Different patterns of longitudinal brain and spinal cord changes and their associations with disability progression in NMO and MS.

OBJECTIVE: To investigate the longitudinal spinal cord and brain changes in neuromyelitis optica (NMO) and multiple sclerosis (MS) and their associations with disability progression. PATIENTS AND METHODS: We recruited 28 NMO, 22 MS, and 20 healthy controls (HC), who underwent both spinal cord and brain MRI at baseline. Twenty-five NMO and 20 MS completed 1-year follow-up. Baseline spinal cord and brain lesion loads, mean upper cervical cord area (MUCCA), brain, and thalamus volume and their changes during a 1-year follow-up were measured and compared between groups. All the measurements were also compared between progressive and non-progressive groups in NMO and MS. RESULTS: MUCCA decreased significantly during the 1-year follow-up in NMO not in MS. Percentage brain volume changes (PBVC) and thalamus volume changes in MS were significantly higher than NMO. MUCCA changes were significantly different between progressive and non-progressive groups in NMO, while baseline brain lesion volume and PBVC were associated with disability progression in MS. MUCCA changes during 1-year follow-up showed association with clinical disability in NMO. CONCLUSION: Spinal cord atrophy changes were associated with disability progression in NMO, while baseline brain lesion load and whole brain atrophy changes were related to disability progression in MS. KEY POINTS: • Spinal cord atrophy progression was observed in NMO. • Spinal cord atrophy changes were associated with disability progression in NMO. • Brain lesion and atrophy were related to disability progression in MS.

Semi-automated delineation of breast cancer tumors and subsequent materialization using three-dimensional printing (rapid prototyping).

OBJECTIVE: Three-dimensional (3D) printing has become widely available, and a few cases of its use in clinical practice have been described. The aim of this study was to explore facilities for the semi-automated delineation of breast cancer tumors and to assess the feasibility of 3D printing of breast cancer tumors. METHODS: In a case series of five patients, different 3D imaging methods-magnetic resonance imaging (MRI), digital breast tomosynthesis (DBT), and 3D ultrasound-were used to capture 3D data for breast cancer tumors. The volumes of the breast tumors were calculated to assess the comparability of the breast tumor models, and the MRI information was used to render models on a commercially available 3D printer to materialize the tumors. RESULTS: The tumor volumes calculated from the different 3D methods appeared to be comparable. Tumor models with volumes between 325 mm3 and 7,770 mm3 were printed and compared with the models rendered from MRI. The materialization of the tumors reflected the computer models of them. CONCLUSION: 3D printing (rapid prototyping) appears to be feasible. Scenarios for the clinical use of the technology might include presenting the model to the surgeon to provide a better understanding of the tumor's spatial characteristics in the breast, in order to improve decision-making in relation to neoadjuvant chemotherapy or surgical approaches. J. Surg. Oncol. 2017;115:238-242. © 2016 Wiley Periodicals, Inc.

Analyzing myocardial torsion based on tissue phase mapping cardiovascular magnetic resonance.

BACKGROUND: The purpose of this work is to analyze differences in left ventricular torsion between volunteers and patients with non-ischemic cardiomyopathy based on tissue phase mapping (TPM) cardiovascular magnetic resonance (CMR). METHODS: TPM was performed on 27 patients with non-ischemic cardiomyopathy and 14 normal volunteers. Patients underwent a standard CMR including late gadolinium enhancement (LGE) for the assessment of myocardial scar and ECG-gated cine CMR for global cardiac function. TPM was acquired in short-axis orientation at base, mid, and apex for all subjects. After evaluation by experienced observers, the patients were divided in subgroups according to the presence or absence of LGE (LGE+/LGE-), local wall motion abnormalities (WM+/WM-), and having a preserved (≥50%) or reduced (<50%) ejection fraction (EF+/EF-). TPM data was semi-automatically segmented and global LV torsion was computed for each cardiac time frame for endocardial and epicardial layers, and for the entire myocardium. RESULTS: Maximum myocardial torsion was significantly lower for patients with reduced EF compared to controls (0.21 ± 0.15°/mm vs. 0.36 ± 0.11°/mm, p = 0.018), but also for patients with wall motion abnormalities (0.21 ± 0.13°/mm vs. 0.36 ± 0.11°/mm, p = 0.004). Global myocardial torsion showed a positive correlation (r = 0.54, p < 0.001) with EF. Moreover, endocardial torsion was significantly higher than epicardial torsion for EF+ subjects (0.56 ± 0.33°/mm vs. 0.34 ± 0.18°/mm, p = 0.039) and for volunteers (0.46 ± 0.16°/mm vs. 0.30 ± 0.09°/mm, p = 0.004). The difference in maximum torsion between endo- and epicardial layers was positively correlated with EF (r = 0.47, p = 0.002) and age (r = 0.37, p = 0.016) for all subjects. CONCLUSIONS: TPM can be used to detect significant differences in LV torsion in patients with reduced EF and in the presence of local wall motion abnormalities. We were able to quantify torsion differences between the endocardium and epicardium, which vary between patient subgroups and are correlated to age and EF.

Principles and methods for automatic and semi-automatic tissue segmentation in MRI data.

The development of magnetic resonance imaging (MRI) revolutionized both the medical and scientific worlds. A large variety of MRI options have generated a huge amount of image data to interpret. The investigation of a specific tissue in 3D or 4D MR images can be facilitated by image processing techniques, such as segmentation and registration. In this work, we provide a brief review of the principles and methods that are commonly applied to achieve superior tissue segmentation results in MRI. The impacts of MR image acquisition on segmentation outcome and the principles of selecting and exploiting segmentation techniques tailored for specific tissue identification tasks are discussed. In the end, two exemplary applications, breast and fibroglandular tissue segmentation in MRI and myocardium segmentation in short-axis cine and real-time MRI, are discussed to explain the typical challenges that can be posed in practical segmentation tasks in MRI data. The corresponding solutions that are adopted to deal with these challenges of the two practical segmentation tasks are thoroughly reviewed.

Cervical spinal cord volume loss is related to clinical disability progression in multiple sclerosis.

OBJECTIVE: To examine the temporal evolution of spinal cord (SC) atrophy in multiple sclerosis (MS), and its association with clinical progression in a large MS cohort. METHODS: A total of 352 patients from two centres with MS (relapsing remitting MS (RRMS): 256, secondary progressive MS (SPMS): 73, primary progressive MS (PPMS): 23) were included. Clinical and MRI parameters were obtained at baseline, after 12 months and 24 months of follow-up. In addition to conventional brain and SC MRI parameters, the annualised percentage brain volume change and the annualised percentage upper cervical cord cross-sectional area change (aUCCA) were quantified. Main outcome measure was disease progression, defined by expanded disability status scale increase after 24 months. RESULTS: UCCA was lower in SPMS and PPMS compared with RRMS for all time points. aUCCA over 24 months was highest in patients with SPMS (-2.2% per year) and was significantly higher in patients with disease progression (-2.3% per year) than in stable patients (-1.2% per year; p=0.003), while annualised percentage brain volume change did not differ between subtypes (RRMS: -0.42% per year; SPMS -0.6% per year; PPMS: -0.46% per year) nor between progressive and stable patients (p=0.055). Baseline UCCA and aUCCA over 24 months were found to be relevant contributors of expanded disability status scale at month-24, while baseline UCCA as well as number of SC segments involved by lesions at baseline but not aUCCA were relevant contributors of disease progression. CONCLUSIONS: SC MRI parameters including baseline UCCA and SC lesions were significant MRI predictors of disease progression. Progressive 24-month upper SC atrophy occurred in all MS subtypes, and was faster in patients exhibiting disease progression at month-24.

Mean upper cervical cord area (MUCCA) measurement in long-standing multiple sclerosis: relation to brain findings and clinical disability.

BACKGROUND: The majority of patients with multiple sclerosis (MS) present with spinal cord pathology. Spinal cord atrophy is thought to be a marker of disease severity, but in long-disease duration its relation to brain pathology and clinical disability is largely unknown. OBJECTIVE: Our aim was to investigate mean upper cervical cord area (MUCCA) in patients with long-standing MS and assess its relation to brain magnetic resonance imaging (MRI) measures and clinical disability. METHODS: MUCCA was measured in 196 MS patients and 55 healthy controls using 3DT1-weighted cervical images obtained at 3T MRI. Clinical disability was measured using the Expanded Disability Status Scale (EDSS), Nine-Hole-Peg test (9-HPT), and 25 feet Timed Walk Test (TWT). Stepwise linear regression was performed to assess the association between MUCCA and MRI measures, and between MUCCA and clinical disability. RESULTS: MUCCA was smaller (mean 11.7%) in MS patients compared with healthy controls (72.56±9.82 and 82.24±7.80 mm2 respectively; p<0.001), most prominently in male patients. MUCCA was associated with normalized brain volume, and number of cervical cord lesions. MUCCA was independently associated with EDSS, TWT, and 9-HPT. CONCLUSION: MUCCA was reduced in MS patients compared with healthy controls. It provides a relevant marker for clinical disability in long-standing disease, independent of other MRI measures.

Cooperative AI training for cardiothoracic segmentation in computed tomography: An iterative multi-center annotation approach.

PURPOSE: Radiological reporting is transitioning to quantitative analysis, requiring large-scale multi-center validation of biomarkers. A major prerequisite and bottleneck for this task is the voxelwise annotation of image data, which is time-consuming for large cohorts. In this study, we propose an iterative training workflow to support and facilitate such segmentation tasks, specifically for high-resolution thoracic CT data. METHODS: Our study included 132 thoracic CT scans from clinical practice, annotated by 13 radiologists. In three iterative training experiments, we aimed to improve and accelerate segmentation of the heart and mediastinum. Each experiment started with manual segmentation of 5-25 CT scans, which served as training data for a nnU-Net. Further iterations incorporated AI pre-segmentation and human correction to improve accuracy, accelerate the annotation process, and reduce human involvement over time. RESULTS: Results showed consistent improvement in AI model quality with each iteration. Resampled datasets improved the Dice similarity coefficients for both the heart (DCS 0.91 [0.88; 0.92]) and the mediastinum (DCS 0.95 [0.94; 0.95]). Our AI models reduced human interaction time by 50 % for heart and 70 % for mediastinum segmentation in the most potent iteration. A model trained on only five datasets achieved satisfactory results (DCS > 0.90). CONCLUSIONS: The iterative training workflow provides an efficient method for training AI-based segmentation models in multi-center studies, improving accuracy over time and simultaneously reducing human intervention. Future work will explore the use of fewer initial datasets and additional pre-processing methods to enhance model quality.

Radiomics workflow definition & challenges - German priority program 2177 consensus statement on clinically applied radiomics.

OBJECTIVES: Achieving a consensus on a definition for different aspects of radiomics workflows to support their translation into clinical usage. Furthermore, to assess the perspective of experts on important challenges for a successful clinical workflow implementation. MATERIALS AND METHODS: The consensus was achieved by a multi-stage process. Stage 1 comprised a definition screening, a retrospective analysis with semantic mapping of terms found in 22 workflow definitions, and the compilation of an initial baseline definition. Stages 2 and 3 consisted of a Delphi process with over 45 experts hailing from sites participating in the German Research Foundation (DFG) Priority Program 2177. Stage 2 aimed to achieve a broad consensus for a definition proposal, while stage 3 identified the importance of translational challenges. RESULTS: Workflow definitions from 22 publications (published 2012-2020) were analyzed. Sixty-nine definition terms were extracted, mapped, and semantic ambiguities (e.g., homonymous and synonymous terms) were identified and resolved. The consensus definition was developed via a Delphi process. The final definition comprising seven phases and 37 aspects reached a high overall consensus (> 89% of experts "agree" or "strongly agree"). Two aspects reached no strong consensus. In addition, the Delphi process identified and characterized from the participating experts' perspective the ten most important challenges in radiomics workflows. CONCLUSION: To overcome semantic inconsistencies between existing definitions and offer a well-defined, broad, referenceable terminology, a consensus workflow definition for radiomics-based setups and a terms mapping to existing literature was compiled. Moreover, the most relevant challenges towards clinical application were characterized. CRITICAL RELEVANCE STATEMENT: Lack of standardization represents one major obstacle to successful clinical translation of radiomics. Here, we report a consensus workflow definition on different aspects of radiomics studies and highlight important challenges to advance the clinical adoption of radiomics. KEY POINTS: Published radiomics workflow terminologies are inconsistent, hindering standardization and translation. A consensus radiomics workflow definition proposal with high agreement was developed. Publicly available result resources for further exploitation by the scientific community.

Relevance of spinal cord abnormalities to clinical disability in multiple sclerosis: MR imaging findings in a large cohort of patients.

PURPOSE: To determine whether spinal cord atrophy differs among disease subtypes in multiple sclerosis (MS) and whether it offers diagnostic and clinical correlative information beyond that provided by other magnetic resonance (MR) imaging markers. MATERIALS AND METHODS: The institutional review board approved the study; all subjects gave written informed consent. Upper cervical cord cross-sectional area (UCCA), brain and spinal cord lesion loads, and brain atrophy were measured in 440 patients with MS (311 with relapsing-remitting [RR] MS, 92 with secondary-progressive [SP] MS, and 37 with primary-progressive [PP] MS) studied in two centers. Disability was scored with the Expanded Disability Status Scale (EDSS), the timed 25-foot walk test (TWT), and the nine-hole peg test. UCCA was compared between groups with the Mann-Whitney U test. Correlations were assessed with the Spearman ρ test. Multivariate associations between UCCA and clinical and other MR imaging parameters, including number of hypointense brain lesions on T1-weighted MR images, presence of diffuse abnormalities, and number of involved segments in the spinal cord, were assessed by using multiple linear regression, adjusted for study center site. RESULTS: The UCCA in patients with SP MS (median, 79 mm(2); interquartile range, 72.4-84.9 mm(2)) and PP MS (median, 77.3 mm(2); interquartile range, 69-82.5 mm(2)) was significantly smaller (P < .001) than that in patients with RR MS (median, 84 mm(2); interquartile range, 78.7-89.3 mm(2)). UCCA was inversely correlated with EDSS score, TWT, and nine-hole peg test findings (ρ ≤ -0.29, P < .001 for all comparisons). UCCA, number of hypointense brain lesions on T1-weighted MR images, presence of diffuse abnormalities, and number of involved segments in the spinal cord were found to be significant explanatory factors for clinical disability (R(2) = 0.564). The UCCA and the number of hypointense brain lesions on T1-weighted images were the strongest MR imaging parameters for explaining physical disability, as measured with the EDSS. CONCLUSION: Spinal cord abnormalities have a strong effect on clinical disability in MS. MR imaging-derived UCCA was found to be the most significant spinal cord parameter for explaining EDSS score.

DTI segmentation via the combined analysis of connectivity maps and tensor distances.

We describe a novel approach to extract the neural tracts of interest from a diffusion tensor image (DTI). Compared to standard streamline tractography, existing probabilistic methods are able to capture fiber paths that deviate from the main tensor diffusion directions. At the same time, tensor clustering methods are able to more precisely delimit the border of the bundle. To the best of our knowledge, we propose the first algorithm which combines the advantages supplied by probabilistic and tensor clustering approaches. The algorithm includes a post-processing step to limit partial-volume related segmentation errors. We extensively test the accuracy of our algorithm on different configurations of a DTI software phantom for which we systematically vary the image noise, the number of gradients, the geometry of the fiber paths and the angle between adjacent and crossing fiber bundles. The reproducibility of the algorithm is supported by the segmentation of the corticospinal tract of nine patients. Additional segmentations of the corticospinal tract, the arcuate fasciculus, and the optic radiations are in accordance with anatomical knowledge. The required user interaction is comparable to that of streamline tractography, which allows for an uncomplicated integration of the algorithm into the clinical routine.

Quantitative evaluation of the influence of multiple MRI sequences and of pathological tissues on the registration of longitudinal data acquired during brain tumor treatment.

Registration methods facilitate the comparison of multiparametric magnetic resonance images acquired at different stages of brain tumor treatments. Image-based registration solutions are influenced by the sequences chosen to compute the distance measure, and the lack of image correspondences due to the resection cavities and pathological tissues. Nonetheless, an evaluation of the impact of these input parameters on the registration of longitudinal data is still missing. This work evaluates the influence of multiple sequences, namely T1-weighted (T1), T2-weighted (T2), contrast enhanced T1-weighted (T1-CE), and T2 Fluid Attenuated Inversion Recovery (FLAIR), and the exclusion of the pathological tissues on the non-rigid registration of pre- and post-operative images. We here investigate two types of registration methods, an iterative approach and a convolutional neural network solution based on a 3D U-Net. We employ two test sets to compute the mean target registration error (mTRE) based on corresponding landmarks. In the first set, markers are positioned exclusively in the surroundings of the pathology. The methods employing T1-CE achieves the lowest mTREs, with a improvement up to 0.8 mm for the iterative solution. The results are higher than the baseline when using the FLAIR sequence. When excluding the pathology, lower mTREs are observable for most of the methods. In the second test set, corresponding landmarks are located in the entire brain volumes. Both solutions employing T1-CE obtain the lowest mTREs, with a decrease up to 1.16 mm for the iterative method, whereas the results worsen using the FLAIR. When excluding the pathology, an improvement is observable for the CNN method using T1-CE. Both approaches utilizing the T1-CE sequence obtain the best mTREs, whereas the FLAIR is the least informative to guide the registration process. Besides, the exclusion of pathology from the distance measure computation improves the registration of the brain tissues surrounding the tumor. Thus, this work provides the first numerical evaluation of the influence of these parameters on the registration of longitudinal magnetic resonance images, and it can be helpful for developing future algorithms.

Segmentation of fiber tracts based on an accuracy analysis on diffusion tensor software phantoms.

Due to its unique sensitivity to tissue microstructure, one of the primary applications of diffusion-weighted magnetic resonance imaging is the reconstruction of neural fiber pathways by means of fiber-tracking algorithms. In this work, we make use of realistic diffusion-tensor software phantoms in order to carry out an analysis of the precision of streamline tractography by systematically varying certain properties of the simulated image data (noise, tensor anisotropy, and image resolution) as well as certain fiber-tracking parameters (number of seed points and step length). Building upon the gained knowledge about the precision of the analyzed fiber-tracking algorithm, we proceed by suggesting a fuzzy segmentation algorithm for diffusion tensor images which better estimates the precise spatial extent of a tracked fiber bundle. The presented segmentation algorithm utilizes information given by the estimated main diffusion direction in a voxel and the respective uncertainty, and its validity is confirmed by both qualitative and quantitative analyses.

Decreased hippocampal volume, indirectly measured, is associated with depressive symptoms and consolidation deficits in multiple sclerosis.

BACKGROUND: The human hippocampus plays a role in episodic memory and depression. Recently, it has been shown, using manual tracings, that the hippocampus is smaller in volume in MS patients compared with healthy controls, and that, at least for depression, hippocampal atrophy correlates with symptom severity. METHODS: Because manual tracing of the hippocampus is time consuming, we used a semi-automatic procedure for temporal horn volumetry in 72 multiple sclerosis (MS) patients and 16 control subjects as an indirect measure of hippocampal volume. We analysed memory performance with the California Verbal Learning Test (using separate indices for encoding, consolidation and retrieval) and depressive mood with the Beck's Depression Inventory (distinguishing between psychic and somatic aspects). RESULTS: MS patients had significantly larger temporal horn volumes and volume correlated with psychic symptoms of depressive mood. Temporal horn volume was also associated with consolidation, in particular in the most impaired group. CONCLUSIONS: Temporal horn volume can be measured relatively easily and appears to correlate with two major clinical problems in MS patients: memory performance and depressive mood. The link between temporal horn volume, consolidation and depression may be hippocampal atrophy, as suggested by their adjacent neuroanatomical localization, and by the similarity in functional loss following impairment of these two structures.

Accuracy and reproducibility of a novel semi-automatic segmentation technique for MR volumetry of the pituitary gland.

INTRODUCTION: Although several reports about volumetric determination of the pituitary gland exist, volumetries have been solely performed by indirect measurements or manual tracing on the gland's boundaries. The purpose of this study was to evaluate the accuracy and reproducibility of a novel semi-automatic MR-based segmentation technique. METHODS: In an initial technical investigation, T1-weighted 3D native magnetised prepared rapid gradient echo sequences (1.5 T) with 1 mm isotropic voxel size achieved high reliability and were utilised in different in vitro and in vivo studies. The computer-assisted segmentation technique was based on an interactive watershed transform after resampling and gradient computation. Volumetry was performed by three observers with different software and neuroradiologic experiences, evaluating phantoms of known volume (0.3, 0.9 and 1.62 ml) and healthy subjects (26 to 38 years; overall 135 volumetries). RESULTS: High accuracy of the volumetry was shown by phantom analysis; measurement errors were <4% with a mean error of 2.2%. In vitro, reproducibility was also promising with intra-observer variability of 0.7% for observer 1 and 0.3% for observers 2 and 3; mean inter-observer variability was in vitro 1.2%. In vivo, scan-rescan, intra-observer and inter-observer variability showed mean values of 3.2%, 1.8% and 3.3%, respectively. Unifactorial analysis of variance demonstrated no significant differences between pituitary volumes for various MR scans or software calculations in the healthy study groups (p > 0.05). CONCLUSION: The analysed semi-automatic MR volumetry of the pituitary gland is a valid, reliable and fast technique. Possible clinical applications are hyperplasia or atrophy of the gland in pathological circumstances either by a single assessment or by monitoring in follow-up studies.

A new sulcus-corrected approach for assessing cerebellar volume in spinocerebellar ataxia.

Precise volumetry of the cerebellum still remains challenging, due to thin sulci and gyri. We present a new fast and reliable sulcus-corrected approach for quantitative assessment of cerebellar atrophy, evaluated on patients with spinocerebellar ataxia (SCA). Thin-sliced T1-weighted magnetic resonance images (MPRAGE) were acquired in 11 genetically confirmed SCA6 patients and in a group of age-matched control subjects (n=14). Post-processing involves a morphological image segmentation pipeline as a basis for a sulcus-corrected cerebellar volume measurement. Cerebellar volumes and intra-rater, inter-rater and scan-rescan reproducibility were quantified. Reliability of the measurements was validated using an anatomical preparation of the cerebellum. Repeatability coefficients (RC: intra-rater/inter-rater/scan-rescan) of the method were 1.07%/1.11%/1.35%. Absolute cerebellar volumes showed good agreement with the actual volume of the anatomical preparation. The cerebellar volume of the SCA 6 was 96.3±12.1ml (mean±S.D.), which was significantly lower than the results of the corresponding control groups. The cerebellar volume correlated significantly to clinical dysfunction in SCA6. This is the first study to demonstrate the feasibility of a new sulcus-corrected approach to assess cerebellar volume. In contrast to currently used methods, this new approach may be more sensitive even to small atrophic changes affecting sulcal widening.

Anisotropic 3D Multi-Stream CNN for Accurate Prostate Segmentation from Multi-Planar MRI.

BACKGROUND AND OBJECTIVE: Accurate and reliable segmentation of the prostate gland in MR images can support the clinical assessment of prostate cancer, as well as the planning and monitoring of focal and loco-regional therapeutic interventions. Despite the availability of multi-planar MR scans due to standardized protocols, the majority of segmentation approaches presented in the literature consider the axial scans only. In this work, we investigate whether a neural network processing anisotropic multi-planar images could work in the context of a semantic segmentation task, and if so, how this additional information would improve the segmentation quality. METHODS: We propose an anisotropic 3D multi-stream CNN architecture, which processes additional scan directions to produce a high-resolution isotropic prostate segmentation. We investigate two variants of our architecture, which work on two (dual-plane) and three (triple-plane) image orientations, respectively. The influence of additional information used by these models is evaluated by comparing them with a single-plane baseline processing only axial images. To realize a fair comparison, we employ a hyperparameter optimization strategy to select optimal configurations for the individual approaches. RESULTS: Training and evaluation on two datasets spanning multiple sites show statistical significant improvement over the plain axial segmentation (p<0.05 on the Dice similarity coefficient). The improvement can be observed especially at the base (0.898 single-plane vs. 0.906 triple-plane) and apex (0.888 single-plane vs. 0.901 dual-plane). CONCLUSION: This study indicates that models employing two or three scan directions are superior to plain axial segmentation. The knowledge of precise boundaries of the prostate is crucial for the conservation of risk structures. Thus, the proposed models have the potential to improve the outcome of prostate cancer diagnosis and therapies.

A fast and robust hepatocyte quantification algorithm including vein processing.

BACKGROUND: Quantification of different types of cells is often needed for analysis of histological images. In our project, we compute the relative number of proliferating hepatocytes for the evaluation of the regeneration process after partial hepatectomy in normal rat livers. RESULTS: Our presented automatic approach for hepatocyte (HC) quantification is suitable for the analysis of an entire digitized histological section given in form of a series of images. It is the main part of an automatic hepatocyte quantification tool that allows for the computation of the ratio between the number of proliferating HC-nuclei and the total number of all HC-nuclei for a series of images in one processing run. The processing pipeline allows us to obtain desired and valuable results for a wide range of images with different properties without additional parameter adjustment. Comparing the obtained segmentation results with a manually retrieved segmentation mask which is considered to be the ground truth, we achieve results with sensitivity above 90% and false positive fraction below 15%. CONCLUSIONS: The proposed automatic procedure gives results with high sensitivity and low false positive fraction and can be applied to process entire stained sections.

Automated density-based counting of FISH amplification signals for HER2 status assessment.

BACKGROUND: Automated image analysis can make quantification of FISH signals in histological sections more efficient and reproducible. Current detection-based methods, however, often fail to accurately quantify densely clustered FISH signals. METHODS: We propose a novel density-based approach to quantifying FISH signals. Instead of detecting individual signals, this approach quantifies FISH signals in terms of the integral over a density map predicted by Deep Learning. We apply the density-based approach to the task of counting and determining ratios of ERBB2 and CEN17 signals and compare it to common detection-based and area-based approaches. RESULTS: The ratios determined by our approach were strongly correlated with results obtained by manual annotation of individual FISH signals (Pearson's r = 0.907). In addition, they were highly consistent with cutoff-scores determined by a pathologist (balanced concordance = 0.971). The density-based approach generally outperformed the other approaches. Its superiority was particularly evident in the presence of dense signal clusters. CONCLUSIONS: The presented approach enables accurate and efficient automated quantification of FISH signals. Since signals in clusters can hardly be detected individually even by human observers, the density-based quantification performs better than detection-based approaches.

Evaluation of deep learning methods for parotid gland segmentation from CT images.

The segmentation of organs at risk is a crucial and time-consuming step in radiotherapy planning. Good automatic methods can significantly reduce the time clinicians have to spend on this task. Due to its variability in shape and low contrast to surrounding structures, segmenting the parotid gland is challenging. Motivated by the recent success of deep learning, we study the use of two-dimensional (2-D), 2-D ensemble, and three-dimensional (3-D) U-Nets for segmentation. The mean Dice similarity to ground truth is ∼ 0.83 for all three models. A patch-based approach for class balancing seems promising for false-positive reduction. The 2-D ensemble and 3-D U-Net are applied to the test data of the 2015 MICCAI challenge on head and neck autosegmentation. Both deep learning methods generalize well onto independent data (Dice 0.865 and 0.88) and are superior to a selection of model- and atlas-based methods with respect to the Dice coefficient. Since appropriate reference annotations are essential for training but often difficult and expensive to obtain, it is important to know how many samples are needed for training. We evaluate the performance after training with different-sized training sets and observe no significant increase in the Dice coefficient for more than 250 training cases.

Spinal cord atrophy in spinocerebellar ataxia type 3 and 6 : impact on clinical disability.

OBJECTIVE: To quantify spinal cord atrophy and its impact on clinical disability in spinocerebellar ataxia (SCA) type 3 and 6. METHODS: Atrophy of the upper spinal cord was assessed by high resolution T1-weighted MRI of patients with SCA3 (n = 14) and SCA6 (n = 10). Furthermore, two groups of age- and sex-matched healthy control subjects (n = 24,) corresponding to the two SCA groups, were studied. Images were post-processed by a semi-automated volumetry method combining a marker based segmentation and an automatic histogram method facilitating highly reliable quantification and morphometry of the upper cervical cord in vivo. RESULTS: We found a significant reduction of normalized mean crosssectional area of the spinal cord in SCA3 (p < 0.0005), whereas in SCA6 patients normalized mean crosssectional area was in the normal range (p = 0.379). No correlation was found between spinal cord atrophy and disease duration as well as CAG repeat length in both subtypes. In SCA6 a negative dependency between clinical disability, as expressed by the International Cooperative Ataxia Rating Scale as a well established ataxia score, and the mean cross-sectional area was found (p = 0.02). A similar correlation was observed in SCA3 but did not reach statistical significance. CONCLUSION: Our results quantify for the first time in vivo spinal cord atrophy as a non-cerebellar neurodegenerative process in SCA3. Our results suggest MR volumetry of the upper cervical cord as a marker of functional importance in SCA3 and SCA6.