Development and Validation of a Deep Learning Algorithm to Differentiate Colon Carcinoma From Acute Diverticulitis in Computed Tomography Images.

Importance: Differentiating between malignant and benign etiology in large-bowel wall thickening on computed tomography (CT) images can be a challenging task. Artificial intelligence (AI) support systems can improve the diagnostic accuracy of radiologists, as shown for a variety of imaging tasks. Improvements in diagnostic performance, in particular the reduction of false-negative findings, may be useful in patient care. Objective: To develop and evaluate a deep learning algorithm able to differentiate colon carcinoma (CC) and acute diverticulitis (AD) on CT images and analyze the impact of the AI-support system in a reader study. Design, Setting, and Participants: In this diagnostic study, patients who underwent surgery between July 1, 2005, and October 1, 2020, for CC or AD were included. Three-dimensional (3-D) bounding boxes including the diseased bowel segment and surrounding mesentery were manually delineated and used to develop a 3-D convolutional neural network (CNN). A reader study with 10 observers of different experience levels was conducted. Readers were asked to classify the testing cohort under reading room conditions, first without and then with algorithmic support. Main Outcomes and Measures: To evaluate the diagnostic performance, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were calculated for all readers and reader groups with and without AI support. Metrics were compared using the McNemar test and relative and absolute predictive value comparisons. Results: A total of 585 patients (AD: n = 267, CC: n = 318; mean [SD] age, 63.2 [13.4] years; 341 men [58.3%]) were included. The 3-D CNN reached a sensitivity of 83.3% (95% CI, 70.0%-96.6%) and specificity of 86.6% (95% CI, 74.5%-98.8%) for the test set, compared with the mean reader sensitivity of 77.6% (95% CI, 72.9%-82.3%) and specificity of 81.6% (95% CI, 77.2%-86.1%). The combined group of readers improved significantly with AI support from a sensitivity of 77.6% to 85.6% (95% CI, 81.3%-89.3%; P < .001) and a specificity of 81.6% to 91.3% (95% CI, 88.1%-94.5%; P < .001). Artificial intelligence support significantly reduced the number of false-negative and false-positive findings (NPV from 78.5% to 86.4% and PPV from 80.9% to 90.8%; P < .001). Conclusions and Relevance: The findings of this study suggest that a deep learning model able to distinguish CC and AD in CT images as a support system may significantly improve the diagnostic performance of radiologists, which may improve patient care.

Variation in the reproductive performance of the Trollius-Chiastocheta mutualism at the edge of its range in north-east Germany.

Empirical studies into obligate pollination mutualisms which elucidate the variation in reproductive performance of shrinking populations within human-altered environments are rare. This study focuses on the obligate pollination mutualism between Trollius europaeus (Ranunculaceae) and fly species of the genus Chiastocheta which act both as the plant's main pollinators and as predators in that their larvae eat a fraction of the developing seeds. The study area is situated in the lowlands of north-east Germany. Many populations of T. europaeus have become comparatively small and scattered in this region as a consequence of agricultural land use intensification. We studied the plant's reproductive fitness in populations ranging in size from 7 to 12,000 flowers. In a field experiment, we applied four pollination treatments and also recorded fly density in 28 natural T. europaeus populations. The fitness of the offspring from 19 populations was studied in a common garden experiment. In both approaches, a reduction in the fitness of small host plant populations could be demonstrated. Fitness loss can be put down to the quantitative and qualitative limitation of pollen caused by inbreeding and the negative feedback on relative seed set caused by the reduced ability of small plant populations to support a sufficiently large fly population. Although increases in fly density are associated with rising predation costs, the plant species' net benefit is a positive function of its population size. Our study highlights the reproductive variability of the Trollius-Chiastocheta interaction along a population size gradient in a marginal region of its range, thus contributing to the understanding of the overall variability of this mutualism.