An Efficient Deep Learning Approach to Automatic Glaucoma Detection Using Optic Disc and Optic Cup Localization

Glaucoma is an eye disease initiated due to excessive intraocular pressure inside it and caused complete sightlessness at its progressed stage. Whereas timely glaucoma screening-based treatment can save the patient from complete vision loss. Accurate screening procedures are dependent on the availability of human experts who performs the manual analysis of retinal samples to identify the glaucomatous-affected regions. However, due to complex glaucoma screening procedures and shortage of human resources, we often face delays which can increase the vision loss ratio around the globe. To cope with the challenges of manual systems, there is an urgent demand for designing an effective automated framework that can accurately identify the Optic Disc (OD) and Optic Cup (OC) lesions at the earliest stage. Efficient and effective identification and classification of glaucomatous regions is a complicated job due to the wide variations in the mass, shade, orientation, and shapes of lesions. Furthermore, the extensive similarity between the lesion and eye color further complicates the classification process. To overcome the aforementioned challenges, we have presented a Deep Learning (DL)-based approach namely EfficientDet-D0 with EfficientNet-B0 as the backbone. The presented framework comprises three steps for glaucoma localization and classification. Initially, the deep features from the suspected samples are computed with the EfficientNet-B0 feature extractor. Then, the Bi-directional Feature Pyramid Network (BiFPN) module of EfficientDet-D0 takes the computed features from the EfficientNet-B0 and performs the top-down and bottom-up keypoints fusion several times. In the last step, the resultant localized area containing glaucoma lesion with associated class is predicted. We have confirmed the robustness of our work by evaluating it on a challenging dataset namely an online retinal fundus image database for glaucoma analysis (ORIGA). Furthermore, we have performed cross-dataset validation on the High-Resolution Fundus (HRF), and Retinal Image database for Optic Nerve Evaluation (RIM ONE DL) datasets to show the generalization ability of our work. Both the numeric and visual evaluations confirm that EfficientDet-D0 outperforms the newest frameworks and is more proficient in glaucoma classification.

Unilateral Hypermature Cataract and Uveitis in Dwarf Campbell’s Hamster (Phodopus campbelli)

Background: In the ophthalmological examination of a 1.5-year-old male dwarf Campbell hamster, who was examined with complaints of photophobia, pain, weakness and whitening of the eye color, hypermature cataract and chronic uveitis were observed in the left eye. Methods: Local antibiotic therapy was administered to the patient for the first ten days in order to eliminate a possible microbial agent. In addition, local NSAI drugs were applied to reduce pain and inflammation. Then, peros Prednol (methylprednisolone) was administered at a dose of 0.5 mg/kg for the first ten days and 1 mg/kg for the next ten days in order to suppress the inflammation associated with uveitis. The patient’s body weight and intraocular pressure were measured before the treatment. During the treatment, intraocular pressure values were checked every day. During this period, the patient was fed ad libitum at normal room temperature, in his own cage. Result: As a result of the treatment applied to the patient, who was followed up for more than a month, symptoms such as pain, photophobia and blepharospasm disappeared and the patient’s eating and drinking status improved compared to the past. However, increasing dose of Prednol did not have the expected effect on intraocular pressure values. Due to the very small size of the hamster eye in the treatment of hypermature cataracts, lens removal cannot be performed as easily as in other species.

Further insight into the global variability of the OCA2-HERC2 locus for human pigmentation from multiallelic markers

The OCA2-HERC2 locus is responsible for the greatest proportion of eye color variation in humans. Numerous studies extensively described both functional SNPs and associated patterns of variation over this region. The goal of our study is to examine how these haplotype structures and allelic associations vary when highly variable markers such as microsatellites are used. Eleven microsatellites spanning 357 Kb of OCA2-HERC2 genes are analyzed in 3029 individuals from worldwide populations. We found that several markers display large differences in allele frequency (10% to 35% difference) among Europeans, East Asians and Africans. In Europe, the alleles showing increased frequency can also discriminate individuals with (IrisPlex) predicted blue and brown eyes. Distinct haplotypes are identified around the variants C and T of the functional SNP rs12913832 (associated to blue eyes), with linkage disequilibrium r2 values significant up to 237 Kb. The haplotype carrying the allele rs12913832 C has high frequency (76%) in blue eye predicted individuals (30% in brown eye predicted individuals), while the haplotype associated to the allele rs12913832 T is restricted to brown eye predicted individuals. Finally, homozygosity values reach levels of 91% near rs12913832. Odds ratios show values of 4.2, 7.4 and 10.4 for four markers around rs12913832 and 7.1 for their core haplotype. Hence, this study provides an example on the informativeness of multiallelic markers that, despite their current limited potential contribution to forensic eye color prediction, supports the use of microsatellites for identifying causing variants showing similar genetic features and history.

The Role of Eye Color in the Emergence of Tinnitus in Silence

Introduction Previous research suggests that African Americans are less likely than Caucasians to perceive tinnitus in sustained silence. Objective To evaluate the association between non-cutaneous melanin as indicated by eye color and the emergence of temporary tinnitus during a brief period of silence. Methods A cross-section of adults grouped according to their eye color were exposed to silence. A total of 62 adults, aged 18 to 35 years (10 males, 52 females) were required to sit in silence for 10 minutes, after which they filled out a questionnaire to report their eye color and any perception of sounds in the ears or head. Results In total, 63% of the participants perceived tinnitus while sitting in silence, and, of these 95% perceived the tinnitus sounds within 5 minutes of sitting in silence. Though African Americans were less likely to perceive tinnitus in silence, this difference was not significant (p = 0.6). After a period of silence, 69% of the subjects with light-colored eyes and 58% of the dark-eyed subjects perceived tinnitus. This difference was not statistically significant (χ2(1) = 0.77; p = 0.38). Conclusion When exposed to reduced auditory stimulation, 3 out of 5 normal-hearing people are likely to experience tinnitus. However, there was no relationship between eye color and the perception of tinnitus in silence. Although melanin has been shown to play a role in the protection of the ear against noise trauma and the effects of age-related hearing loss, its role in the emergence of tinnitus needs further investigation.

Blue Eyes Help Men Reduce the Cost of Cuckoldry

Men with light eyes lack the dominant gene allele that codes for dark-brown eyes. Pairing with a woman who lacks the same allele must increase paternity confidence in these men, because any children with dark eyes would be extremely unlikely to have been fathered by them. This notion implies that men with light (blue or green) eyes should (1) prefer light-eyed women, especially in a long-term context, and (2) feel more threatened by light-eyed than by dark-eyed rivals. Yet because choosiness is costly and paternity concerns are entirely driven by the prospect of paternal investment, any such inclinations would be adaptive only in men who expect to invest in their children. Here I test these ideas using the data of over 1000 men who rated the facial attractiveness of potential partners, and the threat of potential rivals, whose eye color had been manipulated. Light-eyed men liked light-eyed women better (particularly as long-term companions), and feared light-eyed rivals more, than did dark-eyed men. An exploratory analysis showed that these large, robust effects disappeared in men who had felt rejected by their fathers while growing up—suggesting that such men are not expecting to invest in their own children either.

Like Mother, Like Daughter: Adults’ Judgements about Genetic Inheritance

Do people think about genetic inheritance as a deterministic or probabilistic process? Do adults display systematic biases when reasoning about genetic inheritance? Knowing how adults think about genetic inheritance is valuable, both for understanding the developmental endpoint of these concepts and for identifying biases that persist even after formal education. We examined adults’ reasoning about genetic inheritance for familiar and unfamiliar animals. First, participants were presented with animals that varied in eye color and were asked to judge whether each could be the offspring of a particular set of animal parents that had either the same or different eye colors. The potential offspring had eye colors that were either identical to the parents, blended the parents’ eye colors, or differed from the parents. Next, participants predicted how six offspring of the animal parents would look. Participants judged a variety of choices as possible—not only the ones resembling the parents—suggesting that they thought genetic inheritance was a probabilistic process. Additionally, many participants thought that female offspring would look more like their mothers and male offspring would look more like their fathers. Thus, systemic biases in reasoning about inheritance persist into adulthood.

The Added Value of Sensitivity to Nonnoxious Stimuli to Predict an Individual’s Sensitivity to Pain

BACKGROUND: Simple tools are needed to predict postoperative pain. Questionnaire-based tools such as the Pain Sensitivity Questionnaire (PSQ) are validated for this purpose, but prediction could be improved by incorporating other parameters. OBJECTIVES: To explore the potency of sensitivity to nonpainful stimuli and biometric data to improve prediction of pain. STUDY DESIGN: Transversal exploratory study. SETTING: Single clinical investigation center. METHODS. Eighty-five healthy volunteers of both genders underwent a multimodal exploration including biometry, questionnaire-based assessment of anxiety, depression, pain catastrophizing, sensitivity to smell, and the PSQ, followed by a psychophysical assessment of unpleasantness thresholds for light and sound, and sensitivity to mechanical, heat, and cold pain. These last 3 parameters were used to calculate a composite pain score. After a multi-step selection, multivariable analyses identified the explanative factors of experimental pain sensitivity, by including biometric, questionnaire-based, and psychophysical nonnociceptive sensitivity parameters, with the aim of having each domain represented. RESULTS: Female gender predicted mechanical pain, a younger age and dark eyes predicted cold pain, and the PSQ predicted heat pain. Sensitivity to unpleasantness of sound predicted mechanical and heat pain, and sensitivity to unpleasantness of light predicted cold pain. Sensitivity to smell was unrelated. The predictors of the composite pain score were the PSQ, the light unpleasantness threshold, and an interaction between gender and eye color, the score being lower in light-eyed men and higher in all women. The final multivariable multi-domain model was more predictive of pain than the PSQ alone (R2 = 0.301 vs 0.122, respectively). LIMITATIONS: Sensitivity to smell was only assessed by a short questionnaire and could lack relevance. Healthy volunteers were unlikely to elicit psychological risk factors such as anxiety, depression, or catastrophizing. These results have not been validated in a clinical setting (e.g., perioperative). CONCLUSION: The predictive potential of the PSQ can be improved by including information about gender, eye color, and light sensitivity. However, there is still a need for a technique suitable for routine clinical use to assess light sensitivity. KEY WORDS: Personalized medicine, postoperative pain, senses, prediction, photophobia, hyperacusis, eye color, hypervigilance, sensory over-responsivity

GenNet framework: interpretable deep learning for predicting phenotypes from genetic data

Applying deep learning in population genomics is challenging because of computational issues and lack of interpretable models. Here, we propose GenNet, a novel open-source deep learning framework for predicting phenotypes from genetic variants. In this framework, interpretable and memory-efficient neural network architectures are constructed by embedding biologically knowledge from public databases, resulting in neural networks that contain only biologically plausible connections. We applied the framework to seventeen phenotypes and found well-replicated genes such as HERC2 and OCA2 for hair and eye color, and novel genes such as ZNF773 and PCNT for schizophrenia. Additionally, the framework identified ubiquitin mediated proteolysis, endocrine system and viral infectious diseases as most predictive biological pathways for schizophrenia. GenNet is a freely available, end-to-end deep learning framework that allows researchers to develop and use interpretable neural networks to obtain novel insights into the genetic architecture of complex traits and diseases.

Knowledge of, and Attitudes towards, Live Fish Transport among Aquaculture Industry Stakeholders in China: A Qualitative Study

China is the largest food fish producer in the world. Chinese consumers normally purchase fish that are still alive to ensure freshness. Therefore, the live transport of fish is important in China’s aquaculture, although it carries potential risks for animal welfare. This study investigated the attitudes and knowledge of stakeholders within Chinese aquaculture towards the live transport and welfare of fish. Semi-structured interviews were conducted with 12 participants who were involved with the aquaculture industry in China. Most participants self-rated their transport-related knowledge as moderate and had some understanding of animal welfare, although this term was generally considered only relevant to terrestrial animals. Participants’ responses indicated that the live transport of fish occurs frequently in China, generally using sealed tanks, plastic bags, and foam boxes, in purpose-built vehicles. Seasonal changes, such as changes in ambient and water temperature, are considered to be important contributors to successful live transport, as well as sufficient oxygen supplies and stocking density. The use of anesthetics was not commonly reported, particularly in food fish, and fish capture is predominantly by conventional dipnets. The health status of transported fish is determined mostly by morphology (body injury, body or eye color, and fin condition), as well as vigor and swimming ability. Our results indicate that live transport poses a number of welfare risks to fish but that participants in the process associated welfare concerns more with terrestrial animals, not fish.