Deep Learning Based on Standard H&E Images of Primary Melanoma Tumors Identifies Patients at Risk for Visceral Recurrence and Death.

PURPOSE: Biomarkers for disease-specific survival (DSS) in early-stage melanoma are needed to select patients for adjuvant immunotherapy and accelerate clinical trial design. We present a pathology-based computational method using a deep neural network architecture for DSS prediction. EXPERIMENTAL DESIGN: The model was trained on 108 patients from four institutions and tested on 104 patients from Yale School of Medicine (YSM, New Haven, CT). A receiver operating characteristic (ROC) curve was generated on the basis of vote aggregation of individual image sequences, an optimized cutoff was selected, and the computational model was tested on a third independent population of 51 patients from Geisinger Health Systems (GHS). RESULTS: Area under the curve (AUC) in the YSM patients was 0.905 (P < 0.0001). AUC in the GHS patients was 0.880 (P < 0.0001). Using the cutoff selected in the YSM cohort, the computational model predicted DSS in the GHS cohort based on Kaplan-Meier (KM) analysis (P < 0.0001). CONCLUSIONS: The novel method presented is applicable to digital images, obviating the need for sample shipment and manipulation and representing a practical advance over current genetic and IHC-based methods.

Cortical Pain Processing in the Rat Anterior Cingulate Cortex and Primary Somatosensory Cortex.

Pain is a complex multidimensional experience encompassing sensory-discriminative, affective-motivational and cognitive-emotional components mediated by different neural mechanisms. Investigations of neurophysiological signals from simultaneous recordings of two or more cortical circuits may reveal important circuit mechanisms on cortical pain processing. The anterior cingulate cortex (ACC) and primary somatosensory cortex (S1) represent two most important cortical circuits related to sensory and affective processing of pain. Here, we recorded in vivo extracellular activity of the ACC and S1 simultaneously from male adult Sprague-Dale rats (n = 5), while repetitive noxious laser stimulations were delivered to animalÕs hindpaw during pain experiments. We identified spontaneous pain-like events based on stereotyped pain behaviors in rats. We further conducted systematic analyses of spike and local field potential (LFP) recordings from both ACC and S1 during evoked and spontaneous pain episodes. From LFP recordings, we found stronger phase-amplitude coupling (theta phase vs. gamma amplitude) in the S1 than the ACC (n = 10 sessions), in both evoked (p = 0.058) and spontaneous pain-like behaviors (p = 0.017, paired signed rank test). In addition, pain-modulated ACC and S1 neuronal firing correlated with the amplitude of stimulus-induced event-related potentials (ERPs) during evoked pain episodes. We further designed statistical and machine learning methods to detect pain signals by integrating ACC and S1 ensemble spikes and LFPs. Together, these results reveal differential coding roles between the ACC and S1 in cortical pain processing, as well as point to distinct neural mechanisms between evoked and putative spontaneous pain at both LFP and cellular levels.

A deep learning approach for real-time detection of sleep spindles.

OBJECTIVE: Sleep spindles have been implicated in memory consolidation and synaptic plasticity during NREM sleep. Detection accuracy and latency in automatic spindle detection are critical for real-time applications. APPROACH: Here we propose a novel deep learning strategy (SpindleNet) to detect sleep spindles based on a single EEG channel. While the majority of spindle detection methods are used for off-line applications, our method is well suited for online applications. MAIN RESULTS: Compared with other spindle detection methods, SpindleNet achieves superior detection accuracy and speed, as demonstrated in two publicly available expert-validated EEG sleep spindle datasets. Our real-time detection of spindle onset achieves detection latencies of 150-350 ms (~two-three spindle cycles) and retains excellent performance under low EEG sampling frequencies and low signal-to-noise ratios. SpindleNet has good generalization across different sleep datasets from various subject groups of different ages and species. SIGNIFICANCE: SpindleNet is ultra-fast and scalable to multichannel EEG recordings, with an accuracy level comparable to human experts, making it appealing for long-term sleep monitoring and closed-loop neuroscience experiments.

Binge alcohol alters exercise-driven neuroplasticity.

Exercise is increasingly being used as a treatment for alcohol use disorders (AUD), but the interactive effects of alcohol and exercise on the brain remain largely unexplored. Alcohol damages the brain, in part by altering glial functioning. In contrast, exercise promotes glial health and plasticity. In the present study, we investigated whether binge alcohol would attenuate the effects of subsequent exercise on glia. We focused on the medial prefrontal cortex (mPFC), an alcohol-vulnerable region that also undergoes neuroplastic changes in response to exercise. Adult female Long-Evans rats were gavaged with ethanol (25% w/v) every 8h for 4days. Control animals received an isocaloric, non-alcohol diet. After 7days of abstinence, rats remained sedentary or exercised for 4weeks. Immunofluorescence was then used to label microglia, astrocytes, and neurons in serial tissue sections through the mPFC. Confocal microscope images were processed using FARSIGHT, a computational image analysis toolkit capable of automated analysis of cell number and morphology. We found that exercise increased the number of microglia in the mPFC in control animals. Binged animals that exercised, however, had significantly fewer microglia. Furthermore, computational arbor analytics revealed that the binged animals (regardless of exercise) had microglia with thicker, shorter arbors and significantly less branching, suggestive of partial activation. We found no changes in the number or morphology of mPFC astrocytes. We conclude that binge alcohol exerts a prolonged effect on morphology of mPFC microglia and limits the capacity of exercise to increase their numbers.

Quantitative 3-D analysis of GFAP labeled astrocytes from fluorescence confocal images.

BACKGROUND: There is a need for effective computational methods for quantifying the three-dimensional (3-D) spatial distribution, cellular arbor morphologies, and the morphological diversity of brain astrocytes to support quantitative studies of astrocytes in health, injury, and disease. NEW METHOD: Confocal fluorescence microscopy of multiplex-labeled (GFAP, DAPI) brain tissue is used to perform imaging of astrocytes in their tissue context. The proposed computational method identifies the astrocyte cell nuclei, and reconstructs their arbors using a local priority based parallel (LPP) tracing algorithm. Quantitative arbor measurements are extracted using Scorcioni's L-measure, and profiled by unsupervised harmonic co-clustering to reveal the morphological diversity. RESULTS: The proposed method identifies astrocyte nuclei, generates 3-D reconstructions of their arbors, and extracts quantitative arbor measurements, enabling a morphological grouping of the cell population. COMPARISON WITH EXISTING METHODS: Our method enables comprehensive spatial and morphological profiling of astrocyte populations in brain tissue for the first time, and overcomes limitations of prior methods. Visual proofreading of the results indicate a >95% accuracy in identifying astrocyte nuclei. The arbor reconstructions exhibited 3.2% fewer erroneous jumps in tracing, and 17.7% fewer false segments compared to the widely used fast-marching method that resulted in 9% jumps and 20.8% false segments. CONCLUSIONS: The proposed method can be used for large-scale quantitative studies of brain astrocyte distribution and morphology.

Algorithms for improved 3-D reconstruction of live mammalian embryo vasculature from optical coherence tomography data.

BACKGROUND: Robust reconstructions of the three-dimensional network of blood vessels in developing embryos imaged by optical coherence tomography (OCT) are needed for quantifying the longitudinal development of vascular networks in live mammalian embryos, in support of developmental cardiovascular research. Past computational methods [such as speckle variance (SV)] have demonstrated the feasibility of vascular reconstruction, but multiple challenges remain including: the presence of vessel structures at multiple spatial scales, thin blood vessels with weak flow, and artifacts resulting from bulk tissue motion (BTM). METHODS: In order to overcome these challenges, this paper introduces a robust and scalable reconstruction algorithm based on a combination of anomaly detection algorithms and a parametric dictionary based sparse representation of blood vessels from structural OCT data. RESULTS: Validation results using confocal data as the baseline demonstrate that the proposed method enables the detection of vessel segments that are either partially missed or weakly reconstructed using the SV method. Finally, quantitative measurements of vessel reconstruction quality indicate an overall higher quality of vessel reconstruction with the proposed method. CONCLUSIONS: Results suggest that sparsity-integrated speckle anomaly detection (SSAD) is potentially a valuable tool for performing accurate quantification of the progression of vascular development in the mammalian embryonic yolk sac as imaged using OCT.