RESUMEN
Purpose: To investigate the visualization capabilities of high-speed swept-source optical coherence tomography (SS-OCT) in cataract surgery. Methods: Cataract surgery was simulated in wet labs with ex vivo porcine eyes. Each phase of the surgery was visualized with a novel surgical microscope-integrated SS-OCT with a variable imaging speed of over 1 million A-scans per second. It was designed to provide four-dimensional (4D) live-volumetric videos, live B-scans, and volume capture scans. Results: Four-dimensional videos, B-scans, and volume capture scans of corneal incision, ophthalmic viscosurgical device injection, capsulorrhexis, phacoemulsification, intraocular lens (IOL) injection, and position of unfolded IOL in the capsular bag were recorded. The flexibility of the SS-OCT system allowed us to tailor the scanning parameters to meet the specific demands of dynamic surgical steps and static pauses. The entire length of the eye was recorded in a single scan, and unfolding of the IOL was visualized dynamically. Conclusions: The presented novel visualization method for fast ophthalmic surgical microscope-integrated intraoperative OCT imaging in cataract surgery allowed the visualization of all major steps of the procedure by achieving large imaging depths covering the entire eye and high acquisition speeds enabling live volumetric 4D-OCT imaging. This promising technology may become an integral part of routine and advanced robotic-assisted cataract surgery in the future. Translational Relevance: We demonstrate the visualization capabilities of a cutting edge swept-source OCT system integrated into an ophthalmic surgical microscope during cataract surgery.
Asunto(s)
Catarata , Lentes Intraoculares , Oftalmología , Porcinos , Animales , Tomografía de Coherencia Óptica , OjoRESUMEN
Diabetic retinopathy (DR), a pathologic change of the human retinal vasculature, is the leading cause of blindness in working-age adults with diabetes mellitus. Optical coherence tomography angiography (OCTA), a functional extension of optical coherence tomography, has shown potential as a tool for early diagnosis of DR through its ability to visualize the retinal vasculature in all spatial dimensions. Previously introduced deep learning-based classifiers were able to support the detection of DR in OCTA images, but require expert labeling at the pixel level, a labor-intensive and expensive process. We present a multiple instance learning-based network, MIL-ResNet,14 that is capable of detecting biomarkers in an OCTA dataset with high accuracy, without the need for annotations other than the information whether a scan is from a diabetic patient or not. The dataset we used for this study was acquired with a diagnostic ultra-widefield swept-source OCT device with a MHz A-scan rate. We were able to show that our proposed method outperforms previous state-of-the-art networks for this classification task, ResNet14 and VGG16. In addition, our network pays special attention to clinically relevant biomarkers and is robust against adversarial attacks. Therefore, we believe that it could serve as a powerful diagnostic decision support tool for clinical ophthalmic screening.
Asunto(s)
Diabetes Mellitus , Retinopatía Diabética , Adulto , Humanos , Retinopatía Diabética/diagnóstico por imagen , Retinopatía Diabética/patología , Angiografía con Fluoresceína/métodos , Tomografía de Coherencia Óptica/métodos , Vasos Retinianos/patología , Diagnóstico Precoz , Diabetes Mellitus/patologíaRESUMEN
By providing three-dimensional visualization of tissues and instruments at high resolution, live volumetric optical coherence tomography (4D-OCT) has the potential to revolutionize ophthalmic surgery. However, the necessary imaging speed is accompanied by increased noise levels. A high data rate and the requirement for minimal latency impose major limitations for real-time noise reduction. In this work, we propose a low complexity neural network for denoising, directly incorporated into the image reconstruction pipeline of a microscope-integrated 4D-OCT prototype with an A-scan rate of 1.2 MHz. For this purpose, we trained a blind-spot network on unpaired OCT images using a self-supervised learning approach. With an optimized U-Net, only a few milliseconds of additional latency were introduced. Simultaneously, these architectural adaptations improved the numerical denoising performance compared to the basic setup, outperforming non-local filtering algorithms. Layers and edges of anatomical structures in B-scans were better preserved than with Gaussian filtering despite comparable processing time. By comparing scenes with and without denoising employed, we show that neural networks can be used to improve visual appearance of volumetric renderings in real time. Enhancing the rendering quality is an important step for the clinical acceptance and translation of 4D-OCT as an intra-surgical guidance tool.
Asunto(s)
Aprendizaje Profundo , Redes Neurales de la Computación , Procesamiento de Imagen Asistido por Computador/métodos , Algoritmos , Tomografía de Coherencia Óptica/métodos , Relación Señal-RuidoRESUMEN
Intraoperative optical coherence tomography is still not overly pervasive in routine ophthalmic surgery, despite evident clinical benefits. That is because today's spectral-domain optical coherence tomography systems lack flexibility, acquisition speed, and imaging depth. We present to the best of our knowledge the most flexible swept-source optical coherence tomography (SS-OCT) engine coupled to an ophthalmic surgical microscope that operates at MHz A-scan rates. We use a MEMS tunable VCSEL to implement application-specific imaging modes, enabling diagnostic and documentary capture scans, live B-scan visualizations, and real-time 4D-OCT renderings. The technical design and implementation of the SS-OCT engine, as well as the reconstruction and rendering platform, are presented. All imaging modes are evaluated in surgical mock maneuvers using ex vivo bovine and porcine eye models. The applicability and limitations of MHz SS-OCT as a visualization tool for ophthalmic surgery are discussed.
RESUMEN
PURPOSE: To evaluate the thickness of the intraoperative layers of 10 different ophthalmic viscosurgical devices (OVD) covering the corneal endothelium during simulated lens surgery in a porcine model. METHODS: This experimental study took place at the Center for Medical Physics and Biomedical Engineering, Medical University of Vienna, Austria. Ten OVDs with different viscoelastic properties (ProVisc, Z-Hyalin plus, Amvisc plus, DisCoVisc, Healon EndoCoat, Viscoat, Z-Hyalcoat, Combivisc, Duo-Visc, and Twinvisc) were assessed in 10 porcine eyes each, yielding a total of 100 eyes. Simulated cataract surgery was performed with volumetric intraoperative OCT imaging during phacoemulsification and during irrigation/aspiration to determine the remaining amount of OVD coating the endothelium over a scan field of 6 × 6 mm. Indirect visualization of the OVD was enabled by replacing the irrigating solution by a higher scattering diluted milk solution. A deep convolutional neural network (CNN) was used to evaluate OVD layer thickness based on the B-scans. RESULTS: Median thickness values after phacoemulsification were lowest for the cohesive OVDs Z-Hyalin plus (38 µm) and ProVisc (39 µm), followed by the combination systems Twinvisc (342 µm) and Duo-Visc (537 µm). Highest values were observed for the dispersive OVDs and the combination system Combivisc (Viscoat: 957 µm; Z-Hyalcoat: 988 µm, Combivisc: 1042 µm; Amvisc plus: 1259 µm; Healon EndoCoat: 1303 µm; DisCoVisc: 1356 µm). The difference between the OVDs was statistically significant (P < 0.01). CONCLUSIONS: The results of this study confirm that at completion of phacoemulsification, thickest residual layers of OVD remain when using dispersive substances, followed by combination systems and lowest thickness values were observed with cohesive OVDs. The use of an intraoperative OCT and a deep convolutional neural network allowed measurements over a large scan field of 6 × 6 mm and a precise evaluation of the OVD layer coating the corneal endothelium. The OVD layer seemed to be more like a ragged terrain instead of a flat layer, indicating that the film-forming effect of dispersive OVDs is the result of their volume rheology rather than a surface interaction. TRANSLATIONAL RELEVANCE: Evaluating the protective properties provides valuable insights into how different OVDs with different viscoelastic properties form layers beneath the corneal endothelium and helps to understand their persistence during the various steps of cataract surgeries.