A method for utilizing automated machine learning for histopathological classification of testis based on Johnsen scores

Predicting Male Infertility Using Artificial Neural Networks: A Review of the Literature

Male infertility is a relevant public health problem, but there is no systematic review of the different machine learning (ML) models and their accuracy so far. The present review aims to comprehensively investigate the use of ML algorithms in predicting male infertility, thus reporting the accuracy of the used models in the prediction of male infertility as a primary outcome. Particular attention will be paid to the use of artificial neural networks (ANNs). A comprehensive literature search was conducted in PubMed, Scopus, and Science Direct between 15 July and 23 October 2023, conducted under the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. We performed a quality assessment of the included studies using the recommended tools suggested for the type of study design adopted. We also made a screening of the Risk of Bias (RoB) associated with the included studies. Thus, 43 relevant publications were included in this review, for a total of 40 different ML models detected. The studies included reported a good quality, even if RoB was not always good for all the types of studies. The included studies reported a median accuracy of 88% in predicting male infertility using ML models. We found only seven studies using ANN models for male infertility prediction, reporting a median accuracy of 84%.

Large language models streamline automated machine learning for clinical studies

A knowledge gap persists between machine learning (ML) developers (e.g., data scientists) and practitioners (e.g., clinicians), hampering the full utilization of ML for clinical data analysis. We investigated the potential of the ChatGPT Advanced Data Analysis (ADA), an extension of GPT-4, to bridge this gap and perform ML analyses efficiently. Real-world clinical datasets and study details from large trials across various medical specialties were presented to ChatGPT ADA without specific guidance. ChatGPT ADA autonomously developed state-of-the-art ML models based on the original study's training data to predict clinical outcomes such as cancer development, cancer progression, disease complications, or biomarkers such as pathogenic gene sequences. Following the re-implementation and optimization of the published models, the head-to-head comparison of the ChatGPT ADA-crafted ML models and their respective manually crafted counterparts revealed no significant differences in traditional performance metrics (p ≥ 0.072). Strikingly, the ChatGPT ADA-crafted ML models often outperformed their counterparts. In conclusion, ChatGPT ADA offers a promising avenue to democratize ML in medicine by simplifying complex data analyses, yet should enhance, not replace, specialized training and resources, to promote broader applications in medical research and practice.

Application of automated machine learning for histological evaluation of feline endoscopic samples

Differentiating intestinal T-cell lymphoma from chronic enteropathy (CE) in endoscopic samples is often challenging. In the present study, automated machine learning systems were developed to distinguish between the two diseases, predict clonality, and detect prognostic factors of intestinal lymphoma in cats. Four models were created for four experimental conditions: experiment 1 to distinguish between intestinal T-cell lymphoma and CE; experiment 2 to distinguish large cell lymphoma, small cell lymphoma, and CE; experiment 3 to distinguish granzyme B+ lymphoma, granzyme B- lymphoma, and CE; and experiment 4 to distinguish between T-cell receptor (TCR) clonal population and TCR polyclonal population. After each experiment, a pathologist reviewed the test images and scored for lymphocytic infiltration, epitheliotropism, and epithelial injury. The models of experiments 1-4 achieved area under the receiver operating characteristic curve scores of 0.943 (precision, 87.59%; recall, 87.59%), 0.962 (precision, 86.30%; recall, 86.30%), 0.904 (precision, 82.86%; recall, 80%), and 0.904 (precision, 81.25%; recall, 81.25%), respectively. The images predicted as intestinal T-cell lymphoma showed significant infiltration of lymphocytes and epitheliotropism than CE. These models can provide evaluation tools to assist pathologists with differentiating between intestinal T-cell lymphoma and CE.

Rapid azoospermia classification by stimulated Raman scattering and second harmonic generation microscopy

Disease diagnosis and classification pose significant challenges due to the limited capabilities of traditional methods to obtain molecular information with spatial distribution. Optical imaging techniques, utilizing (auto)fluorescence and nonlinear optical signals, introduce new dimensions for biomarkers exploration that can improve diagnosis and classification. Nevertheless, these signals often cover only a limited number of species, impeding a comprehensive assessment of the tissue microenvironment, which is crucial for effective disease diagnosis and therapy. To address this challenge, we developed a multimodal platform, termed stimulated Raman scattering and second harmonic generation microscopy (SRASH), capable of simultaneously providing both chemical bonds and structural information of tissues. Applying SRASH imaging to azoospermia patient samples, we successfully identified lipids, protein, and collagen contrasts, unveiling molecular and structural signatures for non-obstructive azoospermia. This achievement is facilitated by LiteBlendNet-Dx (LBNet-Dx), our diagnostic algorithm, which achieved an outstanding 100% sample-level accuracy in classifying azoospermia, surpassing conventional imaging modalities. As a label-free technique, SRASH imaging eliminates the requirement for sample pre-treatment, demonstrating great potential for clinical translation and enabling molecular imaging-based diagnosis and therapy.

State-of-the-art and future perspectives in infertility diagnosis: Conventional versus nanotechnology-based assays

According to the latest World Health Organization statistics, around 50 to 80 million people worldwide suffer from infertility, amongst which male factors are responsible for around 20 to 30 % of all infertility cases while 50 % were attributed to the female ones. As it is becoming a recurrent health problem worldwide, clinicians require more accurate methods for the improvement of both diagnosis and treatment schemes. By emphasizing the potential use of innovative methods for the rapid identification of the infertility causes, this review presents the news from this dynamic domain and highlights the benefits brought by emerging research fields. A systematic description of the standard techniques used in clinical protocols for diagnosing infertility in both genders is firstly provided, followed by the presentation of more accurate and comprehensive nanotechnology-related analysis methods such as nanoscopic-resolution imaging, biosensing approaches and assays that employ nanomaterials in their design. Consequently, the implementation of nanotechnology related tools in clinical practice, as recently demonstrated in the selection of spermatozoa, the detection of key proteins in the fertilization process or the testing of DNA integrity or the evaluation of oocyte quality, might confer excellent advantages both for improving the assessment of infertility, and for the success of the fertilization process.

The Histological Detection of Ulcerative Colitis Using a No-Code Artificial Intelligence Model

Ulcerative colitis (UC) is an intractable disease that affects young adults. Histological findings are essential for its diagnosis; however, the number of diagnostic pathologists is limited. Herein, we used a no-code artificial intelligence (AI) platform "Teachable Machine" to train a model that could distinguish between histological images of UC, non-UC coloproctitis, adenocarcinoma, and control. A total of 5100 histological images for training and 900 histological images for testing were prepared by pathologists. Our model showed accuracies of 0.99, 1.00, 0.99, and 0.99, for UC, non-UC coloproctitis, adenocarcinoma, and control, respectively. This is the first report in which a no-code easy AI platform has been able to comprehensively recognize the distinctive histologic patterns of UC.

Analysis of functional connectivity using machine learning and deep learning in different data modalities from individuals with schizophrenia

Objective. Schizophrenia(SCZ) is a severe mental disorder associated with persistent or recurrent psychosis, hallucinations, delusions, and thought disorders that affect approximately 26 million people worldwide, according to the World Health Organization. Several studies encompass machine learning (ML) and deep learning algorithms to automate the diagnosis of this mental disorder. Others study SCZ brain networks to get new insights into the dynamics of information processing in individuals suffering from the condition. In this paper, we offer a rigorous approach with ML and deep learning techniques for evaluating connectivity matrices and measures of complex networks to establish an automated diagnosis and comprehend the topology and dynamics of brain networks in SCZ individuals.Approach.For this purpose, we employed an functional magnetic resonance imaging (fMRI) and electroencephalogram (EEG) dataset. In addition, we combined EEG measures, i.e. Hjorth mobility and complexity, with complex network measurements to be analyzed in our model for the first time in the literature.Main results.When comparing the SCZ group to the control group, we found a high positive correlation between the left superior parietal lobe and the left motor cortex and a positive correlation between the left dorsal posterior cingulate cortex and the left primary motor. Regarding complex network measures, the diameter, which corresponds to the longest shortest path length in a network, may be regarded as a biomarker because it is the most crucial measure in different data modalities. Furthermore, the SCZ brain networks exhibit less segregation and a lower distribution of information. As a result, EEG measures outperformed complex networks in capturing the brain alterations associated with SCZ.Significance. Our model achieved an area under receiver operating characteristic curve (AUC) of 100% and an accuracy of 98.5% for the fMRI, an AUC of 95%, and an accuracy of 95.4% for the EEG data set. These are excellent classification results. Furthermore, we investigated the impact of specific brain connections and network measures on these results, which helped us better describe changes in the diseased brain.

Male infertility

Clinical infertility is the inability of a couple to conceive after 12 months of trying. Male factors are estimated to contribute to 30-50% of cases of infertility. Infertility or reduced fertility can result from testicular dysfunction, endocrinopathies, lifestyle factors (such as tobacco and obesity), congenital anatomical factors, gonadotoxic exposures and ageing, among others. The evaluation of male infertility includes detailed history taking, focused physical examination and selective laboratory testing, including semen analysis. Treatments include lifestyle optimization, empirical or targeted medical therapy as well as surgical therapies that lead to measurable improvement in fertility. Although male infertility is recognized as a disease with effects on quality of life for both members of the infertile couple, fewer data exist on specific quantification and impact compared with other health-related conditions.

Diagnosis of autism spectrum disorder based on functional brain networks and machine learning

Autism is a multifaceted neurodevelopmental condition whose accurate diagnosis may be challenging because the associated symptoms and severity vary considerably. The wrong diagnosis can affect families and the educational system, raising the risk of depression, eating disorders, and self-harm. Recently, many works have proposed new methods for the diagnosis of autism based on machine learning and brain data. However, these works focus on only one pairwise statistical metric, ignoring the brain network organization. In this paper, we propose a method for the automatic diagnosis of autism based on functional brain imaging data recorded from 500 subjects, where 242 present autism spectrum disorder considering the regions of interest throughout Bootstrap Analysis of Stable Cluster map. Our method can distinguish the control group from autism spectrum disorder patients with high accuracy. Indeed the best performance provides an AUC near 1.0, which is higher than that found in the literature. We verify that the left ventral posterior cingulate cortex region is less connected to an area in the cerebellum of patients with this neurodevelopment disorder, which agrees with previous studies. The functional brain networks of autism spectrum disorder patients show more segregation, less distribution of information across the network, and less connectivity compared to the control cases. Our workflow provides medical interpretability and can be used on other fMRI and EEG data, including small data sets.

Detection of spermatogonial stem/progenitor cells in prepubertal mouse testis with deep learning

PURPOSE

Rapid and easy detection of spermatogonial stem/progenitor cells (SSPCs) is crucial for clinicians dealing with male infertility caused by prepubertal testicular damage. Deep learning (DL) methods may offer visual tools for tracking SSPCs on testicular strips of prepubertal animal models. The purpose of this study is to detect and count the seminiferous tubules and SSPCs in newborn mouse testis sections using a DL method.

METHODS

Testicular sections of the C57BL/6-type newborn mice were obtained and enumerated. Odd-numbered sections were stained with hematoxylin and eosin (H&E), and even-numbered sections were immune labeled (IL) with SSPC specific marker, SALL4. Seminiferous tubule and SSPC datasets were created using odd-numbered sections. SALL4-labeled sections were used as positive control. The YOLO object detection model based on DL was used to detect seminiferous tubules and stem cells.

RESULTS

Test scores of the DL model in seminiferous tubules were obtained as 0.98 mAP, 0.93 precision, 0.96 recall, and 0.94 f1-score. The SSPC test scores were obtained as 0.88 mAP, 0.80 precision, 0.93 recall, and 0.82 f1-score.

CONCLUSION

Seminiferous tubules and SSPCs on prepubertal testicles were detected with a high sensitivity by preventing human-induced errors. Thus, the first step was taken for a system that automates the detection and counting process of these cells in the infertility clinic.

Cadmium-induced impairment of spermatozoa development by reducing exosomal-MVBs secretion: a novel pathway

Cadmium is a heavy environmental pollutant that presents a high risk to male-fertility and targets the different cellular and steroidogenic supporting germ cells networks during spermatogenesis. However, the mechanism accounting for its toxicity in multivesicular bodies (MVBs) biogenesis, and exosomal secretion associated with spermatozoa remains obscure. In the current study, the light and electron microscopy revealed that, the Sertoli cells perform a dynamic role with secretion of well-developed early endosomes (Ee) and MVBs pathway associated with spermatozoa during spermatogenesis. In addition, some apical blebs containing nano-scale exosomes located on the cell surface and after fragmentation nano-scale exosomes were directly linked with spermatozoa in the luminal compartment of seminiferous tubules, indicating normal spermatogenesis. Controversially, the cadmium treated group showed limited and deformed spermatozoa with damaging acromion process and mid-peace, and the cytoplasmic vacuolization of spermatids. After cadmium treatment, there is very limited biogenesis of MVBs inside the cytoplasm of Sertoli cells, and no obvious secretions of nano-scale exosomes interacted with spermatozoa. Interestingly, the cadmium treated group demonstrated relatively higher formation of autophagosomes and autolysosome, and the autophagosomes were enveloped by MVBs that later formed the amphisome which degraded by lysosomes, indicating the hypo-spermatogenesis. Moreover, cadmium declined the exosomal protein cluster of differentiation (CD63) and increased the autophagy-related proteins microtubule-associated light chain (LC3), sequestosome 1 (P62) and lysosomal-associated membrane protein 2 (LAMP2) expression level were confirmed by Western blotting. These results provide rich information regarding how cadmium is capable of triggering impaired spermatozoa development during spermatogenesis by reduction of MVBs pathway through high activation of autophagic pathway. This study explores the toxicant effect of cadmium on nano-scale exosomes secretion interacting with spermatozoa.

Code-free machine learning for classification of central nervous system histopathology images

Machine learning (ML), an application of artificial intelligence, is currently transforming the analysis of biomedical data and specifically of biomedical images including histopathology. The promises of this technology contrast, however, with its currently limited application in routine clinical practice. This discrepancy is in part due to the extent of informatics expertise typically required for implementation of ML. Therefore, we assessed the suitability of 2 publicly accessible code-free ML platforms (Microsoft Custom Vision and Google AutoML), for classification of histopathological images of diagnostic central nervous system tissue samples. When trained with typically 100 to more than 1000 images, both systems were able to perform nontrivial classifications (glioma vs brain metastasis; astrocytoma vs astrocytosis, prediction of 1p/19q co-deletion in IDH-mutant tumors) based on hematoxylin and eosin-stained images with high accuracy (from ∼80% to nearly 100%). External validation of the predicted accuracy and negative control experiments were found to be crucial for verification of the accuracy predicted by the algorithms. Furthermore, we propose a possible diagnostic workflow for pathologists to implement classification of histopathological images based on code-free machine platforms.

Artificial intelligence model for analyzing colonic endoscopy images to detect changes associated with irritable bowel syndrome

IBS is not considered to be an organic disease and usually shows no abnormality on lower gastrointestinal endoscopy, although biofilm formation, dysbiosis, and histological microinflammation have recently been reported in patients with IBS. In this study, we investigated whether an artificial intelligence (AI) colorectal image model can identify minute endoscopic changes, which cannot typically be detected by human investigators, that are associated with IBS. Study subjects were identified based on electronic medical records and categorized as IBS (Group I; n = 11), IBS with predominant constipation (IBS-C; Group C; n = 12), and IBS with predominant diarrhea (IBS-D; Group D; n = 12). The study subjects had no other diseases. Colonoscopy images from IBS patients and from asymptomatic healthy subjects (Group N; n = 88) were obtained. Google Cloud Platform AutoML Vision (single-label classification) was used to construct AI image models to calculate sensitivity, specificity, predictive value, and AUC. A total of 2479, 382, 538, and 484 images were randomly selected for Groups N, I, C and D, respectively. The AUC of the model discriminating between Group N and I was 0.95. Sensitivity, specificity, positive predictive value, and negative predictive value of Group I detection were 30.8%, 97.6%, 66.7%, and 90.2%, respectively. The overall AUC of the model discriminating between Groups N, C, and D was 0.83; sensitivity, specificity, and positive predictive value of Group N were 87.5%, 46.2%, and 79.9%, respectively. Using the image AI model, colonoscopy images of IBS could be discriminated from healthy subjects at AUC 0.95. Prospective studies are needed to further validate whether this externally validated model has similar diagnostic capabilities at other facilities and whether it can be used to determine treatment efficacy.

Modeling methods for busulfan-induced oligospermia and asthenozoospermia in mice: a systematic review and meta-analysis

OBJECTIVE

Modeling methods for busulfan-induced oligoasthenozoospermia are controversial. We aimed to systematically review the modeling method of busulfan-induced oligospermia and asthenozoospermia, and analyze changes in various evaluation indicators at different busulfan doses over time.

METHODS

We searched the Cochrane Library, PubMed databases, Web of Science, the Chinese National Knowledge Infrastructure, and the Chinese Biomedical Literature Service System until April 9, 2022. Animal experiments of busulfan-induced spermatogenesis dysfunction were included and screened. The model mortality and parameters of the evaluation indicators were subjected to meta-analysis.

RESULTS

Twenty-nine animal studies were included (control/model: 669/1829). The mortality of mice increased with busulfan dose. Significant spermatogenesis impairment occurred within 5 weeks, regardless of busulfan dose (10-40 mg/kg). Testicular weight (weighted mean difference [WMD]: - 0.04, 95% CI: - 0.05, - 0.03), testicular index (WMD: - 2.10, 95% CI: - 2.43, - 1.76), and Johnsen score (WMD: - 4.67, 95% CI: - 5.99, - 3.35) were significantly decreased. The pooled sperm counts of the model group were reduced by 32.8 × 106/ml (WMD: - 32.8, 95% CI: - 44.34, - 21.28), and sperm motility decreased by 37% (WMD: - 0.37, 95% CI: - 0.47, - 0.27). Sperm counts decreased slightly (WMD: - 3.03, 95% CI: - 3.42, - 2.64) in an intratesticular injection of low-dose busulfan (4 - 6 mg/kg), and the model almost returned to normal after one seminiferous cycle.

CONCLUSION

The model using low-dose busulfan (10 - 20 mg/kg) returned to normal after 10 - 15 weeks. However, in some spermatogenesis cycles, testicular weight reduction and testicular spermatogenic function damage were not proportional to busulfan dose. Sperm counts and motility results in different studies had significant heterogeneity. Standard protocols for sperm assessment in animal models were needed to reduce heterogeneity between studies.

Application of machine learning and complex network measures to an EEG dataset from ayahuasca experiments

Ayahuasca is a blend of Amazonian plants that has been used for traditional medicine by the inhabitants of this region for hundreds of years. Furthermore, this plant has been demonstrated to be a viable therapy for a variety of neurological and mental diseases. EEG experiments have found specific brain regions that changed significantly due to ayahuasca. Here, we used an EEG dataset to investigate the ability to automatically detect changes in brain activity using machine learning and complex networks. Machine learning was applied at three different levels of data abstraction: (A) the raw EEG time series, (B) the correlation of the EEG time series, and (C) the complex network measures calculated from (B). Further, at the abstraction level of (C), we developed new measures of complex networks relating to community detection. As a result, the machine learning method was able to automatically detect changes in brain activity, with case (B) showing the highest accuracy (92%), followed by (A) (88%) and (C) (83%), indicating that connectivity changes between brain regions are more important for the detection of ayahuasca. The most activated areas were the frontal and temporal lobe, which is consistent with the literature. F3 and PO4 were the most important brain connections, a significant new discovery for psychedelic literature. This connection may point to a cognitive process akin to face recognition in individuals during ayahuasca-mediated visual hallucinations. Furthermore, closeness centrality and assortativity were the most important complex network measures. These two measures are also associated with diseases such as Alzheimer's disease, indicating a possible therapeutic mechanism. Moreover, the new measures were crucial to the predictive model and suggested larger brain communities associated with the use of ayahuasca. This suggests that the dissemination of information in functional brain networks is slower when this drug is present. Overall, our methodology was able to automatically detect changes in brain activity during ayahuasca consumption and interpret how these psychedelics alter brain networks, as well as provide insights into their mechanisms of action.

SATINN: an automated neural network-based classification of testicular sections allows for high-throughput histopathology of mouse mutants

MOTIVATION

The mammalian testis is a complex organ with a cellular composition that changes smoothly and cyclically in normal adults. While testis histology is already an invaluable tool for identifying and describing developmental differences in evolution and disease, methods for standardized, digital image analysis of testis are needed to expand the utility of this approach.

RESULTS

We developed SATINN (Software for Analysis of Testis Images with Neural Networks), a multi-level framework for automated analysis of multiplexed immunofluorescence images from mouse testis. This approach uses residual learning to train convolutional neural networks (CNNs) to classify nuclei from seminiferous tubules into seven distinct cell types with an accuracy of 81.7%. These cell classifications are then used in a second-level tubule CNN, which places seminiferous tubules into one of 12 distinct tubule stages with 57.3% direct accuracy and 94.9% within ±1 stage. We further describe numerous cell- and tubule-level statistics that can be derived from wild-type testis. Finally, we demonstrate how the classifiers and derived statistics can be used to rapidly and precisely describe pathology by applying our methods to image data from two mutant mouse lines. Our results demonstrate the feasibility and potential of using computer-assisted analysis for testis histology, an area poised to evolve rapidly on the back of emerging, spatially resolved genomic and proteomic technologies.

AVAILABILITY AND IMPLEMENTATION

The source code to reproduce the results described here and a SATINN standalone application with graphic-user interface are available from http://github.com/conradlab/SATINN.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Future of Male Infertility Evaluation and Treatment: Brief Review of Emerging Technology

Over the past few decades, there have been significant advances in male infertility, particularly in the development of novel diagnostic tools. Unfortunately, there remains a substantial number of patients that remain infertile despite these improvements. In this review, we take heed of the emerging technologies that will shape the future of male infertility diagnosis, evaluation and treatment. Improvement in computer-assisted semen analyses and portability allow males to obtain basic semen parameters from the comfort of their home. Additionally, breakthrough ultrasound technology allows for preoperative prediction of potential areas of spermatogenesis within the testes, high-resolution optics permits better visualization during microdissection testicular sperm extraction (mTESE), and artificial intelligence improves sperm selection and identification.

Advanced molecular approaches in male infertility diagnosis

In the recent years a special attention has been given to a major health concern namely to male infertility, defined as the inability to conceive after 12 months of regular unprotected sexual intercourse, taken into account the statistics that highlight that sperm counts have dropped by 50-60% in recent decades. According to the WHO, infertility affects approximately 9% of couples globally, and the male factor is believed to be present in roughly 50% of cases, with exclusive responsibility in 30%. The aim of this manuscript is to present an evidence-based approach for diagnosing male infertility that includes finding new solutions for diagnosis and critical outcomes, retrieving up-to-date studies and existing guidelines. The diverse factors that induce male infertility generated in a vast amount of data that needed to be analysed by a clinician before a decision could be made for each individual. Modern medicine faces numerous obstacles as a result of the massive amount of data generated by the molecular biology discipline. To address complex clinical problems, vast data must be collected, analysed, and used, which can be very challenging. The use of artificial intelligence (AI) methods to create a decision support system can help predict the diagnosis and guide treatment for infertile men, based on analysis of different data as environmental and lifestyle, clinical (sperm count, morphology, hormone testing, karyotype, etc.) and "omics" bigdata. Ultimately, the development of AI algorithms will assist clinicians in formulating diagnosis, making treatment decisions, and predicting outcomes for assisted reproduction techniques.