Deep learning can yield clinically useful right ventricular segmentations faster than fully manual analysis

Abstract

Right ventricular (RV) volumes are commonly obtained through time-consuming manual delineations of cardiac magnetic resonance (CMR) images. Deep learning-based methods can generate RV delineations, but few studies have assessed their ability to accelerate clinical practice. Therefore, we aimed to develop a clinical pipeline for deep learning-based RV delineations and validate its ability to reduce the manual delineation time. Quality-controlled delineations in short-axis CMR scans from 1114 subjects were used for development. Time reduction was assessed by two observers using 50 additional clinical scans. Automated delineations were subjectively rated as (A) sufficient for clinical use, or as needing (B) minor or (C) major corrections. Times were measured for manual corrections of delineations rated as B or C, and for fully manual delineations on all 50 scans. Fifty-eight % of automated delineations were rated as A, 42% as B, and none as C. The average time was 6 min for a fully manual delineation, 2 s for an automated delineation, and 2 min for a minor correction, yielding a time reduction of 87%. The deep learning-based pipeline could substantially reduce the time needed to manually obtain clinically applicable delineations, indicating ability to yield right ventricular assessments faster than fully manual analysis in clinical practice. However, these results may not generalize to clinics using other RV delineation guidelines.

Figure 1

The data inclusion and data curation process. The refinement refers to the process of removing subjects with inadequate delineations in some timeframe.

Figure 2

A flowchart of the pipeline. An input timeframe is pre-processed and inserted into a slice selection network that selects slices containing RV cross-sections. The RV center point is then detected in each selected slice by the RV center point detection network and used to crop (or pad) each slice around the RV before insertion into the segmentation network. This yields a segmentation of the RV, that is then inversely padded or cropped to match the original slice size.

Figure 3

Bland–Altman and correlation plots between the pipeline’s automated (A) and the reference (R) RVEDV (left column) and RVESV (right column) on the clinical validation set (CVS). The Bland–Altman plots contain bias (full lines) and limits of agreement (± 1.96 SD, dashed lines). The correlation plots contain identity lines (black, dashed lines), least squares lines (grey, full lines), Spearman’s rank correlation coefficients (r), and corresponding p values.

Figure 4

Bland–Altman plots and scatter plots on the clinical validation set. The left column (blue) shows the pipeline's automated (A) delineations vs. Observer 1 (O1), the middle column (red) shows A vs. Observer 2 (O2), and the right column (magenta) shows O1 vs. O2. The top half shows right ventricular (RV) end-diastolic volumes (RVEDV) and the bottom row RV end-systolic volumes (RVESV). The Bland–Altman plots contain bias (full lines) and limits of agreement (± 1.96 SD, dashed lines). The correlation plots contain identity lines (black, dashed lines), least squares lines (grey, full lines), Spearman’s rank correlation coefficients (r) and corresponding p values.

Figure 5

Bland–Altman plots and correlation plots showing the inter-observer variability for manual delineations (blue) and the corrections of delineations from the pipeline (red). To the left are results for end-diastolic volumes (RVEDV) and to the right are results for end-systolic volumes (RVESV). The Bland–Altman plots contain bias (full lines) and limits of agreement (± 1.96 SD, dashed lines). The correlation plots contain identity lines (black, dashed lines), least squares lines (full lines), Spearman’s rank correlation coefficients (r) and corresponding p values. Both plots indicate that the inter-observer variability decreased when the pipeline was used, and delineations were corrected.