DBSegment: Fast and robust segmentation of deep brain structures considering domain generalisation

in Human Brain Mapping (2022)

Segmenting deep brain structures from magnetic resonance images is important for patient diagnosis, surgical planning, and research. Most current state-of-the-art solutions follow a segmentation-by ... [more ▼]

Segmenting deep brain structures from magnetic resonance images is important for patient diagnosis, surgical planning, and research. Most current state-of-the-art solutions follow a segmentation-by-registration approach, where subject magnetic resonance imaging (MRIs) are mapped to a template with well-defined segmentations. However, registration-based pipelines are time-consuming, thus, limiting their clinical use. This paper uses deep learning to provide a one-step, robust, and efficient deep brain segmentation solution directly in the native space. The method consists of a preprocessing step to conform all MRI images to the same orientation, followed by a convolutional neural network using the nnU-Net framework. We use a total of 14 datasets from both research and clinical collections. Of these, seven were used for training and validation and seven were retained for testing. We trained the network to segment 30 deep brain structures, as well as a brain mask, using labels generated from a registration-based approach. We evaluated the generalizability of the network by performing a leave-one-dataset-out cross-validation, and independent testing on unseen datasets. Furthermore, we assessed cross-domain transportability by evaluating the results separately on different domains. We achieved an average dice score similarity of 0.89 ± 0.04 on the test datasets when compared to the registration-based gold standard. On our test system, the computation time decreased from 43 min for a reference registration-based pipeline to 1.3 min. Our proposed method is fast, robust, and generalizes with high reliability. It can be extended to the segmentation of other brain structures. It is publicly available on GitHub, and as a pip package for convenient usage. [less ▲]

Generalising from conventional pipelines using deep learning in high‑throughput screening workfows

in Scientific Reports (2022)

The study of complex diseases relies on large amounts of data to build models toward precision medicine. Such data acquisition is feasible in the context of high-throughput screening, in which the quality ... [more ▼]

The study of complex diseases relies on large amounts of data to build models toward precision medicine. Such data acquisition is feasible in the context of high-throughput screening, in which the quality of the results relies on the accuracy of the image analysis. Although state-of-the-art solutions for image segmentation employ deep learning approaches, the high cost of manually generating ground truth labels for model training hampers the day-to-day application in experimental laboratories. Alternatively, traditional computer vision-based solutions do not need expensive labels for their implementation. Our work combines both approaches by training a deep learning network using weak training labels automatically generated with conventional computer vision methods. Our network surpasses the conventional segmentation quality by generalising beyond noisy labels, providing a 25% increase of mean intersection over union, and simultaneously reducing the development and inference times. Our solution was embedded into an easy-to-use graphical user interface that allows researchers to assess the predictions and correct potential inaccuracies with minimal human input. To demonstrate the feasibility of training a deep learning solution on a large dataset of noisy labels automatically generated by a conventional pipeline, we compared our solution against the common approach of training a model from a small manually curated dataset by several experts. Our work suggests that humans perform better in context interpretation, such as error assessment, while computers outperform in pixel-by-pixel fne segmentation. Such pipelines are illustrated with a case study on image segmentation for autophagy events. This work aims for better translation of new technologies to real-world settings in microscopy-image analysis. [less ▲]

Initialisation of Deep Brain Stimulation Parameters with Multi-objective Optimisation Using Imaging Data

in Bildverarbeitung für die Medizin 2022 (2022)

Following the deep brain stimulation (DBS) surgery, the stimulation parameters are manually tuned to reduce symptoms. This procedure can be timeconsuming, especially with directional leads. We propose an ... [more ▼]

Following the deep brain stimulation (DBS) surgery, the stimulation parameters are manually tuned to reduce symptoms. This procedure can be timeconsuming, especially with directional leads. We propose an automated methodology to initialise contact configurations using imaging techniques. The goal is to maximise the electric field on the target while minimising the spillover, and the electric field on regions of avoidance. By superposing pre-computed electric fields, we solve the optimisation problem in less than a minute, much more efficient compared to finite element methods. Our method offers a robust and rapid solution, and it is expected to considerably reduce the time required for manual parameter tuning. [less ▲]

The need of standardised metadata to encode causal relationships: Towards safer data-driven machine learning biological solutions

Scientific Conference (2021, November 16)

In this paper, we discuss the importance of considering causal relations in the development of machine learning solutions to prevent factors hampering the robustness and generalisation capacity of the ... [more ▼]

In this paper, we discuss the importance of considering causal relations in the development of machine learning solutions to prevent factors hampering the robustness and generalisation capacity of the models, such as induced biases. This issue often arises when the algorithm decision is affected by confounding factors. In this work, we argue that the integration of causal relationships can identify potential confounders. We call for standardised meta-information practices as a crucial step for proper machine learning solutions development, validation, and data sharing. Such practices include detailing the dataset generation process, aiming for automatic integration of causal relationships. [less ▲]

Model bias and its impact on computer-aided diagnosis: A data-centric approach

Poster (2021, August)

Machine learning and data-driven solutions open exciting opportunities in many disciplines including healthcare. The recent transition to this technology into real clinical settings brings new challenges ... [more ▼]

Machine learning and data-driven solutions open exciting opportunities in many disciplines including healthcare. The recent transition to this technology into real clinical settings brings new challenges. Such problems derive from several factors, including their dataset origin, composition and description, hampering their fairness and secure application. Considering the potential impact of incorrect predictions in applied-ML healthcare research is urgent. Undetected bias induced by inappropriate use of datasets and improper consideration of confounders prevents the translation of prediction models into clinical practice. Therefore, in this work, the use of available systematic tools to assess the risk of bias in models is employed as the first step to explore robust solutions for better dataset choice, dataset merge and design of the training and validation step during the ML development pipeline. [less ▲]

Application of Raman Spectroscopy for Detection of Histologically Distinct Areas in Formalin-fixed Paraffin-embedded (FFPE) Glioblastoma

in Neuro-Oncology Advances (2021)

Background Although microscopic assessment is still the diagnostic gold standard in pathology, non-light microscopic methods such as new imaging methods and molecular pathology have considerably ... [more ▼]

Background Although microscopic assessment is still the diagnostic gold standard in pathology, non-light microscopic methods such as new imaging methods and molecular pathology have considerably contributed to more precise diagnostics. As an upcoming method, Raman spectroscopy (RS) offers a "molecular fingerprint" which could be used to differentiate tissue heterogeneity or diagnostic entities. RS has been successfully applied on fresh and frozen tissue, however more aggressively, chemically treated tissue such as formalin-fixed, paraffin-embedded (FFPE) samples are challenging for RS. Methods To address this issue, we examined FFPE samples of morphologically highly heterogeneous glioblastoma (GBM) using RS in order to classify histologically defined GBM areas according to RS spectral properties. We have set up a SVM (support vector machine)-based classifier in a training cohort and corroborated our findings in a validation cohort. Results Our trained classifier identified distinct histological areas such as tumor core and necroses in GBM with an overall accuracy of 70.5% based on spectral properties of RS. With an absolute misclassification of 21 out of 471 Raman measurements, our classifier has the property of precisely distinguishing between normal appearing brain tissue and necrosis. When verifying the suitability of our classifier system in a second independent dataset, very little overlap between necrosis and normal appearing brain tissue can be detected. Conclusion These findings show that histologically highly variable samples such as GBM can be reliably recognized by their spectral properties using RS. As a conclusion, we propose that RS may serve useful as a future method in the pathological toolbox. [less ▲]

Differentiation of primary CNS lymphoma and glioblastoma using Raman spectroscopy and machine learning algorithms

in Free Neuropathology (2021), 2

Objective and Methods: Timely discrimination between primary CNS lymphoma (PCNSL) and glioblastoma is crucial for diagnostics and therapy, but most importantly also determines the intraoperative surgical ... [more ▼]

Objective and Methods: Timely discrimination between primary CNS lymphoma (PCNSL) and glioblastoma is crucial for diagnostics and therapy, but most importantly also determines the intraoperative surgical course. Advanced radiological methods allow this to a certain extent but ultimately, biopsy is still necessary for final diagnosis. As an upcoming method that enables tissue analysis by tracking changes in the vibrational state of molecules via inelastic scattered photons, we used Raman Spectroscopy (RS) as a label free method to examine specimens of both tumor entities intraoperatively, as well as postoperatively in formalin fixed paraffin embedded (FFPE) samples. Results: We applied and compared statistical performance of linear and nonlinear machine learning algorithms (Logistic Regression, Random Forest and XGBoost), and found that Random Forest classification distinguished the two tumor entities with a balanced accuracy of 82,4% in intraoperative tissue condition and with 94% using measurements of distinct tumor areas on FFPE tissue. Taking a deeper insight into the spectral properties of the tumor entities, we describe different tumor-specific Raman shifts of interest for classification. Conclusions: Due to our findings, we propose RS as an additional tool for fast and non-destructive, perioperative tumor tissue discrimination, which may augment treatment options at an early stage. RS may further serve as a useful additional tool for neuropathological diagnostics with little requirements for tissue integrity. [less ▲]

Analysis and visualisation of tremor dynamics in deep brain stimulation patients

in Current Directions in Biomedical Engineering (2020), 6(3), 4

Automatic Detection of Nigrosome Degeneration in Susceptibility-Weighted MRI for Computer-Aided Diagnosis of Parkinson’s Disease Using Machine Learning

in Movement Disorders (2020, September 12)

Objective: Automatize the detection of ‘swallow-tail’ appearance in substantia nigra dopaminergic neurons using MRI for more robust tests on Parkinson’s disease (PD) diagnosis. Background: Differential ... [more ▼]

Objective: Automatize the detection of ‘swallow-tail’ appearance in substantia nigra dopaminergic neurons using MRI for more robust tests on Parkinson’s disease (PD) diagnosis. Background: Differential diagnosis of PD is challenging even in specialized centers. The use of imaging techniques can be bene cial for the diagnosis. Although DaTSCAN has been proven to be clinically useful, it is not widely available and has radiation risk and high-cost associated. Therefore, MRI scans for PD diagnosis offer several advantages over DaTSCAN [1]. Recent literature shows strong evidence of high diagnostic accuracy using the ‘swallow-tail’ shape of the dorsolateral substantia nigra in 3T – SWI [2]. Nevertheless, the majority of such studies rely on the subjective opinion of experts and manual methods for the analysis to assess the accuracy of these features. Alternatively, we propose a fully automated solution to evaluate the absence or presence of this feature for computer-aided diagnosis (CAD) of PD. Method: Restrospective study of 27 PD and 18 non-PD was conducted, including standard high-resolution 3D MRI – T1 & SWI sequences (additionally, T2 scans were used to increase the registration references). Firstly, spatial registration and normalization of the images were performed. Then, the ROI was extracted using atlas references. Finally, a supervised machine learning model was built using 5-fold-within-5-fold nested cross-validation. Results: Preliminary results show signi cant sensitivity (0.92) and ROC AUC (0.82), allowing for automated classi cation of patients based on swallow-tail biomarker from MRI. Conclusion: Detection of nigrosome degeneration (swallow-tail biomarker) in accessible brain imaging techniques can be automatized with signi cant accuracy, allowing for computer-aided PD diagnosis. References: [1] Schwarz, S. T., Xing, Y., Naidu, S., Birchall, J., Skelly, R., Perkins, A., ... & Gowland, P. (2017). Protocol of a single group prospective observational study on the diagnostic value of 3T susceptibility weighted MRI of nigrosome-1 in patients with parkinsonian symptoms: the N3iPD study (nigrosomal iron imaging in Parkinson’s disease). BMJ open, 7(12), e016904. [2] – Schwarz, S. T., Afzal, M., Morgan, P. S., Bajaj, N., Gowland, P. A., & Auer, D. P. (2014). The ‘swallow tail’ appearance of the healthy nigrosome –a new accurate test of Parkinson’s disease: a case-control and retrospective cross-sectional MRI study at 3T. PloS one, 9(4). [less ▲]

Primary and recurrent glioma patient-derived orthotopic xenografts (PDOX) represent relevant patient avatars for precision medicine

E-print/Working paper (2020)

Patient-derived cancer models are essential tools for studying tumor biology and preclinical interventions. Here, we show that glioma patient-derived orthotopic xenografts (PDOXs) enable long-term ... [more ▼]

Patient-derived cancer models are essential tools for studying tumor biology and preclinical interventions. Here, we show that glioma patient-derived orthotopic xenografts (PDOXs) enable long-term propagation of patient tumors and represent clinically relevant patient avatars. We created a large collection of PDOXs from primary and recurrent gliomas with and without mutations in IDH1, which retained histopathological, genetic, epigenetic and transcriptomic features of patient tumors with no mouse-specific clonal evolution. Longitudinal PDOX models recapitulate the limited genetic evolution of gliomas observed in patient tumors following treatment. PDOX-derived standardized tumor organoid cultures enabled assessment of drug responses, which were validated in mice. PDOXs showed clinically relevant responses to Temozolomide and to targeted treatments such as EGFR and CDK4/6 inhibitors in (epi)genetically defined groups, according to MGMT promoter and EGFR/CDK status respectively. Dianhydrogalactitol, a bifunctional alkylating agent, showed promising potential against glioblastoma. Our study underlines the clinical relevance of glioma PDOX models for translational research and personalized treatment studies. [less ▲]