Twelve tips for addressing ethical concerns in the implementation of artificial intelligence in medical education

Artificial Intelligence (AI) holds immense potential for revolutionizing medical education and healthcare. Despite its proven benefits, the full integration of AI faces hurdles, with ethical concerns standing out as a key obstacle. Thus, educators should be equipped to address the ethical issues that arise and ensure the seamless integration and sustainability of AI-based interventions. This article presents twelve essential tips for addressing the major ethical concerns in the use of AI in medical education. These include emphasizing transparency, addressing bias, validating content, prioritizing data protection, obtaining informed consent, fostering collaboration, training educators, empowering students, regularly monitoring, establishing accountability, adhering to standard guidelines, and forming an ethics committee to address the issues that arise in the implementation of AI. By adhering to these tips, medical educators and other stakeholders can foster a responsible and ethical integration of AI in medical education, ensuring its long-term success and positive impact.

Preparing healthcare leaders of the digital age with an integrative artificial intelligence curriculum: a pilot study

Artificial intelligence (AI) is rapidly being introduced into the clinical workflow of many specialties. Despite the need to train physicians who understand the utility and implications of AI and mitigate a growing skills gap, no established consensus exists on how to best introduce AI concepts to medical students during preclinical training. This study examined the effectiveness of a pilot Digital Health Scholars (DHS) non-credit enrichment elective that paralleled the Dartmouth Geisel School of Medicine's first-year preclinical curriculum with a focus on introducing AI algorithms and their applications in the concurrently occurring systems-blocks. From September 2022 to March 2023, ten self-selected first-year students enrolled in the elective curriculum run in parallel with four existing curricular blocks (Immunology, Hematology, Cardiology, and Pulmonology). Each DHS block consisted of a journal club, a live-coding demonstration, and an integration session led by a researcher in that field. Students' confidence in explaining the content objectives (high-level knowledge, implications, and limitations of AI) was measured before and after each block and compared using Mann-Whitney U tests. Students reported significant increases in confidence in describing the content objectives after all four blocks (Immunology: U = 4.5, p = 0.030; Hematology: U = 1.0, p = 0.009; Cardiology: U = 4.0, p = 0.019; Pulmonology: U = 4.0, p = 0.030) as well as an average overall satisfaction level of 4.29/5 in rating the curriculum content. Our study demonstrates that a digital health enrichment elective that runs in parallel to an institution's preclinical curriculum and embeds AI concepts into relevant clinical topics can enhance students' confidence in describing the content objectives that pertain to high-level algorithmic understanding, implications, and limitations of the studied models. Building on this elective curricular design, further studies with a larger enrollment can help determine the most effective approach in preparing future physicians for the AI-enhanced clinical workflow.

Explainable machine learning model for identifying key gut microbes and metabolites biomarkers associated with myasthenia gravis

Diagnostic markers for myasthenia gravis (MG) are limited; thus, innovative approaches are required for supportive diagnosis and personalized care. Gut microbes are associated with MG pathogenesis; however, few studies have adopted machine learning (ML) to identify the associations among MG, gut microbiota, and metabolites. In this study, we developed an explainable ML model to predict biomarkers for MG diagnosis. We enrolled 19 MG patients and 10 non-MG individuals. Stool samples were collected and microbiome assessment was performed using 16S rRNA sequencing. Untargeted metabolic profiling was conducted to identify fecal amplicon significant variants (ASVs) and metabolites. We developed an explainable ML model in which the top ASVs and metabolites are combined to identify the best predictive performance. This model uses the SHapley Additive exPlanations method to generate both global and personalized explanations. Fecal microbe-metabolite composition differed significantly between groups. The key bacterial families were Lachnospiraceae and Ruminococcaceae, and the top three features were Lachnospiraceae, inosine, and methylhistidine. An ML model trained with the top 1 % ASVs and top 15 % metabolites combined outperformed all other models. Personalized explanations revealed different patterns of microbe-metabolite contributions in patients with MG. The integration of the microbiota-metabolite features and the development of an explainable ML framework can accurately identify MG and provide personalized explanations, revealing the associations between gut microbiota, metabolites, and MG. An online calculator employing this algorithm was developed that provides a streamlined interface for MG diagnosis screening and conducting personalized evaluations.

Machine learning in infectious diseases: potential applications and limitations

Infectious diseases are a major threat for human and animal health worldwide. Artificial Intelligence (AI) combined algorithms including Machine Learning and Big Data analytics have emerged as a potential solution to analyse diverse datasets and face challenges posed by infectious diseases. In this commentary we explore the potential applications and limitations of ML to management of infectious disease. It explores challenges in key areas such as outbreak prediction, pathogen identification, drug discovery, and personalized medicine. We propose potential solutions to mitigate these hurdles and applications of ML to identify biomolecules for effective treatment and prevention of infectious diseases. In addition to use of ML for management of infectious diseases, potential applications are based on catastrophic evolution events for the identification of biomolecular targets to reduce risks for infectious diseases and vaccinomics for discovery and characterization of vaccine protective antigens using intelligent Big Data analytics techniques. These considerations set a foundation for developing effective strategies for managing infectious diseases in the future.

Comparative evaluation of slide scanners, scan settings, and cytopreparations for digital urine cytology

Background

Acquiring well-focused digital images of cytology slides with scanners can be challenging due to the 3-dimensional nature of the slides. This study evaluates performances of whole-slide images (WSIs) obtained from 2 different cytopreparations by 2 distinct scanners with 3 focus modes.

Methods

Fourteen urine specimens were collected from patients with urothelial carcinoma. Each specimen was equally divided into 2 portions, prepared with Cytospin and ThinPrep methods and scanned for WSIs using Leica (Aperio AT2) and Hamamatsu (NanoZoomer S360) scanners, respectively. The scan settings included 3 focus modes (default, semi-auto, and manual) for single-layer scanning, along with a manual focus mode for 21 Z-layers scanning. Performance metrics were evaluated including scanning success rate, artificial intelligence (AI) algorithm-inferred atypical cell numbers and coverage rate (atypical cell numbers in single or multiple Z-layers divided by the total atypical cell numbers in 21 Z-layers), scanning time, and image file size.

Results

The default mode had scanning success rates of 85.7% or 92.9%, depending on the scanner used. The semi-auto mode increased success to 92.9% or 100%, and manual even further to 100%. However, these changes did not affect the standardized median atypical cell numbers and coverage rates. The selection of scanners, cytopreparations, and Z-stacking influenced standardized median atypical cell numbers and coverage rates, scanning times, and image file sizes.

Discussion

Both scanners showed satisfactory scanning. We recommend using semi-auto or manual focus modes to achieve a scanning success rate of up to 100%. Additionally, a minimum of 9-layer Z-stacking at 1 μm intervals is required to cover 80% of atypical cells. These advanced focus methods do not impact the number of atypical cells or their coverage rate. While Z-stacking enhances the AI algorithm's inferred quantity and coverage rates of atypical cells, it simultaneously results in longer scanning times and larger image file sizes.

Harbor seal whiskers optimization algorithm with deep learning-based medical imaging analysis for gastrointestinal cancer detection

Gastrointestinal (GI) cancer detection includes the detection of cancerous or potentially cancerous lesions within the GI tract. Earlier diagnosis is critical for increasing the success of treatment and improving patient outcomes. Medical imaging plays a major role in diagnosing and detecting GI cancer. CT scans, endoscopy, MRI, ultrasound, and positron emission tomography (PET) scans can help detect lesions, abnormal masses, and changes in tissue structure. Artificial intelligence (AI) and machine learning (ML) methods are being gradually applied to medical imaging for cancer diagnosis. ML algorithms, including deep learning methodologies like convolutional neural network (CNN), are applied frequently for cancer diagnosis. These models learn features and patterns from labelled datasets to discriminate between normal and abnormal areas in medical images. This article presents a new Harbor Seal Whiskers Optimization Algorithm with Deep Learning based Medical Imaging Analysis for Gastrointestinal Cancer Detection (HSWOA-DLGCD) technique. The goal of the HSWOA-DLGCD algorithm is to explore the GI images for the cancer diagnosis. In order to accomplish this, the HSWOA-DLGCD system applies bilateral filtering (BF) approach for the removal of noise. In addition, the HSWOA-DLGCD technique makes use of HSWOA with Xception model for feature extraction. For cancer recognition, the HSWOA-DLGCD technique applies extreme gradient boosting (XGBoost) model. Finally, the parameters compared with the XGBoost system can be selected by moth flame optimization (MFO) system. The experimental results of the HSWOA-DLGCD technique could be verified on the Kvasir database. The simulation outcome demonstrated a best possible solution of the HSWOA-DLGCD method than other recent methods.

Artificial intelligence-based prescription of personalized scalp cosmetics improved the scalp condition: efficacy results from 100 participants

Background: Scalp-related symptoms such as dandruff and itching are common with diverse underlying etiologies. We previously proposed a novel classification and scoring system for scalp conditions, called the scalp photographic index (SPI); it grades five scalp features using trichoscopic images with good reliability. However, it requires trained evaluators.Aim: To develop artificial intelligence (AI) algorithms for assessment of scalp conditions and to assess the feasibility of AI-based recommendations on personalized scalp cosmetics.Methods: Using EfficientNet, convolutional neural network (CNN) models (SPI-AI) ofeach scalp feature were established. 101,027 magnified scalp images graded according to the SPI scoring were used for training, validation, and testing the model Adults with scalp discomfort were prescribed shampoos and scalp serums personalized according to their SPI-AI-defined scalp types. Using the SPI, the scalp conditions were evaluated at baseline and at weeks 4, 8, and 12 of treatment.Results: The accuracies of the SPI-AI for dryness, oiliness, erythema, folliculitis, and dandruff were 91.3%, 90.5%, 89.6%, 87.3%, and 95.2%, respectively. Overall, 100 individuals completed the 4-week study; 43 of these participated in an extension study until week 12. The total SPI score decreased from 32.70 ± 7.40 at baseline to 15.97 ± 4.68 at week 4 (p < 0.001). The efficacy was maintained throughout 12 weeks.Conclusions: SPI-AI accurately assessed the scalp condition. AI-based prescription of tailored scalp cosmetics could significantly improve scalp health.

Structural and functional prediction, evaluation, and validation in the post-sequencing era

The surge of genome sequencing data has underlined substantial genetic variants of uncertain significance (VUS). The decryption of VUS discovered by sequencing poses a major challenge in the post-sequencing era. Although experimental assays have progressed in classifying VUS, only a tiny fraction of the human genes have been explored experimentally. Thus, it is urgently needed to generate state-of-the-art functional predictors of VUS in silico. Artificial intelligence (AI) is an invaluable tool to assist in the identification of VUS with high efficiency and accuracy. An increasing number of studies indicate that AI has brought an exciting acceleration in the interpretation of VUS, and our group has already used AI to develop protein structure-based prediction models. In this review, we provide an overview of the previous research on AI-based prediction of missense variants, and elucidate the challenges and opportunities for protein structure-based variant prediction in the post-sequencing era.

Perspectives on AI-based recommendations for mask-wearing and COVID-19 vaccination for transplant recipients in the post-COVID-19 era

In the aftermath of the COVID-19 pandemic, the ongoing necessity for preventive measures such as mask-wearing and vaccination remains particularly critical for organ transplant recipients, a group highly susceptible to infections due to immunosuppressive therapy. Given that many individuals nowadays increasingly utilize Artificial Intelligence (AI), understanding AI perspectives is important. Thus, this study utilizes AI, specifically ChatGPT 4.0, to assess its perspectives in offering precise health recommendations for mask-wearing and COVID-19 vaccination tailored to this vulnerable population. Through a series of scenarios reflecting diverse environmental settings and health statuses in December 2023, we evaluated the AI's responses to gauge its precision, adaptability, and potential biases in advising high-risk patient groups. Our findings reveal that ChatGPT 4.0 consistently recommends mask-wearing in crowded and indoor environments for transplant recipients, underscoring their elevated risk. In contrast, for settings with fewer transmission risks, such as outdoor areas where social distancing is possible, the AI suggests that mask-wearing might be less imperative. Regarding vaccination guidance, the AI strongly advocates for the COVID-19 vaccine across most scenarios for kidney transplant recipients. However, it recommends a personalized consultation with healthcare providers in cases where patients express concerns about vaccine-related side effects, demonstrating an ability to adapt recommendations based on individual health considerations. While this study provides valuable insights into the current AI perspective on these important topics, it is crucial to note that the findings do not directly reflect or influence health policy. Nevertheless, given the increasing utilization of AI in various domains, understanding AI's viewpoints on such critical matters is essential for informed decision-making and future research.

Glucocorticoid therapy for sepsis in the AI era: a survey on current and future approaches

Sepsis, a life-threatening medical condition, manifests as new or worsening organ failures due to a dysregulated host response to infection. Many patients with sepsis have manifested a hyperinflammatory phenotype leading to the identification of inflammatory modulation by corticosteroids as a key treatment modality. However, the optimal use of corticosteroids in sepsis treatment remains a contentious subject, necessitating a deeper understanding of their physiological and pharmacological effects. Our study conducts a comprehensive review of randomized controlled trials (RCTs) focusing on traditional corticosteroid treatment in sepsis, alongside an analysis of evolving clinical guidelines. Additionally, we explore the emerging role of artificial intelligence (AI) in medicine, particularly in diagnosing, prognosticating, and treating sepsis. AI's advanced data processing capabilities reveal new avenues for enhancing corticosteroid therapeutic strategies in sepsis. The integration of AI in sepsis treatment has the potential to address existing gaps in knowledge, especially in the application of corticosteroids. Our findings suggest that combining corticosteroid therapy with AI-driven insights could lead to more personalized and effective sepsis treatments. This approach holds promise for improving clinical outcomes and presents a significant advancement in the management of this complex and often fatal condition.

Artificial intelligence-based framework to identify the abnormalities in the COVID-19 disease and other common respiratory diseases from digital stethoscope data using deep CNN

The utilization of lung sounds to diagnose lung diseases using respiratory sound features has significantly increased in the past few years. The Digital Stethoscope data has been examined extensively by medical researchers and technical scientists to diagnose the symptoms of respiratory diseases. Artificial intelligence-based approaches are applied in the real universe to distinguish respiratory disease signs from human pulmonary auscultation sounds. The Deep CNN model is implemented with combined multi-feature channels (Modified MFCC, Log Mel, and Soft Mel) to obtain the sound parameters from lung-based Digital Stethoscope data. The model analysis is observed with max-pooling and without max-pool operations using multi-feature channels on respiratory digital stethoscope data. In addition, COVID-19 sound data and enriched data, which are recently acquired data to enhance model performance using a combination of L2 regularization to overcome the risk of overfitting because of less respiratory sound data, are included in the work. The suggested DCNN with Max-Pooling on the improved dataset demonstrates cutting-edge performance employing a multi-feature channels spectrogram. The model has been developed with different convolutional filter sizes (1 × 12 , 1 × 24 , 1 × 36 , 1 × 48 , and 1 × 60 ) that helped to test the proposed neural network. According to the experimental findings, the suggested DCNN architecture with a max-pooling function performs better to identify respiratory disease symptoms than DCNN without max-pooling. In order to demonstrate the model's effectiveness in categorization, it is trained and tested with the DCNN model that extract several modalities of respiratory sound data.

Dynamic changes in AI-based analysis of endometrial cellular composition: Analysis of PCOS and RIF endometrium

Background

The human endometrium undergoes a monthly cycle of tissue growth and degeneration. During the mid-secretory phase, the endometrium establishes an optimal niche for embryo implantation by regulating cellular composition (e.g., epithelial and stromal cells) and differentiation. Impaired endometrial development observed in conditions such as polycystic ovary syndrome (PCOS) and recurrent implantation failure (RIF) contributes to infertility. Surprisingly, despite the importance of the endometrial lining properly developing prior to pregnancy, precise measures of endometrial cellular composition in these two infertility-associated conditions are entirely lacking. Additionally, current methods for measuring the epithelial and stromal area have limitations, including intra- and inter-observer variability and efficiency.

Methods

We utilized a deep-learning artificial intelligence (AI) model, created on a cloud-based platform and developed in our previous study. The AI model underwent training to segment both areas populated by epithelial and stromal endometrial cells. During the training step, a total of 28.36 mm2 areas were annotated, comprising 2.56 mm2 of epithelium and 24.87 mm2 of stroma. Two experienced pathologists validated the performance of the AI model. 73 endometrial samples from healthy control women were included in the sample set to establish cycle phase-dependent dynamics of the endometrial epithelial-to-stroma ratio from the proliferative (PE) to secretory (SE) phases. In addition, 91 samples from PCOS cases, accounting for the presence or absence of ovulation and representing all menstrual cycle phases, and 29 samples from RIF patients on day 5 after progesterone administration in the hormone replacement treatment cycle were also included and analyzed in terms of cellular composition.

Results

Our AI model exhibited reliable and reproducible performance in delineating epithelial and stromal compartments, achieving an accuracy of 92.40% and 99.23%, respectively. Moreover, the performance of the AI model was comparable to the pathologists' assessment, with F1 scores exceeding 82% for the epithelium and >96% for the stroma. Next, we compared the endometrial epithelial-to-stromal ratio during the menstrual cycle in women with PCOS and in relation to endometrial receptivity status in RIF patients. The ovulatory PCOS endometrium exhibited epithelial cell proportions similar to those of control and healthy women's samples in every cycle phase, from the PE to the late SE, correlating with progesterone levels (control SE, r2 = 0.64, FDR < 0.001; PCOS SE, r2 = 0.52, FDR < 0.001). The mid-SE endometrium showed the highest epithelial percentage compared to both the early and late SE endometrium in both healthy women and PCOS patients. Anovulatory PCOS cases showed epithelial cellular fractions comparable to those of PCOS cases in the PE (Anovulatory, 14.54%; PCOS PE, 15.56%, p = 1.00). We did not observe significant differences in the epithelial-to-stroma ratio in the hormone-induced endometrium in RIF patients with different receptivity statuses.

Conclusion

The AI model rapidly and accurately identifies endometrial histology features by calculating areas occupied by epithelial and stromal cells. The AI model demonstrates changes in epithelial cellular proportions according to the menstrual cycle phase and reveals no changes in epithelial cellular proportions based on PCOS and RIF conditions. In conclusion, the AI model can potentially improve endometrial histology assessment by accelerating the analysis of the cellular composition of the tissue and by ensuring maximal objectivity for research and clinical purposes.

Digital analysis of the prostate tumor microenvironment with high-order chromogenic multiplexing

As our understanding of the tumor microenvironment grows, the pathology field is increasingly utilizing multianalyte diagnostic assays to understand important characteristics of tumor growth. In clinical settings, brightfield chromogenic assays represent the gold-standard and have developed significant trust as the first-line diagnostic method. However, conventional brightfield tests have been limited to low-order assays that are visually interrogated. We have developed a hybrid method of brightfield chromogenic multiplexing that overcomes these limitations and enables high-order multiplex assays. However, how compatible high-order brightfield multiplexed images are with advanced analytical algorithms has not been extensively evaluated. In the present study, we address this gap by developing a novel 6-marker prostate cancer assay that targets diverse aspects of the tumor microenvironment such as prostate-specific biomarkers (PSMA and p504s), immune biomarkers (CD8 and PD-L1), a prognostic biomarker (Ki-67), as well as an adjunctive diagnostic biomarker (basal cell cocktail) and apply the assay to 143 differentially graded adenocarcinoma prostate tissues. The tissues were then imaged on our spectroscopic multiplexing imaging platform and mined for proteomic and spatial features that were correlated with cancer presence and disease grade. Extracted features were used to train a UMAP model that differentiated healthy from cancerous tissue with an accuracy of 89% and identified clusters of cells based on cancer grade. For spatial analysis, cell-to-cell distances were calculated for all biomarkers and differences between healthy and adenocarcinoma tissues were studied. We report that p504s positive cells were at least 2× closer to cells expressing PD-L1, CD8, Ki-67, and basal cell in adenocarcinoma tissues relative to the healthy control tissues. These findings offer a powerful insight to understand the fingerprint of the prostate tumor microenvironment and indicate that high-order chromogenic multiplexing is compatible with digital analysis. Thus, the presented chromogenic multiplexing system combines the clinical applicability of brightfield assays with the emerging diagnostic power of high-order multiplexing in a digital pathology friendly format that is well-suited for translational studies to better understand mechanisms of tumor development and growth.

Determining the recurrence rate of premature ventricular complexes and idiopathic ventricular tachycardia after radiofrequency catheter ablation with the help of designing a machine-learning model

Ventricular arrhythmias increase cardiovascular morbidity and mortality. Recurrent PVCs and IVT are generally considered benign in the absence of structural heart abnormalities. Artificial intelligence is a rapidly growing field. In recent years, medical professionals have shown great interest in the potential use of ML, an integral part of AI, in various disciplines, including diagnostic applications, decision-making, prognostic stratification, and solving complex pathophysiological aspects of diseases from these data at extraordinary complexity, scale, and acquisition rate. The aim of this study was to design an ML model to predict the probability of PVC and IVT recurrence after RF ablation. Data of patients were collected and manipulated using traditional analysis and various artificial intelligence models, namely MLP, Gradient Boosting Machines, Random Forest, and Logistic Regression. Hypertension, male sex, and the use of non-irrigate catheters were associated with less freedom from arrhythmia. All these results were obtained through traditional analytic methods, and according to AI, none of the variables had a clear effect on the recurrence of arrhythmia. Each AI model presents unique strengths and weaknesses, and further optimization and fine-tuning of these models are necessary to increase their clinical utility. By expanding the dataset, improved predictions can be fostered to ultimately increase the clinical utility of AI in predicting PVC erosion outcomes.

Artificial intelligence for human gunshot wound classification

Certain features are helpful in the identification of gunshot entrance and exit wounds, such as the presence of muzzle imprints, peripheral tears, stippling, bone beveling, and wound border irregularity. Some cases are less straightforward and wounds can thus pose challenges to an emergency room doctor or forensic pathologist. In recent years, deep learning has shown promise in various automated medical image classification tasks. This study explores the feasibility of using a deep learning model to classify entry and exit gunshot wounds in digital color images. A collection of 2418 images of entrance and exit gunshot wounds were procured. Of these, 2028 entrance and 1314 exit wounds were cropped, focusing on the area around each gunshot wound. A ConvNext Tiny deep learning model was trained using the Fastai deep learning library, with a train/validation split ratio of 70/30, until a maximum validation accuracy of 92.6% was achieved. An additional 415 entrance and 293 exit wound images were collected for the test (holdout) set. The model achieved an accuracy of 87.99%, precision of 83.99%, recall of 87.71%, and F1-score 85.81% on the holdout set. Correctly classified were 88.19% of entrance wounds and 87.71% of exit wounds. The results are comparable to what a forensic pathologist can achieve without other morphologic cues. This study represents one of the first applications of artificial intelligence to the field of forensic pathology. This work demonstrates that deep learning models can discern entrance and exit gunshot wounds in digital images with high accuracy.

NeuralBeds: Neural embeddings for efficient DNA data compression and optimized similarity search

The availability of high throughput sequencing tools coupled with the declining costs in the production of DNA sequences has led to the generation of enormous amounts of omics data curated in several databases such as NCBI and EMBL. Identification of similar DNA sequences from these databases is one of the fundamental tasks in bioinformatics. It is essential for discovering homologous sequences in organisms, phylogenetic studies of evolutionary relationships among several biological entities, or detection of pathogens. Improving DNA similarity search is of outmost importance because of the increased complexity of the evergrowing repositories of sequences. Therefore, instead of using the conventional approach of comparing raw sequences, e.g., in fasta format, a numerical representation of the sequences can be used to calculate their similarities and optimize the search process. In this study, we analyzed different approaches for numerical embeddings, including Chaos Game Representation, hashing, and neural networks, and compared them with classical approaches such as principal component analysis. It turned out that neural networks generate embeddings that are able to capture the similarity between DNA sequences as a distance measure and outperform the other approaches on DNA similarity search, significantly.

True-T - Improving T-cell response quantification with holistic artificial intelligence based prediction in immunohistochemistry images

The immune response associated with oncogenesis and potential oncological ther- apeutic interventions has dominated the field of cancer research over the last decade. T-cell lymphocytes in the tumor microenvironment are a crucial aspect of cancer's adaptive immunity, and the quantification of T-cells in specific can- cer types has been suggested as a potential diagnostic aid. However, this is cur- rently not part of routine diagnostics. To address this challenge, we present a new method called True-T, which employs artificial intelligence-based techniques to quantify T-cells in colorectal cancer (CRC) using immunohistochemistry (IHC) images. True-T analyses the chromogenic tissue hybridization signal of three widely recognized T-cell markers (CD3, CD4, and CD8). Our method employs a pipeline consisting of three stages: T-cell segmentation, density estimation from the segmented mask, and prediction of individual five-year survival rates. In the first stage, we utilize the U-Net method, where a pre-trained ResNet-34 is em- ployed as an encoder to extract clinically relevant T-cell features. The segmenta- tion model is trained and evaluated individually, demonstrating its generalization in detecting the CD3, CD4, and CD8 biomarkers in IHC images. In the second stage, the density of T-cells is estimated using the predicted mask, which serves as a crucial indicator for patient survival statistics in the third stage. This ap- proach was developed and tested in 1041 patients from four reference diagnostic institutions, ensuring broad applicability. The clinical effectiveness of True-T is demonstrated in stages II-IV CRC by offering valuable prognostic information that surpasses previous quantitative gold standards, opening possibilities for po- tential clinical applications. Finally, to evaluate the robustness and broader ap- plicability of our approach without additional training, we assessed the universal accuracy of the CD3 component of the True-T algorithm across 13 distinct solid tumors.

Role of artificial intelligence in digital pathology for gynecological cancers

The diagnosis of cancer is typically based on histopathological sections or biopsies on glass slides. Artificial intelligence (AI) approaches have greatly enhanced our ability to extract quantitative information from digital histopathology images as a rapid growth in oncology data. Gynecological cancers are major diseases affecting women's health worldwide. They are characterized by high mortality and poor prognosis, underscoring the critical importance of early detection, treatment, and identification of prognostic factors. This review highlights the various clinical applications of AI in gynecological cancers using digitized histopathology slides. Particularly, deep learning models have shown promise in accurately diagnosing, classifying histopathological subtypes, and predicting treatment response and prognosis. Furthermore, the integration with transcriptomics, proteomics, and other multi-omics techniques can provide valuable insights into the molecular features of diseases. Despite the considerable potential of AI, substantial challenges remain. Further improvements in data acquisition and model optimization are required, and the exploration of broader clinical applications, such as the biomarker discovery, need to be explored.

AI-algorithm training and validation for identification of endometrial CD138+ cells in infertility-associated conditions; polycystic ovary syndrome (PCOS) and recurrent implantation failure (RIF)

Background

Endometrial CD138+ plasma cells serve as a diagnostic biomarker for endometrial inflammation, and their elevated occurrence correlates positively with adverse pregnancy outcomes. Infertility-related conditions like polycystic ovary syndrome (PCOS) and recurrent implantation failure (RIF) are closely associated with systemic and local chronic inflammatory status, wherein endometrial CD138+ plasma cell accumulation could also contribute to endometrial pathology. Current methods for quantifying CD138+ cells typically involve laborious and time-consuming microscopic assessments of only a few random areas from a slide. These methods have limitations in accurately representing the entire slide and are susceptible to significant biases arising from intra- and interobserver variations. Implementing artificial intelligence (AI) for CD138+ cell identification could enhance the accuracy, reproducibility, and reliability of analysis.

Methods

Here, an AI algorithm was developed to identify CD138+ plasma cells within endometrial tissue. The AI model comprised two layers of convolutional neural networks (CNNs). CNN1 was trained to segment epithelium and stroma across 28,363 mm2 (2.56 mm2 of epithelium and 24.87 mm2 of stroma), while CNN2 was trained to distinguish stromal cells based on CD138 staining, encompassing 7345 cells in the object layers (6942 CD138- cells and 403 CD138+ cells). The training and performance of the AI model were validated by three experienced pathologists. We collected 193 endometrial tissues from healthy controls (n = 73), women with PCOS (n = 91), and RIF patients (n = 29) and compared the CD138+ cell percentages based on cycle phases, ovulation status, and endometrial receptivity utilizing the AI model.

Results

The AI algorithm consistently and reliably distinguished CD138- and CD138+ cells, with total error rates of 6.32% and 3.23%, respectively. During the training validation, there was a complete agreement between the decisions made by the pathologists and the AI algorithm, while the performance validation demonstrated excellent accuracy between the AI and human evaluation methods (intraclass correlation; 0.76, 95% confidence intervals; 0.36-0.93, p = 0.002) and a positive correlation (Spearman's rank correlation coefficient: 0.79, p < 0.01). In the AI analysis, the AI model revealed higher CD138+ cell percentages in the proliferative phase (PE) endometrium compared to the secretory phase or anovulatory PCOS endometrium, irrespective of PCOS diagnosis. Interestingly, CD138+ percentages differed according to PCOS phenotype in the PE (p = 0.03). On the other hand, the receptivity status had no impact on the cell percentages in RIF samples.

Conclusion

Our findings emphasize the potential and accuracy of the AI algorithm in detecting endometrial CD138+ plasma cells, offering distinct advantages over manual inspection, such as rapid analysis of whole slide images, reduction of intra- and interobserver variations, sparing the valuable time of trained specialists, and consistent productivity. This supports the application of AI technology to help clinical decision-making, for example, in understanding endometrial cycle phase-related dynamics, as well as different reproductive disorders.

Utility of artificial intelligence in a binary classification of soft tissue tumors

Soft tissue tumors (STTs) pose diagnostic and therapeutic challenges due to their rarity, complexity, and morphological overlap. Accurate differentiation between benign and malignant STTs is important to set treatment directions, however, this task can be difficult. The integration of machine learning and artificial intelligence (AI) models can potentially be helpful in classifying these tumors. The aim of this study was to investigate AI and machine learning tools in the classification of STT into benign and malignant categories. This study consisted of three components: (1) Evaluation of whole-slide images (WSIs) to classify STT into benign and malignant entities. Five specialized soft tissue pathologists from different medical centers independently reviewed 100 WSIs, representing 100 different cases, with limited clinical information and no additional workup. The results showed an overall concordance rate of 70.4% compared to the reference diagnosis. (2) Identification of cell-specific parameters that can distinguish benign and malignant STT. Using an image analysis software (QuPath) and a cohort of 95 cases, several cell-specific parameters were found to be statistically significant, most notably cell count, nucleus/cell area ratio, nucleus hematoxylin density mean, and cell max caliper. (3) Evaluation of machine learning library (Scikit-learn) in differentiating benign and malignant STTs. A total of 195 STT cases (156 cases in the training group and 39 cases in the validation group) achieved approximately 70% sensitivity and specificity, and an AUC of 0.68. Our limited study suggests that the use of WSI and AI in soft tissue pathology has the potential to enhance diagnostic accuracy and identify parameters that can differentiate between benign and malignant STTs. We envision the integration of AI as a supportive tool to augment the pathologists' diagnostic capabilities.

Addressing docking pose selection with structure-based deep learning: Recent advances, challenges and opportunities

Molecular docking is a widely used technique in drug discovery to predict the binding mode of a given ligand to its target. However, the identification of the near-native binding pose in docking experiments still represents a challenging task as the scoring functions currently employed by docking programs are parametrized to predict the binding affinity, and, therefore, they often fail to correctly identify the ligand native binding conformation. Selecting the correct binding mode is crucial to obtaining meaningful results and to conveniently optimizing new hit compounds. Deep learning (DL) algorithms have been an area of a growing interest in this sense for their capability to extract the relevant information directly from the protein-ligand structure. Our review aims to present the recent advances regarding the development of DL-based pose selection approaches, discussing limitations and possible future directions. Moreover, a comparison between the performances of some classical scoring functions and DL-based methods concerning their ability to select the correct binding mode is reported. In this regard, two novel DL-based pose selectors developed by us are presented.

Combining a deep learning model with clinical data better predicts hepatocellular carcinoma behavior following surgery

Hepatocellular carcinoma (HCC) is among the most common cancers worldwide, and tumor recurrence following liver resection or transplantation is one of the highest contributors to mortality in HCC patients after surgery. Using artificial intelligence (AI), we developed an interdisciplinary model to predict HCC recurrence and patient survival following surgery. We collected whole-slide H&E images, clinical variables, and follow-up data from 300 patients with HCC who underwent transplant and 169 patients who underwent resection at the Cleveland Clinic. A deep learning model was trained to predict recurrence-free survival (RFS) and disease-specific survival (DSS) from the H&E-stained slides. Repeated cross-validation splits were used to compute robust C-index estimates, and the results were compared to those obtained by fitting a Cox proportional hazard model using only clinical variables. While the deep learning model alone was predictive of recurrence and survival among patients in both cohorts, integrating the clinical and histologic models significantly increased the C-index in each cohort. In every subgroup analyzed, we found that a combined clinical and deep learning model better predicted post-surgical outcome in HCC patients compared to either approach independently.

Computational methods for metastasis detection in lymph nodes and characterization of the metastasis-free lymph node microarchitecture: A systematic-narrative hybrid review

Background

Histological examination of tumor draining lymph nodes (LNs) plays a vital role in cancer staging and prognostication. However, as soon as a LN is classed as metastasis-free, no further investigation will be performed and thus, potentially clinically relevant information detectable in tumor-free LNs is currently not captured.

Objective

To systematically study and critically assess methods for the analysis of digitized histological LN images described in published research.

Methods

A systematic search was conducted in several public databases up to December 2023 using relevant search terms. Studies using brightfield light microscopy images of hematoxylin and eosin or immunohistochemically stained LN tissue sections aiming to detect and/or segment LNs, their compartments or metastatic tumor using artificial intelligence (AI) were included. Dataset, AI methodology, cancer type, and study objective were compared between articles.

Results

A total of 7201 articles were collected and 73 articles remained for detailed analyses after article screening. Of the remaining articles, 86% aimed at LN metastasis identification, 8% aimed at LN compartment segmentation, and remaining focused on LN contouring. Furthermore, 78% of articles used patch classification and 22% used pixel segmentation models for analyses. Five out of six studies (83%) of metastasis-free LNs were performed on publicly unavailable datasets, making quantitative article comparison impossible.

Conclusions

Multi-scale models mimicking multiple microscopy zooms show promise for computational LN analysis. Large-scale datasets are needed to establish the clinical relevance of analyzing metastasis-free LN in detail. Further research is needed to identify clinically interpretable metrics for LN compartment characterization.

External validation of a deep learning-based algorithm for detection of tall cells in papillary thyroid carcinoma: A multicenter study

The tall cell subtype (TC-PTC) is an aggressive subtype of papillary thyroid carcinoma (PTC). The TC-PTC is defined as a PTC comprising at least 30% epithelial cells that are three times as tall as they are wide. In practice, this definition is difficult to adhere to, resulting in high inter-observer variability. In this multicenter study, we validated a previously trained deep learning (DL)-based algorithm for detection of tall cells on 160 externally collected hematoxylin and eosin (HE)-stained PTC whole-slide images. In a test set of 360 manual annotations of regions of interest from 18 separate tissue sections in the external dataset, the DL-based algorithm detected TCs with a sensitivity of 90.6% and a specificity of 88.5%. The DL algorithm detected non-TC areas with a sensitivity of 81.6% and a specificity of 92.9%. In the validation datasets, 20% and 30% TC thresholds correlated with a significantly shorter relapse-free survival. In conclusion, the DL algorithm detected TCs in unseen, external scanned HE tissue slides with high sensitivity and specificity without any retraining.

RIscoper 2.0: A deep learning tool to extract RNA biomedical relation sentences from literature

RNA plays an extensive role in a multi-dimensional regulatory system, and its biomedical relationships are scattered across numerous biological studies. However, text mining works dedicated to the extraction of RNA biomedical relations remain limited. In this study, we established a comprehensive and reliable corpus of RNA biomedical relations, recruiting over 30,000 sentences manually curated from more than 15,000 biomedical literature. We also updated RIscoper 2.0, a BERT-based deep learning tool to extract RNA biomedical relation sentences from literature. Benefiting from approximately 100,000 annotated named entities, we integrated the text classification and named entity recognition tasks in this tool. Additionally, RIscoper 2.0 outperformed the original tool in both tasks and can discover new RNA biomedical relations. Additionally, we provided a user-friendly online search tool that enables rapid scanning of RNA biomedical relationships using local and online resources. Both the online tools and data resources of RIscoper 2.0 are available at http://www.rnainter.org/riscoper.