INTRODUCTION: The histopathological classification for antineutrophil cytoplasmic autoantibody (ANCA)-associated glomerulonephritis (ANCA-GN) is a well-established tool to reflect the variety of patterns and severity of lesions that can occur in kidney biopsies. It was demonstrated previously that deep learning (DL) approaches can aid in identifying histopathological classes of kidney diseases; for example, of diabetic kidney disease. These models can potentially be used as decision support tools for kidney pathologists. Although they reach high prediction accuracies, their "black box" structure makes them nontransparent. Explainable (X) artificial intelligence (AI) techniques can be used to make the AI model decisions accessible for human experts. We have developed a DL-based model, which detects and classifies the glomerular lesions according to the Berden classification. METHODS: Kidney biopsy slides of 80 patients with ANCA-GN from 3 European centers, who underwent a diagnostic kidney biopsy between 1991 and 2011, were included. We also investigated the explainability of our model using Gradient-weighted Class Activation Mapping (Grad-CAM) heatmaps. These maps were analyzed by pathologists to compare the decision-making criteria of humans and the DL model and assess the impact of different training settings. RESULTS: The DL model shows a prediction accuracy of 93% for classifying lesions. The heatmaps from our trained DL models showed that the most predictive areas in the image correlated well with the areas deemed to be important by the pathologist. CONCLUSION: We present the first DL-based computational pipeline for classifying ANCA-GN kidney biopsies as per the Berden classification. XAI techniques helped us to make the decision-making criteria of the DL accessible for renal pathologists, potentially improving clinical decision-making.

• Publication type
• Journal Article MeSH

Pituitary adenomas (PA) represent the most common type of sellar neoplasm. Extracting relevant information from radiological images is essential for decision support in addressing various objectives related to PA. Given the critical need for an accurate assessment of the natural progression of PA, computer vision (CV) and artificial intelligence (AI) play a pivotal role in automatically extracting features from radiological images. The field of "Radiomics" involves the extraction of high-dimensional features, often referred to as "Radiomic features," from digital radiological images. This survey offers an analysis of the current state of research in PA radiomics. Our work comprises a systematic review of 34 publications focused on PA radiomics and other automated information mining pertaining to PA through the analysis of radiological data using computer vision methods. We begin with a theoretical exploration essential for understanding the theoretical background of radionmics, encompassing traditional approaches from computer vision and machine learning, as well as the latest methodologies in deep radiomics utilizing deep learning (DL). Thirty-four research works under examination are comprehensively compared and evaluated. The overall results achieved in the analyzed papers are high, e.g., the best accuracy is up to 96% and the best achieved AUC is up to 0.99, which establishes optimism for the successful use of radiomic features. Methods based on deep learning seem to be the most promising for the future. In relation to this perspective DL methods, several challenges are remarkable: It is important to create high-quality and sufficiently extensive datasets necessary for training deep neural networks. Interpretability of deep radiomics is also a big open challenge. It is necessary to develop and verify methods that will explain to us how deep radiomic features reflect various physics-explainable aspects.

• MeSH
• Adenoma * diagnostic imaging   MeSH
• Deep Learning MeSH
• Humans MeSH
• Pituitary Neoplasms * diagnostic imaging   MeSH
• Image Processing, Computer-Assisted methods   MeSH
• Radiomics MeSH
• Machine Learning MeSH
• Artificial Intelligence MeSH
• Check Tag
• Humans MeSH
• Publication type
• Journal Article MeSH
• Review MeSH
• Systematic Review MeSH

Microglial cells mediate diverse homeostatic, inflammatory, and immune processes during normal development and in response to cytotoxic challenges. During these functional activities, microglial cells undergo distinct numerical and morphological changes in different tissue volumes in both rodent and human brains. However, it remains unclear how these cytostructural changes in microglia correlate with region-specific neurochemical functions. To better understand these relationships, neuroscientists need accurate, reproducible, and efficient methods for quantifying microglial cell number and morphologies in histological sections. To address this deficit, we developed a novel deep learning (DL)-based classification, stereology approach that links the appearance of Iba1 immunostained microglial cells at low magnification (20×) with the total number of cells in the same brain region based on unbiased stereology counts as ground truth. Once DL models are trained, total microglial cell numbers in specific regions of interest can be estimated and treatment groups predicted in a high-throughput manner (<1 min) using only low-power images from test cases, without the need for time and labor-intensive stereology counts or morphology ratings in test cases. Results for this DL-based automatic stereology approach on two datasets (total 39 mouse brains) showed >90% accuracy, 100% percent repeatability (Test-Retest) and 60× greater efficiency than manual stereology (<1 min vs. ∼ 60 min) using the same tissue sections. Ongoing and future work includes use of this DL-based approach to establish clear neurodegeneration profiles in age-related human neurological diseases and related animal models.

• MeSH
• Deep Learning * MeSH
• Humans MeSH
• Microglia * MeSH
• Brain pathology   MeSH
• Mice MeSH
• Cell Count methods   MeSH
• Animals MeSH
• Check Tag
• Humans MeSH
• Mice MeSH
• Animals MeSH
• Publication type
• Journal Article MeSH

Drowning diagnosis is a complicated process in the autopsy, even with the assistance of autopsy imaging and the on-site information from where the body was found. Previous studies have developed well-performed deep learning (DL) models for drowning diagnosis. However, the validity of the DL models was not assessed, raising doubts about whether the learned features accurately represented the medical findings observed by human experts. In this paper, we assessed the medical validity of DL models that had achieved high classification performance for drowning diagnosis. This retrospective study included autopsy cases aged 8-91 years who underwent postmortem computed tomography between 2012 and 2021 (153 drowning and 160 non-drowning cases). We first trained three deep learning models from a previous work and generated saliency maps that highlight important features in the input. To assess the validity of models, pixel-level annotations were created by four radiological technologists and further quantitatively compared with the saliency maps. All the three models demonstrated high classification performance with areas under the receiver operating characteristic curves of 0.94, 0.97, and 0.98, respectively. On the other hand, the assessment results revealed unexpected inconsistency between annotations and models' saliency maps. In fact, each model had, respectively, around 30%, 40%, and 80% of irrelevant areas in the saliency maps, suggesting the predictions of the DL models might be unreliable. The result alerts us in the careful assessment of DL tools, even those with high classification performance.

• MeSH
• Deep Learning * MeSH
• Child MeSH
• Adult MeSH
• Middle Aged MeSH
• Humans MeSH
• Adolescent MeSH
• Young Adult MeSH
• Autopsy * methods   MeSH
• Tomography, X-Ray Computed * methods   MeSH
• Postmortem Imaging MeSH
• Reproducibility of Results MeSH
• Retrospective Studies MeSH
• ROC Curve MeSH
• Aged, 80 and over MeSH
• Aged MeSH
• Drowning * diagnosis   MeSH
• Check Tag
• Child MeSH
• Adult MeSH
• Middle Aged MeSH
• Humans MeSH
• Adolescent MeSH
• Young Adult MeSH
• Male MeSH
• Aged, 80 and over MeSH
• Aged MeSH
• Female MeSH
• Publication type
• Journal Article MeSH

PURPOSE: The aims of this work are (1) to explore deep learning (DL) architectures, spectroscopic input types, and learning designs toward optimal quantification in MR spectroscopy of simulated pathological spectra; and (2) to demonstrate accuracy and precision of DL predictions in view of inherent bias toward the training distribution. METHODS: Simulated 1D spectra and 2D spectrograms that mimic an extensive range of pathological in vivo conditions are used to train and test 24 different DL architectures. Active learning through altered training and testing data distributions is probed to optimize quantification performance. Ensembles of networks are explored to improve DL robustness and reduce the variance of estimates. A set of scores compares performances of DL predictions and traditional model fitting (MF). RESULTS: Ensembles of heterogeneous networks that combine 1D frequency-domain and 2D time-frequency domain spectrograms as input perform best. Dataset augmentation with active learning can improve performance, but gains are limited. MF is more accurate, although DL appears to be more precise at low SNR. However, this overall improved precision originates from a strong bias for cases with high uncertainty toward the dataset the network has been trained with, tending toward its average value. CONCLUSION: MF mostly performs better compared to the faster DL approach. Potential intrinsic biases on training sets are dangerous in a clinical context that requires the algorithm to be unbiased to outliers (i.e., pathological data). Active learning and ensemble of networks are good strategies to improve prediction performances. However, data quality (sufficient SNR) has proven as a bottleneck for adequate unbiased performance-like in the case of MF.

• MeSH
• Algorithms MeSH
• Deep Learning * MeSH
• Bias MeSH
• Publication type
• Journal Article MeSH
• Research Support, Non-U.S. Gov't MeSH

PURPOSE: A supervised deep learning (DL) approach for frequency and phase correction (FPC) of MRS data recently showed encouraging results, but obtaining transients with labels for supervised learning is challenging. This work investigates the feasibility and efficiency of unsupervised deep learning-based FPC. METHODS: Two novel deep learning-based FPC methods (deep learning-based Cr referencing and deep learning-based spectral registration), which use a priori physics domain knowledge, are presented. The proposed networks were trained, validated, and evaluated using simulated, phantom, and publicly accessible in vivo MEGA-edited MRS data. The performance of our proposed FPC methods was compared with other generally used FPC methods, in terms of precision and time efficiency. A new measure was proposed in this study to evaluate the FPC method performance. The ability of each of our methods to carry out FPC at varying SNR levels was evaluated. A Monte Carlo study was carried out to investigate the performance of our proposed methods. RESULTS: The validation using low-SNR manipulated simulated data demonstrated that the proposed methods could perform FPC comparably with other methods. The evaluation showed that the deep learning-based spectral registration over a limited frequency range method achieved the highest performance in phantom data. The applicability of the proposed method for FPC of GABA-edited in vivo MRS data was demonstrated. Our proposed networks have the potential to reduce computation time significantly. CONCLUSIONS: The proposed physics-informed deep neural networks trained in an unsupervised manner with complex data can offer efficient FPC of large MRS data in a shorter time.

• MeSH
• Deep Learning * MeSH
• Phantoms, Imaging MeSH
• Monte Carlo Method MeSH
• Neural Networks, Computer MeSH
• Image Processing, Computer-Assisted methods   MeSH
• Publication type
• Journal Article MeSH

Strojové učení zaznamenalo v posledních letech pozoruhodný pokrok od téměř nepoužitelného rozpoznávání řeči a obrazu k nadlidské přesnosti. Od programů, které nedokázaly porazit jen trochu zkušenějšího hráče go, jsme dospěli k přemožiteli mistra světa. Za pokrokem ve vývoji učících se programů stojí tzv. hluboké učení - deep learning.; Strojové učení zaznamenalo v posledních letech pozoruhodný pokrok od téměř nepoužitelného rozpoznávání řeči a obrazu k nadlidské přesnosti. Od programů, které nedokázaly porazit jen trochu zkušenějšího hráče go, jsme dospěli k přemožiteli mistra světa. Za pokrokem ve vývoji učících se programů stojí tzv. hluboké učení – deep learning.

BACKGROUND: The presence of diffusion-weighted imaging (DWI) and fluid-attenuated inversion recovery (FLAIR) mismatch was used to determine eligibility for intravenous thrombolysis in clinical trials. However, due to the restricted availability of MRI and the ambiguity of image assessment, it is not widely implemented in clinical practice. METHODS: A total of 222 acute ischemic stroke patients underwent non-contrast computed tomography (NCCT), DWI, and FLAIR within 1 h of one another. Human experts manually segmented ischemic lesions on DWI and FLAIR images and independently graded the presence of DWI-FLAIR mismatch. Deep learning (DL) models based on the nnU-net architecture were developed to predict ischemic lesions visible on DWI and FLAIR images using NCCT images. Inexperienced neurologists evaluated the DWI-FLAIR mismatch on NCCT images without and with the model's results. RESULTS: The mean age of included subjects was 71.8 ± 12.8 years, 123 (55%) were male, and the baseline NIHSS score was a median of 11 [IQR, 6-18]. All images were taken in the following order: NCCT - DWI - FLAIR, starting after a median of 139 [81-326] min after the time of the last known well. Intravenous thrombolysis was administered in 120 patients (54%) after NCCT. The DL model's prediction on NCCT images revealed a Dice coefficient and volume correlation of 39.1% and 0.76 for DWI lesions and 18.9% and 0.61 for FLAIR lesions. In the subgroup with 15 mL or greater lesion volume, the evaluation of DWI-FLAIR mismatch from NCCT by inexperienced neurologists improved in accuracy (from 0.537 to 0.610) and AUC-ROC (from 0.493 to 0.613). CONCLUSION: The DWI-FLAIR mismatch may be reckoned using NCCT images through advanced artificial intelligence techniques.

• Publication type
• Journal Article MeSH

In this article, we introduce a new approach to human movement by defining the movement as a static super object represented by a single two-dimensional image. The described method is applicable in remote healthcare applications, such as physiotherapeutic exercises. It allows researchers to label and describe the entire exercise as a standalone object, isolated from the reference video. This approach allows us to perform various tasks, including detecting similar movements in a video, measuring and comparing movements, generating new similar movements, and defining choreography by controlling specific parameters in the human body skeleton. As a result of the presented approach, we can eliminate the need to label images manually, disregard the problem of finding the start and the end of an exercise, overcome synchronization issues between movements, and perform any deep learning network-based operation that processes super objects in images in general. As part of this article, we will demonstrate two application use cases: one illustrates how to verify and score a fitness exercise. In contrast, the other illustrates how to generate similar movements in the human skeleton space by addressing the challenge of supplying sufficient training data for deep learning applications (DL). A variational auto encoder (VAE) simulator and an EfficientNet-B7 classifier architecture embedded within a Siamese twin neural network are presented in this paper in order to demonstrate the two use cases. These use cases demonstrate the versatility of our innovative concept in measuring, categorizing, inferring human behavior, and generating gestures for other researchers.

• Publication type
• Journal Article MeSH

Advanced mathematical and deep learning (DL) algorithms have recently played a crucial role in diagnosing medical parameters and diseases. One of these areas that need to be more focused on is dentistry. This is why creating digital twins of dental issues in the metaverse is a practical and effective technique to benefit from the immersive characteristics of this technology and adapt the real world of dentistry to the virtual world. These technologies can create virtual facilities and environments for patients, physicians, and researchers to access a variety of medical services. Experiencing an immersive interaction between doctors and patients can be another considerable advantage of these technologies, which can dramatically improve the efficiency of the healthcare system. In addition, offering these amenities through a blockchain system enhances reliability, safety, openness, and the ability to trace data exchange. It also brings about cost savings through improved efficiencies. In this paper, a digital twin of cervical vertebral maturation (CVM), which is a critical factor in a wide range of dental surgery, within a blockchain-based metaverse platform is designed and implemented. A DL method has been used to create an automated diagnosis process for the upcoming CVM images in the proposed platform. This method includes MobileNetV2, a mobile architecture that improves the performance of mobile models in multiple tasks and benchmarks. The proposed technique of digital twinning is simple, fast, and suitable for physicians and medical specialists, as well as for adapting to the Internet of Medical Things (IoMT) due to its low latency and computing costs. One of the important contributions of the current study is to use of DL-based computer vision as a real-time measurement method so that the proposed digital twin does not require additional sensors. Furthermore, a comprehensive conceptual framework for creating digital twins of CVM based on MobileNetV2 within a blockchain ecosystem has been designed and implemented, showing the applicability and suitability of the introduced approach. The high performance of the proposed model on a collected small dataset demonstrates that low-cost deep learning can be used for diagnosis, anomaly detection, better design, and many more applications of the upcoming digital representations. In addition, this study shows how digital twins can be performed and developed for dental issues with the lowest hardware infrastructures, reducing the costs of diagnosis and treatment for patients.

• Publication type
• Journal Article MeSH