Illumination matters Part II: advanced comparative analysis of flexible ureteroscopes in a kidney model by PEARLS.

PURPOSE: The aim of the study was to evaluate illumination properties in an in-vitro kidney calyx model in saline. DESIGN AND METHODS: We evaluated a series of contemporary flexible ureteroscopes including the Storz Flex-Xc and Flex-X2s, Olympus V3 and P7, Pusen 7.5F and 9.2F, as well as OTU WiScope using a 3D-printed closed pink kidney calyx model, submerged in saline. A spectrometer was used for illuminance and color temperature measurements at different openings located at center (direct light), 45° (direct and indirect light) and 90°(indirect light) to the axis of the scope. RESULTS: Maximum illuminance was at the center opening for all scopes (range: 284 to 12,058 lx at 50% brightness and 454 to 11,871 lx at 100% brightness settings). The scope with the highest center illuminance (Flex-Xc) was 26 times superior to the scope with the lowest illuminance (Pusen 7.5Fr) at 100% brightness setting. For each scope, there was a peripheral illuminance drop ranging from - 43 to - 92% at 50% brightness and - 43% to - 88% at 100% brightness settings, respectively (all p < 0.01). Highest drop was for the P7 and the Pusen 9.2F. All scopes had illuminance skew, except the V3. All scopes had a warm color temperature. CONCLUSION: Illumination properties vary between ureteroscopes in an enclosed cavity in saline, and differs at center vs 45° and 90° positions within scopes. Peripheral illuminance drop can be as high as - 92%, which is undesirable. This may affect the choice of ureteroscope and light brightness settings used in surgery by urologists.

Improving Patient Understanding of Femoroacetabular Impingement Syndrome With Three-Dimensional Models.

INTRODUCTION: Three-dimensional (3D) printed models may help patients understand complex anatomic pathologies such as femoroacetabular impingement syndrome (FAIS). We aimed to assess patient understanding and satisfaction when using 3D printed models compared with standard imaging modalities for discussion of FAIS diagnosis and surgical plan. METHODS: A consecutive series of 76 new patients with FAIS (37 patients in the 3D model cohort and 39 in the control cohort) from a single surgeon's clinic were educated using imaging and representative 3D printed models of FAI or imaging without models (control). Patients received a voluntary post-visit questionnaire that evaluated their understanding of the diagnosis, surgical plan, and visit satisfaction. RESULTS: Patients in the 3D model cohort reported a significantly higher mean understanding of FAIS (90.0 ± 11.5 versus 79.8 ± 14.9 out of 100; P = 0.001) and surgery (89.5 ± 11.6 versus 81.0 ± 14.5; P = 0.01) compared with the control cohort. Both groups reported high levels of satisfaction with the visit. CONCLUSION: In this study, the use of 3D printed models in clinic visits with patients with FAIS improved patients' perceived understanding of diagnosis and surgical treatment.

Feasibility and impact of three-dimensional (3D) printing technology in simulated teaching of congenital malformations.

AIMS: This study aimed to investigate the feasibility and effectiveness of utilizing three-dimensional (3D) printing technology in the simulation teaching of congenital malformations. METHODS: We conducted a comparative analysis between an experimental group that received traditional teaching supplemented with 3D printing model demonstrations and hands-on model operation, and a control group that received traditional teaching methods. Various parameters, including classroom interest, classroom interaction, learning enthusiasm, disease awareness, teaching satisfaction, and independent operation confidence, were assessed, along with theoretical and practical tests. RESULTS: The results showed no significant difference in theoretical test scores between the two groups (91.92 ± 15.04 vs. 89.44 ± 14.89), but the practical test revealed a significantly higher number of qualified trainees in the experimental group compared to the control group (23 vs. 8). In terms of classroom engagement, both groups exhibited similar levels of interest (8.08 ± 1.52 vs. 8.74 ± 0.984), classroom interaction (7.88 ± 1.97 vs. 8.7 ± 1.33), learning enthusiasm (8.81 ± 1.021 vs. 8.52 ± 1.189), and disease awareness (8.58 ± 0.99 vs. 8.58 ± 0.99). However, the experimental group demonstrated significantly higher teaching satisfaction (8.81 ± 1.06 vs. 9.19 ± 0.96) and greater operation confidence (7.67 ± 2.56 vs. 5.5 ± 2.79) than the control group. CONCLUSION: 3D printing technology can be effectively utilized to create surgical teaching models, enhancing the confidence of standardized training doctors and improving teaching outcomes.

3D bioprinting: a review and potential applications for Mohs micrographic surgery.

Mohs Micrographic Surgery (MMS) is effective for treating common cutaneous malignancies, but complex repairs may often present challenges for reconstruction. This paper explores the potential of three-dimensional (3D) bioprinting in MMS, offering superior outcomes compared to traditional methods. 3D printing technologies show promise in advancing skin regeneration and refining surgical techniques in dermatologic surgery. A PubMed search was conducted using the following keywords: "Three-dimensional bioprinting" OR "3-D printing" AND "Mohs" OR "Mohs surgery" OR "Surgery." Peer-reviewed English articles discussing medical applications of 3D bioprinting were included, while non-peer-reviewed and non-English articles were excluded. Patients using 3D MMS models had lower anxiety scores (3.00 to 1.7, p < 0.0001) and higher knowledge assessment scores (5.59 or 93.25% correct responses), indicating better understanding of their procedure. Surgical residents using 3D models demonstrated improved proficiency in flap reconstructions (p = 0.002) and knowledge assessment (p = 0.001). Additionally, 3D printing offers personalized patient care through tailored surgical guides and anatomical models, reducing intraoperative time while enhancing surgical. Concurrently, efforts in tissue engineering and regenerative medicine are being explored as potential alternatives to address organ donor shortages, eliminating autografting needs. However, challenges like limited training and technological constraints persist. Integrating optical coherence tomography with 3D bioprinting may expedite grafting, but challenges remain in pre-printing grafts for complex cases. Regulatory and ethical considerations are paramount for patient safety, and further research is needed to understand long-term effects and cost-effectiveness. While promising, significant advancements are necessary for full utilization in MMS.

A 3D printed esophageal atresia-tracheoesophageal fistula thorascopy simulator for young surgeons.

We developed a 3D-printed thoracoscopic surgery simulator for esophageal atresia with tracheoesophageal fistula (EA-TEF) and assessed its effectiveness in educating young pediatric surgeons. Prototype production and modifications were repeated five times before producing the 3-D printed final product based on a patient's preoperative chest computed tomography. A 24-item survey was used to rate the simulator, adapted from a previous report, with 16 young surgeons with an average of 6.2 years of experience in pediatric surgery for validation. Reusable parts of the thoracic cage were printed to combine with replaceable parts. Each structure was fabricated using diverse printing materials, and subsequently affixed to a frame. In evaluating the simulator, the scores for each factor were 4.33, 4.33, 4.27, 4.31, 4.63, and 4.75 out of 5, respectively, with the highest ratings in value and relevance. The global rating was 3.38 out of 4, with ten stating that it could be used with slight improvements. The most common comment from participants was that the esophageal anastomosis was close to the actual EA-TEF surgery. The 3D-printed thoracoscopic EA-TEF surgery simulator was developed and reflected the actual surgical environment. It could become an effective method of training young pediatric surgeons.

Integration of 3D-printed middle ear models and middle ear prostheses in otosurgical training.

BACKGROUND: In otosurgical training, cadaveric temporal bones are primarily used to provide a realistic tactile experience. However, using cadaveric temporal bones is challenging due to their limited availability, high cost, and potential for infection. Utilizing current three-dimensional (3D) technologies could overcome the limitations associated with cadaveric bones. This study focused on how a 3D-printed middle ear model can be used in otosurgical training. METHODS: A cadaveric temporal bone was imaged using microcomputed tomography (micro-CT) to generate a 3D model of the middle ear. The final model was printed from transparent photopolymers using a laser-based 3D printer (vat photopolymerization), yielding a 3D-printed phantom of the external ear canal and middle ear. The feasibility of this phantom for otosurgical training was evaluated through an ossiculoplasty simulation involving ten otosurgeons and ten otolaryngology-head and neck surgery (ORL-HNS) residents. The participants were tasked with drilling, scooping, and placing a 3D-printed partial ossicular replacement prosthesis (PORP). Following the simulation, a questionnaire was used to collect the participants' opinions and feedback. RESULTS: A transparent photopolymer was deemed suitable for both the middle ear phantom and PORP. The printing procedure was precise, and the anatomical landmarks were recognizable. Based on the evaluations, the phantom had realistic maneuverability, although the haptic feedback during drilling and scooping received some criticism from ORL-HNS residents. Both otosurgeons and ORL-HNS residents were optimistic about the application of these 3D-printed models as training tools. CONCLUSIONS: The 3D-printed middle ear phantom and PORP used in this study can be used for low-threshold training in the future. The integration of 3D-printed models in conventional otosurgical training holds significant promise.

Longitudinal Evaluation of Congenital Cardiovascular Surgical Performance and Skills Retention Using Silicone-Molded Heart Models.

Objective: Hands-on surgical training (HOST) for congenital heart surgery (CHS), utilizing silicone-molded models created from 3D-printing of patients' imaging data, was shown to improve surgical skills. However, the impact of repetition and frequency of repetition in retaining skills has not been previously investigated. We aimed to longitudinally evaluate the outcome for HOST on two example procedures of different technical difficulties with repeated attempts over a 15-week period. Methods: Five CHS trainees were prospectively recruited. Repair of coarctation of the aorta (CoA) and arterial switch operation (ASO) were selected as example procedures of relatively low and high technical difficulty. Procedural time and technical performance (using procedure-specific assessment tools by the participant, a peer-reviewer, and the proctor) were measured. Results: Coarctation repair performance scores improved after the first repetition but remained unchanged at the follow-up session. Likewise, CoA procedural time showed an early reduction but then remained stable (mean [standard deviation]: 29[14] vs 25[15] vs 23[9] min at 0, 1, and 4 weeks). Conversely, ASO performance scores improved during the first repetitions, but decreased after a longer time delay (>9 weeks). Arterial switch operation procedural time showed modest improvements across simulations but significantly reduced from the first to the last attempt: 119[20] versus 106[28] min at 0 and 15 weeks, P = .049. Conclusions: Complex procedures require multiple HOST repetitions, without excessive time delay to maintain long-term skills improvement. Conversely, a single session may be planned for simple procedures to achieve satisfactory medium-term results. Importantly, a consistent reduction in procedural times was recorded, supporting increased surgical efficiency.

3D printing: a useful tool for safe clinical practice in children with complex vasculature.

BACKGROUND: 3D printing has been used in different medical contexts, although it is underutilised in paediatrics. We present the first use of 3D printing in the management of three paediatric patients with complex renovascular disease. METHODS: Patient-specific 3D models were produced from conventional 2D imaging and manufactured using 3D polyjet printing technology. All three patients had different underlying pathologies, but all underwent multiple endovascular interventions (renal artery balloon angioplasty) prior to 3D printing and subsequent vascular surgery. The models were verified by an expert radiologist and then presented to the multidisciplinary team to aid with surgical planning. RESULTS: Following evaluation of the 3D-printed models, all patients underwent successful uni/bilateral renal auto-transplants and aortic bypass surgery. The 3D models allowed more detailed preoperative discussions and more focused planning of surgical approach, therefore enhancing safer surgical planning. It influenced clinical decision-making and shortened general anaesthetic time. The families and the patients reported that they had a significantly improved understanding of the patient's condition and had more confidence in understanding proposed surgical intervention, thereby contributing to obtaining good-quality informed consent. CONCLUSION: 3D printing has a great potential to improve both surgical safety and decision-making as well as patient understanding in the field of paediatrics and may be considered in wider surgical areas.

An open-source, three-dimensional growth model of the mandible.

The available reference data for the mandible and mandibular growth consists primarily of two-dimensional linear or angular measurements. The aim of this study was to create the first open-source, three-dimensional statistical shape model of the mandible that spans the complete growth period. Computed tomography scans of 678 mandibles from children and young adults between 0 and 22 years old were included in the model. The mandibles were segmented using a semi-automatic or automatic (artificial intelligence-based) segmentation method. Point correspondence among the samples was achieved by rigid registration, followed by non-rigid registration of a symmetrical template onto each sample. The registration process was validated with adequate results. Principal component analysis was used to gain insight in the variation within the dataset and to investigate age-related changes and sexual dimorphism. The presented growth model is accessible globally and free-of-charge for scientists, physicians and forensic investigators for any kind of purpose deemed suitable. The versatility of the model opens up new possibilities in the fields of oral and maxillofacial surgery, forensic sciences or biological anthropology. In clinical settings, the model may aid diagnostic decision-making, treatment planning and treatment evaluation.

Construct validation of a novel synthetic tendon model used for assessing surgeon performance in a simulated core suture tendon repair technique.

BACKGROUND: The strength of tendon repair is dependent on the quality of the core suture. Organic and synthetic materials have been used to simulate tendon repair for training; however, no model has undergone construct validation. OBJECTIVES: To determine the construct validity of a novel synthetic tendon repair model. METHODS: Synthetic silicone tendon models were used to simulate adult Achilles tendon (AT) and digital flexor tendon (FT). Participants were categorised into novice, intermediate, and advanced groups based on prior surgical experience. Participants repaired tendons using the modified Kessler technique. A validated motion analysis system was used to measure the duration, path length, and movement count during the simulated task. A global rating score was also used to assess the performance. RESULTS: All participants in the novice (n = 12), intermediate (n = 8) and advanced (n = 11) groups completed the tasks. The results (mean±standard deviation) were duration (872 ± 335, 492 ± 257 and 357 ± 40 s), path length (9493 ± 3173, 6668 ± 1740 and 4672 ± 1228 cm), movement count (4974 ± 673, 4228 ± 259 and 3962 ± 69) and global rating (39 ± 13, 61 ± 14, 81 ± 5), respectively. The Kruskal-Wallis test was significant for all outcome measures (p < 0.01). Significant differences in duration and movement count were identified post-hoc in the AT model for each experience group (p < 0.05), and between novice and intermediate participants for FT repair (p < 0.04). Global rating was significantly different between all groups and was highly correlated with motion metrics (p < 0.01). CONCLUSION: The results support construct validity of this novel simulated tendon repair model. The global rating scores may allow wide utility of this simulation. This model provides a valid and safe environment for surgical trainees to practice tendon repair with several cost, ethical and logistical benefits over animal tendon use. 248/250.

Unveiling new patterns: A surgical deep learning model for intestinal obstruction management.

BACKGROUND: Swift and accurate decision-making is pivotal in managing intestinal obstructions. This study aims to integrate deep learning and surgical expertise to enhance decision-making in intestinal obstruction cases. METHODS: We developed a deep learning model based on the YOLOv8 framework, trained on a dataset of 700 images categorised into operated and non-operated groups, with surgical outcomes as ground truth. The model's performance was evaluated through standard metrics. RESULTS: At a confidence threshold of 0.5, the model demonstrated sensitivity of 83.33%, specificity of 78.26%, precision of 81.7%, recall of 75.1%, and mAP@0.5 of 0.831. CONCLUSIONS: The model exhibited promising outcomes in distinguishing operative and nonoperative management cases. The fusion of deep learning with surgical expertise enriches decision-making in intestinal obstruction management. The proposed model can assist surgeons in intricate scenarios such as intestinal obstruction management and promotes the synergy between technology and clinical acumen for advancing patient care.

Radiologically derived 3D virtual models for neurosurgical planning.

Three dimensional (3D) virtual models for neurosurgery have demonstrated substantial clinical utility, especially for neuro-oncological cases. Computer-aided design (CAD) modelling of radiological images can provide realistic and high-quality 3D models which neurosurgeons may use pre-operatively for surgical planning. 3D virtual models are useful as they are the basis for other models that build off this design. 3D virtual models are quick to segment but can also be easily added to normal neurosurgical and radiological workflow without disruption. Three anatomically complex neuro-oncology cases that were referred from a single institution by three different neurosurgeons were segmented and 3D virtual models were created for pre-operative surgical planning. A face-to-face interview was performed with the surgeons after the models were delivered to gauge the usefulness of the model in pre-surgical planning. All three neurosurgeons found that the 3D virtual model was useful for presurgical planning. Specifically, the virtual model helped in planning operative positioning, understanding spatial relationship between lesion and surrounding critical anatomy and identifying anatomy that will be encountered intra-operatively in a sequential manner. It provided benefit in Multidisciplinary team (MDT) meetings and patient education for shared decision making.3D virtual models are beneficial for pre-surgical planning and patient education for shared decision making for neurosurgical neuro-oncology cases. We believe this could be further expanded to other surgical specialties. The integration of 3D virtual models into normal workflow as the initial step will provide an easier transition into modalities that build off the virtual models such as printed, virtual, augmented and mixed reality models.

[Surgical Simulation Using a Three-Dimensional Printer].

3D printers have been applied in bone-based surgeries, including craniofacial, plastic, oral, and orthopedic surgeries. The improved capabilities of diagnostic imaging equipment and 3D printers have enabled the development of more precise models, and research on surgical simulations and training in the field of neurosurgery is increasing. This review outlines the use of 3D printers in neurosurgery at our institution in terms of modeling methods and surgical simulations. Modeling with the powder-sticking lamination method using plaster as the material allows drilling, which is a surgical procedure. Therefore, it is useful for simulating skull base tumors, such as petrosectomy in a combined transpetrosal approach or anterior clinoidectomy in an orbitozygomatic approach. The color coding of each part of the model facilitates anatomical understanding, and meshed tumor modeling allows deep translucency. As shown above, the 3D printer's modeling ingenuity allows for useful surgical simulations for each case.

[Preoperative Simulation of Neuroendovascular Therapy Using a Three-Dimensional Printer Model of a Tailor-Made Hollow Cerebral Aneurysm].

Several studies have reported the importance of preoperative simulations. This report describes the methods and utility of neuroendovascular treatment using a three-dimensional(3D)-printed hollow cerebral aneurysm model. This model was created using a stereolithography apparatus-type 3D printer with digital imaging and communications in medicine data from 3D digital subtraction angiograms. The 3D model was used to perform preoperative simulations of microcatheter placement in aneurysms, microguidewire manipulation, and stent deployment. We performed each simulated procedure during surgery. The hollow cerebral aneurysm 3D model can also be used as a training model for surgical trainees. Preoperative simulation using a high-precision hollow cerebral aneurysm model created using 3D printers enables the discussion of specific treatment strategies for each case, including new devices and device sizes, and is expected to develop into "tailor-made medicine" in the future, contributing to safe and reliable treatment implementation.

Development and validation of 3-dimensional simulators for penile prosthesis surgery.

BACKGROUND: The acquisition of skills in penile prosthesis surgery has many limitations mainly due to the absence of simulators and models for training. Three-dimensional (3D) printed models can be utilized for surgical simulations, as they provide an opportunity to practice before entering the operating room and provide better understanding of the surgical approach. AIM: This study aimed to evaluate and validate a 3D model of human male genitalia for penile prosthesis surgery. METHODS: This study included 3 evaluation and validation stages. The first stage involved verification of the 3D prototype model for anatomic landmarks compared with a cadaveric pelvis. The second stage involved validation of the improved model for anatomic accuracy and teaching purposes with the Rochester evaluation score. The third stage comprised validation of the suitability of the 3D prototype model as a surgical simulator and for skill acquisition. The third stage was performed at 3 centers using a modified version of a pre-existing, validated questionnaire and correlated with the Rochester evaluation score. OUTCOME: We sought to determine the suitability of 3D model for training in penile prosthesis surgery in comparison with the available cadaveric model. RESULTS: The evaluation revealed a high Pearson correlation coefficient (0.86) between questions of the Rochester evaluation score and modified validated questionnaire. The 3D model scored 4.33 ± 0.57 (on a Likert scale from 1 to 5) regarding replication of the relevant human anatomy for the penile prosthesis surgery procedure. The 3D model scored 4.33 ± 0.57 (on a Likert scale from 1 to 5) regarding its ability to improve technical skills, teach and practice the procedure, and assess a surgeon's ability. Furthermore, the experts stated that compared with the cadaver, the 3D model presented greater ethical suitability, reduced costs, and easier accessibility. CLINICAL IMPLICATIONS: A validated 3D model is a suitable alternative for penile prosthesis surgery training. STRENGTHS AND LIMITATIONS: This is the first validated 3D hydrogel model for penile prosthesis surgery teaching and training that experts consider suitable for skill acquisition. Because specific validated guidelines and questionnaires for the validation and verifications of 3D simulators for penile surgery are not available, a modified questionnaire was used. CONCLUSION: The current 3D model for penile prosthesis surgery shows promising results regarding anatomic properties and suitability to train surgeons to perform penile implant surgery. The possibility of having an ethical, easy-to-use model with lower costs and limited consequences for the environment is encouraging for further development of the models.

Simulation training of laparoscopic biliary-enteric anastomosis with a three-dimensional-printed model leads to better skill transfer: a randomized controlled trial.

AIM: A new simulation model and training curriculum for laparoscopic bilioenteric anastomosis has been developed. Currently, this concept lacks evidence for the transfer of skills from simulation to clinical settings. This study was conducted to determine whether training with a three-dimensional (3D) bilioenteric anastomosis model result in greater transfer of skills than traditional training methods involving video observation and a general suture model. METHODS: Fifteen general surgeons with no prior experience in laparoscopic biliary-enteric anastomosis were included in this study and randomised into three training groups: video observation only, practice using a general suture model, and practice using a 3D-printed biliary-enteric anastomosis model. Following five training sessions, each surgeon was asked to perform a laparoscopic biliary-enteric anastomosis procedure on an isolated swine organ model. The operative time and performance scores of the procedure were recorded and compared among the three training groups. RESULTS: The operation time in the 3D-printed model group was significantly shorter than the suture and video observation groups ( P =0.040). Furthermore, the performance score of the 3D-printed model group was significantly higher than those of the suture and video observation groups ( P =0.001). Finally, the goal score for laparoscopic biliary-enteric anastomosis in the isolated swine organ model was significantly higher in the 3D model group than in the suture and video observation groups ( P =0.004). CONCLUSIONS: The utilisation of a novel 3D-printed model for simulation training in laparoscopic biliary-enteric anastomosis facilitates improved skill acquisition and transferability to an animal setting compared with traditional training techniques.

WATTS happening? Evaluation of thermal dose during holmium laser lithotripsy in a high-fidelity anatomic model.

PURPOSE: To evaluate the thermal profiles of the holmium laser at different laser parameters at different locations in an in vitro anatomic pelvicalyceal collecting system (PCS) model. Laser lithotripsy is the cornerstone of treatment for urolithiasis. With the prevalence of high-powered lasers, stone ablation efficiency has become more pronounced. Patient safety remains paramount during surgery. It is well recognized that the heat generated from laser lithotripsy has the potential to cause thermal tissue damage. METHODS: Utilizing high-fidelity, 3D printed hydrogel models of a PCS with a synthetic BegoStone implanted in the renal pelvis, laser lithotripsy was performed with the Moses 2.0 holmium laser. At a standard power (40 W) and irrigation pressure (100 cm H2O), we evaluated operator duty cycle (ODC) variations with different time-on intervals at four different laser settings. Temperature was measured at two separate locations-at the stone and away from the stone. RESULTS: Temperatures were highest closest to the laser tip with a decrease away from the laser. Fluid temperatures increased with longer laser-on times and higher ODCs. Thermal doses were greater with increased ODCs and the threshold for thermal injury was reached for ODCs of 75% and 100%. CONCLUSION: Temperature generation and thermal dose delivered are greatest closer to the tip of the laser fiber and are not dependent on power alone. Significant temperature differences were noted between four laser settings at a standardized power (40 W). Temperatures can be influenced by a variety of factors, such as laser-on time, operator duty cycle, and location in the PCS.

3D-printed model for gingival flap surgery simulation: Development and pilot test.

INTRODUCTION: To assess the feasibility of a realistic model for learning oral flaps using 3D printing technology. MATERIALS AND METHODS: A mould was designed to reproduce the mandibular gingival mucosa, and a mandibular model was created using a three-dimensional printer for training undergraduate students to perform gingival flaps. After a short interview about its use, the participants were asked to use the simulator and provide feedback using a 5-point Likert questionnaire. RESULTS: The 3D-printed oral surgery flap training model was practical and inexpensive. The model was very realistic, educational and useful for hands-on training. CONCLUSIONS: 3D printing technology offers new possibilities for training in dental treatments that are currently difficult to replicate. The use of this simulator for oral flap surgery was well-received and considered promising by the participants.

Automated personalization of biomechanical knee model.

PURPOSE: Patient-specific biomechanical models of the knee joint can effectively aid in understanding the reasons for pathologies and improve diagnostic methods and treatment procedures. For deeper research of knee diseases, the development of biomechanical models with appropriate configurations is essential. In this study, we mainly focus on the development of a personalized biomechanical model for the investigation of knee joint pathologies related to patellar motion using automated methods. METHODS: This study presents a biomechanical model created for patellar motion pathologies research and some techniques for automating the generation of the biomechanical model. To generate geometric models of bones, the U-Net neural network was adapted for 3D input datasets. The method uses the same neural network for segmentation of femur, tibia, patella and fibula. The total size of the train/validation (75/25%) dataset is 18,183 3D volumes of size 512 × 512 × 4 voxels. The configuration of the biomechanical knee model proposed in the paper includes six degrees of freedom for the tibiofemoral and patellofemoral joints, lateral and medial contact surfaces for femur and tibia, and ligaments, representing, among other things, the medial and lateral stabilizers of the knee cap. The development of the personalized biomechanical model was carried out using the OpenSim software system. The automated model generation was implemented using OpenSim Python scripting commands. RESULTS: The neural network for bones segmentation achieves mean DICE 0.9838. A biomechanical model for realistic simulation of patellar movement within the trochlear groove was proposed. Generation of personalized biomechanical models was automated. CONCLUSIONS: In this paper, we have implemented a neural network for the segmentation of 3D CT scans of the knee joint to produce a biomechanical model for the study of knee cap motion pathologies. Most stages of the generation process have been automated and can be used to generate patient-specific models.