Search

Abstract Background Colorectal cancer is a leading cause of cancer-related deaths worldwide. The best method to prevent CRC is a colonoscopy. However, not all colon polyps have the risk of becoming cancerous. Therefore, polyps are classified using different classification systems. After the classification, further treatment and procedures are based on the classification of the polyp. Nevertheless, classification is not easy. Therefore, we suggest two novel automated classifications system assisting gastroenterologists in classifying polyps based on the NICE and Paris classification. Methods We build two classification systems. One is classifying polyps based on their shape (Paris). The other classifies polyps based on their texture and surface patterns (NICE). A two-step process for the Paris classification is introduced: First, detecting and cropping the polyp on the image, and secondly, classifying the polyp based on the cropped area with a transformer network. For the NICE classification, we design a few-shot learning algorithm based on the Deep Metric Learning approach. The algorithm creates an embedding space for polyps, which allows classification from a few examples to account for the data scarcity of NICE annotated images in our database. Results For the Paris classification, we achieve an accuracy of 89.35 %, surpassing all papers in the literature and establishing a new state-of-the-art and baseline accuracy for other publications on a public data set. For the NICE classification, we achieve a competitive accuracy of 81.13 % and demonstrate thereby the viability of the few-shot learning paradigm in polyp classification in data-scarce environments. Additionally, we show different ablations of the algorithms. Finally, we further elaborate on the explainability of the system by showing heat maps of the neural network explaining neural activations. Conclusion Overall we introduce two polyp classification systems to assist gastroenterologists. We achieve state-of-the-art performance in the Paris classification and demonstrate the viability of the few-shot learning paradigm in the NICE classification, addressing the prevalent data scarcity issues faced in medical machine learning.

Abstract Background Machine learning, especially deep learning, is becoming more and more relevant in research and development in the medical domain. For all the supervised deep learning applications, data is the most critical factor in securing successful implementation and sustaining the progress of the machine learning model. Especially gastroenterological data, which often involves endoscopic videos, are cumbersome to annotate. Domain experts are needed to interpret and annotate the videos. To support those domain experts, we generated a framework. With this framework, instead of annotating every frame in the video sequence, experts are just performing key annotations at the beginning and the end of sequences with pathologies, e.g., visible polyps. Subsequently, non-expert annotators supported by machine learning add the missing annotations for the frames in-between. Methods In our framework, an expert reviews the video and annotates a few video frames to verify the object’s annotations for the non-expert. In a second step, a non-expert has visual confirmation of the given object and can annotate all following and preceding frames with AI assistance. After the expert has finished, relevant frames will be selected and passed on to an AI model. This information allows the AI model to detect and mark the desired object on all following and preceding frames with an annotation. Therefore, the non-expert can adjust and modify the AI predictions and export the results, which can then be used to train the AI model. Results Using this framework, we were able to reduce workload of domain experts on average by a factor of 20 on our data. This is primarily due to the structure of the framework, which is designed to minimize the workload of the domain expert. Pairing this framework with a state-of-the-art semi-automated AI model enhances the annotation speed further. Through a prospective study with 10 participants, we show that semi-automated annotation using our tool doubles the annotation speed of non-expert annotators compared to a well-known state-of-the-art annotation tool. Conclusion In summary, we introduce a framework for fast expert annotation for gastroenterologists, which reduces the workload of the domain expert considerably while maintaining a very high annotation quality. The framework incorporates a semi-automated annotation system utilizing trained object detection models. The software and framework are open-source.

The failure of roughness parameters to predict surface properties stems from their inherent scale-dependence; in other words, the measured value depends on how the parameter was measured. Here we take advantage of this scale-dependence to develop a new framework for characterizing rough surfaces: the Scale-Dependent Roughness Parameters (SDRP) analysis, which yields slope, curvature, and higher-order derivatives of surface topography at many scales, even for a single topography measurement. We demonstrate the relationship between SDRP and other common statistical methods for analyzing surfaces: the height-difference autocorrelation function (ACF), variable bandwidth methods (VBMs) and the power spectral density (PSD). We use computer-generated and measured topographies to demonstrate the benefits of SDRP analysis, including: novel metrics for characterizing surfaces across scales, and the detection of measurement artifacts. The SDRP is a generalized framework for scale-dependent analysis of surface topography that yields metrics that are intuitively understandable.

Among the major phytohormones, the cytokinin exhibits unique features for its ability to positively affect the developmental status of plastids. Even early on in its research, cytokinins were known to promote plastid differentiation and to reduce the loss of chlorophyll in detached leaves. Since the discovery of the components of cytokinin perception and primary signaling, the genes involved in photosynthesis and plastid differentiation have been identified as those directly targeted by type-B response regulators. Furthermore, cytokinins are known to modulate versatile cellular processes such as promoting the division and differentiation of cells and, in concert with auxin, initiating the de novo formation of shoot apical meristem (SAM) in tissue cultures. Yet how cytokinins precisely participate in such diverse cellular phenomena, and how the associated cellular processes are coordinated as a whole, remains unclear. A plausible presumption that would account for the coordinated gene expression is the tight and reciprocal communication between the nucleus and plastid. The fact that cytokinins affect plastid developmental status via gene expression in both the nucleus and plastid is interpreted here to suggest that cytokinin functions as an initiator of anterograde (nucleus-to-plastid) signaling. Based on this viewpoint, we first summarize the physiological relevance of cytokinins to the coordination of plastid differentiation with de novo shoot organogenesis in tissue culture systems. Next, the role of endogenous cytokinins in influencing plastid differentiation within the SAM of intact plants is discussed. Finally, a presumed plastid-derived signal in response to cytokinins for coupled nuclear gene expression is proposed.

BackgroundThe objective of this study was to identify clinical risk factors for COVID-19 in a German outpatient fever clinic that allow distinction of SARS-CoV-2 infected patients from other patients with flu-like symptoms.MethodsThis is a retrospective, single-centre cohort study. Patients were included visiting the fever clinic from 4th of April 2020 to 15th of May 2020. Symptoms, comorbidities, and socio-demographic factors were recorded in a standardized fashion. Multivariate logistic regression was used to identify risk factors of COVID-19, on the bases of those a model discrimination was assessed using area under the receiver operation curves (AUROC).ResultsThe final analysis included 930 patients, of which 74 (8%) had COVID-19. Anosmia (OR 10.71; CI 6.07-18.9) and ageusia (OR 9.3; CI 5.36-16.12) were strongly associated with COVID-19. High-risk exposure (OR 12.20; CI 6.80-21.90), especially in the same household (OR 4.14; CI 1.28-13.33), was also correlated; the more household members, especially with flu-like symptoms, the higher the risk of COVID-19. Working in an essential workplace was also associated with COVID-19 (OR 2.35; CI 1.40-3.96), whereas smoking was inversely correlated (OR 0.19; CI 0.08-0.44). A model that considered risk factors like anosmia, ageusia, concomitant of symptomatic household members and smoking well discriminated COVID-19 patients from other patients with flu-like symptoms (AUROC 0.84).ConclusionsWe report a set of four readily available clinical parameters that allow the identification of high-risk individuals of COVID-19. Our study will not replace molecular testing but will help guide containment efforts while waiting for test results.

The plant hormone cytokinin, existing in several molecular forms, is perceived by membrane-localized histidine kinases. The signal is transduced to transcription factors of the type-B response regulator family localized in the nucleus by a multi-step histidine-aspartate phosphorelay network employing histidine phosphotransmitters as shuttle proteins across the nuclear envelope. The type-B response regulators activate a number of primary response genes, some of which trigger in turn further signaling events and the expression of secondary response genes. Most genes activated in both rounds of transcription were identified with high confidence using different transcriptomic toolkits and meta analyses of multiple individual published datasets. In this review, we attempt to summarize the existing knowledge about the primary and secondary cytokinin response genes in order to try connecting gene expression with the multitude of effects that cytokinin exerts within the plant body and throughout the lifespan of a plant.

This article discusses a study that compares the performance of different computer-aided detection (CADe) systems in detecting polyps during colonoscopies. The study found that the CADe systems have varying levels of sensitivity and accuracy in detecting polyps, with some systems performing better than others. However, certain systems did miss some polyps, which could potentially lead to delays in patient follow-up. The study provides valuable insights into the performance of CADe systems and can help clinicians choose the system that best suits their needs. [Extracted from the article]

Abstract Ultrasound (US) is the most commonly used liver imaging modality worldwide. Due to its low cost, it is increasingly used in the follow-up of cancer patients with metastases localized in the liver. In this contribution, we present the results of an interactive segmentation approach for liver metastases in US acquisitions. A (semi-) automatic segmentation is still very challenging because of the low image quality and the low contrast between the metastasis and the surrounding liver tissue. Thus, the state of the art in clinical practice is still manual measurement and outlining of the metastases in the US images. We tackle the problem by providing an interactive segmentation approach providing real-time feedback of the segmentation results. The approach has been evaluated with typical US acquisitions from the clinical routine, and the datasets consisted of pancreatic cancer metastases. Even for difficult cases, satisfying segmentations results could be achieved because of the interactive real-time behavior of the approach. In total, 40 clinical images have been evaluated with our method by comparing the results against manual ground truth segmentations. This evaluation yielded to an average Dice Score of 85% and an average Hausdorff Distance of 13 pixels.

As a new feature of our polyp detection system, "EndoMind", Poseidon analyzed the images containing a waterjet to determine the polyp size [19]. Artificial intelligence (AI) was introduced in clinical practice several years ago, with the main focus being polyp detection [12][13]; however, AI-based diagnosis has been further explored for polyp characterization [14] and other gastroenterological diseases, such as eosinophilic esophagitis [15] and Crohn's disease [12]. The waterjet should be aimed adjacent to a polyp to be equally distanced away from the endoscope, and the polyp needs to be recognized by our polyp detection system. [Extracted from the article]

Jasmonic acid (JA), its derivatives and its precursor cis-12-oxo phytodienoic acid (OPDA) form a group of phytohormones, the jasmonates, representing signal molecules involved in plant stress responses, in the defense against pathogens as well as in development. Elevated levels of JA have been shown to play a role in arbuscular mycorrhiza and in the induction of nitrogen-fixing root nodules. In this study, the gene families of two committed enzymes of the JA biosynthetic pathway, allene oxide synthase (AOS) and allene oxide cyclase (AOC), were characterized in the determinate nodule-forming model legume Lotus japonicus JA levels were to be analysed in the course of nodulation. Since in all L. japonicus organs examined, JA levels increased upon mechanical disturbance and wounding, an aeroponic culture system was established to allow for a quick harvest, followed by the analysis of JA levels in whole root and shoot systems. Nodulated plants were compared with non-nodulated plants grown on nitrate or ammonium as N source, respectively, over a five week-period. JA levels turned out to be more or less stable independently of the growth conditions. However, L. japonicus nodules formed on aeroponically grown plants often showed patches of cells with reduced bacteroid density, presumably a stress symptom. Immunolocalization using a heterologous antibody showed that the vascular systems of these nodules also seemed to contain less AOC protein than those of nodules of plants grown in perlite/vermiculite. Hence, aeroponically grown L. japonicus plants are likely to be habituated to stress which could have affected JA levels.

Background: The quartan malaria parasite Plasmodium malariae is the widest spread and best adapted human malaria parasite. The simian Plasmodium brasilianum causes quartan fever in New World monkeys and resembles P. malariae morphologically. Since the genetics of the two parasites are nearly identical, differing only in a range of mutations expected within a species, it has long been speculated that the two are the same. However, no naturally acquired infection with parasites termed as P. brasilianum has been found in humans until now. Methods: We investigated malaria cases from remote Yanomami indigenous communities of the Venezuelan Amazon and analyzed the genes coding for the circumsporozoite protein (CSP) and the small subunit of ribosomes (18S) by species-specific PCR and capillary based-DNA sequencing. Findings: Based on 18S rRNA gene sequencing, we identified 12 patients harboring malaria parasites which were 100% identical with P. brasilianum isolated from the monkey, Alouatta seniculus. Translated amino acid sequences of the CS protein gene showed identical immunodominant repeat units between quartan malaria parasites isolated from both humans and monkeys. Interpretation: This study reports, for the first time, naturally acquired infections in humans with parasites termed as P. brasilianum. We conclude that quartan malaria parasites are easily exchanged between humans and monkeys in Latin America. We hypothesize a lack of host specificity in mammalian hosts and consider quartan malaria to be a true anthropozoonosis. Since the name P. brasilianum suggests a malaria species distinct from P. malariae, we propose that P. brasilianum should have a nomenclatorial revision in case further research confirms our findings. The expansive reservoir of mammalian hosts discriminates quartan malaria from other Plasmodium spp. and requires particular research efforts.