Automated detection and staging of malaria parasites from cytological smears using convolutional neural networks.

Microscopic examination of blood smears remains the gold standard for laboratory inspection and diagnosis of malaria. Smear inspection is, however, time-consuming and dependent on trained microscopists with results varying in accuracy. We sought to develop an automated image analysis method to improve accuracy and standardization of smear inspection that retains capacity for expert confirmation and image archiving.

Detection of Complex Sounds in Quiet Conditions by Seals and Sea Lions.

To test how accurately baseline audiometric data predict detection of complex stimuli, absolute detection thresholds for frequency-modulated (FM), amplitude-modulated (AM), and harmonic stimuli were obtained for one Phoca vitulina (harbor seal) and one Zalophus californianus (California sea lion) at frequencies spanning the functional range of hearing. These thresholds were then compared with a priori predictions based on the tonal audiograms of these subjects. Predicted thresholds were accurate for most FM signals and for AM signals for the California sea lion.

High-frequency hearing in seals and sea lions.

Existing evidence suggests that some pinnipeds (seals, sea lions, and walruses) can detect underwater sound at frequencies well above the traditional high-frequency hearing limits for their species. This phenomenon, however, is not well studied: Sensitivity patterns at frequencies beyond traditional high-frequency limits are poorly resolved, and the nature of the auditory mechanism mediating hearing at these frequencies is unknown. In the first portion of this study, auditory sensitivity patterns in the 50-180 kHz range were measured for one California sea lion (Zalophus californianus), one harbor seal (Phoca vitulina), and one spotted seal (Phoca largha).

Auditory sensitivity of seals and sea lions in complex listening scenarios.

Standard audiometric data, such as audiograms and critical ratios, are often used to inform marine mammal noise-exposure criteria. However, these measurements are obtained using simple, artificial stimuli-i.e.

Auditory detection of ultrasonic coded transmitters by seals and sea lions.

Ultrasonic coded transmitters (UCTs) are high-frequency acoustic tags that are often used to conduct survivorship studies of vulnerable fish species. Recent observations of differential mortality in tag control studies suggest that fish instrumented with UCTs may be selectively targeted by marine mammal predators, thereby skewing valuable survivorship data. In order to better understand the ability of pinnipeds to detect UCT outputs, behavioral high-frequency hearing thresholds were obtained from a trained harbor seal (Phoca vitulina) and a trained California sea lion (Zalophus californianus).

Simulated masking of right whale sounds by shipping noise: incorporating a model of the auditory periphery.

Many species of large, mysticete whales are known to produce low-frequency communication sounds. These low-frequency sounds are susceptible to communication masking by shipping noise, which also tends to be low frequency in nature. The size of these species makes behavioral assessment of auditory capabilities in controlled, captive environments nearly impossible, and field-based playback experiments are expensive and necessarily limited in scope.