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.

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.

C17,20-lyase inhibitors I. Structure-based de novo design and SAR study of C17,20-lyase inhibitors.

Novel nonsteroidal C(17,20)-lyase inhibitors were synthesized using de novo design based on its substrate, 17 alpha-hydroxypregnenolone, and several compounds exhibited potent C(17,20)-lyase inhibition. However, in vivo activities were found to be short-lasting, and in order to improve the duration of action, a series of benzothiophene derivatives were evaluated. As a result, compounds 9h, (S)-9i, and 9k with nanomolar enzyme inhibition (IC(50)=4-9 nM) and 9e (IC(50)=27 nM) were identified to have powerful in vivo efficacy with extended duration of action. The key structural determinants for the in vivo efficacy were demonstrated to be the 5-fluoro group on the benzothiophene ring and the 4-imidazolyl moiety. Superimposition of 9k and 17 alpha-hydroxypregnenolone demonstrated their structural similarity and enabled rationalization of the pharmacological results. In addition, selected compounds were also identified to be potent inhibitors of human enzyme with IC(50) values of 20-30 nM.