Whole Brain Network effects of subcallosal cingulate deep brain stimulation for treatment-resistant depression

Abstract

Ongoing experimental studies of subcallosal cingulate deep brain stimulation (SCC DBS) for treatment-resistant depression (TRD) show a differential timeline of behavioral effects with rapid changes after initial stimulation, and both early and delayed changes over the course of ongoing chronic stimulation. This study examined the longitudinal resting-state regional cerebral blood ow (rCBF) changes in intrinsic connectivity networks (ICNs) with SCC DBS for TRD over 6 months and repeated the same analysis by glucose metabolite changes in a new cohort. A total of twenty-two patients with TRD, 17 [15O]-water and 5 [18]-Fluorodeoxyglucose (FDG) positron emission tomography (PET) patients, received SCC DBS and were followed weekly for 7 months. PET scans were collected at 4-time points: baseline, 1-month after surgery, and 1 and 6 months of chronic stimulation. A linear mixed model was conducted to examine the differential trajectory of rCBF changes over time. Post-hoc tests were also examined to assess postoperative, early, and late ICN changes and response-specific effects. SCC DBS had significant time-specific effects in the salience network (SN) and the default mode network (DMN). The rCBF in SN and DMN was decreased after surgery, but responder and non-responders diverged thereafter, with a net increase in DMN activity in responders with chronic stimulation. Additionally, the rCBF in the DMN uniquely correlated with depression severity. The glucose metabolic changes in a second cohort show the same DMN changes. The trajectory of PET changes with SCC DBS is not linear, consistent with the chronology of therapeutic effects. These data provide novel evidence of both an acute reset and ongoing plastic effects in the DMN that may provide future biomarkers to track clinical improvement with ongoing treatment.

Figure 1

Longitudinal changes of Hamilton Depression Rating Scale (HDRS-17) and regional cerebral blood ow (rCBF) in intrinsic connectivity networks (ICNs). (A) HDRS-17 over time. The grey line in the bottom indicates the off-stimulation phase for 1-month, while the black line in the bottom indicates the chronic stimulation on. (B-D) Time effect of rCBF in ICNs using linear mixed model for repeated measure (FDR q<0.05). There were time effects in (B) salience/ventral attention B (F=4.62, q=0.042), (C) default A (F=4.94, q=0.045), (D) left anterior thalamus (F=5.88, q=0.032). Asterisk represents statistically significant changes (*: p<0.05, **: p<0.005). Transparent lines in the boxes represent individual longitudinal trajectories, and the solid line is the mean of longitudinal trajectory.

Figure 2

Main effect of clinical improvement. Relationship between percent changes of rCBF and percent changes of HDRS-17 from baseline in default A networks (Conditional R²=0.75, p<0.001). Red circle indicates the last time point of each patient (after 6-months of chronic stimulation).

Figure 3

Changes of HDRS-17 and rCBF of default A in responders and non-responders. (A) HDRS-17 over time for responders and non-responders with DBS. (B) Significant rCBF changes over time in default A in responders (F=3.96, p=0.026). For post-hoc analysis, there were not only early decreased changes of rCBF after surgery (p=0.023), but also late increased rCBF changes between after surgery and 6-months stimulation (p=0.006). (C) Significant rCBF changes over time in default A in non-responders (F=3.13, p=0.043). For post-hoc analysis, there were early decreased changes of rCBF after surgery (p=0.015) and maintained over time. Asterisk represents statistically significant changes (*: p<0.05).

Figure 4

Main effect of clinical improvement after surgery or ongoing chronic stimulation from baseline. (A) Relationship between percent changes of rCBF and percent changes of HDRS-17 after surgery in default A network (R²=0.289, p=0.039). (B) Relationship between percent changes of rCBF and percent changes of HDRS-17 with ongoing stimulation in default A network (Conditional R²=0.779, p=0.029). Red circle indicates the last time point of each patient (after 6-months of chronic stimulation).

Figure 5

Summary of replicated results in cohort 2 using [F18]-FDG PET. Red line represents the responders (n=4), and blue line represents the non-responders (n=1). (A) Percent changes of HDRS-17 over time from baseline. (B-C) Longitudinal patterns of standardized uptake value ratio (SUVR) in ICNs which were significant in the cohort 1; (B) default A, and (C) left anterior thalamus. Asterisk represents statistically significant changes (*: p<0.05, **: p<0.005).