Deep Learning-Derived Myocardial Strain.

BACKGROUND: Echocardiographic strain measurements require extensive operator experience and have significant intervendor variability. Creating an automated, open-source, vendor-agnostic method to retrospectively measure global longitudinal strain (GLS) from standard echocardiography B-mode images would greatly improve post hoc research applications and may streamline patient analyses. OBJECTIVES: This study was seeking to develop an automated deep learning strain (DLS) analysis pipeline and validate its performance across multiple applications and populations. METHODS: Interobserver/-vendor variation of traditional GLS, and simulated effects of variation in contour on speckle-tracking measurements were assessed. The DLS pipeline was designed to take semantic segmentation results from EchoNet-Dynamic and derive longitudinal strain by calculating change in the length of the left ventricular endocardial contour. DLS was evaluated for agreement with GLS on a large external dataset and applied across a range of conditions that result in cardiac hypertrophy. RESULTS: In patients scanned by 2 sonographers using 2 vendors, GLS had an intraclass correlation of 0.29 (95% CI: -0.01 to 0.53, P = 0.03) between vendor measurements and 0.63 (95% CI: 0.48-0.74, P < 0.001) between sonographers. With minor changes in initial input contour, step-wise pixel shifts resulted in a mean absolute error of 3.48% and proportional strain difference of 13.52% by a 6-pixel shift. In external validation, DLS maintained moderate agreement with 2-dimensional GLS (intraclass correlation coefficient [ICC]: 0.56, P = 0.002) with a bias of -3.31% (limits of agreement: -11.65% to 5.02%). The DLS method showed differences (P < 0.0001) between populations with cardiac hypertrophy and had moderate agreement in a patient population of advanced cardiac amyloidosis: ICC was 0.64 (95% CI: 0.53-0.72), P < 0.001, with a bias of 0.57%, limits of agreement of -4.87% to 6.01% vs 2-dimensional GLS. CONCLUSIONS: The open-source DLS provides lower variation than human measurements and similar quantitative results. The method is rapid, consistent, vendor-agnostic, publicly released, and applicable across a wide range of imaging qualities.

Hand scanning optical coherence tomography imaging using encoder feedback.

We present a new method for generating micron-scale OCT images of interstitial tissue with a hand scanning probe and a linear optical encoder that senses probe movement relative to a fixed reference point, i.e., tissue surface. Based on this approach, we demonstrate high resolution optical imaging of biological tissues through a very long biopsy needle. Minor artifacts caused by tissue noncompliance are corrected using a software algorithm which detects the simple repetition of the adjacent A-scans. This hand-scanning OCT imaging approach offers the physician the freedom to access imaging sites of interest repeatedly.

Low coherence interferometry approach for aiding fine needle aspiration biopsies.

We present portable preclinical low-coherence interference (LCI) instrumentation for aiding fine needle aspiration biopsies featuring the second-generation LCI-based biopsy probe and an improved scoring algorithm for tissue differentiation. Our instrument and algorithm were tested on 38 mice with cultured tumor mass and we show the specificity, sensitivity, and positive predictive value of tumor detection of over 0.89, 0.88, and 0.96, respectively.

Detection of breast surgical margins with optical coherence tomography imaging: a concept evaluation study.

This study aimed to evaluate the concept of using high-resolution optical coherence tomography (OCT) imaging to rapidly assess surgical specimens and determine if cancer positive margins were left behind in the surgical bed. A mouse model of breast cancer was used in this study. Surgical specimens from 30 animals were investigated with OCT and automated interpretation of the OCT images was performed and tested against histopathology findings. Specimens from 10 animals were used to build a training set of OCT images, while the remaining 20 specimens were used for a validation set of images. The validation study showed that automated interpretation of OCT images can differentiate tissue types and detect cancer positive margins with at least 81% sensitivity and 89% specificity. The findings of this pilot study suggest that OCT imaging of surgical specimens and automated interpretation of OCT data may enable in the future real-time feedback to the surgeon about margin status in patients with breast cancer, and potentially with other types of cancers. Currently, such feedback is not provided and if positive margins are left behind, patients have to undergo another surgical procedure. Therefore, this approach can have a potentially high impact on breast surgery outcome.