Development of an algorithm for intraoperative autofluorescence assessment of parathyroid glands in primary hyperparathyroidism using artificial intelligence

Near-Infrared Autofluorescence Signatures of Single- vs Multigland Disease in Primary Hyperparathyroidism

Importance

The success of parathyroidectomy depends on accurate intraoperative localization and identification of all diseased glands in parathyroid exploration based on surgeon expertise to prevent persistent hyperparathyroidism. Near-infrared autofluorescence (NIRAF) imaging has recently emerged as a promising adjunctive intraoperative tool for localizing parathyroid glands; however, its potential utility in the assessment of parathyroid glands has yet to be established.

Objective

To analyze the differences in NIRAF signatures of parathyroid glands in single vs multiple glands in primary hyperparathyroidism (pHPT).

Design, Setting, and Participants

This prospective diagnostic study analyzed in vivo NIRAF images of parathyroid glands obtained during parathyroidectomies between November 18, 2019, and December 31, 2023, at a single tertiary referral center. Pixel intensities of the images were measured using third-party software. Patients who underwent parathyroidectomy for sporadic pHPT using a second-generation NIRAF imaging device were included. Patients with multiple endocrine neoplasm disorders were excluded. In vivo NIRAF images obtained during the procedures were analyzed.

Exposure

Near-infrared autofluorescence imaging during parathyroidectomy.

Main Outcomes and Measures

The primary outcomes were the autofluorescence intensity and heterogeneity of single adenomas and multigland disease (ie, double adenomas and 3- or 4-gland hyperplasia) in sporadic pHPT. Normalized autofluorescence intensity was calculated by dividing the mean pixel intensity of the parathyroid gland by the background tissue. A heterogeneity index was calculated by dividing the standard deviation by the mean pixel intensity of the gland. The secondary outcome was the visibility of each parathyroid gland on NIRAF imaging before it became apparent to the naked eye during exploration.

Results

A total of 1287 in vivo NIRAF images obtained from 377 patients (median [IQR] age, 66 [56-73] years; 299 female [79.3%]) were analyzed. Of all patients, 230 (61.0%) had a single adenoma, 91 (24.1%) had double adenomas, and 56 (14.9%) had 3- or 4-gland hyperplasia. A mean (SD) of 3.4 (1.1) parathyroid glands were identified in the procedures. A comparison of 581 diseased glands (45.1%) and 706 normal glands (54.9%) showed a lower median normalized autofluorescence intensity of 2.09 (95% CI, 1.07-4.01) vs 2.66 (95% CI, 1.43-4.20; effect size = 0.36) and higher heterogeneity index of 0.18 (95% CI, 0.07-0.41) vs 0.11 (95% CI, 0.01-0.27; effect size = 0.45), respectively. Of diseased glands, single adenomas (233 [40.1%]) vs double adenomas (187 [32.2%]) and 3- or 4-gland hyperplasia (161 [27.7%]) had a lower median autofluorescence intensity of 1.92 (95% CI, 1.02-4.44) vs 2.22 (95% CI, 1.10-3.97; effect size = 0.21), respectively. On receiver operating characteristic analysis, the optimal autofluorescence intensity threshold to differentiate between single adenomas vs multigland disease was 2.14, with a sensitivity of 64.4%, specificity of 58.1%, and area under the curve of 0.626.

Conclusions and Relevance

These findings suggest that parathyroid glands in single- vs multigland disease may exhibit different autofluorescence characteristics. Although the effect size was modest, the differences identified should be kept in mind when assessing the parathyroid glands during surgical exploration.

Correlation Between Near-Infrared Autofluorescence Properties and Sestamibi Uptakes of Parathyroid Glands in Primary Hyperparathyroidism

OBJECTIVE

Near-infrared autofluorescence (NIRAF) characteristics of parathyroid glands in primary hyperparathyroidism (pHPT) vary, with unclarity regarding the underlying mechanism. Similarly, 99mTc-sestamibi uptake in diseased parathyroid glands is variable. There is a suggestion that oxyphilic cell content may influence both imaging modalities. This study aims to analyze the relationship between NIRAF imaging characteristics, 99mTc-sestamibi uptake, and cellular composition in pHPT.

STUDY DESIGN

Retrospective analysis of an Institutional Review Board-monitored prospective database.

SETTING

Single tertiary referral center.

METHODS

NIRAF characteristics of parathyroid glands of patients with pHPT between 2019 and 2024 were compared with 99mTc-sestamibi scan findings from a prospective database. Using third-party software, brightness intensity and heterogeneity index (HI) of the glands were calculated. A subgroup of parathyroid glands obtained from consecutive patients with pHPT in 2020 to 2021 underwent histological analysis.

RESULTS

A total of 428 patients with 638 diseased parathyroid glands were analyzed. Forty-seven percent of the glands showed an uptake on 99mTc-sestamibi scans. The brightness intensity of the NIRAF signals from parathyroid glands that were seen versus not seen on sestamibi was 2.1 versus 2.3 (P = .002) and HI 0.18 versus 0.17 (P = .35), respectively. On multivariate analysis, low autofluorescence intensity, high gland volume, and single adenoma were associated with detectability on 99mTc-sestamibi scan (P < .0001). Intraglandular adipose tissue content was lower in diseased glands that were detected on 99mTc-sestamibi scans (0% vs 5%, P < .0001).

CONCLUSION

Our findings indicate an inverse relationship between autofluorescence intensity and detectability on 99mTc-sestamibi scans and a lack of correlation between different cell types and autofluorescence properties.

Artificial intelligence in screening and diagnosis of surgical diseases: A narrative review

Artificial intelligence (AI) is playing an increasing role in several fields of medicine. It is also gaining popularity among surgeons as a valuable screening and diagnostic tool for many conditions such as benign and malignant colorectal, gastric, thyroid, parathyroid, and breast disorders. In the literature, there is no review that groups together the various application domains of AI when it comes to the screening and diagnosis of main surgical diseases. The aim of this review is to describe the use of AI in these settings. We performed a literature review by searching PubMed, Web of Science, Scopus, and Embase for all studies investigating the role of AI in the surgical setting, published between January 01, 2000, and June 30, 2023. Our focus was on randomized controlled trials (RCTs), meta-analysis, systematic reviews, and observational studies, dealing with large cohorts of patients. We then gathered further relevant studies from the reference list of the selected publications. Based on the studies reviewed, it emerges that AI could strongly enhance the screening efficiency, clinical ability, and diagnostic accuracy for several surgical conditions. Some of the future advantages of this technology include implementing, speeding up, and improving the automaticity with which AI recognizes, differentiates, and classifies the various conditions.

Future Directions in the Treatment of Thyroid and Parathyroid Disease

The surgical management of thyroid and parathyroid disease has evolved considerably since the era of Theodor Kocher. We review the current trends in thyroid and parathyroid surgery concerning robotic surgery for remote access, the use of parathyroid autofluorescence detection technology to aid in the prevention of hypocalcemia as well as the use of thermal ablation to target thyroid nodules in a minimally invasive way. We also discuss how artificial intelligence is being used to improve the workflow and diagnostics preoperatively as well as for intraoperative decision-making. We also discuss potential areas where future research may enhance outcomes.

An update on the use of near-infrared autofluorescence imaging in endocrine surgical procedures

Over the past decade, near-infrared autofluorescence (NIRAF) imaging has been a major breakthrough in endocrine surgery. Although initial focus was directed at the parathyroid glands, subsequent work has also shown that non-parathyroid neuroendocrine tumors also possess autofluorescence properties. The aim of this review is to present an update and synopsis about NIRAF applications in various endocrine surgical procedures. Methodology includes a review of the literature supplemented with expert opinion. Overall, our review reveals that the use of NIRAF may provide the surgeon with adjunctive critical information that has the potential to change the conduct of many various endocrine surgical procedures.

Educational Review: Intraoperative Parathyroid Fluorescence Detection Technology in Thyroid and Parathyroid Surgery

BACKGROUND

Accurate parathyroid gland (PG) identification is a critical yet challenging component of cervical endocrine procedures. PGs possess strong near-infrared autofluorescence (NIRAF) compared with other tissues in the neck. This property has been harnessed by image- and probe-based near-infrared fluorescence detection systems, which have gained increasing popularity in clinical use for their ability to accurately aid in PG identification in a rapid, noninvasive, and cost-effective manner. All NIRAF technologies, however, cannot differentiate viable from devascularized PGs without the use of contrast enhancement. Here, we aim to provide an overview of the rapid evolution of these technologies and update the surgery community on the most recent advancements in the field.

METHODS

A PubMed literature review was performed using the key terms "parathyroid," "near-infrared," and "fluorescence." Recommendations regarding the use of these technologies in clinical practice were developed on the basis of the reviewed literature and in conjunction with expert surgeons' opinions.

RESULTS

The use of near-infrared fluorescence detection can be broadly categorized as (1) using parathyroid NIRAF to identify both healthy and diseased PGs, and (2) using contrast-enhanced (i.e., indocyanine green) near-infrared fluorescence to evaluate PG perfusion and viability. Each of these approaches possess unique advantages and disadvantages, and clinical trials are ongoing to better define their utility.

CONCLUSIONS

Near-infrared fluorescence detection offers the opportunity to improve our collective ability to identify and preserve PGs intraoperatively. While additional work is needed to propel this technology further, we hope this review will be valuable to the practicing surgeon.

Advances in Endocrine Surgery

Recent changes in the landscape of endocrine surgery include a shift from total thyroidectomy for almost all patients with papillary thyroid cancer to the incorporation of thyroid lobectomy for well-selected patients with low-risk disease; minimally invasive parathyroidectomy with, and potentially without, intraoperative parathyroid hormone monitoring for patients with well-localized primary hyperparathyroidism; improvement in the management of parathyroid cancer with the incorporation of immune checkpoint blockade and/or targeted therapies; and the incorporation of minimally invasive techniques in the management of patients with benign tumors and selected secondary malignancies of the adrenal gland.

A coaxial excitation, dual-red-green-blue/near-infrared paired imaging system toward computer-aided detection of parathyroid glands in situ and ex vivo

Early and precise detection of parathyroid glands (PGs) is a challenging problem in thyroidectomy due to their small size and similar appearance to surrounding tissues. Near-infrared autofluorescence (NIRAF) has stimulated interest as a method to localize PGs. However, high incidence of false positives for PGs has been reported with this technique. We introduce a prototype equipped with a coaxial excitation light (785 nm) and a dual-sensor to address the issue of false positives with the NIRAF technique. We test the clinical feasibility of our prototype in situ and ex vivo using sterile drapes on 10 human subjects. Video data (1287 images) of detected PGs were collected to train, validate and compare the performance for PG detection. We achieved a mean average precision of 94.7% and a 19.5-millisecond processing time/detection. This feasibility study supports the effectiveness of the optical design and may open new doors for a deep learning-based PG detection method.

A visual deep learning model to predict abnormal versus normal parathyroid glands using intraoperative autofluorescence signals

BACKGROUND

Previous work demonstrated that abnormal versus normal parathyroid glands (PGs) exhibit different patterns of autofluorescence, with former appearing darker and more heterogenous. Our objective was to develop a visual artificial intelligence model using intraoperative autofluorescence signals to predict whether a PG is abnormal (hypersecreting and/or hypercellular) or normal before excision during surgical exploration for primary hyperparathyroidism.

METHODS

A total of 906 intraoperative parathyroid autofluorescence images of 303 patients undergoing parathyroidectomy/thyroidectomy were used to develop model. Autofluorescence image of each PG was uploaded into the visual artificial intelligence platform as abnormal or normal. For deep learning, randomly chosen 80% of data was used for training, 10% for testing, 10% for validation. The area under the receiver operating characteristic (AUROC), area under the precision-recall curve (AUPRC), recall (sensitivity), and precision (positive predictive value) of the model were calculated.

RESULTS

AUROC and AUPRC of the model to predict normal and abnormal PGs were 0.90 and 0.93, respectively. Recall and precision of the model were 89% each.

CONCLUSION

Visual artificial intelligence platforms may be used to compare the autofluorescence signal of a given parathyroid gland against a large database. This may be a new adjunctive tool for intraoperative assessment of parathyroid glands during surgical exploration for primary hyperparathyroidism.

Comparison of Parathyroid Autofluorescence Signals in Different Types of Hyperparathyroidism

BACKGROUND

There are scant data in the literature regarding whether parathyroid autofluorescence (AF) signal patterns vary based on the etiology of hyperparathyroidism. The aim of this study was to compare AF signals of parathyroid glands across different etiologies of hyperparathyroidism.

METHODS

As a prospective institutional review board-approved study between 2016 and 2019, AF intensities and heterogeneity indexes (HIs) of parathyroid glands in patients who underwent parathyroidectomy using AF were calculated and compared using Chi-square, Kruskal Wallis, Mann Whitney U, and logistic regression tests.

RESULTS

Of the total of 183 patients, 127 patients had sporadic classic primary hyperparathyroidism, 30 patients had sporadic normohormonal primary hyperparathyroidism, 10 patients had sporadic normocalcemic primary hyperparathyroidism, 12 patients had tertiary hyperparathyroidism, and 4 patients had familial primary hyperparathyroidism related to multiple endocrine neoplasia (MEN) 2A. There were no statistical differences in AF signals of abnormal parathyroid glands in classic, normohormonal or normocalcemic sporadic hyperparathyroidism. Parathyroid glands in patients with tertiary hyperparathyroidism were similar in intensity, but more homogenous compared to those in sporadic primary hyperparathyroidism.

CONCLUSIONS

The pattern of AF exhibited by abnormal parathyroid glands was similar across different spectrums of primary hyperparathyroidism, in accordance with observations in the literature. However, parathyroid glands in tertiary hyperparathyroidism were more homogeneous, despite exhibiting a similar intensity of AF compared to those in sporadic primary hyperparathyroidism. These differences should be kept in mind when using the AF pattern as an adjunct to visual assessment in parathyroid exploration.