News

Lorenz Rumbergers work on Instance Segmentation accepted at European conference on computer vision

In the field of computer vision, probabilistic convolutional neural networks, which predict distributions of predictions instead of point estimates led to many recent advances. Besides state of the art benchmark results, these networks made it possible to quantify local uncertainties in the predictions. These were used in active learning frameworks to target the labeling efforts of specialist annotators or to assess the quality of a prediction in a safety-critical environment. However, for instance segmentation problems, which aim at separating different objects (e.g. cells) from one another, these methods are not frequently used so far. We seek to close this gap by proposing a generic method to obtain model-inherent uncertainty estimates within proposal-free instance segmentation models. Furthermore, the quality of the uncertainty estimates is analyzed with a metric adapted from semantic segmentation, which seeks to separate objects based on their class (e.g. epithelial cells or other cells). The method is evaluated on a dataset that contains C.elegans brightfield microscopy images, where it yields competitive performance while also predicting uncertainty estimates that carry information about object-level inaccuracies like false splits and false merges. These uncertainty estimates are then used in a simulation study to guide proofreading efforts.

The manuscript was accepted for the Bio Image Computing Workshop within ECCV2020 and is available at arXiv

Rumberger, J.L., Mais, L., Kainmüller, D. Probabilistic Deep Learning for Instance Segmentation

https://arxiv.org/abs/2008.10678

Wanja Kassuhn contributes to a study on Epithelial Ovarian Cancer

Epithelial ovarian cancer (EOC) is the leading cause of death within gynecological cancers in the developed countries. Due to the lack of specific symptoms, EOC is often detected at an advanced stage with a five-year survival rate less than 40%. However, 25% of EOC patients are diagnosed in early stage (I-II), where the disease is often cured by surgery alone, or in combination with platinum-based chemotherapy. Even though the prognosis of patients with FIGO stage I-II increases dramatically with treatment, with five-year survival rates between 80–90%, some subgroups of early-stage EOC will relapse and 20–30% of these patients will finally succumb to the disease. Nevertheless, the optimal clinical management is still a controversial debate and patients with early-stage high-grade serous EOC might be over-treated which could potentially result in complications after radical surgical management and an increase in toxicity of chemotherapy. Hence, it is of utmost importance to identify novel diagnostic markers for this patient cohort in order to improve the risk assessment of tumor recurrence. Here, we have applied MALDI-imaging mass spectrometry (MALDI-IMS), a new method to identify distinct mass profiles including protein signatures on paraffin embedded tissue sections. In search of prognostic biomarker candidates, we compared proteomic profiles of primary tumor section from early-stage HGSOC patients with either recurrent or non-recurrent disease, and were able to identify a discriminative peptide signature to predict clinical outcome and treatment extent for patients with early-stage HGSOC.

Kulbe H., ... , Kassuhn W., et al., Discovery of Prognostic Markers for Early-Stage High-Grade Serous Ovarian Cancer by Maldi-Imaging, Cancers 2020

https://www.mdpi.com/2072-6694/12/8/2000/htm

Life after Phd seminar - with Claudia Reschke

we would like to announce our next "LAP-Life after PhD" seminar which will take place on July, 21 at 4:30 p.m. as an online seminar.

Our speaker will be Dr. Claudia Reschke, a former „Personal Assistant to the Scientific Director of DKFZ“ and now „Adviser Helmholtz Information & Data Science Academy (HIDA)“, the Helmholtz Information and Data Science Academy. She will talk about both her career path from her PhD to Science Management and the activities of the HIDA which offers extensive training in Information and Data Science to doctoral researchers and postdocs.

Date: July, 21st
Time: 4:30 p.m.
Venue: Zoom

Room and password upon reasonable request (contact: compcancer at charite dot de). You will find regular updates at https://www.regulatory-genome.hu-berlin.de/en/events/lectures/lap-series.

Life after Phd seminar - with Wiebke Skeffington

We are delighted to announce our next LAP seminar. This time Wiebke Skeffington, who is coordinating the IRTG2403 will speak about her career. Wiebke studied biology and during her career spent time in the US and UK and by now switched from research to research management.

Date: June, 23rd
Time: 4:30 p.m.
Venue: Zoom (https://zoom.us/j/878362909)
Speaker: Wiebke Skeffington - program coordinator

In addition to speaking about her own career, Wiebke will also give tips and tricks how to apply successfully for a postdoc position.

Password upon reasonable request (contact: compcancer at charite dot de). You will find regular updates at https://www.regulatory-genome.hu-berlin.de/en/events/lectures/lap-series.

Tincy Simons integrative characterization of PanNEN tumors is on bioRxiv

https://www.biorxiv.org/content/10.1101/2020.06.12.146811v2

In the wake of the multi-omics era, stratification of cancer entities at multiple molecular levels have become increasingly prominent for diagnostic and therapeutic purposes. By uncovering the diversity within a cancer entity, we can understand inter-tumor heterogeneity as well as the biological mechanism contributing to it. Our study presents an integrative multi-omics approach that classifies pancreatic neuroendocrine neoplasms (PanNENs) subgroups, highlights cell-of-origin distinction, as well as differences in multi-genomic aberration and proteomic changes grounded within these subgroups. We determined that PanNEN tumor methylome profile closely resembles either α-like and β-like cells of Islet of Langerhans. The most aggressive tumor grades of PanNEN contain β-cell features and show hypermethylation of various transcription factors involved in Islet cell differentiation and maintenance. Mutations within MEN1/DAXX/ATRX tumor suppressor genes and overexpression of mTOR pathway proteins are key features of α-like tumors. DNA copy number data further implicates differences in tumor progression mechanism within the α-like tumors. Taken together, our data provides new insights into the PanNEN heterogeneity and further establishes a foundation for future diagnostic and therapy-relevant patient stratification.

< 1 ... 6 7 8 9 10 11 >

About

The research training group CompCancer (RTG2424) is a DFG funded PhD programme in Berlin, focussing on computational aspects of cancer research.

Contact: compcancer at charite dot de