Identification Of Anatomical Landmarks Research Articles

POCUS Diagnosis of Deep Neck Space Abscess: A Case Series

BackgroundPara and Retropharyngeal abscesses are deep neck infections of early childhood that can be complicated by serious sequelae such as airway obstruction, cervical necrotizing fasciitis, mediastinitis, aspiration pneumonia, jugular thrombosis or aneurysm of the carotid artery. Traditionally, these infections were diagnosed with CT of the neck, which exposes sensitive structures to radiation and may require sedation. Case ReportWe present a case series of four children diagnosed on POCUS with para and/or retropharyngeal abscess later confirmed on CT. All four had alternative working diagnoses on pediatric emergency physician and/or otolaryngology physical examination prior to investigation with POCUS. We also describe a novel imaging approach that allows for easier identification of deep neck anatomic landmarks."Why should an emergency physician be aware of this?"Pediatric emergency physicians should be skilled in imaging the deep neck spaces in order to avoid delayed diagnosis of deep neck space abscess and its potentially catastrophic sequelae.

A systematic review of 3D printing in autologous breast reconstruction

Aim: The use of three-dimensionally printed (3DP), patient-specific models in autologous breast reconstruction is gaining popularity, namely for their benefits in surgical planning and ability to aid in aesthetic outcomes. Furthermore, 3DP patient-specific models serve as a safe alternative to intraoperative surgical training and act as a useful tool for visualizing the intramuscular course of deep inferior epigastric perforator vessels. Despite demonstrated usefulness in other surgical specialties and areas of plastic surgery, there remains a significant gap in the literature exploring specific perioperative, preoperative, and intraoperative uses as well as the educational advantages of 3DP in autologous breast reconstruction. Methods: PubMed, MEDLINE, EMBASE, Scopus, and the Cochrane Central Register of Controlled Trials were searched for all English language articles using specific MeSH terms (3dp OR 3D-print* OR three dimension* print*) AND (breast reconstruction). Only studies discussing the use of 3DP for surgical planning or as an educational tool in autologous breast reconstruction were included. Studies using 3DP as interventions or implants were excluded. Results: A total of 168 articles were identified, 13 of which were selected for inclusion. Risk of bias was low for 8 articles and moderate for 5 articles. Seven (53.8%) articles discussed 3DP usage in preoperative planning. Most papers (12, 92.3%) focused on 3DP models as guides for intraoperative identification of anatomical landmarks and 3DP molds as tools to achieve desired breast volume, shape, and projection. Only 4 (30.7%) articles discussed patient outcomes. Of the 4 (30.7%) articles that discussed education, only one of these properly assessed trainees and faculty using pre- and post-intervention surveys. Conclusion: The majority of 3DP research as an intraoperative guide and educational tool is concentrated outside of autologous breast reconstruction. Studies that do discuss this have found significantly higher success rates in dissecting true DIEP flaps when 3DP vascular modeling is used and can result in improved confidence and competence in surgical training for microsurgical anastomosis. Although 3DP has been shown to aid microsurgeons in preoperative planning, most research concentrates on the aid of this novel technology in dynamic, intraoperative decision making. Existing research has identified five 3DP breast molds, but studies have yet to compare these molds in a controlled setting to assess for superiority in feasibility and outcomes. There is little investigation into the usefulness of 3DP as an educational tool, and more research should be conducted as this methodology expands to cover more forms of autologous breast reconstruction.

Effect of preoperative three-dimensional modeling on uniportal video-assisted thoracoscopic bronchial sleeve resection and early postoperative outcomes.

The aim of this study was to evaluate the effects of preoperative three-dimensional (3D) modeling on the performance of uniportal video-assisted thoracoscopic bronchial sleeve resection and early postoperative outcomes. A total of 10 patients (5 males, 5 females; mean age: 53.8±16.9 years; range, 18 to 75 years) who underwent uniportal video-assisted thoracoscopic bronchial sleeve resection with preoperative 3D modeling between April 2021 and November 2023 were retrospectively analyzed. Preoperative 3D modeling was prepared using computed tomography with an open-source 3D software program. Demographic, clinical, intraoperative, and postoperative data of the patients were recorded. Anatomical landmarks identified by preoperative 3D modeling were compared with intraoperative findings. The anatomical landmarks created with the 3D model were in 100% agreement with the intraoperative findings. The procedures performed were three left lower lobes, three right upper lobes, one middle lobe, one right lower lobe, and one parenchyma-sparing intermediate bronchial sleeve resection. Bronchial sleeve resection was completed using uniportal video-assisted thoracoscopic technique in 90% of patients, with only one patient requiring conversion to open thoracotomy. The mean resection time was 264.2±40.5 min, and the mean anastomosis time was 86.0±20.3 min. Anastomosis times decreased with increasing experience (p=0.008). Postoperative atelectasis was observed in two patients, and there was no mortality. The mean follow-up duration was 12.2±11.8 months. Preoperative 3D modeling significantly contributed to the successful implementation of uniportal video-assisted thoracoscopic bronchial sleeve resection surgery. In the future, with advancements in simulation programs, patient-specific 3D modeling is expected to benefit the identification of anatomical landmarks for bronchial sleeve resections.

The pie-crust surgical technique for medial collateral ligament release: enhancing visualization of the medial compartment in knee arthroscopy.

This study presents a comprehensive surgical technique for performing a 'pie-crust' release of the medial collateral ligament (MCL) to enhance visualization of the medial compartment during arthroscopic knee procedures. The primary objective of this research is to improve the precision of diagnosis and treatment for injuries specifically affecting the posterior horn and posterior root of the medial meniscus. Arthroscopic knee procedures have become increasingly common in orthopedic surgery, offering the advantage of minimally invasive techniques for treating a wide range of knee conditions. However, accessing and visualizing the posterior structures within the medial compartment can be challenging. To overcome this limitation, the surgical technique presented in this study offers a systematic approach that includes patient positioning, precise identification of anatomical landmarks, and a detailed, step-by-step procedural description. The process begins with meticulous marking of anatomical landmarks to provide reference points. Precisely identifying the location for the MCL release is of utmost importance. This involves making needle punctures with guidance from arthroscopic visualization and applying valgus strain to the knee as necessary. One of the key advantages of this described surgical technique is its focus on safety and efficacy. Surgeons can work more confidently and precisely by reducing the risk of iatrogenic cartilage damage and facilitating access to the posterior structures within the medial compartment. Clinical outcomes from this approach have demonstrated consistently favorable results, leading to improved patient recovery and reduced complications. Furthermore, it is noteworthy that the postoperative use of a brace is not mandatory, adding to the appeal of this technique for both patients and surgeons. This surgical technique's enhanced visualization and optimized treatment outcomes make it a valuable tool in the arsenal of orthopedic surgeons specializing in knee arthroscopy. In conclusion, this study's surgical technique has the potential to significantly improve the diagnosis and treatment of patients with meniscal injuries in the medial compartment, ultimately leading to better clinical outcomes and patient satisfaction.

Scoliotic postural alignment in prepubertal children: somatoscopic analysis of anatomical landmarks and development of a working model to limit spinal changes

Abstract: Background. The study aims to perform a somatoscopic analysis on a sample of 100 prepubertal children aged 10-14 years, girls and boys, who are diagnosed with scoliosis. Somato-scopic assessment is one of the most commonly used, therefore we thought that making a way of interpreting the results could be useful to monitor postural attitude in children diagnosed with scoliosis. Identifying the early onset of physical impairment in the spine with somatoscopy can be a key factor in maintaining optimal postural status. This approach may help in achieving a way of working that limits the negative effects of scoliosis on the subjects. Materials and methods. The selection of subjects is based on exclusion and inclusion criteria related to age, comorbidities, therapeutic approach, and other criteria. Also, aspects that accompany the growth and devel-opment process of children in this prepubertal period and factors that may disturb this process are described in detail. Also in this context, we will present basic notions of body posture and eti-opathogenesis of the onset of scoliotic deficiencies in children during this period of growth and development. Somatoscopic analysis is performed in the orthostatic position and is based on the identification of anatomical landmarks of the body concerning body posture. Results. From the total analyzed scoliosis, n = 100, 74% are type „C” scoliosis and only 26% are type „S” and in terms of gender, 59% are girls and 41% boys; type „C1” (Cobb angle <100) scoliosis n = 60, with an angulation < 100 are 43.24% stabilized, therefore type „C1” scoliosis are more likely to be stabilized. „S”-type scoliosis with an angulation < 150 is only 3 cases representing 11.53%, and those with an angulation from < 200 to < 400 are number 23 cases 88.64% which concludes that „S” type scoliosis is more aggressive and more difficult to manage. Conclusions. Our study show that only 13% of the subjects had a regression of the angulation following the kinetotherapy program, therefore the main objective remains to stabilize the scoliosis attitude and limit the effects of this pathology. A regular assessment and somatotopic analysis resulting in a physiotherapy exercises program containing corrective postural postures and postural education is the most beneficial approach to stabilize the postural deficit.

Impact of obesity on outcomes of extracorporeal membrane oxygenation support: a systematic review and meta-analysis

BackgroundExtracorporeal membrane oxygenation (ECMO) is used when standard methods of standard treatment methods are not successful. Obese patients present unique challenges during ECMO due to large body size hindering sufficient flows, difficulties with patient positioning and anatomical landmark identification, and restricted radiology scans. This meta-analysis aims to investigate the impact of obesity on the outcomes of patients undergoing ECMO.MethodsDatabases (PubMed, Embase, and Scopus databases) were searched to identify relevant studies published until July 2023. Data were reported as odds ratios (OR) with 95% confidence interval (CI), and the descriptive data were reported as standard difference of means (SDM) by a random effects model.ResultsA literature search identified 345 studies. Of them, 18 studies met the inclusion criteria. The findings from the meta-analysis revealed no significant association between obesity and survival outcomes after ECMO (odds ratio (OR): 0.91, 95% confidence interval (CI): 0.70–1.17, p: 0.46). Moreover, no comparative significant differences were found between obese and non-obese individuals on the duration of ECMO procedure (standardized mean difference (SMD): 0.07, -0.03–0.17), length of hospital stay (-0.03, -0.19 to 0.12), and duration of ventilation support (-0.10, -0.44 to 0.24).ConclusionThe meta-analysis findings suggest no significant impact of obesity on the survival outcomes after the ECMO procedure. There was no significant impact of obesity on the duration of ECMO procedures, length of hospital stay, and duration of ventilation support.

Student training in administering inferior alveolar nerve block anesthesia with a simple manufactured simulation model.

To compare the effectiveness of administering inferior alveolar nerve blocks (IANB) for the first time with or without a previous practical lesson using a simple manufactured simulator. This was a study designed to compare students' first administration of IANB anesthesia during 2022, with or without a previous practical lesson. Students were randomized into two groups. The experimental group attended both theoretical lessons and a practical lesson with a simulator device, while the control group attended only theoretical lessons. The theoretical lesson included usual contents such as anatomy, physiology, technical maneuvers for administering anesthesia, tips, and complications, and the practical lesson consisted of the administration of anesthesia using a simple manufactured simulator. After students applied their first IANB, its efficacy, and their answers to a questionnaire on a 5-point Likert scale were recorded. Statistical analysis consisted of the Chi-square test (p<0.05). The study recorded 60 anonymous surveys. The main difference observed was in instrument handing (p<0.05), and there was a tendency in the ease of recognition of the anatomical marks used for the technique-pterygomandibular raphe and coronoid notch of the mandible (p=0.08 and 0.11, respectively). No difference in success was observed (p>0.05). Self-confidence and personal feelings did not differ statistically. All students agreed strongly or partially that training with the simulator model was helpful. Students who used simple manufactured simulators achieved better outcomes for instrument handling, and possibly for identification of anatomical landmarks, than those who received only theoretical lessons.

A Comparative Analysis of Artificial Intelligence and Manual Methods for Three-Dimensional Anatomical Landmark Identification in Dentofacial Treatment Planning.

With the growing demand for orthognathic surgery and other facial treatments, the accurate identification of anatomical landmarks has become crucial. Recent advancements have shifted towards using three-dimensional radiologic analysis instead of traditional two-dimensional methods, as it allows for more precise treatment planning, primarily relying on direct identification by clinicians. However, manual tracing can be time-consuming, mainly when dealing with a large number of patients. This study compared the accuracy and reliability of identifying anatomical landmarks using artificial intelligence (AI) and manual identification. Thirty patients over 19 years old who underwent pre-orthodontic and orthognathic surgery treatment and had pre-orthodontic three-dimensional radiologic scans were selected. Thirteen anatomical indicators were identified using both AI and manual methods. The landmarks were identified by AI and four experienced clinicians, and multiple ANOVA was performed to analyze the results. The study results revealed minimal significant differences between AI and manual tracing, with a maximum deviation of less than 2.83 mm. This indicates that utilizing AI to identify anatomical landmarks can be a reliable method in planning orthognathic surgery. Our findings suggest that using AI for anatomical landmark identification can enhance treatment accuracy and reliability, ultimately benefiting clinicians and patients.

Enhancing YOLO5 for the Assessment of Irregular Pelvic Radiographs with Multimodal Information.

Developmental dysplasia of the hip (DDH) is one of the most common orthopedic disorders in infants and young children. Accurate identification and localization of anatomical landmarks are prerequisites for the diagnosis of DDH. In recent years, various works have employed deep learning algorithms on radiography images for DDH diagnosis. However, none of these works have considered the incorporation of multimodal information. The pelvis exhibits distinct structures at different developmental stages, and there are also gender-based differences. In light of this, this study proposes a method to enhance the performance of deep learning models in diagnosing DDH by incorporating age and gender information into the channels. The study utilizes YOLO5 to construct a deep learning network for detecting hip joint landmarks. Moreover, a comprehensive dataset of 7750 pelvic X-ray images is established, covering ages from 4months to 16years and encompassing various conditions, such as deformities and post-operative cases, which authentically capture the temporal diversity and pathological complexities of DDH. Experimental results show that the YOLO5 model with integrated multimodal information achieves a mAP0.5-0.95 of 83.1% and a diagnostic accuracy of 86.7% in test dataset. The F1 scores for diagnosing cases of normal (NM), suspected dislocation (SD), mild dislocation (MD), and heavily dislocation (HD) are 90.9%, 79.8%, 63.5%, and 97.4%, respectively. Furthermore, experiments conducted on datasets of different sizes and networks of different sizes demonstrate the beneficial impact of multimodal information in improving the effectiveness of deep learning in diagnosing DDH.

Endoscopic anterior capsulectomy for severe elbow contractures

Elbow stiffness secondary to trauma or surgical reconstruction can sometimes result in a severe contracture with restricted joint space, and arthroscopic access to the joint is difficult. Previous surgery and severe stiffness can also alter the position of neurovascular structures and iatrogenic injury is possible with an inside-out arthroscopic approach. To overcome these technical difficulties, an endoscopic approach to the anterior capsule can be performed as an alternative to open approach. The endoscopic approach utilises the sub-brachialis space for an outside-in capsular resection under vision. Identification of standard anatomic landmarks is useful as a guide for safe resection in a central to peripheral direction.

Investigation of The Accuracy of Palpation of Physical Therapy Students to Different Anatomical Landmarks

Purpose: Surface anatomy plays a crucial role in physical therapy education as it enables the examination of subcutaneous structures through palpation. This study aims to investigate the accuracy of palpation on landmarks among physical therapy students (PT).&#x0D; Material and Methods: This cross-sectional, observational study evaluated the accuracy of palpation on anatomical landmarks. The researchers specified 21 landmarks for palpation assessment. Each landmark was scored on a scale of 0 to 3, and the Landmark Total Palpation Score (Lt) was calculated based on the scores of all 21 landmarks. A higher score indicated poorer accuracy in identifying anatomical landmarks.&#x0D; Results: The participants' Lt scores had a mean of 10.09 ± 9.66, with a standard deviation. The Lt demonstrated excellent intra-rater reliability (ICC = 0.91). Conclusion: The study findings indicate a good level of anatomical landmark identification among PT students.&#x0D; Conclusion: The results of this study showed that there was a good level anatomical landmark identification among PT students

Determinants of Accuracy of Freehand, EVD Placement by Neurosurgical Trainees.

Background: The insertion of an external ventricular drain (EVD) is a fundamental neurosurgical procedure predominantly performed by junior neurosurgical trainees. It is vital for managing conditions like hydrocephalus, intracranial hypertension, traumatic brain injury, and others. The procedure's success heavily relies on the precise identification of anatomical landmarks and the trainee's experience. Objective: This study aims to assess the precision and safety of EVD placement in patients treated by first-year (R1) and second-year (R2) neurosurgical residents, evaluating the impact of the residents' experience levels on the outcomes of the procedure. Methods: Conducted at the Neurosurgery Department of Jinnah Post Graduate Medical Center, Karachi, from February to July 2022, this prospective cohort study involved individuals aged 18 years or older undergoing EVD placement for hydrocephalus. Exclusion criteria included patients with more than 5mm midline shift on initial scans or those without a post-EVD placement scan. Procedures were performed under senior resident supervision, with postoperative CT scans assessing catheter tip placement and potential complications. Statistical analyses utilized IBM SPSS Statistics for Windows, Version 25.0, with Student’s t-test, Chi-square, and Fisher exact tests applied as appropriate. Results: The study comprised 152 patients (mean age: 39.4 ± 10.7 years; 52.6% male). The initial GCS scores varied, with 44.7% scoring above 8. Most EVD placements (60.5%) were by residents in their fourth or fifth year. The average procedure duration was 43 ± 8.7 minutes, with an average of 1.44 ± 0.12 passes. Optimal placement (Kakarla Grade 1) was achieved in 59.2% of cases, with significant differences in placement accuracy between R1 and R2 residents (p&lt;0.05). Conclusion: The study highlights the significant role of experience and training in the successful placement of EVDs. The higher accuracy rates in more experienced residents underscore the need for enhanced training programs for junior neurosurgical trainees, focusing on anatomical landmark identification and procedural practice.

Artificial Intelligence Assisted Recognition of Anatomical Landmarks and Laparoscopic Instruments in Transabdominal Preperitoneal Inguinal Hernia Repair.

Laparoscopic TAPP (Trans-Abdominal PrePeritoneal) is a minimally invasive surgical procedure used to repair inguinal hernias. Arguably, one important aspect to TAPP hernia repair is the identification of anatomical landmarks and the correct use of various laparoscopic instruments. There are very few studies regarding the use of artificial intelligence in laparoscopic inguinal hernia repair and more specifically in TAPP. The aim of this study is to evaluate the feasibility and usefulness of AI in the recognition of anatomical landmarks and tools in laparoscopic TAPP videos. Imaging data have been exported from 20 Laparoscopic TAPP videos that have been performed by the authors and another 5 high quality TAPP videos from the internet (free access) performed by other surgeons. In total 1095 selected images have been exported for annotation. To accomplish the AI result of computer vision, the YOLOv8 model of deep learning was used. In total 2716 segmented areas of interest have been exported. The AI model was able to detect the various classes with a maximum F1 score of .82 when the confidence threshold was set to .406. The mAP50 was .873 for all classes. The Precision was above 50% when the confidence was over 10%. The Recall rate was above 50% when confidence was less than 70%. These results suggest that the model is effective at balancing precision and recall, capturing both true positives and minimizing false negatives. Artificial Intelligence recognition of anatomical landmarks and laparoscopic instruments in TAPP is feasible with acceptable success rates.

Fluorophores in Endoscopic Neurosurgery.

The complexity of intracranial anatomy and pathologies warrants the optimization of multimodal techniques to ensure safe and effective surgical treatment. Endoscopy is being more widely implemented in intracranial procedures as an important visualization tool, as it can offer panoramic views of deep structures while reducing the invasiveness of approaches. Fluorophores are frequently utilized to augment the identification of intracranial anatomic landmarks and pathologies. This chapter discusses the integration of these two surgical adjuncts, highlighting the key fluorophores used in endoscopic neurosurgery and their clinical applications.

The Lateral Supraorbital Approach: 2-Dimensional Operative Video.

The lateral supraorbital approach (LSO), a minimally invasive alternative to the pterional approach, can be used for anterior circulation aneurysms (except distal anterior cerebral artery), some posterior circulation aneurysms, and tumors located around the sellar and suprasellar regions. Performing one-layer myocutaneous flap that is retracted anteriorly, exposure of the superior temporal line, and zygomatic process of the frontal bone and the inferior limit of the craniotomy represent the upper edge of the Sylvian fissure, exposing the anterolateral skull base. Skin incision behind the hairline, one-layer myocutaneous flap retracted anteriorly, minimal detachment of the temporalis muscle, burr hole over the superior temporal line, and craniotomy of 4 cm in diameter (inferior limit of the craniotomy represents the Sylvian fissure). Potential risks include opening of the frontal sinus, entering the orbit and exposure of the orbital fat, wrong craniotomy location, and limited exposure. Inadequate craniotomy size limits instruments maneuverability. To avoid complication, identification of anatomic landmarks, sinus closure, preoperative evaluation of computed tomography scans, and use of neuronavigation are necessary. This requires surgical expertise and familiarity of minimal invasive craniotomies. Anatomic limitations of the LSO include temporomesial region, distal Sylvian +/-, posterior communicating artery aneurysms medial projection, retro carotid space, and carotid cave. For pathologies requiring an additional lateral trajectory, we use an extended LSO, drilling the sphenoid wing through the fronto-pterio-orbital window without drilling of the temporal bone. Additional variations include performing an intradural or extradural clinoidectomy. The patient consented to the procedure and to the publication of their image.

IBC-Oxford University2023_BJSOral_18The Use of Indocyanine Green (ICG) Fluorescence Angiography in Laparoscopic Roux-en-Y Gastric Bypass for Perfusion Assessment and Structure Visualisation

Abstract Introduction Indocyanine green (ICG) fluorescence angiography (FA) has been utilised in bariatric surgery for assessment of tissue perfusion and blood supply in laparoscopic sleeve gastrectomy (LSG). However, there is limited literature on its use in laparoscopic Roux-en-Y gastric bypass (LRYGB). The aim of this study was to evaluate the use of ICG-FA in LRYGB for qualitative assessment of tissue perfusion and structure identification. These are the first cases utilising ICG-FA in LRYGB to be performed in the United Kingdom. Methods Thirty-five patients (12 male, 34%, 23 females, 66%) with median (IQR) age of 45 (38 – 52) years and preoperative median (IQR) BMI 45 (37 – 49) kg/m2 underwent LRYGB with ICG-FA. ICG was administered intravenously according to an agreed protocol. Karl Storz® Image 1 Rubina system with overlay and monochromatic modes was utilised for perfusion assessment. ICGFA was utilised for qualitative assessment of gastric pouch perfusion before and after linear stapled gastro-jejunal anastomosis and visualisation of key anatomical landmarks. The perfusion pattern was assessed by the operating team based on a ICG scoring system (ICG-S), which ranged from 1 (no perfusion) to 4 (excellent perfusion) based on timing following ICG injection and intensity of fluorescence detected in the anatomical structures. Results From April 2021 to August 2022, 34 patients underwent primary LRYGB with use of ICG- FA. ICG was utilised in one revisional case. No adverse effects to ICG were observed. ICG-S was 4 in 33 patients. (94%). In two patients (6%), operative strategy was modified based on focal area of no perfusion (ICG score 1) in gastric pouch. ICG-FA helped improve operative safety during division of omentum and in recognition of duodeno-jejunal flexure with fluorescence detection in epiploic vessels and inferior mesenteric vein (IMV) respectively. There were no leaks at a median follow up of 9 months. Conclusion ICGFA imaging allows for qualitative assessment of perfusion and identification of critical anatomical landmarks during LRYGB. The technology is safe and its utilisation in LRYGB provides a “real-time image” of gastric pouch perfusion, helping to demonstrate ischaemic or poorly perfused areas with an opportunity to modify operative strategy.

Fully automatic algorithm for detecting and tracking anatomical shoulder landmarks on fluoroscopy images with artificial intelligence

ObjectivePatients with rotator cuff tears present often with glenohumeral joint instability. Assessing anatomic angles and shoulder kinematics from fluoroscopy requires labelling of specific landmarks in each image. This study aimed to develop an artificial intelligence model for automatic landmark detection from fluoroscopic images for motion tracking of the scapula and humeral head.Materials and methodsFluoroscopic images were acquired for both shoulders of 25 participants (N = 12 patients with unilateral rotator cuff tear, 6 men, mean (standard deviation) age: 63.7 ± 9.7 years; 13 asymptomatic subjects, 7 men, 58.2 ± 8.9 years) during a 30° arm abduction and adduction movement in the scapular plane with and without handheld weights of 2 and 4 kg. A 3D full-resolution convolutional neural network (nnU-Net) was trained to automatically locate five landmarks (glenohumeral joint centre, humeral shaft, inferior and superior edges of the glenoid and most lateral point of the acromion) and a calibration sphere.ResultsThe nnU-Net was trained with ground-truth data from 6021 fluoroscopic images of 40 shoulders and tested with 1925 fluoroscopic images of 10 shoulders. The automatic landmark detection algorithm achieved an accuracy above inter-rater variability and slightly below intra-rater variability. All landmarks and the calibration sphere were located within 1.5 mm, except the humeral landmark within 9.6 mm, but differences in abduction angles were within 1°.ConclusionThe proposed algorithm detects the desired landmarks on fluoroscopic images with sufficient accuracy and can therefore be applied to automatically assess shoulder motion, scapular rotation or glenohumeral translation in the scapular plane.Clinical relevance statementThis nnU-net algorithm facilitates efficient and objective identification and tracking of anatomical landmarks on fluoroscopic images necessary for measuring clinically relevant anatomical configuration (e.g. critical shoulder angle) and enables investigation of dynamic glenohumeral joint stability in pathological shoulders.Key Points• Anatomical configuration and glenohumeral joint stability are often a concern after rotator cuff tears.• Artificial intelligence applied to fluoroscopic images helps to identify and track anatomical landmarks during dynamic movements.• The developed automatic landmark detection algorithm optimised the labelling procedures and is suitable for clinical application.

Development of a deep learning model for safe direct optical trocar insertion in minimally invasive surgery: an innovative method to prevent trocar injuries.

Direct optical trocar insertion is a common procedure in laparoscopic minimally invasive surgery. However, misinterpretations of the abdominal wall anatomy can lead to severe complications. Artificial intelligence has shown promise in surgical endoscopy, particularly in the employment of deep learning models for anatomical landmark identification. This study aimed to integrate a deep learning model with an alarm system algorithm for the precise detection of abdominal wall layers during trocar placement. Annotated bounding boxes and assigned classes were based on the six layers of the abdominal wall: subcutaneous, anterior rectus sheath, rectus muscle, posterior rectus sheath, peritoneum, and abdominal cavity. The cutting-edge YOLOv8 model was combined with a deep learning detector to train the dataset. The model was trained on still images and inferenced on laparoscopic videos to ensure real-time detection in the operating room. The alarm system was activated upon recognizing the peritoneum and abdominal cavity layers. We assessed the model's performance using mean average precision (mAP), precision, and recall metrics. A total of 3600 images were captured from 89 laparoscopic video cases. The proposed model was trained on 3000 images, validated with a set of 200 images, and tested on a separate set of 400 images. The results from the test set were 95.8% mAP, 89.8% precision, and 91.7% recall. The alarm system was validated and accepted by experienced surgeons at our institute. We demonstrated that deep learning has the potential to assist surgeons during direct optical trocar insertion. During trocar insertion, the proposed model promptly detects precise landmark references in real-time. The integration of this model with the alarm system enables timely reminders for surgeons to tilt the scope accordingly. Consequently, the implementation of the framework provides the potential to mitigate complications associated with direct optical trocar placement, thereby enhancing surgical safety and outcomes.

Clinician accuracy in identifying essential laryngeal landmarks on swallowing fluoroscopy.

Identification of anatomical landmarks is essential for interpretation of video fluoroscopic swallow studies (VFSS). This investigation sought to confirm the location of essential laryngeal landmarks and determine clinician accuracy in structure identification on VFSS. A single human cadaver was used to generate unmarked standard lateral and anterior-posterior (AP) fluoroscopic images. Essential laryngeal structures (e.g., true vocal fold, arytenoid) were directly identified using a guidewire placed through an endoscope while obtaining corresponding marked fluoroscopic images. Licensed clinicians (speech-language pathologists [SLP], laryngologists) and trainees (otolaryngology residents, SLP clinical fellows [CF]) identified 18 structures (9 lateral, 9 AP) on unmarked images. Answers were compared to corresponding marked images. The percentage of accurate identification was calculated for each clinician and then compared between groups using t-tests. Twenty-four individuals (10 SLPs, 1 CF, 9 residents, 4 laryngologists) from six institutions completed structure identification. Mean overall accuracy was 41.7 ± 13.0% (range 18.8-68.8%). There were no significant differences in mean overall accuracy between trainees (41.9 ± 12.9%) and clinicians (42.0 ± 13.1%), p = .97, or between SLPs (45.5 ± 12.8%) and physicians (38.9 ± 12.3%), p = .22. On average, participants were significantly more accurate identifying structures on lateral view (53.1 ± 16.1%) than AP (27.3 ± 22.8%), p < .001. Less than half of participants accurately identified the laryngeal ventricle, cricoid, epiglottic petiole, and the anterior commissure on lateral view. The ability of certified clinicians and trainees to correctly identify essential anatomic landmarks on swallowing fluoroscopy may be poor. Future work is needed to identify how we can train clinicians on more accurate identification of essential anatomic structures on swallowing fluoroscopy.Level of Evidence: NA.

The impact of dental operating microscopes on the success rates of endodontic treatments

Recent advancements in dental technology, such as magnification devices like loupes and surgical microscopes, have greatly improved the accuracy and quality of root canal treatments. Dental operating microscopes (DOMs) have become widely accepted in endodontics, providing enhanced visualization and facilitating precise identification of anatomical landmarks, root canal orifices, and pulp remnants. The increased magnification and illumination offered by DOMs have improved treatment outcomes by enabling more efficient removal of bacteria, debris, and obturation materials from the root canal system. Studies have shown that the use of DOMs can significantly increase the success rates of endodontic treatments, allowing for the identification and treatment of even the smallest canals and anatomical variations. Additionally, DOMs enhance ergonomics, patient communication, and documentation in dental practice. However, challenges such as cost and limited office space hinder their widespread use. Increased education and awareness of the benefits of operating microscope utilization are essential for its broader adoption in endodontic procedures.