Enhancing inhibition-induced plasticity in tinnitus--spectral energy contrasts in tailor-made notched music matter

Abstract

Chronic tinnitus seems to be caused by reduced inhibition among frequency selective neurons in the auditory cortex. One possibility to reduce tinnitus perception is to induce inhibition onto over-activated neurons representing the tinnitus frequency via tailor-made notched music (TMNM). Since lateral inhibition is modifiable by spectral energy contrasts, the question arises if the effects of inhibition-induced plasticity can be enhanced by introducing increased spectral energy contrasts (ISEC) in TMNM. Eighteen participants suffering from chronic tonal tinnitus, pseudo randomly assigned to either a classical TMNM or an ISEC-TMNM group, listened to notched music for three hours on three consecutive days. The music was filtered for both groups by introducing a notch filter centered at the individual tinnitus frequency. For the ISEC-TMNM group a frequency bandwidth of 3/8 octaves on each side of the notch was amplified, additionally, by about 20 dB. Before and after each music exposure, participants rated their subjectively perceived tinnitus loudness on a visual analog scale. During the magnetoencephalographic recordings, participants were stimulated with either a reference tone of 500 Hz or a test tone with a carrier frequency representing the individual tinnitus pitch. Perceived tinnitus loudness was significantly reduced after TMNM exposure, though TMNM type did not influence the loudness ratings. Tinnitus related neural activity in the N1m time window and in the so called tinnitus network comprising temporal, parietal and frontal regions was reduced after TMNM exposure. The ISEC-TMNM group revealed even enhanced inhibition-induced plasticity in a temporal and a frontal cortical area. Overall, inhibition of tinnitus related neural activity could be strengthened in people affected with tinnitus by increasing spectral energy contrast in TMNM, confirming the concepts of inhibition-induced plasticity via TMNM and spectral energy contrasts.

Fig 1. Study procedure.

Tinnitus frequency was estimated before beginning of the training. The training session consisted of a hearing threshold determination for the reference tone of 500 Hz (RT). Ratings on the visual analog scale (VAS) were done before and after MEG measurements. Classical or ISEC tailor-made notched music (TMNM) was presented for 3 hours in between two VAS/MEG/VAS sessions. The training session was repeated on the next two days.

Fig 2. Power spectral density of Brownian noise filtered with both procedures.

Brownian noise was chosen to illustrate the filter procedure, as it resembles the typical energy spectrum of music (lower energy in higher frequencies, 1/f behavior). Black line: frequency spectrum of Brownian noise with 3 s duration. Blue line: frequency spectrum of 3 s of Brownian noise filtered with the applied online filter for classical tailor-made notched music (TMNM). First, spectral energy was re-distributed from low to high frequency ranges (“flattening”). Second, a frequency band of 1/2 octave width centered at 6 kHz was removed from the energy spectrum of Brownian noise (classical TMNM). Green line: frequency spectrum of 3 s of Brownian noise filtered with the applied online filter for increased spectral energy contrast TMNM (ISEC-TMNM). In addition to the filtering procedure of classical TMNM, 3/8 octaves bandwidth of the edge frequency bands around the notch were amplified by 20 dB.

Fig 3. Global source power plot of the source waveforms averaged across all subjects.

Neural activities evoked by the tinnitus tone pre (dotted line) and post (solid line) tailor-made notched music (TMNM) exposure. The a priori N1 time interval of interest (IOI) is highlighted in grey.

Fig 4. Results for the main effect Session.

A: the right part depicts Statistical Parametric Maps of F-values for the main effect Session (pre vs. post tailor-made notched music (TMNM) exposure) in a temporal (B: parietal, C: orbitofrontal, D: occipital-temporal) cluster. Only spatiotemporal clusters which survived the cluster-based permutation test are colorized. Black cylinders reflect the source locations within the significant clusters. The right part framed with a circle disentangles the direction of the effect by depicting the mean activity evoked by the tinnitus tone before and after TMNM exposure within the significant temporal (B: parietal, C: orbitofrontal, D: occipital-temporal) cluster. Error bars denote one standard error of the mean. Stars denote significance-values of the F-test (** = p <. 01, * = p <. 05, ns = non-significant).

Fig 5. Results for the interaction effect Session x Group.

A: left part depicts Statistical Parametric Maps of F-values for the interaction effect Session (pre vs. post tailor-made notched music (TMNM) exposure) x Group (increased spectral energy contrast (ISEC) vs. classical TMNM) in an inferior temporal (B: frontal) cluster. Only spatiotemporal clusters which survived the cluster-based permutation test are colorized. Black cylinders reflect the source locations within the significant clusters. The right part framed with a circle disentangles the direction of the interaction effect by depicting the mean activity evoked by the tinnitus tone before and after TMNM exposure within the significant inferior temporal (B: frontal) cluster for each group individually. Error bars denote one standard error of the mean. Stars denote significance values of pairwise t-tests disentangling the interaction effect (** = p <. 01, * = p <. 05, ns = non-significant).

Fig 6. Tinnitus loudness ratings.

Averaged ratings (across all three days) on a visual analog scale (VAS) of the subjectively perceived tinnitus loudness before (grey bar) and after (red bar) tailor-made notched music (TMNM) exposure for the increased spectral energy (ISEC) TMNM (left) and the classical TMNM (right) group. Error bars denote one standard error of the mean. Stars denote significance values of F-test depicting a significant main effect (** = p <. 01) of Session (pre vs. post music exposure) and a non-significant (ns) interaction effect Session x Group.