Refine
Year of publication
Document Type
- Article (20)
- Working Paper (3)
Language
- English (23)
Has Fulltext
- yes (23)
Is part of the Bibliography
- no (23)
Keywords
- Machine learning (23) (remove)
Institute
- Medizin (11)
- Wirtschaftswissenschaften (7)
- Center for Financial Studies (CFS) (3)
- House of Finance (HoF) (3)
- Psychologie (3)
- Sustainable Architecture for Finance in Europe (SAFE) (3)
- Informatik und Mathematik (2)
- Frankfurt Institute for Advanced Studies (FIAS) (1)
- Informatik (1)
- MPI für Hirnforschung (1)
Pattern recognition approaches, such as the Support Vector Machine (SVM), have been successfully used to classify groups of individuals based on their patterns of brain activity or structure. However these approaches focus on finding group differences and are not applicable to situations where one is interested in accessing deviations from a specific class or population. In the present work we propose an application of the one-class SVM (OC-SVM) to investigate if patterns of fMRI response to sad facial expressions in depressed patients would be classified as outliers in relation to patterns of healthy control subjects. We defined features based on whole brain voxels and anatomical regions. In both cases we found a significant correlation between the OC-SVM predictions and the patients' Hamilton Rating Scale for Depression (HRSD), i.e. the more depressed the patients were the more of an outlier they were. In addition the OC-SVM split the patient groups into two subgroups whose membership was associated with future response to treatment. When applied to region-based features the OC-SVM classified 52% of patients as outliers. However among the patients classified as outliers 70% did not respond to treatment and among those classified as non-outliers 89% responded to treatment. In addition 89% of the healthy controls were classified as non-outliers.
Nerve tissue contains a high density of chemical synapses, about 1 per µm3 in the mammalian cerebral cortex. Thus, even for small blocks of nerve tissue, dense connectomic mapping requires the identification of millions to billions of synapses. While the focus of connectomic data analysis has been on neurite reconstruction, synapse detection becomes limiting when datasets grow in size and dense mapping is required. Here, we report SynEM, a method for automated detection of synapses from conventionally en-bloc stained 3D electron microscopy image stacks. The approach is based on a segmentation of the image data and focuses on classifying borders between neuronal processes as synaptic or non-synaptic. SynEM yields 97% precision and recall in binary cortical connectomes with no user interaction. It scales to large volumes of cortical neuropil, plausibly even whole-brain datasets. SynEM removes the burden of manual synapse annotation for large densely mapped connectomes.
The Gleason grading system remains the most powerful prognostic predictor for patients with prostate cancer since the 1960s. Its application requires highly-trained pathologists, is tedious and yet suffers from limited inter-pathologist reproducibility, especially for the intermediate Gleason score 7. Automated annotation procedures constitute a viable solution to remedy these limitations. In this study, we present a deep learning approach for automated Gleason grading of prostate cancer tissue microarrays with Hematoxylin and Eosin (H&E) staining. Our system was trained using detailed Gleason annotations on a discovery cohort of 641 patients and was then evaluated on an independent test cohort of 245 patients annotated by two pathologists. On the test cohort, the inter-annotator agreements between the model and each pathologist, quantified via Cohen’s quadratic kappa statistic, were 0.75 and 0.71 respectively, comparable with the inter-pathologist agreement (kappa = 0.71). Furthermore, the model’s Gleason score assignments achieved pathology expert-level stratification of patients into prognostically distinct groups, on the basis of disease-specific survival data available for the test cohort. Overall, our study shows promising results regarding the applicability of deep learning-based solutions towards more objective and reproducible prostate cancer grading, especially for cases with heterogeneous Gleason patterns.
CRFVoter : gene and protein related object recognition using a conglomerate of CRF-based tools
(2019)
Background: Gene and protein related objects are an important class of entities in biomedical research, whose identification and extraction from scientific articles is attracting increasing interest. In this work, we describe an approach to the BioCreative V.5 challenge regarding the recognition and classification of gene and protein related objects. For this purpose, we transform the task as posed by BioCreative V.5 into a sequence labeling problem. We present a series of sequence labeling systems that we used and adapted in our experiments for solving this task. Our experiments show how to optimize the hyperparameters of the classifiers involved. To this end, we utilize various algorithms for hyperparameter optimization. Finally, we present CRFVoter, a two-stage application of Conditional Random Field (CRF) that integrates the optimized sequence labelers from our study into one ensemble classifier.
Results: We analyze the impact of hyperparameter optimization regarding named entity recognition in biomedical research and show that this optimization results in a performance increase of up to 60%. In our evaluation, our ensemble classifier based on multiple sequence labelers, called CRFVoter, outperforms each individual extractor’s performance. For the blinded test set provided by the BioCreative organizers, CRFVoter achieves an F-score of 75%, a recall of 71% and a precision of 80%. For the GPRO type 1 evaluation, CRFVoter achieves an F-Score of 73%, a recall of 70% and achieved the best precision (77%) among all task participants.
Conclusion: CRFVoter is effective when multiple sequence labeling systems are to be used and performs better then the individual systems collected by it.
Purpose: To determine whether machine learning assisted-texture analysis of multi-energy virtual monochromatic image (VMI) datasets from dual-energy CT (DECT) can be used to differentiate metastatic head and neck squamous cell carcinoma (HNSCC) lymph nodes from lymphoma, inflammatory, or normal lymph nodes.
Materials and methods: A retrospective evaluation of 412 cervical nodes from 5 different patient groups (50 patients in total) having undergone DECT of the neck between 2013 and 2015 was performed: (1) HNSCC with pathology proven metastatic adenopathy, (2) HNSCC with pathology proven benign nodes (controls for (1)), (3) lymphoma, (4) inflammatory, and (5) normal nodes (controls for (3) and (4)). Texture analysis was performed with TexRAD® software using two independent sets of contours to assess the impact of inter-rater variation. Two machine learning algorithms (Random Forests (RF) and Gradient Boosting Machine (GBM)) were used with independent training and testing sets and determination of accuracy, sensitivity, specificity, PPV, NPV, and AUC.
Results: In the independent testing (prediction) sets, the accuracy for distinguishing different groups of pathologic nodes or normal nodes ranged between 80 and 95%. The models generated using texture data extracted from the independent contour sets had substantial to almost perfect agreement. The accuracy, sensitivity, specificity, PPV, and NPV for correctly classifying a lymph node as malignant (i.e. metastatic HNSCC or lymphoma) versus benign were 92%, 91%, 93%, 95%, 87%, respectively.
Conclusion: Machine learning assisted-DECT texture analysis can help distinguish different nodal pathology and normal nodes with a high accuracy.
Background: Germinal center-derived B cell lymphomas are tumors of the lymphoid tissues representing one of the most heterogeneous malignancies. Here we characterize the variety of transcriptomic phenotypes of this disease based on 873 biopsy specimens collected in the German Cancer Aid MMML (Molecular Mechanisms in Malignant Lymphoma) consortium. They include diffuse large B cell lymphoma (DLBCL), follicular lymphoma (FL), Burkitt’s lymphoma, mixed FL/DLBCL lymphomas, primary mediastinal large B cell lymphoma, multiple myeloma, IRF4-rearranged large cell lymphoma, MYC-negative Burkitt-like lymphoma with chr. 11q aberration and mantle cell lymphoma.
Methods: We apply self-organizing map (SOM) machine learning to microarray-derived expression data to generate a holistic view on the transcriptome landscape of lymphomas, to describe the multidimensional nature of gene regulation and to pursue a modular view on co-expression. Expression data were complemented by pathological, genetic and clinical characteristics.
Results: We present a transcriptome map of B cell lymphomas that allows visual comparison between the SOM portraits of different lymphoma strata and individual cases. It decomposes into one dozen modules of co-expressed genes related to different functional categories, to genetic defects and to the pathogenesis of lymphomas. On a molecular level, this disease rather forms a continuum of expression states than clearly separated phenotypes. We introduced the concept of combinatorial pattern types (PATs) that stratifies the lymphomas into nine PAT groups and, on a coarser level, into five prominent cancer hallmark types with proliferation, inflammation and stroma signatures. Inflammation signatures in combination with healthy B cell and tonsil characteristics associate with better overall survival rates, while proliferation in combination with inflammation and plasma cell characteristics worsens it. A phenotypic similarity tree is presented that reveals possible progression paths along the transcriptional dimensions. Our analysis provided a novel look on the transition range between FL and DLBCL, on DLBCL with poor prognosis showing expression patterns resembling that of Burkitt’s lymphoma and particularly on "double-hit" MYC and BCL2 transformed lymphomas.
Conclusions: The transcriptome map provides a tool that aggregates, refines and visualizes the data collected in the MMML study and interprets them in the light of previous knowledge to provide orientation and support in current and future studies on lymphomas and on other cancer entities.
Background: Enhancers play a fundamental role in orchestrating cell state and development. Although several methods have been developed to identify enhancers, linking them to their target genes is still an open problem. Several theories have been proposed on the functional mechanisms of enhancers, which triggered the development of various methods to infer promoter–enhancer interactions (PEIs). The advancement of high-throughput techniques describing the three-dimensional organization of the chromatin, paved the way to pinpoint long-range PEIs. Here we investigated whether including PEIs in computational models for the prediction of gene expression improves performance and interpretability.
Results: We have extended our TEPIC framework to include DNA contacts deduced from chromatin conformation capture experiments and compared various methods to determine PEIs using predictive modelling of gene expression from chromatin accessibility data and predicted transcription factor (TF) motif data. We designed a novel machine learning approach that allows the prioritization of TFs binding to distal loop and promoter regions with respect to their importance for gene expression regulation. Our analysis revealed a set of core TFs that are part of enhancer–promoter loops involving YY1 in different cell lines.
Conclusion: We present a novel approach that can be used to prioritize TFs involved in distal and promoter-proximal regulatory events by integrating chromatin accessibility, conformation, and gene expression data. We show that the integration of chromatin conformation data can improve gene expression prediction and aids model interpretability.
This article discusses the counterpart of interactive machine learning, i.e., human learning while being in the loop in a human-machine collaboration. For such cases we propose the use of a Contradiction Matrix to assess the overlap and the contradictions of human and machine predictions. We show in a small-scaled user study with experts in the area of pneumology (1) that machine-learning based systems can classify X-rays with respect to diseases with a meaningful accuracy, (2) humans partly use contradictions to reconsider their initial diagnosis, and (3) that this leads to a higher overlap between human and machine diagnoses at the end of the collaboration situation. We argue that disclosure of information on diagnosis uncertainty can be beneficial to make the human expert reconsider her or his initial assessment which may ultimately result in a deliberate agreement. In the light of the observations from our project, it becomes apparent that collaborative learning in such a human-in-the-loop scenario could lead to mutual benefits for both human learning and interactive machine learning. Bearing the differences in reasoning and learning processes of humans and intelligent systems in mind, we argue that interdisciplinary research teams have the best chances at tackling this undertaking and generating valuable insights.
Purpose: To develop and validate a CT-based radiomics signature for the prognosis of loco-regional tumour control (LRC) in patients with locally advanced head and neck squamous cell carcinoma (HNSCC) treated by primary radiochemotherapy (RCTx) based on retrospective data from 6 partner sites of the German Cancer Consortium - Radiation Oncology Group (DKTK-ROG).
Material and methods: Pre-treatment CT images of 318 patients with locally advanced HNSCC were collected. Four-hundred forty-six features were extracted from each primary tumour volume and then filtered through stability analysis and clustering. First, a baseline signature was developed from demographic and tumour-associated clinical parameters. This signature was then supplemented by CT imaging features. A final signature was derived using repeated 3-fold cross-validation on the discovery cohort. Performance in external validation was assessed by the concordance index (C-Index). Furthermore, calibration and patient stratification in groups with low and high risk for loco-regional recurrence were analysed.
Results: For the clinical baseline signature, only the primary tumour volume was selected. The final signature combined the tumour volume with two independent radiomics features. It achieved moderately good discriminatory performance (C-Index [95% confidence interval]: 0.66 [0.55–0.75]) on the validation cohort along with significant patient stratification (p = 0.005) and good calibration.
Conclusion: We identified and validated a clinical-radiomics signature for LRC of locally advanced HNSCC using a multi-centric retrospective dataset. Prospective validation will be performed on the primary cohort of the HNprädBio trial of the DKTK-ROG once follow-up is completed.
Objectives: To analyze the performance of radiological assessment categories and quantitative computational analysis of apparent diffusion coefficient (ADC) maps using variant machine learning algorithms to differentiate clinically significant versus insignificant prostate cancer (PCa). Methods: Retrospectively, 73 patients were included in the study. The patients (mean age, 66.3 ± 7.6 years) were examined with multiparametric MRI (mpMRI) prior to radical prostatectomy (n = 33) or targeted biopsy (n = 40). The index lesion was annotated in MRI ADC and the equivalent histologic slides according to the highest Gleason Grade Group (GrG). Volumes of interest (VOIs) were determined for each lesion and normal-appearing peripheral zone. VOIs were processed by radiomic analysis. For the classification of lesions according to their clinical significance (GrG ≥ 3), principal component (PC) analysis, univariate analysis (UA) with consecutive support vector machines, neural networks, and random forest analysis were performed. Results: PC analysis discriminated between benign and malignant prostate tissue. PC evaluation yielded no stratification of PCa lesions according to their clinical significance, but UA revealed differences in clinical assessment categories and radiomic features. We trained three classification models with fifteen feature subsets. We identified a subset of shape features which improved the diagnostic accuracy of the clinical assessment categories (maximum increase in diagnostic accuracy ΔAUC = + 0.05, p < 0.001) while also identifying combinations of features and models which reduced overall accuracy. Conclusions: The impact of radiomic features to differentiate PCa lesions according to their clinical significance remains controversial. It depends on feature selection and the employed machine learning algorithms. It can result in improvement or reduction of diagnostic performance.