PDGF-D Is Dispensable for the Development and Progression of Murine Alport Syndrome.

Alport syndrome is an inherited kidney disease, which can lead to glomerulosclerosis and fibrosis, as well as end-stage kidney disease in children and adults. Platelet-derived growth factor-D (PDGF-D) mediates glomerulosclerosis and interstitial fibrosis in various models of kidney disease, prompting investigation of its role in a murine model of Alport syndrome. In vitro, PDGF-D induced proliferation and profibrotic activation of conditionally immortalized human parietal epithelial cells. In Col4a3-/- mice, a model of Alport syndrome, PDGF-D mRNA and protein were significantly up-regulated compared with non-diseased wild-type mice. To analyze the therapeutic potential of PDGF-D inhibition, Col4a3-/- mice were treated with a PDGF-D neutralizing antibody. Surprisingly, PDGF-D antibody treatment had no effect on renal function, glomerulosclerosis, fibrosis, or other indices of kidney injury compared with control treatment with unspecific IgG. To characterize the role of PDGF-D in disease development, Col4a3-/- mice with a constitutive genetic deletion of Pdgfd were generated and analyzed. No difference in pathologic features or kidney function was observed in Col4a3-/-Pdgfd-/- mice compared with Col4a3-/-Pdgfd+/+ littermates, confirming the antibody treatment data. Mechanistically, lack of proteolytic PDGF-D activation in Col4a3-/- mice might explain the lack of effects in vivo. In conclusion, despite its established role in kidney fibrosis, PDGF-D, without further activation, does not mediate the development and progression of Alport syndrome in mice.

Detection of PatIent-Level distances from single cell genomics and pathomics data with Optimal Transport (PILOT).

Although clinical applications represent the next challenge in single-cell genomics and digital pathology, we still lack computational methods to analyze single-cell or pathomics data to find sample-level trajectories or clusters associated with diseases. This remains challenging as single-cell/pathomics data are multi-scale, i.e., a sample is represented by clusters of cells/structures, and samples cannot be easily compared with each other. Here we propose PatIent Level analysis with Optimal Transport (PILOT). PILOT uses optimal transport to compute the Wasserstein distance between two individual single-cell samples. This allows us to perform unsupervised analysis at the sample level and uncover trajectories or cellular clusters associated with disease progression. We evaluate PILOT and competing approaches in single-cell genomics or pathomics studies involving various human diseases with up to 600 samples/patients and millions of cells or tissue structures. Our results demonstrate that PILOT detects disease-associated samples from large and complex single-cell or pathomics data. Moreover, PILOT provides a statistical approach to find changes in cell populations, gene expression, and tissue structures related to the trajectories or clusters supporting interpretation of predictions.

Finerenone Added to RAS/SGLT2 Blockade for CKD in Alport Syndrome. Results of a Randomized Controlled Trial with Col4a3-/- Mice.

SIGNIFICANCE STATEMENT: We hypothesized that triple therapy with inhibitors of the renin-angiotensin system (RAS), sodium-glucose transporter (SGLT)-2, and the mineralocorticoid receptor (MR) would be superior to dual RAS/SGLT2 blockade in attenuating CKD progression in Col4a3 -deficient mice, a model of Alport syndrome. Late-onset ramipril monotherapy or dual ramipril/empagliflozin therapy attenuated CKD and prolonged overall survival by 2 weeks. Adding the nonsteroidal MR antagonist finerenone extended survival by 4 weeks. Pathomics and RNA sequencing revealed significant protective effects on the tubulointerstitium when adding finerenone to RAS/SGLT2 inhibition. Thus, triple RAS/SGLT2/MR blockade has synergistic effects and might attenuate CKD progression in patients with Alport syndrome and possibly other progressive chronic kidney disorders. BACKGROUND: Dual inhibition of the renin-angiotensin system (RAS) plus sodium-glucose transporter (SGLT)-2 or the mineralocorticoid receptor (MR) demonstrated additive renoprotective effects in large clinical trials. We hypothesized that triple therapy with RAS/SGLT2/MR inhibitors would be superior to dual RAS/SGLT2 blockade in attenuating CKD progression. METHODS: We performed a preclinical randomized controlled trial (PCTE0000266) in Col4a3 -deficient mice with established Alport nephropathy. Treatment was initiated late (age 6 weeks) in mice with elevated serum creatinine and albuminuria and with glomerulosclerosis, interstitial fibrosis, and tubular atrophy. We block-randomized 40 male and 40 female mice to either nil (vehicle) or late-onset food admixes of ramipril monotherapy (10 mg/kg), ramipril plus empagliflozin (30 mg/kg), or ramipril plus empagliflozin plus finerenone (10 mg/kg). Primary end point was mean survival. RESULTS: Mean survival was 63.7±10.0 days (vehicle), 77.3±5.3 days (ramipril), 80.3±11.0 days (dual), and 103.1±20.3 days (triple). Sex did not affect outcome. Histopathology, pathomics, and RNA sequencing revealed that finerenone mainly suppressed the residual interstitial inflammation and fibrosis despite dual RAS/SGLT2 inhibition. CONCLUSION: Experiments in mice suggest that triple RAS/SGLT2/MR blockade may substantially improve renal outcomes in Alport syndrome and possibly other progressive CKDs because of synergistic effects on the glomerular and tubulointerstitial compartments.

Next-Generation Morphometry for pathomics-data mining in histopathology.

Pathology diagnostics relies on the assessment of morphology by trained experts, which remains subjective and qualitative. Here we developed a framework for large-scale histomorphometry (FLASH) performing deep learning-based semantic segmentation and subsequent large-scale extraction of interpretable, quantitative, morphometric features in non-tumour kidney histology. We use two internal and three external, multi-centre cohorts to analyse over 1000 kidney biopsies and nephrectomies. By associating morphometric features with clinical parameters, we confirm previous concepts and reveal unexpected relations. We show that the extracted features are independent predictors of long-term clinical outcomes in IgA-nephropathy. We introduce single-structure morphometric analysis by applying techniques from single-cell transcriptomics, identifying distinct glomerular populations and morphometric phenotypes along a trajectory of disease progression. Our study provides a concept for Next-generation Morphometry (NGM), enabling comprehensive quantitative pathology data mining, i.e., pathomics.

Stain-Independent Deep Learning-Based Analysis of Digital Kidney Histopathology.

Convolutional neural network (CNN)-based image analysis applications in digital pathology (eg, tissue segmentation) require a large amount of annotated data and are mostly trained and applicable on a single stain. Here, a novel concept based on stain augmentation is proposed to develop stain-independent CNNs requiring only one annotated stain. In this benchmark study on stain independence in digital pathology, this approach is comprehensively compared with state-of-the-art techniques including image registration and stain translation, and several modifications thereof. A previously developed CNN for segmentation of periodic acid-Schiff-stained kidney histology was used and applied to various immunohistochemical stainings. Stain augmentation showed very high performance in all evaluated stains and outperformed all other techniques in all structures and stains. Without the need for additional annotations, it enabled segmentation on immunohistochemical stainings with performance nearly comparable to that of the annotated periodic acid-Schiff stain and could further uphold performance on several held-out stains not seen during training. Herein, examples of how this framework can be applied for compartment-specific quantification of immunohistochemical stains for inflammation and fibrosis in animal models and patient biopsy specimens are presented. The results show that stain augmentation is a highly effective approach to enable stain-independent applications of deep-learning segmentation algorithms. This opens new possibilities for broad implementation in digital pathology.

Improving unsupervised stain-to-stain translation using self-supervision and meta-learning.

Background: In digital pathology, many image analysis tasks are challenged by the need for large and time-consuming manual data annotations to cope with various sources of variability in the image domain. Unsupervised domain adaptation based on image-to-image translation is gaining importance in this field by addressing variabilities without the manual overhead. Here, we tackle the variation of different histological stains by unsupervised stain-to-stain translation to enable a stain-independent applicability of a deep learning segmentation model. Methods: We use CycleGANs for stain-to-stain translation in kidney histopathology, and propose two novel approaches to improve translational effectivity. First, we integrate a prior segmentation network into the CycleGAN for a self-supervised, application-oriented optimization of translation through semantic guidance, and second, we incorporate extra channels to the translation output to implicitly separate artificial meta-information otherwise encoded for tackling underdetermined reconstructions. Results: The latter showed partially superior performances to the unmodified CycleGAN, but the former performed best in all stains providing instance-level Dice scores ranging between 78% and 92% for most kidney structures, such as glomeruli, tubules, and veins. However, CycleGANs showed only limited performance in the translation of other structures, e.g. arteries. Our study also found somewhat lower performance for all structures in all stains when compared to segmentation in the original stain. Conclusions: Our study suggests that with current unsupervised technologies, it seems unlikely to produce "generally" applicable simulated stains.

Tackling stain variability using CycleGAN-based stain augmentation.

Background: Considerable inter- and intra-laboratory stain variability exists in pathology, representing a challenge in development and application of deep learning (DL) approaches. Since tackling all sources of stain variability with manual annotation is not feasible, we here investigated and compared unsupervised DL approaches to reduce the consequences of stain variability in kidney pathology. Methods: We aimed to improve the applicability of a pretrained DL segmentation model to 3 external multi-centric cohorts with large stain variability. In contrast to the traditional approach of training generative adversarial networks (GAN) for stain normalization, we here propose to tackle stain variability by data augmentation. We augment the training data of the pretrained model by the stain variability using CycleGANs and then retrain the model on the stain-augmented dataset. We compared the performance of i/ the unmodified pretrained segmentation model with ii/ CycleGAN-based stain normalization, iii/ a feature-preserving modification to ii/ for improved normalization, and iv/ the proposed stain-augmented model. Results: The proposed stain-augmented model showed highest mean segmentation accuracy in all external cohorts and maintained comparable performance on the training cohort. However, the increase in performance was only marginal compared to the pretrained model. CycleGAN-based stain normalization suffered from encoded imperceptible information into the normalizations that confused the pretrained model and thus resulted in slightly worse performance. Conclusions: Our findings suggest that stain variability can be tackled more effectively by augmenting data by it than by following the commonly used approach of normalizing the stain. However, the applicability of this approach providing only a rather slight performance increase has to be weighted against an additional carbon footprint.

Large-scale extraction of interpretable features provides new insights into kidney histopathology - A proof-of-concept study.

Whole slide images contain a magnitude of quantitative information that may not be fully explored in qualitative visual assessments. We propose: (1) a novel pipeline for extracting a comprehensive set of visual features, which are detectable by a pathologist, as well as sub-visual features, which are not discernible by human experts and (2) perform detailed analyses on renal images from mice with experimental unilateral ureteral obstruction. An important criterion for these features is that they are easy to interpret, as opposed to features obtained from neural networks. We extract and compare features from pathological and healthy control kidneys to learn how the compartments (glomerulus, Bowman's capsule, tubule, interstitium, artery, and arterial lumen) are affected by the pathology. We define feature selection methods to extract the most informative and discriminative features. We perform statistical analyses to understand the relation of the extracted features, both individually, and in combinations, with tissue morphology and pathology. Particularly for the presented case-study, we highlight features that are affected in each compartment. With this, prior biological knowledge, such as the increase in interstitial nuclei, is confirmed and presented in a quantitative way, alongside with novel findings, like color and intensity changes in glomeruli and Bowman's capsule. The proposed approach is therefore an important step towards quantitative, reproducible, and rater-independent analysis in histopathology.

Recommendations on compiling test datasets for evaluating artificial intelligence solutions in pathology.

Artificial intelligence (AI) solutions that automatically extract information from digital histology images have shown great promise for improving pathological diagnosis. Prior to routine use, it is important to evaluate their predictive performance and obtain regulatory approval. This assessment requires appropriate test datasets. However, compiling such datasets is challenging and specific recommendations are missing. A committee of various stakeholders, including commercial AI developers, pathologists, and researchers, discussed key aspects and conducted extensive literature reviews on test datasets in pathology. Here, we summarize the results and derive general recommendations on compiling test datasets. We address several questions: Which and how many images are needed? How to deal with low-prevalence subsets? How can potential bias be detected? How should datasets be reported? What are the regulatory requirements in different countries? The recommendations are intended to help AI developers demonstrate the utility of their products and to help pathologists and regulatory agencies verify reported performance measures. Further research is needed to formulate criteria for sufficiently representative test datasets so that AI solutions can operate with less user intervention and better support diagnostic workflows in the future.

Current kidney function parameters overestimate kidney tissue repair in reversible experimental kidney disease.

Although underlying mechanisms and the clinical course of kidney disease progression are well described, less is known about potential disease reversibility. Therefore, to analyze kidney recovery, we adapted a commonly used murine chronic kidney disease (CKD) model of 2,8- dihydroxyadenine (2,8-DHA) crystal-induced nephropathy to study disease recovery and efficacy of disease-modifying interventions. The recovery phase after CKD was characterized by improved kidney function after two weeks which remained stable thereafter. By contrast, even after eight weeks recovery, tubular injury and inflammation were only partially reduced, and fibrosis persisted. Deep-learning-based histologic analysis of 8,604 glomeruli and 596,614 tubular cross sections revealed numerous tubules had undergone either prominent dilation or complete atrophy, leading to atubular glomeruli and irreversible nephron loss. We confirmed these findings in a second CKD model, reversible unilateral ureteral obstruction, in which a rapid improvement of glomerular filtration rate during recovery also did not reflect the permanent histologic kidney injury. In 2,8-DHA nephropathy, increased drinking volume was highly effective in disease prevention. However, in therapeutic approaches, high fluid intake was only effective in moderate but not severe CKD and established tissue injury was again poorly reflective of kidney function parameters. The injury was particularly localized in the medulla, which is often not analyzed. Thus, recovery after crystal- or obstruction-induced CKD is characterized by ongoing tissue injury, fibrosis, and nephron loss, but not reflected by standard measures of kidney function. Hence, our data might aid in designing kidney recovery studies and suggest the need for biomarkers specifically monitoring intra-kidney tissue injury.

Immune cell infiltration pattern in non-small cell lung cancer PDX models is a model immanent feature and correlates with a distinct molecular and phenotypic make-up.

BACKGROUND: The field of cancer immunology is rapidly moving towards innovative therapeutic strategies, resulting in the need for robust and predictive preclinical platforms reflecting the immunological response to cancer. Well characterized preclinical models are essential for the development of predictive biomarkers in the oncology as well as the immune-oncology space. In the current study, gold standard preclinical models are being refined and combined with novel image analysis tools to meet those requirements. METHODS: A panel of 14 non-small cell lung cancer patient-derived xenograft models (NSCLC PDX) was propagated in humanized NOD/Shi-scid/IL-2Rnull mice. The models were comprehensively characterized for relevant phenotypic and molecular features, including flow cytometry, immunohistochemistry, histology, whole exome sequencing and cytokine secretion. RESULTS: Models reflecting hot (>5% tumor-infiltrating lymphocytes/TILs) as opposed to cold tumors (<5% TILs) significantly differed regarding their cytokine profiles, molecular genetic aberrations, stroma content, and programmed cell death ligand-1 status. Treatment experiments including anti cytotoxic T-lymphocyte-associated protein 4, anti-programmed cell death 1 or the combination thereof across all 14 models in the single mouse trial format showed distinctive tumor growth response and spatial immune cell patterns as monitored by computerized analysis of digitized whole-slide images. Image analysis provided for the first time qualitative evaluation of the extent to which PDX models retain the histological features from their original human donors. CONCLUSIONS: Deep phenotyping of PDX models in a humanized setting by combinations of computational pathology, immunohistochemistry, flow cytometry and proteomics enables the exhaustive analysis of innovative preclinical models and paves the way towards the development of translational biomarkers for immuno-oncology drugs.

Deep Learning-Based Segmentation and Quantification in Experimental Kidney Histopathology.

BACKGROUND: Nephropathologic analyses provide important outcomes-related data in experiments with the animal models that are essential for understanding kidney disease pathophysiology. Precision medicine increases the demand for quantitative, unbiased, reproducible, and efficient histopathologic analyses, which will require novel high-throughput tools. A deep learning technique, the convolutional neural network, is increasingly applied in pathology because of its high performance in tasks like histology segmentation. METHODS: We investigated use of a convolutional neural network architecture for accurate segmentation of periodic acid-Schiff-stained kidney tissue from healthy mice and five murine disease models and from other species used in preclinical research. We trained the convolutional neural network to segment six major renal structures: glomerular tuft, glomerulus including Bowman's capsule, tubules, arteries, arterial lumina, and veins. To achieve high accuracy, we performed a large number of expert-based annotations, 72,722 in total. RESULTS: Multiclass segmentation performance was very high in all disease models. The convolutional neural network allowed high-throughput and large-scale, quantitative and comparative analyses of various models. In disease models, computational feature extraction revealed interstitial expansion, tubular dilation and atrophy, and glomerular size variability. Validation showed a high correlation of findings with current standard morphometric analysis. The convolutional neural network also showed high performance in other species used in research-including rats, pigs, bears, and marmosets-as well as in humans, providing a translational bridge between preclinical and clinical studies. CONCLUSIONS: We developed a deep learning algorithm for accurate multiclass segmentation of digital whole-slide images of periodic acid-Schiff-stained kidneys from various species and renal disease models. This enables reproducible quantitative histopathologic analyses in preclinical models that also might be applicable to clinical studies.

Multimodal 3D medical image registration guided by shape encoder-decoder networks.

PURPOSE: Nonlinear multimodal image registration, for example, the fusion of computed tomography (CT) and magnetic resonance imaging (MRI), fundamentally depends on a definition of image similarity. Previous methods that derived modality-invariant representations focused on either global statistical grayscale relations or local structural similarity, both of which are prone to local optima. In contrast to most learning-based methods that rely on strong supervision of aligned multimodal image pairs, we aim to overcome this limitation for further practical use cases. METHODS: We propose a new concept that exploits anatomical shape information and requires only segmentation labels for both modalities individually. First, a shape-constrained encoder-decoder segmentation network without skip connections is jointly trained on labeled CT and MRI inputs. Second, an iterative energy-based minimization scheme is introduced that relies on the capability of the network to generate intermediate nonlinear shape representations. This further eases the multimodal alignment in the case of large deformations. RESULTS: Our novel approach robustly and accurately aligns 3D scans from the multimodal whole-heart segmentation dataset, outperforming classical unsupervised frameworks. Since both parts of our method rely on (stochastic) gradient optimization, it can be easily integrated in deep learning frameworks and executed on GPUs. CONCLUSIONS: We present an integrated approach for weakly supervised multimodal image registration. Achieving promising results due to the exploration of intermediate shape features as registration guidance encourages further research in this direction.

OBELISK-Net: Fewer layers to solve 3D multi-organ segmentation with sparse deformable convolutions.

Deep networks have set the state-of-the-art in most image analysis tasks by replacing handcrafted features with learned convolution filters within end-to-end trainable architectures. Still, the specifications of a convolutional network are subject to much manual design - the shape and size of the receptive field for convolutional operations is a very sensitive part that has to be tuned for different image analysis applications. 3D fully-convolutional multi-scale architectures with skip-connection that excel at semantic segmentation and landmark localisation have huge memory requirements and rely on large annotated datasets - an important limitation for wider adaptation in medical image analysis. We propose a novel and effective method based on trainable 3D convolution kernels that learns both filter coefficients and spatial filter offsets in a continuous space based on the principle of differentiable image interpolation first introduced for spatial transformer network. A deep network that incorporates this one binary extremely large and inflecting sparse kernel (OBELISK) filter requires fewer trainable parameters and less memory while achieving high quality results compared to fully-convolutional U-Net architectures on two challenging 3D CT multi-organ segmentation tasks. Extensive validation experiments indicate that the performance of sparse deformable convolutions is due to their ability to capture large spatial context with few expressive filter parameters and that network depth is not always necessary to learn complex shape and appearance features. A combination with conventional CNNs further improves the delineation of small organs with large shape variations and the fast inference time using flexible image sampling may offer new potential use cases for deep networks in computer-assisted, image-guided interventions.

Learning to Predict Ischemic Stroke Growth on Acute CT Perfusion Data by Interpolating Low-Dimensional Shape Representations.

Cerebrovascular diseases, in particular ischemic stroke, are one of the leading global causes of death in developed countries. Perfusion CT and/or MRI are ideal imaging modalities for characterizing affected ischemic tissue in the hyper-acute phase. If infarct growth over time could be predicted accurately from functional acute imaging protocols together with advanced machine-learning based image analysis, the expected benefits of treatment options could be better weighted against potential risks. The quality of the outcome prediction by convolutional neural networks (CNNs) is so far limited, which indicates that even highly complex deep learning algorithms are not fully capable of directly learning physiological principles of tissue salvation through weak supervision due to a lack of data (e.g., follow-up segmentation). In this work, we address these current shortcomings by explicitly taking into account clinical expert knowledge in the form of segmentations of the core and its surrounding penumbra in acute CT perfusion images (CTP), that are trained to be represented in a low-dimensional non-linear shape space. Employing a multi-scale CNN (U-Net) together with a convolutional auto-encoder, we predict lesion tissue probabilities for new patients. The predictions are physiologically constrained to a shape embedding that encodes a continuous progression between the core and penumbra extents. The comparison to a simple interpolation in the original voxel space and an unconstrained CNN shows that the use of such a shape space can be advantageous to predict time-dependent growth of stroke lesions on acute perfusion data, yielding a Dice score overlap of 0.46 for predictions from expert segmentations of core and penumbra. Our interpolation method models monotone infarct growth robustly on a linear time scale to automatically predict clinically plausible tissue outcomes that may serve as a basis for more clinical measures such as the expected lesion volume increase and can support the decision making on treatment options and triage.