Diagnosis of pulmonary embolism: planar images generated from V/Q SPECT are not a reliable substitute for traditional planar V/Q scan

The Past, Present, and Future Role of Artificial Intelligence in Ventilation/Perfusion Scintigraphy: A Systematic Review

Ventilation-perfusion (V/Q) lung scans constitute one of the oldest nuclear medicine procedures, remain one of the few studies performed in the acute setting, and are amongst the few performed in the emergency setting. V/Q studies have witnessed a long fluctuation in adoption rates in parallel to continuous advances in image processing and computer vision techniques. This review provides an overview on the status of artificial intelligence (AI) in V/Q scintigraphy. To clearly assess the past, current, and future role of AI in V/Q scans, we conducted a systematic Ovid MEDLINE(R) literature search from 1946 to August 5, 2022 in addition to a manual search. The literature was reviewed and summarized in terms of methodologies and results for the various applications of AI to V/Q scans. The PRISMA guidelines were followed. Thirty-one publications fulfilled our search criteria and were grouped into two distinct categories: (1) disease diagnosis/detection (N = 22, 71.0%) and (2) cross-modality image translation into V/Q images (N = 9, 29.0%). Studies on disease diagnosis and detection relied heavily on shallow artificial neural networks for acute pulmonary embolism (PE) diagnosis and were primarily published between the mid-1990s and early 2000s. Recent applications almost exclusively regard image translation tasks from CT to ventilation or perfusion images with modern algorithms, such as convolutional neural networks, and were published between 2019 and 2022. AI research in V/Q scintigraphy for acute PE diagnosis in the mid-90s to early 2000s yielded promising results but has since been largely neglected and thus have yet to benefit from today's state-of-the art machine-learning techniques, such as deep neural networks. Recently, the main application of AI for V/Q has shifted towards generating synthetic ventilation and perfusion images from CT. There is therefore considerable potential to expand and modernize the use of real V/Q studies with state-of-the-art deep learning approaches, especially for workflow optimization and PE detection at both acute and chronic stages. We discuss future challenges and potential directions to compensate for the lag in this domain and enhance the value of this traditional nuclear medicine scan.

Lung Ventilation/Perfusion Scintigraphy for the Screening of Chronic Thromboembolic Pulmonary Hypertension (CTEPH): Which Criteria to Use?

Objective

The diagnosis of chronic thromboembolic pulmonary hypertension (CTEPH) is a major challenge as it is a curable cause of pulmonary hypertension (PH). Ventilation/Perfusion (V/Q) lung scintigraphy is the imaging modality of choice for the screening of CTEPH. However, there is no consensus on the criteria to use for interpretation. The aim of this study was to assess the accuracy of various interpretation criteria of planar V/Q scintigraphy for the screening of CTEPH in patients with PH.

Methods

The eligible study population consisted of consecutive patients with newly diagnosed PH in the Brest University Hospital, France. Final diagnosis (CTEPH or non-CTEPH) was established in a referential center on the management of PH, based on the ESC/ERS guidelines and a minimum follow-up of 3 years. A retrospective central review of planar V/Q scintigraphy was performed by three nuclear physicians blinded to clinical findings and to final diagnosis. The number, extent (sub-segmental or segmental) and type (matched or mismatched) of perfusion defects were reported. Sensitivity and specificity were evaluated for various criteria based on the number of mismatched perfusion defects and the number of perfusion defects (regardless of ventilation). Receiver operating characteristic (ROC) curves were generated and areas under the curve (AUC) were calculated for both.

Results

A total of 226 patients with newly diagnosed PH were analyzed. Fifty six (24.8%) were diagnosed with CTEPH while 170 patients (75.2%) were diagnosed with non-CTEPH. The optimal threshold was 2.5 segmental mismatched perfusion defects, providing a sensitivity of 100 % (95% CI 93.6–100%) and a specificity of 94.7% (95%CI 90.3–97.2%). Lower diagnostic cut-offs of mismatched perfusion defects provided similar sensitivity but lower specificity. Ninety five percent of patients with CTEPH had more than 4 segmental mismatched defects. An interpretation only based on perfusion provided similar sensitivity but a specificity of 81.8% (95%CI 75.3–86.9%).

Conclusion

Our study confirmed the high diagnostic performance of planar V/Q scintigraphy for the screening of CTEPH in patients with PH. The optimal diagnostic cut-off for interpretation was 2.5 segmental mismatched perfusion defects. An interpretation only based on perfusion defects provided similar sensitivity but lower specificity.

The Economic Value of Hybrid Single-photon Emission Computed Tomography With Computed Tomography Imaging in Pulmonary Embolism Diagnosis

Objective

The objective was to quantify the potential economic value of single‐photon emission computed tomography (SPECT) with computed tomography (CT; SPECT/CT) versus CT pulmonary angiography (CTPA), ventilation–perfusion (V/Q) planar scintigraphy, and V/Q SPECT imaging modalities for diagnosing suspected pulmonary embolism (PE) patients in an emergency setting.

Methods

An Excel‐based simulation model was developed to compare SPECT/CT versus the alternate scanning technologies from a payer's perspective. Clinical endpoints (diagnosis, treatment, complications, and mortality) and their corresponding cost data (2016 USD) were obtained by performing a best evidence review of the published literature. Studies were pooled and parameters were weighted by sample size. Outcomes measured included differences in 1) excess costs, 2) total costs, and 3) lives lost per annum between SPECT/CT and the other imaging modalities. One‐way (±25%) sensitivity and three scenario analyses were performed to gauge the robustness of the results.

Results

For every 1,000 suspected PE patients undergoing imaging, expected annual economic burden by modality was found to be 3.2 million (SPECT/CT), 3.8 million (CTPA), 5.8 million (planar), and 3.6 million (SPECT) USD, with a switch to SPECT/CT technology yielding per‐patient‐per‐month cost savings of $51.80 (vs. CTPA), $213.80 (vs. planar), and $36.30 (vs. SPECT), respectively. The model calculated that the incremental number of lives saved with SPECT/CT was six (vs. CTPA) and three (vs. planar). Utilizing SPECT/CT as the initial imaging modality for workup of acute PE was also expected to save $994,777 (vs. CTPA), $2,852,014 (vs. planar), and $435,038 (vs. SPECT) in “potentially avoidable”’ excess costs per annum for a payer or health plan.

Conclusion

Compared to the currently available scanning technologies for diagnosing suspected PE, SPECT/CT appears to confer superior economic value, primarily via improved sensitivity and specificity and low nondiagnostic rates. In turn, the improved diagnostic accuracy accords this modality the lowest ratio of expenses attributable to potentially avoidable complications, misdiagnosis, and underdiagnosis.

Pulmonary Scintigraphy for the Diagnosis of Acute Pulmonary Embolism: A Survey of Current Practices in Australia, Canada, and France

There are currently no data published regarding the proportion of nuclear medicine centers using SPECT or SPECT/CT rather than planar ventilation/perfusion (V/Q) imaging in patients with suspected acute pulmonary embolism (PE). Furthermore, the reporting criteria used for interpretation of both planar and SPECT V/Q scans are variable and data are lacking regarding which criteria are commonly used in various centers. The aim of this study was to assess current practices regarding the performance and interpretation of lung scintigraphy across 3 different countries.

METHODS

A short online survey composed of simple multiple-choice questions was distributed to nuclear medicine departments in Australia, Canada, and France during the period April to December 2014. The survey covered image acquisition, interpretation criteria for SPECT and planar images, and use of pseudoplanar images and radiopharmaceuticals. Information was initially solicited by 2 sets of e-mails, which pointed to the survey internet link. Departments were subsequently contacted by telephone. A single response per department was consolidated.

RESULTS

Three hundred thirty-one responses were collected (Australia, 74; Canada, 48; and France, 209). Twenty-eight percent of centers indicated use of V/Q planar imaging alone whereas 72% of centers included some form of SPECT in their acquisition protocol for evaluation of PE, specifically V/Q SPECT in 36%, V/Q SPECT/CT in 29%, Q SPECT/CT in 2%, and both V/Q planar and SPECT in 5%, with a strong variability among countries. The most commonly used criteria for SPECT interpretation were the those of the European Association of Nuclear Medicine (60%). Criteria used for planar interpretation were heterogeneous (European Association of Nuclear Medicine criteria, 35%; Prospective Investigation of Pulmonary Embolism Diagnosis study, 29%; no standardized criteria, 21%). Sixty-three percent of departments used pseudoplanar images in addition to SPECT images.

CONCLUSION

In the 3 countries surveyed, SPECT has largely replaced planar imaging for evaluation of PE, with almost half of the SPECT studies incorporating a CT acquisition. Criteria used for interpretation are inconsistent, especially for planar imaging.