatectomy using the Hinotori robot-assisted surgical system: Docking-free design may contribute to reduction in postoperative pain","authors":"Yutaro Sasaki,&nbsp;Yoshito Kusuhara,&nbsp;Takuro Oyama,&nbsp;Mitsuki Nishiyama,&nbsp;Saki Kobayashi,&nbsp;Kei Daizumoto,&nbsp;Ryotaro Tomida,&nbsp;Yoshiteru Ueno,&nbsp;Tomoya Fukawa,&nbsp;Kunihisa Yamaguchi,&nbsp;Yasuyo Yamamoto,&nbsp;Masayuki Takahashi,&nbsp;Hiroomi Kanayama,&nbsp;Junya Furukawa","doi":"10.1002/rcs.2648","DOIUrl":"10.1002/rcs.2648","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>The docking-free design of the Japanese Hinotori surgical robotic system allows the robotic arm to avoid trocar grasping, thereby minimising excessive abdominal wall stress. The aim of this study was to evaluate the safety and efficacy of robotic-assisted radical prostatectomy (RARP) using the Hinotori system and to explore the potential contribution of its docking-free design to postoperative pain reduction.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>This study reviewed the clinical records of 94 patients who underwent RARP: 48 patients in the Hinotori group and 46 in the da Vinci Xi group.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>Hinotori group had significantly longer operative and console times (<i>p</i> = 0.030 and <i>p</i> = 0.029, respectively). Perioperative complications and oncologic outcomes did not differ between the two groups. On postoperative day 4, the rate of decline from the maximum visual analogue scale score was marginally significant in the Hinotori group (<i>p</i> = 0.062).</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusions</h3>\u0000 \u0000 <p>The docking-free design may contribute to reducing postoperative pain.</p>\u0000 </section>\u0000 </div>","PeriodicalId":50311,"journal":{"name":"International Journal of Medical Robotics and Computer Assisted Surgery","volume":"20 3","pages":""},"PeriodicalIF":2.5,"publicationDate":"2024-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141187144","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A haptic guidance system for simulated catheter navigation with different kinaesthetic feedback profiles","authors":"Taha Abbasi-Hashemi,&nbsp;Farrokh Janabi-Sharifi,&nbsp;Asim N. Cheema,&nbsp;Kourosh Zareinia","doi":"10.1002/rcs.2638","DOIUrl":"10.1002/rcs.2638","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>This paper proposes a haptic guidance system to improve catheter navigation within a simulated environment.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>Three force profiles were constructed to evaluate the system: collision prevention; centreline navigation; and a novel force profile of reinforcement learning (RL). All force profiles were evaluated from the left common iliac to the right atrium.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>Our findings show that providing haptic feedback improved surgical safety compared to visual-only feedback. If staying inside the vasculature is the priority, RL provides the safest option. It is also shown that the performance of each force profile varies in different anatomical regions.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusion</h3>\u0000 \u0000 <p>The implications of these findings are significant, as they hold the potential to improve how and when haptic feedback is applied for cardiovascular intervention.</p>\u0000 </section>\u0000 </div>","PeriodicalId":50311,"journal":{"name":"International Journal of Medical Robotics and Computer Assisted Surgery","volume":"20 3","pages":""},"PeriodicalIF":2.5,"publicationDate":"2024-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141184716","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A back propagation neural network based respiratory motion modelling method","authors":"Shan Jiang,&nbsp;Bowen Li,&nbsp;Zhiyong Yang,&nbsp;Yuhua Li,&nbsp;Zeyang Zhou","doi":"10.1002/rcs.2647","DOIUrl":"10.1002/rcs.2647","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>This study presents the development of a backpropagation neural network-based respiratory motion modelling method (BP-RMM) for precisely tracking arbitrary points within lung tissue throughout free respiration, encompassing deep inspiration and expiration phases.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>Internal and external respiratory data from four-dimensional computed tomography (4DCT) are processed using various artificial intelligence algorithms. Data augmentation through polynomial interpolation is employed to enhance dataset robustness. A BP neural network is then constructed to comprehensively track lung tissue movement.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>The BP-RMM demonstrates promising accuracy. In cases from the public 4DCT dataset, the average target registration error (TRE) between authentic deep respiration phases and those forecasted by BP-RMM for 75 marked points is 1.819 mm. Notably, TRE for normal respiration phases is significantly lower, with a minimum error of 0.511 mm.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusions</h3>\u0000 \u0000 <p>The proposed method is validated for its high accuracy and robustness, establishing it as a promising tool for surgical navigation within the lung.</p>\u0000 </section>\u0000 </div>","PeriodicalId":50311,"journal":{"name":"International Journal of Medical Robotics and Computer Assisted Surgery","volume":"20 3","pages":""},"PeriodicalIF":2.5,"publicationDate":"2024-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141158124","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"ERegPose: An explicit regression based 6D pose estimation for snake-like wrist-type surgical instruments","authors":"Jinhua Li,&nbsp;Zhengyang Ma,&nbsp;Xinan Sun,&nbsp;He Su","doi":"10.1002/rcs.2640","DOIUrl":"10.1002/rcs.2640","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>Accurately estimating the 6D pose of snake-like wrist-type surgical instruments is challenging due to their complex kinematics and flexible design.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>We propose ERegPose, a comprehensive strategy for precise 6D pose estimation. The strategy consists of two components: ERegPoseNet, an original deep neural network model designed for explicit regression of the instrument's 6D pose, and an annotated in-house dataset of simulated surgical operations. To capture rotational features, we employ an Single Shot multibox Detector (SSD)-like detector to generate bounding boxes of the instrument tip.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>ERegPoseNet achieves an error of 1.056 mm in 3D translation, 0.073 rad in 3D rotation, and an average distance (ADD) metric of 3.974 mm, indicating an overall spatial transformation error. The necessity of the SSD-like detector and L1 loss is validated through experiments.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusions</h3>\u0000 \u0000 <p>ERegPose outperforms existing approaches, providing accurate 6D pose estimation for snake-like wrist-type surgical instruments. Its practical applications in various surgical tasks hold great promise.</p>\u0000 </section>\u0000 </div>","PeriodicalId":50311,"journal":{"name":"International Journal of Medical Robotics and Computer Assisted Surgery","volume":"20 3","pages":""},"PeriodicalIF":2.5,"publicationDate":"2024-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141094787","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A new ring fixator system for automated bone fixation","authors":"Ahmet Aydi(ı)n,&nbsp;M. Kerem U(Ü)n","doi":"10.1002/rcs.2637","DOIUrl":"10.1002/rcs.2637","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>In the field of orthopaedics, external fixators are commonly employed for treating extremity fractures and deformities. Computer-assisted systems offer a promising and less error-prone treatment alternative to manual fixation by utilising a software to plan treatments based on radiological and clinical data. Nevertheless, existing computer-assisted systems have limitations and constraints.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>This work represents the culmination of a project aimed at developing a new automatised fixation system and a corresponding software to minimise human intervention and associated errors, and the developed system incorporates enhanced functionalities and has fewer constraints compared to existing systems.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>The automatised fixation system and its graphical user interface (GUI) demonstrate promising results in terms of accuracy, efficiency, and reliability.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusion</h3>\u0000 \u0000 <p>The developed fixation system and its accompanying GUI represent an improvement in computer-assisted fixation systems. Future research may focus on further refining the system and conducting clinical trials.</p>\u0000 </section>\u0000 </div>","PeriodicalId":50311,"journal":{"name":"International Journal of Medical Robotics and Computer Assisted Surgery","volume":"20 3","pages":""},"PeriodicalIF":2.5,"publicationDate":"2024-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/rcs.2637","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141088785","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Transfer learning for anatomical structure segmentation in otorhinolaryngology microsurgery","authors":"Xin Ding,&nbsp;Yu Huang,&nbsp;Yang Zhao,&nbsp;Xu Tian,&nbsp;Guodong Feng,&nbsp;Zhiqiang Gao","doi":"10.1002/rcs.2634","DOIUrl":"10.1002/rcs.2634","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>Reducing the annotation burden is an active and meaningful area of artificial intelligence (AI) research.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>Multiple datasets for the segmentation of two landmarks were constructed based on 41 257 labelled images and 6 different microsurgical scenarios. These datasets were trained using the multi-stage transfer learning (TL) methodology.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>The multi-stage TL enhanced segmentation performance over baseline (mIOU 0.6892 vs. 0.8869). Besides, Convolutional Neural Networks (CNNs) achieved a robust performance (mIOU 0.8917 vs. 0.8603) even when the training dataset size was reduced from 90% (30 078 images) to 10% (3342 images). When directly applying the weight from one certain surgical scenario to recognise the same target in images of other scenarios without training, CNNs still obtained an optimal mIOU of 0.6190 ± 0.0789.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusions</h3>\u0000 \u0000 <p>Model performance can be improved with TL in datasets with reduced size and increased complexity. It is feasible for data-based domain adaptation among different microsurgical fields.</p>\u0000 </section>\u0000 </div>","PeriodicalId":50311,"journal":{"name":"International Journal of Medical Robotics and Computer Assisted Surgery","volume":"20 3","pages":""},"PeriodicalIF":2.5,"publicationDate":"2024-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141066207","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Exploring the feasibility of indocyanine green fluorescence for intraoperative ureteral visualisation in robotic transvaginal natural orifice transluminal endoscopy surgery during endometriosis resection","authors":"Luis E. Delgadillo Chabolla,&nbsp;Linda A. Alpuing Radilla,&nbsp;Tamisa Koythong,&nbsp;Sowmya Sunkara,&nbsp;Yamely Mendez,&nbsp;Qianqing Wang,&nbsp;Xiaoming Guan","doi":"10.1002/rcs.2636","DOIUrl":"https://doi.org/10.1002/rcs.2636","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>To assess the feasibility of use of indocyanine green (ICG) in identifying and minimising urinary tract injury during surgical resection of endometriosis through robotic transvaginal natural orifice transluminal endoscopy surgery (RvNOTES).</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>We conducted a retrospective case series in two academic tertiary care hospitals. We examined 53 patients who underwent RvNOTES hysterectomy with planned endometriosis resection.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>The study involved 53 patients undergoing RvNOTES with ICG fluorescence for endometriosis resection. Mean patient age was 37.98 ± 6.65 years. Operative time averaged 181.32 ± 53.94 min, with estimated blood loss at 45.57 ± 33.62 mL. Postoperative stay averaged 0.23 ± 0.47 days. No ICG-related complications occurred.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusion</h3>\u0000 \u0000 <p>No complications occurred with ICG fluorescence in RvNOTES. It appears to be a safe option for ureteral localisation and preservation. ICG fluorescence is widely used in diverse medical specialities for identifying ureters during complex surgeries. Larger studies are needed to firmly establish its advantages in intraoperative ureteral visualisation during RvNOTES for deep infiltrative endometriosis.</p>\u0000 </section>\u0000 </div>","PeriodicalId":50311,"journal":{"name":"International Journal of Medical Robotics and Computer Assisted Surgery","volume":"20 3","pages":""},"PeriodicalIF":2.5,"publicationDate":"2024-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140952999","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Robot-assisted total knee arthroplasty system provides more precise control of the femoral rotation angle: A retrospective study","authors":"Peng Yan,&nbsp;Xudong Duan,&nbsp;Yutian Lei,&nbsp;Fangze Xing,&nbsp;Ruomu Cao,&nbsp;Sen Luo,&nbsp;Yang Chen,&nbsp;Zeyu Liu,&nbsp;Kunzheng Wang,&nbsp;Pei Yang,&nbsp;Run Tian","doi":"10.1002/rcs.2635","DOIUrl":"10.1002/rcs.2635","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>Rotational alignment in total knee arthroplasty (TKA) is a crucial technical point that needs attention. We conducted a retrospective study to investigate whether a new robot-assisted TKA (RA-TKA) could improve the accuracy of rotational alignment and whether rotational alignment affects postoperative pain and functional evaluation of the knee.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>A total of 136 consecutive patients who underwent TKA were included in this study. Half of the patients underwent RA-TKA and the other half underwent conventional TKA (CON-TKA) by the same group of surgeons. Collect the relevant parameters.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>The postoperative femoral rotation angle (FRA) was −0.72 ± 2.59° in the robot-assisted group and 1.13 ± 2.73° in the conventional group, and were statistically significantly different (<i>p</i> &lt; 0.001).</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusion</h3>\u0000 \u0000 <p>This study provides preliminary evidence that the RA-TKA provides more precise control of FRA than CON-TKA, and verifies that tibial rotation angle and combined rotation angle affect postoperative knee pain and functional evaluation.</p>\u0000 </section>\u0000 </div>","PeriodicalId":50311,"journal":{"name":"International Journal of Medical Robotics and Computer Assisted Surgery","volume":"20 3","pages":""},"PeriodicalIF":2.5,"publicationDate":"2024-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140909695","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automatic pterygopalatine fossa segmentation and localisation based on DenseASPP","authors":"Bing Wang,&nbsp;Weili Shi","doi":"10.1002/rcs.2633","DOIUrl":"https://doi.org/10.1002/rcs.2633","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>Allergic rhinitis constitutes a widespread health concern, with traditional treatments often proving to be painful and ineffective. Acupuncture targeting the pterygopalatine fossa proves effective but is complicated due to the intricate nearby anatomy.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>To enhance the safety and precision in targeting the pterygopalatine fossa, we introduce a deep learning-based model to refine the segmentation of the pterygopalatine fossa. Our model expands the U-Net framework with DenseASPP and integrates an attention mechanism for enhanced precision in the localisation and segmentation of the pterygopalatine fossa.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>The model achieves Dice Similarity Coefficient of 93.89% and 95% Hausdorff Distance of 2.53 mm with significant precision. Remarkably, it only uses 1.98 M parameters.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusions</h3>\u0000 \u0000 <p>Our deep learning approach yields significant advancements in localising and segmenting the pterygopalatine fossa, providing a reliable basis for guiding pterygopalatine fossa-assisted punctures.</p>\u0000 </section>\u0000 </div>","PeriodicalId":50311,"journal":{"name":"International Journal of Medical Robotics and Computer Assisted Surgery","volume":"20 2","pages":""},"PeriodicalIF":2.5,"publicationDate":"2024-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140639573","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}