Deep clustering for abdominal organ classification in ultrasound imaging.

Purpose: The purpose of this study is to examine the utilization of unlabeled data for abdominal organ classification in multi-label (non-mutually exclusive classes) ultrasound images, as an alternative to the conventional transfer learning approach. Approach: We present a new method for classifying abdominal organs in ultrasound images. Unlike previous approaches that only relied on labeled data, we consider the use of both labeled and unlabeled data. To explore this approach, we first examine the application of deep clustering for pretraining a classification model. We then compare two training methods, fine-tuning with labeled data through supervised learning and fine-tuning with both labeled and unlabeled data using semisupervised learning. All experiments were conducted on a large dataset of unlabeled images (nu=84967) and a small set of labeled images (ns=2742) comprising progressively 10%, 20%, 50%, and 100% of the images. Results: We show that for supervised fine-tuning, deep clustering is an effective pre-training method, with performance matching that of ImageNet pre-training using five times less labeled data. For semi-supervised learning, deep clustering pre-training also yields higher performance when the amount of labeled data is limited. Best performance is obtained with deep clustering pre-training combined with semi-supervised learning and 2742 labeled example images with an F1-score weighted average of 84.1%. Conclusions: This method can be used as a tool to preprocess large unprocessed databases, thus reducing the need for prior annotations of abdominal ultrasound studies for the training of image classification algorithms, which in turn could improve the clinical use of ultrasound images.

Deep Learning for the Detection, Localization, and Characterization of Focal Liver Lesions on Abdominal US Images.

Purpose: To train and assess the performance of a deep learning-based network designed to detect, localize, and characterize focal liver lesions (FLLs) in the liver parenchyma on abdominal US images. Materials and Methods: In this retrospective, multicenter, institutional review board-approved study, two object detectors, Faster region-based convolutional neural network (Faster R-CNN) and Detection Transformer (DETR), were fine-tuned on a dataset of 1026 patients (n = 2551 B-mode abdominal US images obtained between 2014 and 2018). Performance of the networks was analyzed on a test set of 48 additional patients (n = 155 B-mode abdominal US images obtained in 2019) and compared with the performance of three caregivers (one nonexpert and two experts) blinded to the clinical history. The sign test was used to compare accuracy, specificity, sensitivity, and positive predictive value among all raters. Results: DETR achieved a specificity of 90% (95% CI: 75, 100) and a sensitivity of 97% (95% CI: 97, 97) for the detection of FLLs. The performance of DETR met or exceeded that of the three caregivers for this task. DETR correctly localized 80% of the lesions, and it achieved a specificity of 81% (95% CI: 67, 91) and a sensitivity of 82% (95% CI: 62, 100) for FLL characterization (benign vs malignant) among lesions localized by all raters. The performance of DETR met or exceeded that of two experts and Faster R-CNN for these tasks. Conclusion: DETR demonstrated high specificity for detection, localization, and characterization of FLLs on abdominal US images. Supplemental material is available for this article. RSNA, 2022Keywords: Computer-aided Diagnosis (CAD), Ultrasound, Abdomen/GI, Liver, Tissue Characterization, Supervised Learning, Transfer Learning, Convolutional Neural Network (CNN).

Screening for orthostatic hypotension using home blood pressure measurements.

OBJECTIVE: Orthostatic hypotension is a common condition associated with adverse cardiovascular and cognitive prognosis. Screening for orthostatic hypotension consists of blood pressure measurements in supine (or sitting) and standing position during clinical consultations. As orthostatic hypotension is a poorly reproducible clinical condition, it is likely that the simple measurement carried out during consultations underestimates the true prevalence of the condition. The objective of this study is, therefore, to determine whether screening for orthostatic hypotension with home blood pressure measurements (HBPM) may improve orthostatic hypotension diagnosis without compromising the quality of the blood pressure readings. MATERIALS AND METHODS: We asked all patients with indications for HBPM in the hypertension unit and in a general medical practice to perform a series of home blood pressure measurements, ending each series with a measurement in standing position. RESULTS: We recruited 505 patients of mean age 68 years of which 93% were hypertensive patients. The success rate of HBPM complying with the ESH criteria (12 out of 18 measurements) was 94.5%, which is comparable with previously published series of measurements. Ninety-one percent of patients measured their blood pressure at least once in standing position, and 88% of patients recorded all six standing measurements. Orthostatic hypotension prevalence defined as the presence of one episode of orthostatic hypotension was 37.47%, much higher than orthostatic hypotension prevalence measured in the same cohort in a clinic setting (15%). CONCLUSION: The measurement of blood pressure in standing position during HBPM is feasible without altering the quality of the blood pressure readings in seated position. Our findings show that orthostatic hypotension is significantly more often detected at home by the patient than at the doctor's office, which may allow quicker initiation of preventive and therapeutic strategies.