Automatic identification of parathyroid in optical coherence tomography images

Classification of neck tissues in OCT images by using convolutional neural network

Identification and classification of surrounding neck tissues are very important in thyroid surgery. The advantages of optical coherence tomography (OCT), high resolution, non-invasion, and non-destruction make it have great potential in identifying different neck tissues during thyroidectomy. We studied the automatic classification for neck tissues in OCT images based on convolutional neural network in this paper. OCT images of five kinds of neck tissues were collected firstly by our home-made swept source (SS-OCT) system, and a dataset was built for neural network training. Three image classification neural networks: LeNet, VGGNet, and ResNet, were used to train and test the dataset. The impact of transfer learning on the classification of neck tissue OCT images was also studied. Through the comparison of accuracy, it was found that ResNet has the best classification accuracy among the three networks. In addition, transfer learning did not significantly improve the accuracy, but it can somewhat accelerate the convergence of the network and shorten the network training time.

Digital refocusing based on deep learning in optical coherence tomography

We present a deep learning-based digital refocusing approach to extend depth of focus for optical coherence tomography (OCT) in this paper. We built pixel-level registered pairs of en face low-resolution (LR) and high-resolution (HR) OCT images based on experimental data and introduced the receptive field block into the generative adversarial networks to learn the complex mapping relationship between LR-HR image pairs. It was demonstrated by results of phantom and biological samples that the lateral resolutions of OCT images were improved in a large imaging depth clearly. We firmly believe deep learning methods have broad prospects in optimizing OCT imaging.

Colorectal cancer: Artificial intelligence and its role in surgical decision making

Despite several advances in the oncological management of colorectal cancer (CRC), there still remains a lacuna in the treatment strategy, which differs from center to center and on the philosophy of the treating clinician that is not without bias. Personalized treatment is essential for the treatment of CRC to achieve better long-term outcomes and to reduce morbidity. Surgery has an important role to play in the treatment. Surgical treatment of CRC is decided based on clinical parameters and investigations and hence likely to have judgmental errors. Artificial intelligence has been reported to be useful in the surveillance, diagnosis, treatment, and follow-up with accuracy in several malignancies. However, it is still evolving and yet to be established in surgical decision making in CRC. It is not only useful preoperatively but also intraoperatively. Artificial intelligence helps to rectify the human surgical decision when clinical data and radiological and laboratory parameters are fed into the computer and may guide correct surgical treatment.

Artificial intelligence-augmented, label-free molecular imaging method for tissue identification, cancer diagnosis, and cancer margin detection

Label-free high-resolution molecular and cellular imaging strategies for intraoperative use are much needed, but not yet available. To fill this void, we developed an artificial intelligence-augmented molecular vibrational imaging method that integrates label-free and subcellular-resolution coherent anti-stokes Raman scattering (CARS) imaging with real-time quantitative image analysis via deep learning (artificial intelligence-augmented CARS or iCARS). The aim of this study was to evaluate the capability of the iCARS system to identify and differentiate the parathyroid gland and recurrent laryngeal nerve (RLN) from surrounding tissues and detect cancer margins. This goal was successfully met.

Classification of oral salivary gland tumors based on texture features in optical coherence tomography images

Currently, the diagnoses of oral diseases primarily depend on the visual recognition of experienced clinicians. It has been proven that automatic recognition based on images can support clinical decision-making by extracting and analyzing objective hidden information. In recent years, optical coherence tomography (OCT) has become a powerful optical imaging technique with the advantages of high resolution and non-invasion. In our study, a dataset composed of four kinds of oral salivary gland tumors (SGTs) was obtained from a homemade swept-source OCT, including two benign and two malignant tumors. Seventy-six texture features were extracted from OCT images to create computational models of diseases. It was demonstrated that the artificial neural network (ANN) based on principal component analysis (PCA) can obtain high diagnostic sensitivity and specificity (higher than 99%) for these four kinds of tumors. The classification accuracy of each tumor is larger than 99%. In addition, the performances of two classifiers (ANN and support vector machine) were quantitatively evaluated based on SGTs. It was proven that the texture features in OCT images provided objective information to classify oral tumors.

Primary study of identification of parathyroid gland based on laser-induced breakdown spectroscopy

The identification and preservation of parathyroid glands (PGs) is a major issue in thyroidectomy. The PG is particularly difficult to distinguish from the surrounding tissues. Accidental damage or removal of the PG may result in temporary or permanent postoperative hypoparathyroidism and hypocalcemia. In this study, a novel method for identification of the PG was proposed based on laser-induced breakdown spectroscopy (LIBS) for the first time. LIBS spectra were collected from the smear samples of PG and non-parathyroid gland (NPG) tissues (thyroid and neck lymph node) of rabbits. The emission lines (related to K, Na, Ca, N, O, CN, C₂, etc.) observed in LIBS spectra were ranked and selected based on the important weight calculated by random forest (RF). Three machine learning algorithms were used as classifiers to distinguish PGs from NPGs. The artificial neural network classifier provided the best classification performance. The results demonstrated that LIBS can be adopted to discriminate between smear samples of PG and NPG, and it has a potential in intra-operative identification of PGs.

Multimodal imaging with integrated auto-fluorescence and optical coherence tomography for identification of neck tissues

We report a multimodal optical system by combining OCT with autofluorescence imaging for identifying neck tissues, which can use the advantages of large field of view and high sensitivity for identifying parathyroid glands of fluorescence imaging, and high-resolution structural imaging of OCT to confirm them and identify lymph nodes and metastatic lymph nodes at the same time. It is proven that this multimodal optical system can be used to identify different neck tissues effectively and efficiently. We think that integrated auto-fluorescence and OCT imaging have the great potential in the application of navigation and assistant diagnosis of thyroid surgery.

Optical coherence tomography for thyroid pathology: 3D analysis of tissue microstructure

To investigate the potential of optical coherence tomography (OCT) to distinguish between normal and pathologic thyroid tissue, 3D OCT images were acquired on ex vivo thyroid samples from adult subjects (n=22) diagnosed with a variety of pathologies. The follicular structure was analyzed in terms of count, size, density and sphericity. Results showed that OCT images highly agreed with the corresponding histopatology and the calculated parameters were representative of the follicular structure variation. The analysis of OCT volumes provides quantitative information that could make automatic classification possible. Thus, OCT can be beneficial for intraoperative surgical guidance or in the pathology assessment routine.

Intraoperative Indocyanine Green (ICG) Angiography for the Identification of the Parathyroid Glands: Current Evidence and Future Perspectives

BACKGROUND/AIM

Recently, indocyanine green (ICG) fluorescence imaging has been used for the identification of the parathyroid glands (PG) during thyroid and parathyroid surgery. However, an overall consensus on the optimal technique, the dosage, the timing of the ICG administration and finally its interpretation and clinical usefulness is still lacking evidence. The aim of this review is to investigate the use of ICG angiography during thyroidectomy and/or parathyroidectomy for identification as well as for the perfusion integrity of the parathyroid glands.

MATERIALS AND METHODS

The PubMed database was systematically searched for publications regarding intraoperative ICG imaging in patients that undergo thyroidectomy or parathyroidectomy.

RESULTS

Eighteen publications reporting on 612 patients, namely 71 parathyroidectomy and 541 thyroidectomy patients met the inclusion criteria. Eleven publications reported the use of ICG angiography for the identification of the parathyroid glands during thyroidectomy and seven during parathyroidectomy for primary and secondary hyperparathyroidism.

CONCLUSION

ICG fluorescence imaging is a simple, fast and reproducible method capable of intraoperatively visualizing and assessing the function of parathyroid glands, and can, therefore, assist surgeons in their decision-making. Despite all this, ICG fluorescence imaging technique for PG detection still lacks standardization and further studies are needed to establish its clinical utility.

Intraoperative use of optical coherence tomography to differentiate normal and diseased thyroid and parathyroid tissues from lymph node and fat

The purpose of this study is twofold: (1) to determine the feasibility of optical coherence tomography (OCT) to differentiate normal and diseased tissue of the neck region intraoperatively and (2) to evaluate how accurately a cohort of test subjects can identify various tissue types when shown a sample set of OCT images. In this in vivo, prospective, single institutional study, an OCT imaging system (Niris, Imalux, Cleveland, OH) was used to image parathyroid, thyroid, lymph node, and fat tissue in 76 patients during neck surgery. Biopsies were performed for comparison of OCT images with histology in select cases (n = 20). Finally, a group of either surgeons or scientists familiar with OCT (n = 17) were shown a sample of OCT images and asked to identify the tissue. A total of 437 OCT images were analyzed, and characteristic features of each tissue type were identified. OCT demonstrated distinct differences in structural architecture and signal intensity that allows differentiation between thyroid and parathyroid tissues, lymph nodes, and fat. OCT images were also compared with histology with good correlation. There was no difference in correctly identifying OCT-imaged tissue type between surgeons and scientists. This study is the first in vivo OCT imaging study to evaluate both normal and diseased tissues that may be encountered during neck surgery. OCT has the potential to become a valuable intraoperative tool to differentiate diseased and normal thyroid tissue intraoperatively to obtain an "optical biopsy" in real time without fixation, staining, or tissue resection.

Grading upper tract urothelial carcinoma with the attenuation coefficient of in-vivo optical coherence tomography

INTRODUCTION

With catheter based optical coherence tomography (OCT), high resolution images of the upper urinary tract can be obtained, thereby facilitating the detection of upper tract urothelial carcinomas (UTUC). We hypothesized that the attenuation coefficient of the OCT signal (μOCT ) is related to the histopathologic grade of the tumor.

OBJECTIVES

In this study, we aimed to define the μOCT cut-off for discriminating high grade and low grade papillary UTUC.

METHODS

For this post-hoc analysis, data from OCT imaging of papillary UTUC was obtained from patients during ureterorenoscopy. OCT images and raw data were simultaneously analyzed with in-house developed software. The μOCT determined in papillary UTUCs and corresponding histopathologic grading from either biopsies or radical resection specimens were compared.

RESULTS

Thirty-five papillary UTUC from 35 patients were included. μOCT analysis was feasible in all cases. The median μOCT was 3.3 mm-1 (IQR 2.7-3.7 mm-1 ) for low-grade UTUC and 4.9 mm-1 (IQR 4.3-6.1 mm-1 ) for high-grade UTUC (P = 0.004). ROC analysis yielded a μOCT cut-off value of >4.0 mm-1 (AUC = 0.85, P < 0.001) with a sensitivity of 83% and a specificity of 94% for high-grade papillary UTUC.

CONCLUSIONS

This study proposes a μOCT cut-off of 4.0 mm-1 for quantitative grading of UTUC with ureterorenoscopic OCT imaging. The promising diagnostic accuracy calculations justify further studies to validate the proposed cut-off value. Implementation of the software for the μOCT analysis in OCT systems may allow for μOCT assessment at real time during ureterorenoscopy. Lasers Surg. Med. 51:399-406, 2019. © 2019 Wiley Periodicals, Inc.

Parathyroid gland management using optical technologies during thyroidectomy or parathyroidectomy: A systematic review

New optical technologies enhancing localization or assessing viability of parathyroid glands (PG) during endocrine surgery have been reported in clinical studies. These technologies could become complementary to the surgeon's eyes and may improve surgical outcomes in thyroidectomy and parathyroidectomy. Here, we conducted a systematic review focusing on PG identification and functional assessment using optical methods to enhance surgery. A systematic literature review was performed using MEDLINE and Embase database. Two authors selected studies and extracted data; qualitative analysis was performed to summarize the characteristics of reported optical tools for thyroidectomy or parathyroidectomy. Identification and vascularisation of PG during surgery were evaluated. Clinical and biochemical outcomes were appraised when reported. Studies relating to parathyroidectomy or thyroidectomy combined with autofluorescence, fluorescent methylene blue, 5-aminolevulinic acid, indocyanine green (ICG), optical coherence tomography, laser speckle contrast imaging, dynamic optical contrast imaging and Raman spectroscopy were identified with MEDLINE and Embase. We included a total of 47 relevant articles with a total of 1615 patients enrolled. Each optical technique is described and appreciated related to its surgical purpose. Autofluorescence and ICG imaging of PG are the most widely reported optical technologies for identification and assessment of vascularisation of PG. Results are mainly based on observational studies and argue for the feasibility of both techniques in endocrine surgery but prospective randomized studies have not been performed. In vivo applications are still limited for the other methods and further investigations correlating these techniques with post-operative parathormone measurements are still needed before considering these technologies in clinical practice.

The use of ICG enhanced fluorescence for the evaluation of parathyroid gland preservation

Indocyanine green (ICG) enhanced fluorescence imaging is recent innovation as the "real-time intraoperative imaging" technique. Many clinical studies have been reported in the literature which use different devices and techniques that employ various doses and usages of ICG as a non-specific contrast agent. Several groups have performed studies in endocrine surgery, especially with regards to parathyroid-related outcomes after thyroid and parathyroid surgery. However, there is no consensus on the technical details that should be applied. With this study, we aimed to review the current literature on potential use of intraoperative ICG angiography for evaluating parathyroid gland (PTG) preservation.