Content-based image retrieval for the diagnosis of myocardial perfusion imaging using a deep convolutional autoencoder.

BACKGROUND: Single-photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI) plays a crucial role in the optimal treatment strategy for patients with coronary heart disease. We tested the feasibility of feature extraction from MPI using a deep convolutional autoencoder (CAE) model. METHODS: Eight hundred and forty-three pairs of stress and rest myocardial perfusion images were collected from consecutive patients who underwent cardiac scintigraphy in our hospital between December 2019 and February 2022. We trained a CAE model to reproduce the input paired image data, so as the encoder to output a 256-dimensional feature vector. The extracted feature vectors were further dimensionally reduced via principal component analysis (PCA) for data visualization. Content-based image retrieval (CBIR) was performed based on the cosine similarity of the feature vectors between the query and reference images. The agreement of the radiologist's finding between the query and retrieved MPI was evaluated using binary accuracy, precision, recall, and F1-score. RESULTS: A three-dimensional scatter plot with PCA revealed that feature vectors retained clinical information such as percent summed difference score, presence of ischemia, and the location of scar reported by radiologists. When CBIR was used as a similarity-based diagnostic tool, the binary accuracy was 81.0%. CONCLUSION: The results indicated the utility of unsupervised feature learning for CBIR in MPI.

Bepridil monotherapy failed to prevent coronary vasospasm in a Brugada syndrome patient.

Coronary vasospasm sometimes coexists with Brugada syndrome (BrS) and is reportedly associated with poor prognosis. Although calcium channel blockers are considered first-line drugs to prevent coronary vasospasm, they also have the potential to induce ST elevation and ventricular fibrillation (VF) in BrS. Therefore, the optimal medication for such a complicated case is still underdetermined. We report a male patient who presented with VF due to BrS, which was later found to have coexisted with coronary vasospasm. He was treated with low-dose bepridil expecting both its anti-arrhythmic and vasodilatory effects, but a later acetylcholine provocation test showed no suppression of vasospasm. Based on these results, we decided to add nitrates to the medication. This case report illustrates that drug selection needs caution in BrS when complicated with vasospastic angina and that bepridil monotherapy may not be sufficient to suppress coronary vasospasm in such cases.

Image similarity-based cardiac rhythm device identification from X-rays using feature point matching.

AIMS: Identifying the manufacturer and the type of cardiac implantable electronic devices (CIEDs) is important in emergent clinical settings. Recent studies have illustrated that artificial neural network models can successfully recognize CIEDs from chest X-ray images. However, all existing methods require a vast amount of medical data to train the classification model. Here, we have proposed a novel method to retrieve an identical CIED image from an image database by employing the feature point matching algorithm. METHODS AND RESULTS: A total of 653 unique X-ray images from 456 patients who visited our pacemaker clinic between April 2012 and August 2020 were collected. The device images were manually square-shaped, and was thereafter resized to 224 × 224 pixels. A scale-invariant feature transform (SIFT) algorithm was used to extract the keypoints from the query image and reference images. Paired feature points were selected via brute-force matching, and the average Euclidean distance was calculated. The image with the shortest average distance was defined as the most similar image. The classification performance was indicated by accuracy, precision, recall, and F1-score for detecting the manufacturers and model groups, respectively. The average accuracy, precision, recall, and F-1 score for the manufacturer classification were 97.0%, 0.97, 0.96, and 0.96, respectively. For the model classification task, the average accuracy, precision, recall, and F-1 score were 93.2%, 0.94, 0.92, and 0.93, respectively, all of which were higher than those of the previously reported machine learning models. CONCLUSION: Feature point matching is useful for identifying CIEDs from X-ray images.

Clinical Utility of Diffusion-weighted Whole-body Magnetic Resonance Imaging with Background Body Signal Suppression for Assessing and Monitoring IgG4-related Disease.

A 77-year-old man with symptoms of chest pain was diagnosed with immunoglobulin G4 (IgG4)-related disease. Fluorodeoxyglucose positron emission tomography/computed tomography (FDG-PET/CT) revealed an intense uptake in the submandibular gland, lymph nodes and abdominal aortic wall. Diffusion-weighted imaging with background body signal suppression (DWIBS) revealed signal enhancements at the same location as those of the FDG-PET/CT findings. The DWIBS signal intensity decreased after steroid treatment, so we decreased the steroid dosage. Relapse did not occur. DWIBS makes it possible to adjust the medicine dosage while confirming the therapeutic effects and will likely be a useful method for monitoring IgG4-related disease.