Frequency difference beyond behavioral limen reflected by frequency following response of human auditory Brainstem

Predicting microvascular invasion in hepatocellular carcinoma: a deep learning model validated across hospitals

BACKGROUND

The accuracy of estimating microvascular invasion (MVI) preoperatively in hepatocellular carcinoma (HCC) by clinical observers is low. Most recent studies constructed MVI predictive models utilizing radiological and/or radiomics features extracted from computed tomography (CT) images. These methods, however, rely heavily on human experiences and require manual tumor contouring. We developed a deep learning-based framework for preoperative MVI prediction by using CT images of arterial phase (AP) with simple tumor labeling and without the need of manual feature extraction. The model was further validated on CT images that were originally scanned at multiple different hospitals.

METHODS

CT images of AP were acquired for 309 patients from China Medical University Hospital (CMUH). Images of 164 patients, who took their CT scanning at 54 different hospitals but were referred to CMUH, were also collected. Deep learning (ResNet-18) and machine learning (support vector machine) models were constructed with AP images and/or patients' clinical factors (CFs), and their performance was compared systematically. All models were independently evaluated on two patient cohorts: validation set (within CMUH) and external set (other hospitals). Subsequently, explainability of the best model was visualized using gradient-weighted class activation map (Grad-CAM).

RESULTS

The ResNet-18 model built with AP images and patients' clinical factors was superior than other models achieving a highest AUC of 0.845. When evaluating on the external set, the model produced an AUC of 0.777, approaching its performance on the validation set. Model interpretation with Grad-CAM revealed that MVI relevant imaging features on CT images were captured and learned by the ResNet-18 model.

CONCLUSIONS

This framework provide evidence showing the generalizability and robustness of ResNet-18 in predicting MVI using CT images of AP scanned at multiple different hospitals. Attention heatmaps obtained from model explainability further confirmed that ResNet-18 focused on imaging features on CT overlapping with the conditions used by radiologists to estimate MVI clinically.

Subclinical Auditory Neural Deficits in Patients With Type 1 Diabetes Mellitus

Supplemental Digital Content is available in the text.

Objectives:

Diabetes mellitus (DM) is associated with a variety of sensory complications. Very little attention has been given to auditory neuropathic complications in DM. The aim of this study was to determine whether type 1 DM (T1DM) affects neural coding of the rapid temporal fluctuations of sounds, and how any deficits may impact on behavioral performance.

Design:

Participants were 30 young normal-hearing T1DM patients, and 30 age-, sex-, and audiogram-matched healthy controls. Measurements included electrophysiological measures of auditory nerve and brainstem function using the click-evoked auditory brainstem response, and of brainstem neural temporal coding using the sustained frequency-following response (FFR); behavioral tests of temporal coding (interaural phase difference discrimination and the frequency difference limen); tests of speech perception in noise; and self-report measures of auditory disability using the Speech, Spatial and Qualities of Hearing Scale.

Results:

There were no significant differences between T1DM patients and controls in the auditory brainstem response. However, the T1DM group showed significantly reduced FFRs to both temporal envelope and temporal fine structure. The T1DM group also showed significantly higher interaural phase difference and frequency difference limen thresholds, worse speech-in-noise performance, as well as lower overall Speech, Spatial and Qualities scores than the control group.

Conclusions:

These findings suggest that T1DM is associated with degraded neural temporal coding in the brainstem in the absence of an elevation in audiometric threshold, and that the FFR may provide an early indicator of neural damage in T1DM, before any abnormalities can be identified using standard clinical tests. However, the relation between the neural deficits and the behavioral deficits is uncertain.

The Effects of Visual Cues, Blindfolding, Synesthetic Experience, and Musical Training on Pure-Tone Frequency Discrimination

How perceptual limits can be reduced has long been examined by psychologists. This study investigated whether visual cues, blindfolding, visual-auditory synesthetic experience, and musical training could facilitate a smaller frequency difference limen (FDL) in a gliding frequency discrimination test. Ninety university students, with no visual or auditory impairment, were recruited for this one-between (blindfolded/visual cues) and one-within (control/experimental session) designed study. Their FDLs were tested by an alternative forced-choice task (gliding upwards/gliding downwards/no change) and two questionnaires (Vividness of Mental Imagery Questionnaire and Projector⁻Associator Test) were used to assess their tendency to synesthesia. The participants provided with visual cues and with musical training showed a significantly smaller FDL; on the other hand, being blindfolded or having a synesthetic experience before could not significantly reduce the FDL. However, no pattern was found between the perception of the gliding upwards and gliding downwards frequencies. Overall, the current study suggests that the inter-sensory perception can be enhanced through the training and facilitation of visual⁻auditory interaction under the multiple resource model. Future studies are recommended in order to verify the effects of music practice on auditory percepts, and the different mechanisms between perceiving gliding upwards and downwards frequencies.

Correlation between the frequency difference limen and an index based on principal component analysis of the frequency-following response of normal hearing listeners

Subcortical phase locking tends to reflect performance differences in tasks related to pitch perception across different types of populations. Enhancement or attenuation in its strength may correspond to population excellence or deficiency in pitch perception. However, it is still unclear whether differences in perceptual capability among individuals with normal hearing can be predicted by subcortical phase locking. In this study, we examined the brain-behavior relationship between frequency-following responses (FFRs) evoked by pure/sweeping tones and frequency difference limens (FDLs). FFRs are considered to reflect subcortical phase locking, and FDLs are a psychophysical measure of behavioral performance in pitch discrimination. Traditional measures of FFR strength were found to be poorly correlated with FDL. Here, we introduced principal component analysis into FFR analysis and extracted an FFR component that was correlated with individual pitch discrimination. The absolute value of the score of this FFR principal component (but not the original score) was negatively correlated with FDL, regardless of stimulus type. The topographic distribution of this component was relatively constant across individuals and across stimulus types, and the inferior colliculus was identified as its origin. The findings suggest that subcortical phase locking at certain but not all FFR generators carries the neural information required for the prediction of individual pitch perception among humans with normal hearing.

Processing Complex Sounds Passing through the Rostral Brainstem: The New Early Filter Model

The rostral brainstem receives both “bottom-up” input from the ascending auditory system and “top-down” descending corticofugal connections. Speech information passing through the inferior colliculus of elderly listeners reflects the periodicity envelope of a speech syllable. This information arguably also reflects a composite of temporal-fine-structure (TFS) information from the higher frequency vowel harmonics of that repeated syllable. The amplitude of those higher frequency harmonics, bearing even higher frequency TFS information, correlates positively with the word recognition ability of elderly listeners under reverberatory conditions. Also relevant is that working memory capacity (WMC), which is subject to age-related decline, constrains the processing of sounds at the level of the brainstem. Turning to the effects of a visually presented sensory or memory load on auditory processes, there is a load-dependent reduction of that processing, as manifest in the auditory brainstem responses (ABR) evoked by to-be-ignored clicks. Wave V decreases in amplitude with increases in the visually presented memory load. A visually presented sensory load also produces a load-dependent reduction of a slightly different sort: The sensory load of visually presented information limits the disruptive effects of background sound upon working memory performance. A new early filter model is thus advanced whereby systems within the frontal lobe (affected by sensory or memory load) cholinergically influence top-down corticofugal connections. Those corticofugal connections constrain the processing of complex sounds such as speech at the level of the brainstem. Selective attention thereby limits the distracting effects of background sound entering the higher auditory system via the inferior colliculus. Processing TFS in the brainstem relates to perception of speech under adverse conditions. Attentional selectivity is crucial when the signal heard is degraded or masked: e.g., speech in noise, speech in reverberatory environments. The assumptions of a new early filter model are consistent with these findings: A subcortical early filter, with a predictive selectivity based on acoustical (linguistic) context and foreknowledge, is under cholinergic top-down control. A prefrontal capacity limitation constrains this top-down control as is guided by the cholinergic processing of contextual information in working memory.