Optical Coherence Tomography Technology Research Articles

Fourier-Domain OCT Imaging of the Ocular Surface and Tear Film Dynamics: A Review of the State of the Art and an Integrative Model of the Tear Behavior During the Inter-Blink Period and Visual Fixation.

In the last few decades, the ocular surface and the tear film have been noninvasively investigated in vivo, in a three-dimensional, high resolution, and real-time mode, by optical coherence tomography (OCT). Recently, OCT technology has made great strides in improving the acquisition speed and image resolution, thus increasing its impact in daily clinical practice and in the research setting. All these results have been achieved because of a transition from traditional time-domain (TD) to Fourier-domain (FD) technology. FD-OCT devices include a spectrometer in the receiver that analyzes the spectrum of reflected light on the retina or ocular surface and transforms it into information about the depth of the structures according to the Fourier principle. In this review, we summarize and provide the state-of-the-art in FD-OCT imaging of the ocular surface system, addressing specific aspects such as tear film dynamics and epithelial changes under physiologic and pathologic conditions. A theory on the dynamic nature of the tear film has been developed to explain the variations within the individual compartments. Moreover, an integrative model of tear film behavior during the inter-blink period and visual fixation is proposed.

Choroidal Vascularity Index: An In-Depth Analysis of This Novel Optical Coherence Tomography Parameter.

Remarkable improvements in optical coherence tomography (OCT) technology have resulted in highly sophisticated, noninvasive machines allowing detailed and advanced morphological evaluation of all retinal and choroidal layers. Postproduction semiautomated imaging analysis with dedicated public-domain software allows precise quantitative analysis of binarized OCT images. In this regard, the choroidal vascularity index (CVI) is emerging as a new imaging tool for the measurement and analysis of the choroidal vascular system by quantifying both luminal and stromal choroidal components. Numerous reports have been published so far regarding CVI and its potential applications in healthy eyes as well as in the evaluation and management of several chorioretinal diseases. Current literature suggests that CVI has a lesser variability and is influenced by fewer physiologic factors as compared to choroidal thickness. It can be considered a relatively stable parameter for evaluating the changes in the choroidal vasculature. In this review, the principles and the applications of this advanced imaging modality for studying and understanding the contributing role of choroid in retinal and optic nerve diseases are discussed. Potential advances that may allow the widespread adoption of this tool in the routine clinical practice are also presented.

Impact of manual correction over automated segmentation of spectral domain optical coherence tomography

ObjectiveTo study the automated segmentation of retinal layers using spectral domain optical coherence tomography (OCT) and the impact of manual correction over segmentation mistakes.MethodsThis was a retrospective, cross-sectional, comparative study that compared the automated segmentation of macular thickness using Spectralis™ OCT technology (Heidelberg Engineering, Heidelberg, Germany) versus manual segmentation in eyes with no macular changes, macular cystoid edema (CME), and choroidal neovascularization (CNV). Automated segmentation of macular thickness was manually corrected by two independent examiners and reanalyzed by them together in case of disagreement.ResultsIn total, 306 eyes of 254 consecutive patients were evaluated. No statistically significant differences were noted between automated and manual macular thickness measurements in patients with normal maculas, while a statistically significant difference was found in central thickness in patients with CNV and with CME. Segmentation mistakes in macular OCTs were present in 5.3% (5 of 95) in the normal macula group, 16.4% (23 of 140) in the CME group, and 66.2% (47 of 71) in CNV group. The difference between automated and manual macular thickness was higher than 10% in 1.4% (2 of 140) in the CME group and in 28.17% (20 of 71) in the CNV group. Only one case in the normal group had a higher than 10% segmentation error (1 of 95).ConclusionThe evaluation of automated segmented OCT images revealed appropriate delimitation of macular thickness in patients with no macular changes or with CME, since the frequency and magnitude of the segmentation mistakes had low impact over clinical evaluation of the images. Conversely, automated macular thickness segmentation in patients with CNV showed a high frequency and magnitude of mistakes, with potential impact on clinical analysis.

Evaluation of choroidal thickness and choroidal vascular blood flow in patients with thyroid-associated orbitopathy (TAO) using SD-OCT and Angio-OCT.

The aim of this study was to evaluate changes in choroidal thickness and in choroidal vascular blood flow in patients with thyroid-associated orbitopathy (TAO) and their relationship with clinical features and disease activity using spectral domain optical coherence tomography (SD-OCT) and Angio-OCT technology. Eighteen patients and control subjects underwent a complete eye examination, OCT, and Angio-OCT. We also obtained angiographic scans at 3 different consecutive levels (L1, L2, and L3) below the choriocapillary. The subfoveal choroid was significantly thicker in TAO patients than the control eyes (285.6275 ± 32.5μm compared with 135.89 ± 19.8μm, respectively, p= 0.0089). The correlation analysis in the TAO group showed a significant correlation between the choroidal thickness and EUGOGO clinical score (r= 0.84, p= 8.44032E-07). Vascular flow of choriocapillary was markedly reduced in subjects with TAO compared with healthy subjects (49.78 ± 4.5 vs. 53.36 ± 1.07; p= 2.5105E-07) and vascular flow of the deeper layer L3 resulted higher in subjects with TAO than in healthy subjects (46.9 ± 20.23 and 41.475 ± 3.06; p= 0.01168). Subfoveal choroidal thickness and choroidal blood flow were significantly different in patients with TAO compared with healthy subjects.

Choroidal thickness is associated with renal hemodynamics in essential hypertension.

The choroid is the most vascularized structure of the eye and plays a central role in the development of the retinal vascular changes that occur in arterial hypertension. Changes of choroidal thickness (ChT) assessed by optical coherence tomography (OCT) technology could reflect the vascular complications of hypertension. Also, intrarenal hemodynamic damage, associated with endothelial dysfunction, demonstrated to be a good indicator of systemic morphofunctional arterial impairment. The aim of this study is to assess the relationship between ChT and renal hemodynamics in subjects with essential hypertension. Routine laboratory tests, clinical history, and physical examination, including blood pressure assessment, were performed in 90 subjects with essential hypertension. All patients underwent Doppler ultrasonographic evaluation of intra-renal hemodynamics and OCT imaging to assess ChT. When subjects were divided in two groups based on renal resistive index (RRI), group I (RRI≥75% percentile) showed significantly lower values of ChT than group II (RRI<75% percentile) (P<.001). When divided in two groups based on the ChT median values, patients with lower ChT had significantly higher RRI values than those with ChT above the median values (P<.05). In multivariate model including age, eGFR, and other variables as confounding factors, RRI≥75% was independently associated with ChT. ChT was significantly correlated with renal resistive index in subjects with essential hypertension, confirmed in multivariate analyses. This result could be referred to changes in vascular elastic properties that occur in retinal and intrarenal vascular system probably due to oxidative stress and endothelial dysfunction commonly found in early complications of hypertension.

The use of optical coherence tomography and convolutional neural networks to distinguish normal and abnormal oral mucosa.

Incomplete surgical resection of head and neck squamous cell carcinoma (HNSCC) is the most common cause of local HNSCC recurrence. Currently, surgeons rely on preoperative imaging, direct visualization, palpation and frozen section to determine the extent of tissue resection. It has been demonstrated that optical coherence tomography (OCT), a minimally invasive, nonionizing near infrared mesoscopic imaging modality can resolve subsurface differences between normal and abnormal head and neck mucosa. Previous work has utilized two-dimensional OCT imaging which is limited to the evaluation of small regions of interest generated frame by frame. OCT technology is capable of performing rapid volumetric imaging, but the capacity and expertise to analyze this massive amount of image data is lacking. In this study, we evaluate the ability of a retrained convolutional neural network to classify three-dimensional OCT images of head and neck mucosa to differentiate normal and abnormal tissues with sensitivity and specificity of 100% and 70%, respectively. This method has the potential to serve as a real-time analytic tool in the assessment of surgical margins.

Exploring choroidal angioarchitecture in health and disease using choroidal vascularity index.

The choroid is one of the most vascularized structures of the human body and plays an irreplaceable role in nourishing photoreceptors. As such, choroidal dysfunction is implicated in a multitude of ocular diseases. Studying the choroid can lead to a better understanding of disease pathogenesis, progression and discovery of novel management strategies. However, current research has produced inconsistent findings, partly due to the physical inaccessibility of the choroid and the lack of reliable biomarkers. With the advancements in optical coherence tomography technology, our group has developed a novel quantitative imaging biomarker known as the choroidal vascularity index (CVI), defined as the ratio of vascular area to the total choroidal area. CVI is a potential tool in establishing early diagnoses, monitoring disease progression and prognosticating patients. CVI has been reported in existing literature as a robust marker in numerous retinal and choroidal diseases. In this review, we will discuss the current role of CVI with reference to existing literature, and make postulations about its potential and future applications.

Retinal correlates of psychiatric disorders.

Diagnosis and monitoring of psychiatric disorders rely heavily on subjective self-reports of clinical symptoms, which are complicated by the varying consistency of accounts reported by patients with an impaired mental state. Hence, more objective and quantifiable measures have been sought to provide clinicians with more robust methods to evaluate symptomology and track progression of disease in response to treatments. Owing to the shared origins of the retina and the brain, it has been suggested that changes in the retina may correlate with structural and functional changes in the brain. Vast improvements in retinal imaging, namely optical coherence tomography (OCT) and electrodiagnostic technology, have made it possible to investigate the eye at a microscopic level, allowing for the investigation of potential biomarkers in vivo. This review provides a summary of retinal biomarkers associated with schizophrenia, bipolar disorder and major depression, demonstrating how retinal biomarkers may be used to complement existing methods and provide structural markers of pathophysiological mechanisms that underpin brain dysfunction in psychiatric disorders.

Editors' note: Optical coherence tomography for diagnosing optic neuritis: Are we there yet?

In the editorial “Optical coherence tomography for diagnosing optic neuritis: Are we there yet?,” Drs. Saidha and Naismith discussed the potential application of optical coherence tomography (OCT) in providing objective support for previous optic neuritis (ON) and in highlighting the research article by Drs. Xu et al. entitled “Optical coherence tomography is highly sensitive in detecting prior optic neuritis.” In a reader response, Dr. Avasarala highlights several potential issues hindering the use of OCT in this context, including the cost of OCT hardware, continually changing algorithms for retinal segmentation, and the paucity of data on OCT's performance relative to pattern shift visual evoked responses (VEPs), a relatively older test. He also notes that an earlier publication by Naismith et al. found that OCT was less sensitive than VEP in detecting subclinical previous ON. Replying to these comments, Drs. Saidha and Naismith note that this previous study used older third-generation time domain OCT and that current fourth-generation spectral domain OCT has a much higher resolution. They cite the excellent reliability and reproducibility of key OCT measures and note that they provide useful information about the global multiple sclerosis disease process. They also argue that OCT and VEP are better viewed as complementary measures of structure and function, respectively. This is especially true because VEP has its limitations too, including distinguishing inner retinal processes from optic nerve ones. Drs. Saidha and Naismith also speculate that the use of OCT in diagnosing acute ON may also become more apparent, given the frequent thickening of the retinal nerve fiber layer during acute ON. As OCT technology continues to evolve, its clinical applications are likely to be further clarified and expanded in the coming years. In the editorial “Optical coherence tomography for diagnosing optic neuritis: Are we there yet?,” Drs. Saidha and Naismith discussed the potential application of optical coherence tomography (OCT) in providing objective support for previous optic neuritis (ON) and in highlighting the research article by Drs. Xu et al. entitled “Optical coherence tomography is highly sensitive in detecting prior optic neuritis.” In a reader response, Dr. Avasarala highlights several potential issues hindering the use of OCT in this context, including the cost of OCT hardware, continually changing algorithms for retinal segmentation, and the paucity of data on OCT's performance relative to pattern shift visual evoked responses (VEPs), a relatively older test. He also notes that an earlier publication by Naismith et al. found that OCT was less sensitive than VEP in detecting subclinical previous ON. Replying to these comments, Drs. Saidha and Naismith note that this previous study used older third-generation time domain OCT and that current fourth-generation spectral domain OCT has a much higher resolution. They cite the excellent reliability and reproducibility of key OCT measures and note that they provide useful information about the global multiple sclerosis disease process. They also argue that OCT and VEP are better viewed as complementary measures of structure and function, respectively. This is especially true because VEP has its limitations too, including distinguishing inner retinal processes from optic nerve ones. Drs. Saidha and Naismith also speculate that the use of OCT in diagnosing acute ON may also become more apparent, given the frequent thickening of the retinal nerve fiber layer during acute ON. As OCT technology continues to evolve, its clinical applications are likely to be further clarified and expanded in the coming years.

OCT and OCT‐A based management of AMD. Present indications for the use of fluorescein angiography

AbstractLate stage age‐related macular degeneration (AMD) has been described as the leading cause of blindness in industrialized countries. Neovascular AMD (nAMD) is characterized by the growth of abnormal blood vessels from the choroid through the Bruch’s membrane (CNV). Fluorescein angiography (FA) is historically considered the gold standard in the diagnosis and classification of CNV while indocyanine green angiography (ICGA) can be used to identify the entire extent of the CNV lesion.Once the diagnosis of CNV is established, the effect of anti‐VEGF therapy is efficiently monitored with non‐invasive Optical Coherence Tomography (OCT). So nowadays clinical practice mostly relies on structural OCT biomarkers of activity. However, conventional OCT devices do not allow direct visualization of the neovascular network and neovascular activity is inferred through indirect signs such as intraretinal fluid, subretinal fluid or pigment epithelial detachments. OCT‐angiography (OCT‐A) is the most recent advance of OCT technology and provides high resolution images of retinal and choroidal vasculature. It can CNV with the same sensitivity as contrast angiography and enables to evaluate morphological characteristics of neovascular networks. Previous works have demonstrated consistent qualitative features associated with exudation on structural OCT. For instance, exudative lesions were associated with a greater rate of small vessels branching and peripheral arcades and non‐exudative lesions with a dead‐tree appearance. On an attempt to eliminate subjectivity of qualitative evaluation, there has been a crescent effort to obtain quantitative features on neovascular networks, and the study of novel imaging biomarkers for nAMD disease activity has become a hot topic in research. The aim of this conference is to evaluate the current indications for FA use in nAMD and to provide an update on subjective and objective OCTA biomarkers in daily clinical practice.

AOCT-NET: a convolutional network automated classification of multiclass retinal diseases using spectral-domain optical coherence tomography images.

Since introducing optical coherence tomography (OCT) technology for 2D eye imaging, it has become one of the most important and widely used imaging modalities for the noninvasive assessment of retinal eye diseases. Age-related macular degeneration (AMD) and diabetic macular edema eye disease are the leading causes of blindness being diagnosed using OCT. Recently, by developing machine learning and deep learning techniques, the classification of eye retina diseases using OCT images has become quite a challenge. In this paper, a novel automated convolutional neural network (CNN) architecture for a multiclass classification system based on spectral-domain optical coherence tomography (SD-OCT) has been proposed. The system used to classify five types of retinal diseases (age-related macular degeneration (AMD), choroidal neovascularization (CNV), diabetic macular edema (DME), and drusen) in addition to normal cases. The proposed CNN architecture with a softmax classifier overall correctly identified 100% of cases with AMD, 98.86% of cases with CNV, 99.17% cases with DME, 98.97% cases with drusen, and 99.15% cases of normal with an overall accuracy of 95.30%. This architecture is a potentially impactful tool for the diagnosis of retinal diseases using SD-OCT images.

Elucidating the fouling mechanism in pharmaceutical wastewater treatment by membrane distillation

This study investigated the fouling mechanism in pharmaceutical wastewater treatment by membrane distillation, with a focus on the interfacial electrokinetic effect between the membrane and foulants as well as the surface hydrophobicity effect, and an advanced in-situ optical coherence tomography (OCT) technology. Three antibiotics with different surface charges were used as feed solutions, consisting of cefotaxime (CTX, negatively charged), tobramycin (TOB, positively charged) and ciprofloxacin (CFX, neutral) for studying the interfacial electrokinetic effect. In order to study the influence of membrane hydrophobicity on the fouling process, two commercial membranes with different hydrophobicity were employed; commercial polyvinylidene fluoride (C-PVDF) and commercial polytetrafluoroethylene (C-PTFE). Additionally, we also fabricated a fouling resistant polyvinylidene fluoride (PVDF) membrane coated with perfluorooctyltriethoxysilane (FTES)-TiO2 nanoparticles to engineer the surface charge and energy, and to achieve a superhydrophobic surface. After the MD operation, OCT scans detected no visible foulant layer on the three negatively charged membranes when treating negatively charged CTX. On the other hand, in the case of positively charged TOB, the rejection efficiency was only 78% due to its accumulation behavior on the C-PVDF membrane surface, with a thick foulant layer (326–408 μm) and blockage of pores, while the TiO2-PVDF membrane exhibited a stable performance.

Особенности витреолентикулярного интерфейса артифакичного глаза

Replacing the native lens with an intraocular lens (IOL) causes anatomical and topographic changes in the anterior segment of the eye. The optical coherence tomography (OCT) technology allows to study the features of the postoperative transformation of the capsular bag and the vitreolenticular interface. Purpose. To study the features of the vitreolenticular interface after the standard lens surgery with IOL implantation. Material and methods. This work was based on the OCT study of 66 patients (86 eyes), aged 22 to 94 years with pseudophakia after the standard phacoemulsification of age-related cataracts (81 cases) or refractive lens replacement (5 cases) with intracapsular implantation of different hydrophobic flexible IOL designs. The OCT analysis of pseudophakic eye features was performed in the early and late postoperative period. Results. Statistically significant changes were revealed: an increase in the anterior chamber depth, a decrease in the «lens thickness» from 4.46±0.53 mm (native lens) up to 0.71±0.18 mm (IOL) and a shift of the posterior capsule forward along the optical axis by 2.26±0.34 mm. A large variability in the configuration of the vitreolenticular interface in the early and late postoperative period was noted. An analysis of the relationships features of the IOL, posterior capsule and the anterior hyaloid membrane allowed to identify some patterns of postoperative transformation of the vitreolenticular interface. Conclusion. Significant anatomical and topographic changes after lens surgery were revealed: a deepening of the anterior chamber, a decrease in the «lens thickness», a forward shift in the position of the posterior lens capsule. Several variants of dynamic transformation of the vitreolenticular interface were detected in the early postoperative period with subsequent outcomes in three types of stable configuration, reflecting the degree of involution of the structures and their tolerance to surgical trauma.

Optical coherence tomography in the diagnosis and follow-up of eye diseases in childhood - a review

After its development approximately 20 years ago, optical coherence tomography (OCT) has taken an important part in the scientific and clinical work of the ophthalmologist and continues to develop. Using OCT technology in every day practice helps the eye doctors to make clinical diagnoses and follow-up of socially significant diseases like glaucoma, degenerative retinal diseases, and pathology of the macula and optic nerve head, which could be responsible for irreversible decrease or loss of central and/or peripheral vision. Because of the above-mentioned, we aimed to summarize the diagnostic and follow-up possibilities of OCT as an imaging technique for childhood eye diseases. Since this technology was initially developed to be used in adults, its use in children is limited to some extent. This could be explained basically with the inapplicability of stationary OCT devices in all children and the absence of normative database for those under 18 years of age. During the last decade, specially developed portable devices for children have been developed. By their use investigating and diagnosing of eye pathology is possible in very early age, and this allows subsequent adequate therapy and prevents from a life with disability.

Update on the usefulness of optical coherence tomography in assessing the iridocorneal angle

The iridocorneal angle, due to its implications in the physiopathology of aqueous humour drainage, is a fundamental structure of the anterior chamber. Anterior segment optical coherence tomography is a rapid and non-invasive technique that obtains images in vivo. The high resolution allows it to analyse the normal anatomy of the angle, any alterations, and the changes that occur after different therapeutic interventions. Anterior segment optical coherence tomography technology has evolved to provide images that allow the identification and quantification of the angular structures in healthy subjects and in glaucoma patients, and especially the trabecular meshwork and the Schlemm's canal. It also enables the angle width to be quantified, with some objective parameters that have been standardised in recent years, such as the trabecular-iris angle, the angle opening distance, and the trabecular-iris area. This technique has multiple uses in the study of the different mechanisms of angle closure, the evaluation of changes after a laser peripheral iridotomy or iridoplasty after cataract surgery, as well as after the implantation of phakic lenses.

Structural and Functional Sensing of Bio-Tissues Based on Compressive Sensing Spectral Domain Optical Coherence Tomography.

In this paper, a full depth 2D CS-SDOCT approach is proposed, which combines two-dimensional (2D) compressive sensing spectral-domain optical coherence tomography (CS-SDOCT) and dispersion encoding (ED) technologies, and its applications in structural imaging and functional sensing of bio-tissues are studied. Specifically, by introducing a large dispersion mismatch between the reference arm and sample arm in SD-OCT system, the reconstruction of the under-sampled A-scan data and the removal of the conjugated images can be achieved simultaneously by only two iterations. The under-sampled B-scan data is then reconstructed using the classic CS reconstruction algorithm. For a 5 mm × 3.2 mm fish-eye image, the conjugated image was reduced by 31.4 dB using 50% × 50% sampled data (250 depth scans and 480 spectral sampling points per depth scan), and all A-scan data was reconstructed in only 1.2 s. In addition, we analyze the application performance of the CS-SDOCT in functional sensing of locally homogeneous tissue. Simulation and experimental results show that this method can correctly reconstruct the extinction coefficient spectrum under reasonable iteration times. When 8 iterations were used to reconstruct the A-scan data in the imaging experiment of fisheye, the extinction coefficient spectrum calculated using 50% × 50% data was approximately consistent with that obtained with 100% data.

Understanding diagnostic disagreement in angle closure assessment between anterior segment optical coherence tomography and gonioscopy

Background/aimsAlthough being a more objective tool for assessment and follow-up of angle closure, reliability studies have reported a moderate diagnostic performance for anterior segment optical coherence tomography (OCT) technologies when...

Anterior Segment Optical Coherence Tomography: Is There a Clinical Role in the Management of Primary Angle Closure Disease?

Primary angle closure disease (PACD) covers a spectrum that includes primary angle closure suspect, primary angle closure, primary angle closure glaucoma, and acute primary angle closure. Accumulating evidence suggests that the pathogenesis of PACD is complex, with multiple contributory factors including variations in the anatomic or biometric characteristics of the angle segment structures. Advances in anterior segment optical coherence tomography technology have further enhanced our understanding of the risk factors and mechanisms involved in the disease process. This review discusses the potential clinical role of the anterior segment optical coherence tomography in the diagnosis, mechanistic evaluation, and as a predictor for future clinical outcomes of patients with PACD.

Abstract 3722: Novel Optical Coherence Tomography (OCT) technology for no-invasive 3D ex vivo drug activity profiling

Abstract Drug discovery and early to late drug development process have relied on 2D monolayer based in vitro assay platforms and small animal models. The limitations posed by 2D in vitro assays for evaluation of targeted and immunomodulatory agents have prompted researchers to develop novel 3D in vitro and ex vivo platforms utilizing the tumor microenvironment like conditions for better understanding of mechanisms of novel targeted and immunomodulatory drug/compound entities. Therefore, rapid development of robust 3D ex vivo cell culture as drug efficacy testing system for drug discovery, development and profiling of standard of care and Immunotherapeutic molecules have led to understanding the relevance of these platforms within the scientific and clinical community. 3D ex vivo platforms are being diligently evaluated as better predictive drug efficacy testing tools in preclinical as well as clinical space in the quest for profiling of novel anticancer entities (as single or two drug combinations). Within this context, there has been growing need in improved imaging and analysis of complex 3D structures (Multicellular tumor spheroids/Organoids) containing multiple cellular components such as, Tumor cells, stromal cells, various immune cells to monitor signaling pathways and assess immune events including T cell infiltration as drug efficacy measurement. At SCREEN LifeScience, we have developed a novel OCT based technology for imaging and analysis of complex 3D structures, such as, spheroid /organoid for growth &amp; morphological profiling, quantification of internal cavities, drug sensitivity testing to capture the events leading to tumor cell death and assessing mechanism of drug action. Additionally, this technology allows us perform large tissue imaging, non-invasive monitoring of macro and sprouted neo-vasculature without the need for fluorescent staining for providing quantitative information about the vascular morphological changes, thereby allowing for the evaluation of anti-angiogenic drugs in real time. In summary, the OCT technology shown to be robust and versatile technology useful for studying multiple disease models, including cancer. Its utility in regeneration medicine is being further evaluated as a versatile non-invasive platform. Citation Format: Sumeer Dhar, Akihiro Ueda, Takemitsu Muira, Yasushi Kuromi, Yuki Mori, Hiroki Fujimoto. Novel Optical Coherence Tomography (OCT) technology for no-invasive 3D ex vivo drug activity profiling [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2019; 2019 Mar 29-Apr 3; Atlanta, GA. Philadelphia (PA): AACR; Cancer Res 2019;79(13 Suppl):Abstract nr 3722.

Using Convolutional Neural Networks for Classification of Bifurcation Regions in IVOCT Images.

Optical Coherence Tomography (OCT) technology enabled the experts to analyze coronary lesions from high-resolution intravascular images. Studies have shown the relationship between bifurcation regions and a higher occurrence of wall thickening and lesions in these areas. Some level of automation could benefit experts, since examining pullback frames is a laborious and time-consuming task. Although Convolutional Neural Networks (CNN) have shown promising results in classification tasks of medical images, we did not identify the use of CNN's in IVOCT images to classify bifurcation regions in the literature. In this work, we evaluated a CNN architecture in the bifurcation classification task trained with IVOCT images from 9 pullbacks from 9 different patients. We used data augmentation to balance the dataset, due to the low amount of bifurcation-labeled frames. Our classification results are comparable to other works in the literature, presenting better result in AUC (99.70%).