ABSTRACT A thorough understanding of ecosystem functioning in the Arctic Ocean, a region under severe threat by climate change, requires detailed studies on linkages between biodiversity and ecosystem stability. The identification of keystone species with special relevance for ecosystem stability is of great importance, yet difficult to achieve with established community assessments. In the case of microbes, metabarcoding and metagenomics offer fundamental insights into community structure and function, yet remain limited regarding the ecological relevance of individual taxa. To overcome this limitation, we have developed an analytical approach based on three different methods: Co-Occurrence Networks, Convergent Cross Mapping, and Energy Landscape Analysis. These methods enable the identification of seasonal communities in microbial ecosystems, elucidate their interactions, and predict potential stable community configurations under varying environmental conditions. Combining the outcomes of these three methods allowed us to define 38 keystone species in the Arctic Fram Strait that represent different trophic modes within the food web, and might signify indicator for ecosystem functionality under the impact of environmental change. Our research reveals a clear seasonal pattern in phytoplankton composition, with distinct assemblages characterizing the phases of carbon fixation (polar day) and consumption (polar night). Species interactions exhibited strong seasonality, with significant influence of summer communities on winter communities but not vice versa. Spring harbored two distinct groups: consumers (heterotrophs), strongly linked to polar night, and photoautotrophs (mainly Bacillariophyta). These groups are not causally related, suggesting a “winter reset” with selective effects that facilitates a new blooming period, allowing survivors of the dark phase to emerge. Energy Landscape Analysis showed that winter communities are more stable than summer communities. In summary, the ecological landscape of the Fram Strait can be categorized into two distinct phases: a production phase governed by specialized organisms that are highly responsive to environmental variability, and a heterotrophic phase dominated by generalist species with enhanced resilience.

The Arctic Ocean is undergoing a major transition as a result of global warming, with uncertain consequences for its ecosystems. Our study introduces an integrated analytical approach using co-occurrence networks, convergent cross-mapping, and energy landscape analysis. Applied to four years of amplicon data from Fram Strait, located at the boundary between Arctic and Atlantic waters, our method identifies keystone species in seasonal microbial communities, elucidates causal interactions, and predicts stable configurations across changing environments. We find strong evidence for a "winter reset", implying that organisms representing the spring bloom are largely determined by prevailing environmental conditions during winter. In addition, our analysis suggests that winter communities may adapt more readily to expected Atlantification than summer communities. These results highlight the utility of innovative time-series analyses in disentangling ecosystem dynamics. This approach provides critical insights into Arctic ecological interactions, dynamics, and resilience and aids in understanding ecosystem responses to environmental change. Winter environmental conditions largely determine prevailing organisms of spring blooms in the Fram Strait, according to a combined framework of co-occurrence networks, convergent cross-mapping networks, and energy landscape analysis.

Zooplankton play a crucial role in the ocean’s ecology, as they form a foundational component in the food chain by consuming phytoplankton or other zooplankton, supporting various marine species and influencing nutrient cycling. The vertical distribution of zooplankton in the ocean is patchy, and its relation to hydrographical conditions cannot be fully deciphered using traditional net casts due to the large depth intervals sampled. The Lightframe On-sight Keyspecies Investigation (LOKI) concentrates zooplankton with a net that leads to a flow-through chamber with a camera taking images. These high-resolution images allow for the determination of zooplankton taxa, often even to genus or species level, and, in the case of copepods, developmental stages. Each cruise produces a substantial volume of images, ideally requiring onboard analysis, which presently consumes a significant amount of time and necessitates internet connectivity to access the EcoTaxa Web service. To enhance the analyses, we developed an AI-based software framework named DeepLOKI, utilizing Deep Transfer Learning with a Convolution Neural Network Backbone. Our DeepLOKI can be applied directly on board. We trained and validated the model on pre-labeled images from four cruises, while images from a fifth cruise were used for testing. The best-performing model, utilizing the self-supervised pre-trained ResNet18 Backbone, achieved a notable average classification accuracy of 83.9%, surpassing the regularly and frequently used method EcoTaxa (default) in this field by a factor of two. In summary, we developed a tool for pre-sorting high-resolution black and white zooplankton images with high accuracy, which will simplify and quicken the final annotation process. In addition, we provide a user-friendly graphical interface for the DeepLOKI framework for efficient and concise processes leading up to the classification stage. Moreover, performing latent space analysis on the self-supervised pre-trained ResNet18 Backbone could prove advantageous in identifying anomalies such as deviations in image parameter settings. This, in turn, enhances the quality control of the data. Our methodology remains agnostic to the specific imaging end system used, such as Loki, UVP, or ZooScan, as long as there is a sufficient amount of appropriately labeled data available to enable effective task performance by our algorithms.

Purpose: Different imaging sequences (T1 etc.) depict different aspects of a brain tumor. As clinical MRI examinations of the brain might be terminated prematurely, not all sequences may be acquired, decreasing the performance of automated tumor segmentation. We attempt to optimize the order of sequences, to maximize information gain in case of incomplete examination. Methods: For segmentation we used the winner algorithm of the Brain Tumor Segmentation challenge 2018, trained on the BraTS 2020 dataset, with the objective to segment necrotic core, peritumoral edema, and enhancing tumor. We compared the segmentation performance for all combinations of sequences, using the Dice score (DS) as the primary metric. We compare the results with those which would be obtained by attempting to follow the consensus recommendations for brain tumor imaging [T1, FLAIR, T2, T1CE]. Results: The average segmentation accuracy varies between 0.476 for T1 only and 0.751 for the full set of sequences. T1CE has a high information content, even regarding peritumoral edema and information of T2 and FLAIR were highly redundant. The optimal order of sequences appears to be [T1, T2, T1CE, FLAIR]. Comparing segmentation accuracy after each fully acquired sequence, the first sequence (T1) is the same for both, DS for [T1, T2] (proposed) is 6.2% higher than [T1, FLAIR] (aborted recommendations), and [T1, T2, T1CE] (proposed) is 34.8% higher than [T1, FLAIR, T2] (aborted recommendations). Conclusion: For the purpose of optimal deep-learning-based segmentation purposes in potentially incomplete MRI examinations, the T1CE sequence should be acquired as early as possible.

Pancreatic cancer is a fatal malignancy with poor prognosis and limited treatment options. Early detection in primary and secondary locations is critical, but fraught with challenges. While digital pathology can assist with the classification of histopathological images, the training of such networks always relies on a ground truth, which is frequently compromised as tissue sections contain several types of tissue entities. Here we show that pancreatic cancer can be detected on hematoxylin and eosin (H&E) sections by convolutional neural networks using deep transfer learning. To improve the ground truth, we describe a preprocessing data clean-up process using two communicators that were generated through existing and new datasets. Specifically, the communicators moved image tiles containing adipose tissue and background to a new data class. Hence, the original dataset exhibited improved labeling and, consequently, a higher ground truth accuracy. Deep transfer learning of a ResNet18 network resulted in a five-class accuracy of about 94% on test data images. The network was validated with independent tissue sections composed of healthy pancreatic tissue, pancreatic ductal adenocarcinoma, and pancreatic cancer lymph node metastases. The screening of different models and hyperparameter fine tuning were performed to optimize the performance with the independent tissue sections. Taken together, we introduce a step of data preprocessing via communicators as a means of improving the ground truth during deep transfer learning and hyperparameter tuning to identify pancreatic ductal adenocarcinoma primary tumors and metastases in histological tissue sections.

Severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) causes COVID-19 and is responsible for the ongoing pandemic. Screening of potential antiviral drugs against SARS-CoV-2 depend on in vitro experiments, which are based on the quantification of the virus titer. Here, we used virus-induced cytopathic effects (CPE) in brightfield microscopy of SARS-CoV-2-infected monolayers to quantify the virus titer. Images were classified using deep transfer learning (DTL) that fine-tune the last layers of a pre-trained Resnet18 (ImageNet). To exclude toxic concentrations of potential drugs, the network was expanded to include a toxic score (TOX) that detected cell death (CPETOXnet). With this analytic tool, the inhibitory effects of chloroquine, hydroxychloroquine, remdesivir, and emetine were validated. Taken together we developed a simple method and provided open access implementation to quantify SARS-CoV-2 titers and drug toxicity in experimental settings, which may be adaptable to assays with other viruses. The quantification of virus titers from brightfield images could accelerate the experimental approach for antiviral testing.

Zielsetzung Die automatisierte Segmentierung von Hirntumoren wurde in den letzten Jahren laufend verbessert. State-of-the-art (SOTA) Modelle basieren auf 3D MRT Sequenzen (T1 ± KM, T2 und FLAIR), jedoch werden in der klinischen Routine häufig nur 2D T2 und FLAIR-Sequenzen akquiriert. Diese Arbeit evaluiert die Segmentierungsgenauigkeit von Modellen, trainiert auf kombinierten 2D/3D MRT Daten.