Fungal evolutionary biology is impeded by the scarcity of fossils, irregular life cycles, immortality, and frequent asexual reproduction. Simple and diminutive bodies of fungi develop inside a substrate and have exceptional metabolic and ecological plasticity, which hinders species delimitation. However, the unique fungal traits can shed light on evolutionary forces that shape the environmental adaptations of these taxa. Higher filamentous fungi that disperse through aerial spores produce amphiphilic and highly surface-active proteins called hydrophobins (HFBs), which coat spores and mediate environmental interactions. We exploited a library of HFB-deficient mutants for two cryptic species of mycoparasitic and saprotrophic fungi from the genus Trichoderma (Hypocreales) and estimated fungal development, reproductive potential, and stress resistance. HFB4 and HFB10 were found to be relevant for Trichoderma fitness because they could impact the spore-mediated dispersal processes and control other fitness traits. An analysis in silico revealed purifying selection for all cases except for HFB4 from T. harzianum, which evolved under strong positive selection pressure. Interestingly, the deletion of the hfb4 gene in T. harzianum considerably increased its fitness-related traits. Conversely, the deletion of hfb4 in T. guizhouense led to the characteristic phenotypes associated with relatively low fitness. The net contribution of the hfb4 gene to fitness was found to result from evolutionary tradeoffs between individual traits. Our analysis of HFB-dependent fitness traits has provided an evolutionary snapshot of the selective pressures and speciation process in closely related fungal species.

In approaches for automatic localization of multiple anatomical landmarks, disambiguation of locally similar structures as obtained by locally accurate candidate generation is often performed by solely including high level knowledge about geometric landmark configuration. In our novel localization approach, we propose to combine both image appearance information and geometric landmark configuration into a unified random forest framework integrated into an optimization procedure that iteratively refines joint landmark predictions by using the coordinate descent algorithm. Depending on how strong multiple landmarks are correlated in a specific localization task, this integration has the benefit that it remains flexible in deciding whether appearance information or the geometric configuration of multiple landmarks is the stronger cue for solving a localization problem both accurately and robustly. Furthermore, no preliminary choice on how to encode a graphical model describing landmark configuration has to be made. In an extensive evaluation on five challenging datasets involving different 2D and 3D imaging modalities, we show that our proposed method is widely applicable and delivers state-of-the-art results when compared to various other related methods.

Bone age estimation (BAE) is an important procedure in forensic practice which recently has seen a shift in attention from Xray to MRI based imaging. To automate BAE from MRI, localization of the joints between hand bones is a crucial first step, which is challenging due to anatomical variations, different poses and repeating structures within the hand. We propose a landmark localization algorithm using multiple random regression forests, first analyzing the shape of the hand from information of the whole image, thus implicitly modeling the global landmark configuration, followed by a refinement based on more local information to increase prediction accuracy. We are able to clearly outperform related approaches on our dataset of 60 T1-weighted MR images, achieving a mean landmark localization error of 1.4±1.5mm, while having only 0.25% outliers with an error greater than 10mm.

No abstract