RESUMEN
Introduction: The use of robotic systems in the surgical domain has become groundbreaking for patients and surgeons in the last decades. While the annual number of robotic surgical procedures continues to increase rapidly, it is essential to provide the surgeon with innovative training courses along with the standard specialization path. To this end, simulators play a fundamental role. Currently, the high cost of the leading VR simulators limits their accessibility to educational institutions. The challenge lies in balancing high-fidelity simulation with cost-effectiveness; however, few cost-effective options exist for robotic surgery training. Methods: This paper proposes the design, development and user-centered usability study of an affordable user interface to control a surgical robot simulator. It consists of a cart equipped with two haptic interfaces, a VR visor and two pedals. The simulations were created using Unity, which offers versatility for expanding the simulator to more complex scenes. An intuitive teleoperation control of the simulated robotic instruments is achieved through a high-level control strategy. Results and Discussion: Its affordability and resemblance to real surgeon consoles make it ideal for implementing robotic surgery training programs in medical schools, enhancing accessibility to a broader audience. This is demonstrated by the results of an usability study involving expert surgeons who use surgical robots regularly, expert surgeons without robotic surgery experience, and a control group. The results of the study, which was based on a traditional Peg-board exercise and Camera Control task, demonstrate the simulator's high usability and intuitive control across diverse user groups, including those with limited experience. This offers evidence that this affordable system is a promising solution for expanding robotic surgery training.
RESUMEN
PURPOSE: Informative image selection in laryngoscopy has the potential for improving automatic data extraction alone, for selective data storage and a faster review process, or in combination with other artificial intelligence (AI) detection or diagnosis models. This paper aims to demonstrate the feasibility of AI in providing automatic informative laryngoscopy frame selection also capable of working in real-time providing visual feedback to guide the otolaryngologist during the examination. METHODS: Several deep learning models were trained and tested on an internal dataset (n = 5147 images) and then tested on an external test set (n = 646 images) composed of both white light and narrow band images. Four videos were used to assess the real-time performance of the best-performing model. RESULTS: ResNet-50, pre-trained with the pretext strategy, reached a precision = 95% vs. 97%, recall = 97% vs, 89%, and the F1-score = 96% vs. 93% on the internal and external test set respectively (p = 0.062). The four testing videos are provided in the supplemental materials. CONCLUSION: The deep learning model demonstrated excellent performance in identifying diagnostically relevant frames within laryngoscopic videos. With its solid accuracy and real-time capabilities, the system is promising for its development in a clinical setting, either autonomously for objective quality control or in conjunction with other algorithms within a comprehensive AI toolset aimed at enhancing tumor detection and diagnosis.
Asunto(s)
Aprendizaje Profundo , Laringoscopía , Humanos , Laringoscopía/métodos , Grabación en Video , Estudios de Factibilidad , Enfermedades de la Laringe/diagnóstico , Enfermedades de la Laringe/diagnóstico por imagenRESUMEN
OBJECTIVE: To investigate the potential of deep learning for automatically delineating (segmenting) laryngeal cancer superficial extent on endoscopic images and videos. METHODS: A retrospective study was conducted extracting and annotating white light (WL) and Narrow-Band Imaging (NBI) frames to train a segmentation model (SegMENT-Plus). Two external datasets were used for validation. The model's performances were compared with those of two otolaryngology residents. In addition, the model was tested on real intraoperative laryngoscopy videos. RESULTS: A total of 3933 images of laryngeal cancer from 557 patients were used. The model achieved the following median values (interquartile range): Dice Similarity Coefficient (DSC) = 0.83 (0.70-0.90), Intersection over Union (IoU) = 0.83 (0.73-0.90), Accuracy = 0.97 (0.95-0.99), Inference Speed = 25.6 (25.1-26.1) frames per second. The external testing cohorts comprised 156 and 200 images. SegMENT-Plus performed similarly on all three datasets for DSC (p = 0.05) and IoU (p = 0.07). No significant differences were noticed when separately analyzing WL and NBI test images on DSC (p = 0.06) and IoU (p = 0.78) and when analyzing the model versus the two residents on DSC (p = 0.06) and IoU (Senior vs. SegMENT-Plus, p = 0.13; Junior vs. SegMENT-Plus, p = 1.00). The model was then tested on real intraoperative laryngoscopy videos. CONCLUSION: SegMENT-Plus can accurately delineate laryngeal cancer boundaries in endoscopic images, with performances equal to those of two otolaryngology residents. The results on the two external datasets demonstrate excellent generalization capabilities. The computation speed of the model allowed its application on videolaryngoscopies simulating real-time use. Clinical trials are needed to evaluate the role of this technology in surgical practice and resection margin improvement. LEVEL OF EVIDENCE: III Laryngoscope, 134:2826-2834, 2024.
Asunto(s)
Aprendizaje Profundo , Neoplasias Laríngeas , Laringoscopía , Imagen de Banda Estrecha , Humanos , Laringoscopía/métodos , Imagen de Banda Estrecha/métodos , Neoplasias Laríngeas/diagnóstico por imagen , Neoplasias Laríngeas/cirugía , Neoplasias Laríngeas/patología , Estudios Retrospectivos , Grabación en Video , Masculino , Femenino , Persona de Mediana Edad , Luz , AncianoRESUMEN
PURPOSE: In twin-to-twin transfusion syndrome (TTTS), abnormal vascular anastomoses in the monochorionic placenta can produce uneven blood flow between the two fetuses. In the current practice, TTTS is treated surgically by closing abnormal anastomoses using laser ablation. This surgery is minimally invasive and relies on fetoscopy. Limited field of view makes anastomosis identification a challenging task for the surgeon. METHODS: To tackle this challenge, we propose a learning-based framework for in vivo fetoscopy frame registration for field-of-view expansion. The novelties of this framework rely on a learning-based keypoint proposal network and an encoding strategy to filter (i) irrelevant keypoints based on fetoscopic semantic image segmentation and (ii) inconsistent homographies. RESULTS: We validate our framework on a dataset of six intraoperative sequences from six TTTS surgeries from six different women against the most recent state-of-the-art algorithm, which relies on the segmentation of placenta vessels. CONCLUSION: The proposed framework achieves higher performance compared to the state of the art, paving the way for robust mosaicking to provide surgeons with context awareness during TTTS surgery.
Asunto(s)
Transfusión Feto-Fetal , Terapia por Láser , Embarazo , Femenino , Humanos , Fetoscopía/métodos , Transfusión Feto-Fetal/diagnóstico por imagen , Transfusión Feto-Fetal/cirugía , Placenta/cirugía , Placenta/irrigación sanguínea , Terapia por Láser/métodos , AlgoritmosRESUMEN
Fetoscopy laser photocoagulation is a widely adopted procedure for treating Twin-to-Twin Transfusion Syndrome (TTTS). The procedure involves photocoagulation pathological anastomoses to restore a physiological blood exchange among twins. The procedure is particularly challenging, from the surgeon's side, due to the limited field of view, poor manoeuvrability of the fetoscope, poor visibility due to amniotic fluid turbidity, and variability in illumination. These challenges may lead to increased surgery time and incomplete ablation of pathological anastomoses, resulting in persistent TTTS. Computer-assisted intervention (CAI) can provide TTTS surgeons with decision support and context awareness by identifying key structures in the scene and expanding the fetoscopic field of view through video mosaicking. Research in this domain has been hampered by the lack of high-quality data to design, develop and test CAI algorithms. Through the Fetoscopic Placental Vessel Segmentation and Registration (FetReg2021) challenge, which was organized as part of the MICCAI2021 Endoscopic Vision (EndoVis) challenge, we released the first large-scale multi-center TTTS dataset for the development of generalized and robust semantic segmentation and video mosaicking algorithms with a focus on creating drift-free mosaics from long duration fetoscopy videos. For this challenge, we released a dataset of 2060 images, pixel-annotated for vessels, tool, fetus and background classes, from 18 in-vivo TTTS fetoscopy procedures and 18 short video clips of an average length of 411 frames for developing placental scene segmentation and frame registration for mosaicking techniques. Seven teams participated in this challenge and their model performance was assessed on an unseen test dataset of 658 pixel-annotated images from 6 fetoscopic procedures and 6 short clips. For the segmentation task, overall baseline performed was the top performing (aggregated mIoU of 0.6763) and was the best on the vessel class (mIoU of 0.5817) while team RREB was the best on the tool (mIoU of 0.6335) and fetus (mIoU of 0.5178) classes. For the registration task, overall the baseline performed better than team SANO with an overall mean 5-frame SSIM of 0.9348. Qualitatively, it was observed that team SANO performed better in planar scenarios, while baseline was better in non-planner scenarios. The detailed analysis showed that no single team outperformed on all 6 test fetoscopic videos. The challenge provided an opportunity to create generalized solutions for fetoscopic scene understanding and mosaicking. In this paper, we present the findings of the FetReg2021 challenge, alongside reporting a detailed literature review for CAI in TTTS fetoscopy. Through this challenge, its analysis and the release of multi-center fetoscopic data, we provide a benchmark for future research in this field.
Asunto(s)
Transfusión Feto-Fetal , Placenta , Femenino , Humanos , Embarazo , Algoritmos , Transfusión Feto-Fetal/diagnóstico por imagen , Transfusión Feto-Fetal/cirugía , Transfusión Feto-Fetal/patología , Fetoscopía/métodos , Feto , Placenta/diagnóstico por imagenRESUMEN
PURPOSE: Fetoscopic laser photocoagulation of placental anastomoses is the most effective treatment for twin-to-twin transfusion syndrome (TTTS). A robust mosaic of placenta and its vascular network could support surgeons' exploration of the placenta by enlarging the fetoscope field-of-view. In this work, we propose a learning-based framework for field-of-view expansion from intra-operative video frames. METHODS: While current state of the art for fetoscopic mosaicking builds upon the registration of anatomical landmarks which may not always be visible, our framework relies on learning-based features and keypoints, as well as robust transformer-based image-feature matching, without requiring any anatomical priors. We further address the problem of occlusion recovery and frame relocalization, relying on the computed features and their descriptors. RESULTS: Experiments were conducted on 10 in-vivo TTTS videos from two different fetal surgery centers. The proposed framework was compared with several state-of-the-art approaches, achieving higher [Formula: see text] on 7 out of 10 videos and a success rate of [Formula: see text] in occlusion recovery. CONCLUSION: This work introduces a learning-based framework for placental mosaicking with occlusion recovery from intra-operative videos using a keypoint-based strategy and features. The proposed framework can compute the placental panorama and recover even in case of camera tracking loss where other methods fail. The results suggest that the proposed framework has large potential to pave the way to creating a surgical navigation system for TTTS by providing robust field-of-view expansion.
Asunto(s)
Transfusión Feto-Fetal , Fetoscopía , Femenino , Humanos , Embarazo , Transfusión Feto-Fetal/cirugía , Fetoscopía/métodos , Fotocoagulación , Placenta/cirugíaRESUMEN
The early detection of head and neck squamous cell carcinoma (HNSCC) is essential to improve patient prognosis and enable organ and function preservation treatments. The objective of this study is to assess the feasibility of using electrical bioimpedance (EBI) sensing technology to detect HNSCC tissue. A prospective study was carried out analyzing tissue from 46 patients undergoing surgery for HNSCC. The goal was the correct identification of pathologic tissue using a novel needle-based EBI sensing device and AI-based classifiers. Considering the data from the overall patient cohort, the system achieved accuracies between 0.67 and 0.93 when tested on tissues from the mucosa, skin, muscle, lymph node, and cartilage. Furthermore, when considering a patient-specific setting, the accuracy range increased to values between 0.82 and 0.95. This indicates that more reliable results may be achieved when considering a tissue-specific and patient-specific tissue assessment approach. Overall, this study shows that EBI sensing may be a reliable technology to distinguish pathologic from healthy tissue in the head and neck region. This observation supports the continuation of this research on the clinical use of EBI-based devices for early detection and margin assessment of HNSCC.
RESUMEN
OBJECTIVE: The endoscopic and laryngoscopic examination is paramount for laryngeal, oropharyngeal, nasopharyngeal, nasal, and oral cavity benign lesions and cancer evaluation. Nevertheless, upper aerodigestive tract (UADT) endoscopy is intrinsically operator-dependent and lacks objective quality standards. At present, there has been an increased interest in artificial intelligence (AI) applications in this area to support physicians during the examination, thus enhancing diagnostic performances. The relative novelty of this research field poses a challenge both for the reviewers and readers as clinicians often lack a specific technical background. DATA SOURCES: Four bibliographic databases were searched: PubMed, EMBASE, Cochrane, and Google Scholar. REVIEW METHODS: A structured review of the current literature (up to September 2022) was performed. Search terms related to topics of AI, machine learning (ML), and deep learning (DL) in UADT endoscopy and laryngoscopy were identified and queried by 3 independent reviewers. Citations of selected studies were also evaluated to ensure comprehensiveness. CONCLUSIONS: Forty-one studies were included in the review. AI and computer vision techniques were used to achieve 3 fundamental tasks in this field: classification, detection, and segmentation. All papers were summarized and reviewed. IMPLICATIONS FOR PRACTICE: This article comprehensively reviews the latest developments in the application of ML and DL in UADT endoscopy and laryngoscopy, as well as their future clinical implications. The technical basis of AI is also explained, providing guidance for nonexpert readers to allow critical appraisal of the evaluation metrics and the most relevant quality requirements.
Asunto(s)
Inteligencia Artificial , Médicos , Humanos , Endoscopía , Laringoscopía , Aprendizaje AutomáticoRESUMEN
Driven by regulatory authorities and the ever-growing demands from industry, various artificial tissue models have been developed. Nevertheless, there is no model to date that is capable of mimicking the biomechanical properties of the skin whilst exhibiting the hydrophilicity/hydrophobicity properties of the skin layers. As a proof-of-concept study, tissue surrogates based on gel and silicone are fabricated for the evaluation of microneedle penetration, drug diffusion, photothermal activity, and ultrasound bioimaging. The silicone layer aims to imitate the stratum corneum while the gel layer aims to mimic the water-rich viable epidermis and dermis present in in vivo tissues. The diffusion of drugs across the tissue model is assessed, and the results reveal that the proposed tissue model shows similar behavior to a cancerous kidney. In place of typical in vitro aqueous solutions, this model can also be employed for evaluating the photoactivity of photothermal agents since the tissue model shows a similar heating profile to skin of mice when irradiated with near-infrared laser. In addition, the designed tissue model exhibits promising results for biomedical applications in optical coherence tomography and ultrasound imaging. Such a tissue model paves the way to reduce the use of animals testing in research whilst obviating ethical concerns.
Asunto(s)
Epidermis , Piel , Animales , Ratones , Piel/diagnóstico por imagen , Ultrasonografía/métodos , Siliconas/químicaRESUMEN
Optical Coherence Tomography (OCT) is an optical imaging technology occupying a unique position in the resolution vs. imaging depth spectrum. It is already well established in the field of ophthalmology, and its application in other fields of medicine is growing. This is motivated by the fact that OCT is a real-time sensing technology with high sensitivity to precancerous lesions in epithelial tissues, which can be exploited to provide valuable information to clinicians. In the prospective case of OCT-guided endoscopic laser surgery, these real-time data will be used to assist surgeons in challenging endoscopic procedures in which high-power lasers are used to eradicate diseases. The combination of OCT and laser is expected to enhance the detection of tumors, the identification of tumor margins, and ensure total disease eradication while avoiding damage to healthy tissue and critical anatomical structures. Therefore, OCT-guided endoscopic laser surgery is an important nascent research area. This paper aims to contribute to this field with a comprehensive review of state-of-the-art technologies that may be exploited as the building blocks for achieving such a system. The paper begins with a review of the principles and technical details of endoscopic OCT, highlighting challenges and proposed solutions. Then, once the state of the art of the base imaging technology is outlined, the new OCT-guided endoscopic laser surgery frontier is reviewed. Finally, the paper concludes with a discussion on the constraints, benefits and open challenges associated with this new type of surgical technology.
RESUMEN
Human-induced pluripotent stem cells (hiPSCs) have provided new methods to study neurodegenerative diseases. In addition to their wide application in neuronal disorders, hiPSCs technology can also encompass specific conditions, such as inherited retinal dystrophies. The possibility of evaluating alterations related to retinal disorders in 3D organoids increases the truthfulness of in vitro models. Moreover, both Alzheimer's (AD) and Parkinson's disease (PD) have been described as causing early retinal alterations, generating beta-amyloid protein accumulation, or affecting dopaminergic amacrine cells. This review addresses recent advances and future perspectives obtained from in vitro modeling of retinal diseases, focusing on retinitis pigmentosa (RP). Additionally, we depicted the possibility of evaluating changes related to AD and PD in retinal organoids obtained from potential patients long before the onset of the disease, constituting a valuable tool in early diagnosis. With this, we pointed out prospects in the study of retinal dystrophies and early diagnosis of AD and PD.
Asunto(s)
Enfermedad de Alzheimer , Células Madre Pluripotentes Inducidas , Enfermedad de Parkinson , Retinitis Pigmentosa , Humanos , Células Madre Pluripotentes Inducidas/metabolismo , Enfermedad de Parkinson/diagnóstico , Enfermedad de Parkinson/metabolismo , Enfermedad de Alzheimer/diagnóstico , Enfermedad de Alzheimer/metabolismo , Retinitis Pigmentosa/metabolismo , Organoides , Diagnóstico PrecozRESUMEN
Introduction: Narrow Band Imaging (NBI) is an endoscopic visualization technique useful for upper aero-digestive tract (UADT) cancer detection and margins evaluation. However, NBI analysis is strongly operator-dependent and requires high expertise, thus limiting its wider implementation. Recently, artificial intelligence (AI) has demonstrated potential for applications in UADT videoendoscopy. Among AI methods, deep learning algorithms, and especially convolutional neural networks (CNNs), are particularly suitable for delineating cancers on videoendoscopy. This study is aimed to develop a CNN for automatic semantic segmentation of UADT cancer on endoscopic images. Materials and Methods: A dataset of white light and NBI videoframes of laryngeal squamous cell carcinoma (LSCC) was collected and manually annotated. A novel DL segmentation model (SegMENT) was designed. SegMENT relies on DeepLabV3+ CNN architecture, modified using Xception as a backbone and incorporating ensemble features from other CNNs. The performance of SegMENT was compared to state-of-the-art CNNs (UNet, ResUNet, and DeepLabv3). SegMENT was then validated on two external datasets of NBI images of oropharyngeal (OPSCC) and oral cavity SCC (OSCC) obtained from a previously published study. The impact of in-domain transfer learning through an ensemble technique was evaluated on the external datasets. Results: 219 LSCC patients were retrospectively included in the study. A total of 683 videoframes composed the LSCC dataset, while the external validation cohorts of OPSCC and OCSCC contained 116 and 102 images. On the LSCC dataset, SegMENT outperformed the other DL models, obtaining the following median values: 0.68 intersection over union (IoU), 0.81 dice similarity coefficient (DSC), 0.95 recall, 0.78 precision, 0.97 accuracy. For the OCSCC and OPSCC datasets, results were superior compared to previously published data: the median performance metrics were, respectively, improved as follows: DSC=10.3% and 11.9%, recall=15.0% and 5.1%, precision=17.0% and 14.7%, accuracy=4.1% and 10.3%. Conclusion: SegMENT achieved promising performances, showing that automatic tumor segmentation in endoscopic images is feasible even within the highly heterogeneous and complex UADT environment. SegMENT outperformed the previously published results on the external validation cohorts. The model demonstrated potential for improved detection of early tumors, more precise biopsies, and better selection of resection margins.
RESUMEN
BACKGROUND: The inability of users to directly and intuitively control their state-of-the-art commercial prosthesis contributes to a low device acceptance rate. Since Electromyography (EMG)-based control has the potential to address those inabilities, research has flourished on investigating its incorporation in microprocessor-controlled lower limb prostheses (MLLPs). However, despite the proposed benefits of doing so, there is no clear explanation regarding the absence of a commercial product, in contrast to their upper limb counterparts. OBJECTIVE AND METHODOLOGIES: This manuscript aims to provide a comparative overview of EMG-driven control methods for MLLPs, to identify their prospects and limitations, and to formulate suggestions on future research and development. This is done by systematically reviewing academical studies on EMG MLLPs. In particular, this review is structured by considering four major topics: (1) type of neuro-control, which discusses methods that allow the nervous system to control prosthetic devices through the muscles; (2) type of EMG-driven controllers, which defines the different classes of EMG controllers proposed in the literature; (3) type of neural input and processing, which describes how EMG-driven controllers are implemented; (4) type of performance assessment, which reports the performance of the current state of the art controllers. RESULTS AND CONCLUSIONS: The obtained results show that the lack of quantitative and standardized measures hinders the possibility to analytically compare the performances of different EMG-driven controllers. In relation to this issue, the real efficacy of EMG-driven controllers for MLLPs have yet to be validated. Nevertheless, in anticipation of the development of a standardized approach for validating EMG MLLPs, the literature suggests that combining multiple neuro-controller types has the potential to develop a more seamless and reliable EMG-driven control. This solution has the promise to retain the high performance of the currently employed non-EMG-driven controllers for rhythmic activities such as walking, whilst improving the performance of volitional activities such as task switching or non-repetitive movements. Although EMG-driven controllers suffer from many drawbacks, such as high sensitivity to noise, recent progress in invasive neural interfaces for prosthetic control (bionics) will allow to build a more reliable connection between the user and the MLLPs. Therefore, advancements in powered MLLPs with integrated EMG-driven control have the potential to strongly reduce the effects of psychosomatic conditions and musculoskeletal degenerative pathologies that are currently affecting lower limb amputees.
Asunto(s)
Amputados , Miembros Artificiales , Electromiografía/métodos , Humanos , CaminataRESUMEN
When planning an operation, surgeons usually rely on traditional 2D imaging. Moreover, colon neoplastic lesions are not always easy to locate macroscopically, even during surgery. A 3D virtual model may allow surgeons to localize lesions with more precision and to better visualize the anatomy. In this study, we primary analyzed and discussed the clinical impact of using such 3D models in colorectal surgery. This is a monocentric prospective observational pilot study that includes 14 consecutive patients who presented colorectal lesions with indication for surgical therapy. A staging computed tomography (CT)/magnetic resonance imaging (MRI) scan and a colonoscopy were performed on each patient. The information gained from them was provided to obtain a 3D rendering. The 2D images were shown to the surgeon performing the operation, while the 3D reconstructions were shown to a second surgeon. Both of them had to locate the lesion and describe which procedure they would have performed; we then compared their answers with one another and with the intraoperative and histopathological findings. The lesion localizations based on the 3D models were accurate in 100% of cases, in contrast to conventional 2D CT scans, which could not detect the lesion in two patients (in these cases, lesion localization was based on colonoscopy). The 3D model reconstruction allowed an excellent concordance correlation between the estimated and the actual location of the lesion, allowing the surgeon to correctly plan the procedure with excellent results. Larger clinical studies are certainly required.
RESUMEN
PURPOSE: Complications related to vascular damage such as intra-operative bleeding may be avoided during neurosurgical procedures such as petroclival meningioma surgery. To address this and improve the patient's safety, we designed a real-time blood vessel avoidance strategy that enables operation on deformable tissue during petroclival meningioma surgery using Micron, a handheld surgical robotic tool. METHODS: We integrated real-time intra-operative blood vessel segmentation of brain vasculature using deep learning, with a 3D reconstruction algorithm to obtain the vessel point cloud in real time. We then implemented a virtual-fixture-based strategy that prevented Micron's tooltip from entering a forbidden region around the vessel, thus avoiding damage to it. RESULTS: We achieved a median Dice similarity coefficient of 0.97, 0.86, 0.87 and 0.77 on datasets of phantom blood vessels, petrosal vein, internal carotid artery and superficial vessels, respectively. We conducted trials with deformable clay vessel phantoms, keeping the forbidden region 400 [Formula: see text]m outside and 400 [Formula: see text]m inside the vessel. Micron's tip entered the forbidden region with a median penetration of just 8.84 [Formula: see text]m and 9.63 [Formula: see text]m, compared to 148.74 [Formula: see text]m and 117.17 [Formula: see text]m without our strategy, for the former and latter trials, respectively. CONCLUSION: Real-time control of Micron was achieved at 33.3 fps. We achieved improvements in real-time segmentation of brain vasculature from intra-operative images and showed that our approach works even on non-stationary vessel phantoms. The results suggest that by enabling precise, real-time control, we are one step closer to using Micron in real neurosurgical procedures.
Asunto(s)
Neoplasias Meníngeas , Meningioma , Algoritmos , Humanos , Neoplasias Meníngeas/diagnóstico por imagen , Neoplasias Meníngeas/cirugía , Meningioma/diagnóstico por imagen , Meningioma/cirugía , Procedimientos Neuroquirúrgicos , Fantasmas de ImagenRESUMEN
OBJECTIVES: To assess a new application of artificial intelligence for real-time detection of laryngeal squamous cell carcinoma (LSCC) in both white light (WL) and narrow-band imaging (NBI) videolaryngoscopies based on the You-Only-Look-Once (YOLO) deep learning convolutional neural network (CNN). STUDY DESIGN: Experimental study with retrospective data. METHODS: Recorded videos of LSCC were retrospectively collected from in-office transnasal videoendoscopies and intraoperative rigid endoscopies. LSCC videoframes were extracted for training, validation, and testing of various YOLO models. Different techniques were used to enhance the image analysis: contrast limited adaptive histogram equalization, data augmentation techniques, and test time augmentation (TTA). The best-performing model was used to assess the automatic detection of LSCC in six videolaryngoscopies. RESULTS: Two hundred and nineteen patients were retrospectively enrolled. A total of 624 LSCC videoframes were extracted. The YOLO models were trained after random distribution of images into a training set (82.6%), validation set (8.2%), and testing set (9.2%). Among the various models, the ensemble algorithm (YOLOv5s with YOLOv5m-TTA) achieved the best LSCC detection results, with performance metrics in par with the results reported by other state-of-the-art detection models: 0.66 Precision (positive predicted value), 0.62 Recall (sensitivity), and 0.63 mean Average Precision at 0.5 intersection over union. Tests on the six videolaryngoscopies demonstrated an average computation time per videoframe of 0.026 seconds. Three demonstration videos are provided. CONCLUSION: This study identified a suitable CNN model for LSCC detection in WL and NBI videolaryngoscopies. Detection performances are highly promising. The limited complexity and quick computational times for LSCC detection make this model ideal for real-time processing. LEVEL OF EVIDENCE: 3 Laryngoscope, 132:1798-1806, 2022.
Asunto(s)
Aprendizaje Profundo , Neoplasias Laríngeas , Laringoscopios , Inteligencia Artificial , Humanos , Neoplasias Laríngeas/diagnóstico por imagen , Laringoscopía , Imagen de Banda Estrecha/métodos , Estudios RetrospectivosRESUMEN
Laser microsurgery is the current gold standard surgical technique for the treatment of selected diseases in delicate organs such as the larynx. However, the operations require large surgical expertise and dexterity, and face significant limitations imposed by available technology, such as the requirement for direct line of sight to the surgical field, restricted access, and direct manual control of the surgical instruments. To change this status quo, the European project µRALP pioneered research towards a complete redesign of current laser microsurgery systems, focusing on the development of robotic micro-technologies to enable endoscopic operations. This has fostered awareness and interest in this field, which presents a unique set of needs, requirements and constraints, leading to research and technological developments beyond µRALP and its research consortium. This paper reviews the achievements and key contributions of such research, providing an overview of the current state of the art in robot-assisted endoscopic laser microsurgery. The primary target application considered is phonomicrosurgery, which is a representative use case involving highly challenging microsurgical techniques for the treatment of glottic diseases. The paper starts by presenting the motivations and rationale for endoscopic laser microsurgery, which leads to the introduction of robotics as an enabling technology for improved surgical field accessibility, visualization and management. Then, research goals, achievements, and current state of different technologies that can build-up to an effective robotic system for endoscopic laser microsurgery are presented. This includes research in micro-robotic laser steering, flexible robotic endoscopes, augmented imaging, assistive surgeon-robot interfaces, and cognitive surgical systems. Innovations in each of these areas are shown to provide sizable progress towards more precise, safer and higher quality endoscopic laser microsurgeries. Yet, major impact is really expected from the full integration of such individual contributions into a complete clinical surgical robotic system, as illustrated in the end of this paper with a description of preliminary cadaver trials conducted with the integrated µRALP system. Overall, the contribution of this paper lays in outlining the current state of the art and open challenges in the area of robot-assisted endoscopic laser microsurgery, which has important clinical applications even beyond laryngology.
RESUMEN
INTRODUCTION: Fully convoluted neural networks (FCNN) applied to video-analysis are of particular interest in the field of head and neck oncology, given that endoscopic examination is a crucial step in diagnosis, staging, and follow-up of patients affected by upper aero-digestive tract cancers. The aim of this study was to test FCNN-based methods for semantic segmentation of squamous cell carcinoma (SCC) of the oral cavity (OC) and oropharynx (OP). MATERIALS AND METHODS: Two datasets were retrieved from the institutional registry of a tertiary academic hospital analyzing 34 and 45 NBI endoscopic videos of OC and OP lesions, respectively. The dataset referring to the OC was composed of 110 frames, while 116 frames composed the OP dataset. Three FCNNs (U-Net, U-Net 3, and ResNet) were investigated to segment the neoplastic images. FCNNs performance was evaluated for each tested network and compared to the gold standard, represented by the manual annotation performed by expert clinicians. RESULTS: For FCNN-based segmentation of the OC dataset, the best results in terms of Dice Similarity Coefficient (Dsc) were achieved by ResNet with 5(×2) blocks and 16 filters, with a median value of 0.6559. In FCNN-based segmentation for the OP dataset, the best results in terms of Dsc were achieved by ResNet with 4(×2) blocks and 16 filters, with a median value of 0.7603. All tested FCNNs presented very high values of variance, leading to very low values of minima for all metrics evaluated. CONCLUSIONS: FCNNs have promising potential in the analysis and segmentation of OC and OP video-endoscopic images. All tested FCNN architectures demonstrated satisfying outcomes in terms of diagnostic accuracy. The inference time of the processing networks were particularly short, ranging between 14 and 115 ms, thus showing the possibility for real-time application.
RESUMEN
In the last decades, new technological devices and instruments have been developed to overcome the technical limits of transoral laser microsurgery. The recent introduction of 3D endoscopy seems to be a promising tool in the field of diagnostic and operative laryngology as an alternative to the traditional microlaryngoscopy. Our work aims to present a novel transoral microsurgical setting that expands the use of exoscopic systems (in this case the VITOM® 3D-HD) as an alternative to the standard operating microscope. A customized support arm and an adaptor to firmly connect the VITOM® 3D-HD camera to the laser micromanipulator were specially designed. This setup was used as an alternative to the standard operating microscope in a cohort of 17 patients affected by suspicious early to intermediate pharyngo-laryngeal neoplasms. A historical cohort of patients treated with the traditional setting and matching the same inclusion criteria was used as a reference for the duration of surgical procedures. The surgical procedures comprised 7 cordectomies, 2 endoscopic partial supraglottic laryngectomies, 4 tongue base resections, and 4 lateral oropharyngectomies or hypopharyngectomies. In 6 cases (35%), a simultaneous neck dissection was performed. The low rate of positive deep (6%) or superficial (12%) margins reinforced the safety of this platform, and the results obtained in terms of operating time were comparable to the control group (p > 0.05), which confirms the feasibility of the system. Our surgical setting setup is a convincing alternative to traditional transoral laser microsurgery for early to intermediate pharyngo-laryngeal neoplasms. The main advantages of this system are comfortable ergonomics for the first surgeon and a potential benefit in terms of teaching if applied in university hospitals, since the entire surgical team can view the same surgical 3D-HD view of the first operator. Further work is still needed to objectively compare the traditional and new technique, and to validate our preliminary clinical findings.