Explainable Artificial Intelligence for Deep-Learning Based Classification of Cystic Fibrosis Lung Changes in MRI.

Algorithms increasing the transparence and explain ability of neural networks are gaining more popularity. Applying them to custom neural network architectures and complex medical problems remains challenging. In this work, several algorithms such as integrated gradients and grad came were used to generate additional explainable outputs for the classification of lung perfusion changes and mucus plugging in cystic fibrosis patients on MRI. The algorithms are applied on top of an already existing deep learning-based classification pipeline. From six explain ability algorithms, four were implemented successfully and one yielded satisfactory results which might provide support to the radiologist. It was evident, that the areas relevant for the classification were highlighted, thus emphasizing the applicability of deep learning for classification of lung changes in CF patients. Using explainable concepts with deep learning could improve confidence of clinicians towards deep learning and introduction of more diagnostic decision support systems.

Architecture of the Mass Spectrometry Data Management Pipeline in the SMART-CARE Project.

In the SMART-CARE project- a systems medicine approach to stratification of cancer recurrence in Heidelberg, Germany - a streamlined mass-spectrometry (MS) workflow for identification of cancer relapse was developed. This project has multiple partners from clinics, laboratories and computational teams. For optimal collaboration, consistent documentation and centralized storage, the linked data repository was designed. Clinical, laboratory and computational group members interact with this platform and store meta- and raw-data. The specific architectural choices, such as pseudonymization service, uploading process and other technical specifications as well as lessons learned are presented in this work. Altogether, relevant information in order to provide other research groups with a head-start for tackling MS data management in the context of systems medicine research projects is described.

The Use of Artificial Intelligence for the Classification of Craniofacial Deformities.

Positional cranial deformities are a common finding in toddlers, yet differentiation from craniosynostosis can be challenging. The aim of this study was to train convolutional neural networks (CNNs) to classify craniofacial deformities based on 2D images generated using photogrammetry as a radiation-free imaging technique. A total of 487 patients with photogrammetry scans were included in this retrospective cohort study: children with craniosynostosis (n = 227), positional deformities (n = 206), and healthy children (n = 54). Three two-dimensional images were extracted from each photogrammetry scan. The datasets were divided into training, validation, and test sets. During the training, fine-tuned ResNet-152s were utilized. The performance was quantified using tenfold cross-validation. For the detection of craniosynostosis, sensitivity was at 0.94 with a specificity of 0.85. Regarding the differentiation of the five existing classes (trigonocephaly, scaphocephaly, positional plagiocephaly left, positional plagiocephaly right, and healthy), sensitivity ranged from 0.45 (positional plagiocephaly left) to 0.95 (scaphocephaly) and specificity ranged from 0.87 (positional plagiocephaly right) to 0.97 (scaphocephaly). We present a CNN-based approach to classify craniofacial deformities on two-dimensional images with promising results. A larger dataset would be required to identify rarer forms of craniosynostosis as well. The chosen 2D approach enables future applications for digital cameras or smartphones.

3D-2D Distance Maps Conversion Enhances Classification of Craniosynostosis.

OBJECTIVE: Diagnosis of craniosynostosis using photogrammetric 3D surface scans is a promising radiation-free alternative to traditional computed tomography. We propose a 3D surface scan to 2D distance map conversion enabling the usage of the first convolutional neural networks (CNNs)-based classification of craniosynostosis. Benefits of using 2D images include preserving patient anonymity, enabling data augmentation during training, and a strong under-sampling of the 3D surface with good classification performance. METHODS: The proposed distance maps sample 2D images from 3D surface scans using a coordinate transformation, ray casting, and distance extraction. We introduce a CNN-based classification pipeline and compare our classifier to alternative approaches on a dataset of 496 patients. We investigate into low-resolution sampling, data augmentation, and attribution mapping. RESULTS: Resnet18 outperformed alternative classifiers on our dataset with an F1-score of 0.964 and an accuracy of 98.4%. Data augmentation on 2D distance maps increased performance for all classifiers. Under-sampling allowed 256-fold computation reduction during ray casting while retaining an F1-score of 0.92. Attribution maps showed high amplitudes on the frontal head. CONCLUSION: We demonstrated a versatile mapping approach to extract a 2D distance map from the 3D head geometry increasing classification performance, enabling data augmentation during training on 2D distance maps, and the usage of CNNs. We found that low-resolution images were sufficient for a good classification performance. SIGNIFICANCE: Photogrammetric surface scans are a suitable craniosynostosis diagnosis tool for clinical practice. Domain transfer to computed tomography seems likely and can further contribute to reducing ionizing radiation exposure for infants.

Impact of data synthesis strategies for the classification of craniosynostosis.

Introduction: Photogrammetric surface scans provide a radiation-free option to assess and classify craniosynostosis. Due to the low prevalence of craniosynostosis and high patient restrictions, clinical data are rare. Synthetic data could support or even replace clinical data for the classification of craniosynostosis, but this has never been studied systematically. Methods: We tested the combinations of three different synthetic data sources: a statistical shape model (SSM), a generative adversarial network (GAN), and image-based principal component analysis for a convolutional neural network (CNN)-based classification of craniosynostosis. The CNN is trained only on synthetic data but is validated and tested on clinical data. Results: The combination of an SSM and a GAN achieved an accuracy of 0.960 and an F1 score of 0.928 on the unseen test set. The difference to training on clinical data was smaller than 0.01. Including a second image modality improved classification performance for all data sources. Conclusions: Without a single clinical training sample, a CNN was able to classify head deformities with similar accuracy as if it was trained on clinical data. Using multiple data sources was key for a good classification based on synthetic data alone. Synthetic data might play an important future role in the assessment of craniosynostosis.

Towards Data Analysis Environment for Multi-Partner Clinical Research Project - SMART-CARE.

A Systems Medicine Approach to Stratification of Cancer Recurrence (SMART-CARE) establishes mass spectrometry-based systems medicine technologies and data analysis pipelines employing expertise of the multiple partners from Heidelberg biomedical campus. We have established a central linked data repository that links clinical, mass spectrometry, and data analysis teams to enable a full cycle of data management. Other questions of setting up the data analysis environment for the multi-partner clinical research project are addressed in this work, too.

Large-File Raw Data Synchronization for openBIS Research Repositories.

In a systems medicine research consortium, openBIS is used as a research data repository. To facilitate efficient upload of large files, openBIS is complemented by a Nextcloud data cloud system. Using a Nextcloud client, raw mass spectrometry data is automatically imported into the repository in the background, enabling comprehensive data provenance.

CNN-Based Classification of Craniosynostosis Using 2D Distance Maps.

Craniosynostosis is a condition associated with the premature fusion of skull sutures affecting infants. 3D photogrammetric scans are a promising alternative to computed tomography scans in cases of single suture or nonsyndromic synostosis for diagnostic imaging, but oftentimes diagnosis is not automated and relies on additional cephalometric measure-ments and the experience of the surgeon. We propose an alternative representation of the infant's head shape created from 3D photogrammetric surface scans as 2D distance maps. Those 2D distance maps rely on ray casting to extract distances from a center point to the head surface, arranging them into a 2D image grid. We use the distance map for an original convolutional neural network (CNN)-based classification approach, which is evaluated on a publicly available synthetic dataset for benchmarking and also tested on clinical data. Qualitative differences of different head shapes can be ob-served in the distance maps. The CNN-based classifier achieves accuracies of 100 % on the publicly available synthetic dataset and 98.86 % on the clinical test set. Our distance map approach demonstrates the diagnostic value of 3D photogrammetry and the possibility of automatic, CNN-based diagnosis. Future steps include the improvement of the mapping method and testing the CNN on more pathologies.

A Radiation-Free Classification Pipeline for Craniosynostosis Using Statistical Shape Modeling.

BACKGROUND: Craniosynostosis is a condition caused by the premature fusion of skull sutures, leading to irregular growth patterns of the head. Three-dimensional photogrammetry is a radiation-free alternative to the diagnosis using computed tomography. While statistical shape models have been proposed to quantify head shape, no shape-model-based classification approach has been presented yet. METHODS: We present a classification pipeline that enables an automated diagnosis of three types of craniosynostosis. The pipeline is based on a statistical shape model built from photogrammetric surface scans. We made the model and pathology-specific submodels publicly available, making it the first publicly available craniosynostosis-related head model, as well as the first focusing on infants younger than 1.5 years. To the best of our knowledge, we performed the largest classification study for craniosynostosis to date. RESULTS: Our classification approach yields an accuracy of 97.8 %, comparable to other state-of-the-art methods using both computed tomography scans and stereophotogrammetry. Regarding the statistical shape model, we demonstrate that our model performs similar to other statistical shape models of the human head. CONCLUSION: We present a state-of-the-art shape-model-based classification approach for a radiation-free diagnosis of craniosynostosis. Our publicly available shape model enables the assessment of craniosynostosis on realistic and synthetic data.

Data Management for Systems Medicine: The SMART-CARE Joint Environment.

For a research project on mass spectrometry, a streamlined, harmonized and robust analytical pipeline is built to predict tumor recurrence. By means of standardization all steps from sample collection, analysis, proteome, and metabolome analysis are harmonized. Challenges like non-central identificators and distributed data are overcome with a centralized high-performant IT-platform in combination with a pseudonymization service and harmonization.