Artificial intelligence and whole slide imaging, a new tool for the microsatellite instability prediction in colorectal cancer: Friend or foe?

Colorectal cancer (CRC) is the third most common and second most deadly cancer worldwide. Despite advances in screening and treatment, CRC is heterogeneous and the response to therapy varies significantly, limiting personalized treatment options. Certain molecular biomarkers, including microsatellite instability (MSI), are critical in planning personalized treatment, although only a subset of patients may benefit. Currently, the primary methods for assessing MSI status include immunohistochemistry (IHC) for DNA mismatch repair proteins (MMRs), polymerase chain reaction (PCR)-based molecular testing, or next-generation sequencing (NGS). However, these techniques have limitations, are expensive and time-consuming, and often result in inter-method inconsistencies. Deficient mismatch repair (dMMR) or high microsatellite instability (MSI-H) are critical predictive biomarkers of response to immune checkpoint inhibitor (ICI) therapy and MSI testing is recommended to identify patients who may benefit. There is a pressing need for a more robust, reliable, and cost-effective approach that accurately assesses MSI status. Recent advances in computational pathology, in particular the development of technologies that digitally scan whole slide images (WSI) at high resolution, as well as new approaches to artificial intelligence (AI) in medicine, are increasingly gaining ground. This review aims to provide an overview of the latest findings on WSI and advances in AI methods for predicting MSI status, summarize their applications in CRC, and discuss their strengths and limitations in daily clinical practice.

Implementing 100% quality control in a cervical cytology workflow using whole slide images and artificial intelligence provided by the Techcyte SureView™ System

BACKGROUND

Recent advancements in digital pathology have extended into cytopathology. Laboratories screening cervical cytology specimens now choose between limited imaging options and traditional manual microscopy. The Techcyte SureView™ Cervical Cytology System, designed for digital cytopathology, was validated at CorePlus, a pathology laboratory in Puerto Rico, and adopted as a 100% quality control (QC) tool.

METHODS

The validation study included 1442 whole slide images (WSIs) from 1273 ThinPrep® and 169 SurePath™ cervical cytology slides, digitized with the 3DHISTECH Panoramic 1000 DX scanner using dry and water immersion scanning profiles. These WSIs were processed by the Techcyte SureView™ system, with a board-certified cytopathologist reviewing artificial intelligence (AI)-identified objects of interest and comparing them to traditional light microscopy results.

RESULTS

Techcyte SureView™ with the water immersion scanning profile outperformed both the dry scanning profile and light microscopy in detecting squamous and glandular abnormalities. It achieved 97% accuracy, 82% sensitivity, 99% specificity, 98% negative predictive value, and 86% positive predictive value. Additionally, the review time was rapid. The system has been operational for several months, enhancing accuracy and workflow efficiency.

CONCLUSIONS

This study demonstrates that digital cytopathology, particularly through the Techcyte SureView™ system, can improve laboratory workflow and performance. Successful validation led CorePlus to integrate the AI algorithm into their workflow as a 100% QC review tool, resulting in improved accuracy, benefiting both laboratory professionals and patients.

The Poly (ADP-Ribose) Polymerase-1 Enzyme Is Overexpressed in Various Solid Canine Tumours: An Immunohistochemical Study

The enzyme poly (ADP-ribose) polymerase-1 (PARP-1) is crucial for cellular regulation and DNA repair. Its immunohistochemical overexpression is known in various human neoplasms, but it was not yet a topic of veterinary research. Formalin-fixed paraffin-embedded canine samples of 15 controls and 34 tumours were immunohistochemically tested for PARP-1 expression. Controls included five skin samples with mast cells, five oral mucosa samples and five thyroid glands. Tumours included 18 mast cell tumours (MCTs), 10 oral squamous cell carcinomas (SCCs) and six follicular thyroid carcinomas. A board-certified veterinary pathologist defined the optimal region for the blind PARP-1 evaluation, assessed by two independent veterinary PhD students. Positive nuclei were evaluated by the immunoreactivity score (IRS) and quick score (QS) and, for both scores, the averages of the two observers were used for statistical analysis. In all MCTs, 6/10 SCCs and all thyroid carcinomas as well as four thyroid controls a nuclear expression was observed. A cytoplasmic granular staining was visible in all dermal mast cells and in 11/18 MCTs due to non-specific antibody uptake. No PARP-1 was expressed in 11/15 controls.Compared to the controls, thyroid carcinomas significantly overexpressed PARP-1 when calculated by IRS and QS (p = 0.003 and p = 0.005, respectively). The latter also applied to the MCTs (p = 0.001). A significantly higher PARP-1 IRS and QS were observed in thyroid carcinomas (p = 0.003, p = 0.005) and MCTs (p = 0.003, p = 0.012) compared to oral SCCs. The immunohistochemical PARP-1 overexpression in these tumours invites further research to assess its potential as a therapeutic target.

Advancements in Hematologic Malignancy Detection: A Comprehensive Survey of Methodologies and Emerging Trends

The investigation and diagnosis of hematologic malignancy using blood cell image analysis are major and emerging subjects that lie at the intersection of artificial intelligence and medical research. This survey systematically examines the state-of-the-art in blood cancer detection through image-based analysis, aimed at identifying the most effective computational strategies and highlighting emerging trends. This review focuses on three principal objectives, namely, to categorize and compare traditional machine learning (ML), deep learning (DL), and hybrid learning approaches; to evaluate performance metrics such as accuracy, precision, recall, and area under the ROC curve; and to identify methodological gaps and propose directions for future research. Methodologically, we organize the literature by categorizing the malignancy types-leukemia, lymphoma, and multiple myeloma-and particularizing the preprocessing steps, feature extraction techniques, network architectures, and ensemble strategies employed. For ML methods, we discuss classical classifiers including support vector machines and random forests; for DL, we analyze convolutional neural networks (e.g., AlexNet, VGG, and ResNet) and transformer-based models; and for hybrid systems, we examine combinations of CNNs with attention mechanisms or traditional classifiers. Our synthesis reveals that DL models consistently outperform ML baselines, achieving classification accuracies above 95% in benchmark datasets, with hybrid models pushing peak accuracy to 99.7%. However, challenges remain in data scarcity, class imbalance, and generalizability to clinical settings. We conclude by recommending the integration of multimodal data, semisupervised learning, and rigorous external validation to advance toward deployable diagnostic tools. This survey also provides a comprehensive roadmap for researchers and clinicians striving to harness AI for reliable hematologic cancer detection.

Artificial intelligence as a predictive tool for gastric cancer: Bridging innovation, clinical translation, and ethical considerations

With gastric cancer ranking among the most prevalent and deadly malignancies worldwide, early detection and individualized prognosis remain essential for improving patient outcomes. This letter discusses recent advancements in artificial intelligence (AI)-driven predictive tools for gastric cancer, emphasizing a computed tomography-based radiomic model that achieved a predictive accuracy of area under the curve of 0.893 for treatment response in advanced cases undergoing neoadjuvant immunochemotherapy. AI offers promising avenues for predictive accuracy and personalized treatment planning in gastric oncology. Additionally, this letter highlights the comparison of these AI tools with traditional methodologies, demonstrating their potential to streamline clinical workflows and address existing gaps in risk stratification and early detection. Furthermore, this letter addresses the ethical considerations and the need for robust clinical-AI collaboration to achieve reliable, transparent, and unbiased outcomes. Strengthening cross-disciplinary efforts will be vital for the responsible and effective deployment of AI in this critical area of oncology.

Bringing AI to Clinicians: Simplifying Pleural Effusion Cytology Diagnosis with User-Friendly Models

Background: Malignant pleural effusions (MPEs) are common in advanced lung cancer patients. Cytological examination of pleural fluid is essential for identifying cell types but presents diagnostic challenges, particularly when reactive mesothelial cells mimic neoplastic cells. AI-powered diagnostic systems have emerged as valuable tools in digital cytopathology. This study explores the applicability of machine-learning (ML) models and highlights the importance of accessible tools for clinicians, enabling them to develop AI solutions and make advanced diagnostic tools available even in resource-limited settings. The focus is on differentiating normal/reactive cells from neoplastic cells in pleural effusions linked to lung adenocarcinoma. Methods: A dataset from the Cytopathology Unit at the Sant'Andrea University Hospital comprising 969 raw images, annotated with 3130 single mesothelial cells and 3260 adenocarcinoma cells, was categorized into two classes based on morphological features. Object-detection models were developed using YOLOv8 and the latest YOLOv11 instance segmentation models. Results: The models achieved an Intersection over Union (IoU) score of 0.72, demonstrating robust performance in class prediction for both categories, with YOLOv11 showing performance improvements over YOLOv8 in different metrics. Conclusions: The application of machine learning in cytopathology offers clinicians valuable support in differential diagnosis while also expanding their ability to engage with AI tools and methodologies. The diagnosis of MPEs is marked by substantial morphological and technical variability, underscoring the need for high-quality datasets and advanced deep-learning models. These technologies have the potential to enhance data interpretation and support more effective clinical treatment strategies in the era of precision medicine.

Association of PD-L1 Expression with Lymph Node Metastasis and Clinical Stage in Ampulla of Vater Cancer: An Observational Study

Background

Ampulla of Vater cancer is a subtype of periampullary cancer originating from pancreatic ducts and the bile ducts. Immune checkpoint proteins, particularly Programmed Death-Ligand 1 (PD-L1), show a crucial function in influencing cancer progression, tumor microenvironment, and immune evasion. This study investigates the association between PD-L1 expression and clinical characteristics in patients with ampulla of Vater cancer.

Methods

A retrospective observational study was carried out at a general hospital in West Java, Indonesia, from July 2019 to June 2024. Forty-four patients diagnosed with ampulla of Vater cancer were included. PD-L1 expression was evaluated using immunohistochemistry, and clinicopathological data were analyzed using chi-square, Mann-Whitney, and independent t-tests.

Results

There were 44 research subject. The PD-L1 expression was positive in 59.1% of patients and negatively associated with carcinoembryonic antigen (CEA) levels (p = 0.010). There was a significant association between PD-L1 positivity and lymph node involvement (p = 0.042) and clinical stage (p = 0.017). No significant association was found between PD-L1 expression and age, sex, histopathological grade, or distant metastasis.

Conclusion

PD-L1 expression in ampulla of Vater cancer is significantly associated with higher lymph node metastasis and advanced clinical stage but not with age, sex, or tumor differentiation. These findings suggest PD-L1 as a potential prognostic marker and therapeutic target.

Automated Description Generation of Cytologic Findings for Lung Cytological Images Using a Pretrained Vision Model and Dual Text Decoders: Preliminary Study

OBJECTIVE

Cytology plays a crucial role in lung cancer diagnosis. Pulmonary cytology involves cell morphological characterisation in the specimen and reporting the corresponding findings, which are extremely burdensome tasks. In this study, we propose a technique to generate cytologic findings from for cytologic images to assist in the reporting of pulmonary cytology.

METHODS

For this study, 801 patch images were retrieved using cytology specimens collected from 206 patients; the findings were assigned to each image as a dataset for generating cytologic findings. The proposed method consists of a vision model and dual text decoders. In the former, a convolutional neural network (CNN) is used to classify a given image as benign or malignant, and the features related to the image are extracted from the intermediate layer. Independent text decoders for benign and malignant cells are prepared for text generation, and the text decoder switches according to the CNN classification results. The text decoder is configured using a transformer that uses the features obtained from the CNN for generating findings.

RESULTS

The sensitivity and specificity were 100% and 96.4%, respectively, for automated benign and malignant case classification, and the saliency map indicated characteristic benign and malignant areas. The grammar and style of the generated texts were confirmed correct, achieving a BLEU-4 score of 0.828, reflecting high degree of agreement with the gold standard, outperforming existing LLM-based image-captioning methods and single-text-decoder ablation model.

CONCLUSION

Experimental results indicate that the proposed method is useful for pulmonary cytology classification and generation of cytologic findings.

Ovarian Cancer Detection in Ascites Cytology with Weakly Supervised Model on Nationwide Dataset

Conventional ascitic fluid cytology for detecting ovarian cancer is limited by its low sensitivity. To address this issue, this multicenter study developed patch image (PI)-based fully supervised convolutional neural network (CNN) models and clustering-constrained attention multiple-instance learning (CLAM) algorithms for detecting ovarian cancer using ascitic fluid cytology. Whole-slide images (WSIs), 356 benign and 147 cancer, were collected, from which 14,699 benign and 8025 cancer PIs were extracted. Additionally, 131 WSIs (44 benign and 87 cancer) were used for external validation. Six CNN algorithms were developed for cancer detection using PIs. Subsequently, two CLAM algorithms, single branch (CLAM-SB) and multiple branch (CLAM-MB), were developed. ResNet50 demonstrated the best performance, achieving an accuracy of 0.973. The performance when interpreting internal WSIs was an area under the curve (AUC) of 0.982. CLAM-SB outperformed CLAM-MB with an AUC of 0.944 in internal WSIs. Notably, in the external test, CLAM-SB exhibited superior performance with an AUC of 0.866 compared with ResNet50's AUC of 0.804. Analysis of the heatmap revealed that cases frequently misinterpreted by AI were easily interpreted by humans, and vice versa. Because AI and humans were found to function complementarily, implementing computer-aided diagnosis is expected to significantly enhance diagnostic accuracy and reproducibility. Furthermore, the WSI-based learning in CLAM, eliminating the need for patch-by-patch annotation, offers an advantage over the CNN model.

Whole slide image-level classification of malignant effusion cytology using clustering-constrained attention multiple instance learning

BACKGROUND

Cytological diagnosis of pleural effusion plays an important role in the early detection and diagnosis of lung cancers. Recently, attempts have been made to overcome low diagnostic accuracy and interobserver variability using artificial intelligence-based image analysis. However, such analysis is primarily performed at the image-patch level and not at the whole-slide image (WSI) level. This study aims to develop a WSI-level classification of malignant effusions in metastatic lung cancer based on pleural fluid cytology using a quality-controlled, nationwide dataset.

METHODS

The dataset was collected by a consortium research group that included three major university hospitals and the Quality Assurance Program Committee of the Korean Society of Cytopathology. It contains 576 normal and 309 cancer WSIs from pleural fluids. A clustering-constrained attention multiple-instance learning (CLAM) model was used for WSI-level classification.

RESULTS

The CLAM model achieved a high accuracy of 97%, with an area under the curve of 0.97, representing a 13% improvement over the image patch classification model-based WSI classification. It also significantly reduced the analysis time and computing resources compared to those required during image patch-level classification and heat map generation on the WSIs.

CONCLUSION

The CLAM model successfully demonstrated high performance in differentiating malignant effusion at the WSI level using a large, quality-controlled, nationwide dataset. Further external validation is required to ensure generalizability.

Diagnosis Test Accuracy of Artificial Intelligence for Endometrial Cancer: Systematic Review and Meta-Analysis

BACKGROUND

Endometrial cancer is one of the most common gynecological tumors, and early screening and diagnosis are crucial for its treatment. Research on the application of artificial intelligence (AI) in the diagnosis of endometrial cancer is increasing, but there is currently no comprehensive meta-analysis to evaluate the diagnostic accuracy of AI in screening for endometrial cancer.

OBJECTIVE

This paper presents a systematic review of AI-based endometrial cancer screening, which is needed to clarify its diagnostic accuracy and provide evidence for the application of AI technology in screening for endometrial cancer.

METHODS

A search was conducted across PubMed, Embase, Cochrane Library, Web of Science, and Scopus databases to include studies published in English, which evaluated the performance of AI in endometrial cancer screening. A total of 2 independent reviewers screened the titles and abstracts, and the quality of the selected studies was assessed using the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) tool. The certainty of the diagnostic test evidence was evaluated using the Grading of Recommendations Assessment, Development, and Evaluation (GRADE) system.

RESULTS

A total of 13 studies were included, and the hierarchical summary receiver operating characteristic model used for the meta-analysis showed that the overall sensitivity of AI-based endometrial cancer screening was 86% (95% CI 79%-90%) and specificity was 92% (95% CI 87%-95%). Subgroup analysis revealed similar results across AI type, study region, publication year, and study type, but the overall quality of evidence was low.

CONCLUSIONS

AI-based endometrial cancer screening can effectively detect patients with endometrial cancer, but large-scale population studies are needed in the future to further clarify the diagnostic accuracy of AI in screening for endometrial cancer.

TRIAL REGISTRATION

PROSPERO CRD42024519835; https://www.crd.york.ac.uk/PROSPERO/view/CRD42024519835.

Immunocytes in the tumor microenvironment: recent updates and interconnections

The tumor microenvironment (TME) is a complex, dynamic ecosystem where tumor cells interact with diverse immune and stromal cell types. This review provides an overview of the TME's evolving composition, emphasizing its transition from an early pro-inflammatory, immune-promoting state to a later immunosuppressive milieu characterized by metabolic reprogramming and hypoxia. It highlights the dual roles of key immunocytes-including T lymphocytes, natural killer cells, macrophages, dendritic cells, and myeloid-derived suppressor cells-which can either inhibit or support tumor progression based on their phenotypic polarization and local metabolic conditions. The article further elucidates mechanisms of immune cell plasticity, such as the M1/M2 macrophage switch and the balance between effector T cells and regulatory T cells, underscoring their impact on tumor growth and metastasis. Additionally, emerging therapeutic strategies, including checkpoint inhibitors and chimeric antigen receptor (CAR) T and NK cell therapies, as well as approaches targeting metabolic pathways, are discussed as promising avenues to reinvigorate antitumor immunity. By integrating recent molecular insights and clinical advancements, the review underscores the importance of deciphering the interplay between immunocytes and the TME to develop more effective cancer immunotherapies.

Surveying the Digital Cytology Workflow in Italy: An Initial Report on AI Integration Across Key Professional Roles

BACKGROUND

The integration of artificial intelligence (AI) in healthcare, particularly in digital cytology, has the potential to enhance diagnostic accuracy and workflow efficiency. However, AI adoption remains limited due to technological and human-related barriers. Understanding the perceptions and experiences of healthcare professionals is essential for overcoming these challenges and facilitating effective AI implementation.

OBJECTIVES

This study aimed to assess AI integration in digital cytology workflows by evaluating professionals' perspectives on its benefits, challenges, and requirements for successful adoption.

METHODS

A survey was conducted among 150 professionals working in public and private healthcare settings in Italy, including laboratory technicians (35%), medical doctors (25%), biologists (20%), and specialists in diagnostic technical sciences (20%). Data were collected through a structured Computer-Assisted Web Interview (CAWI) and a Virtual Focus Group (VFG) to capture quantitative and qualitative insights on AI familiarity, perceived advantages, and barriers to adoption.

RESULTS

The findings indicated varying levels of AI familiarity among professionals. While many recognized AI's potential to improve diagnostic accuracy and streamline workflows, concerns were raised regarding resistance to change, implementation costs, and doubts about AI reliability. Participants emphasized the need for structured training and continuous support to facilitate AI adoption in digital cytology.

CONCLUSIONS

Addressing barriers such as resistance, cost, and trust is essential for the successful integration of AI in digital cytology workflows. Tailored training programs and ongoing professional support can enhance AI adoption, ultimately optimizing diagnostic processes and improving clinical outcomes.

Prospects for the application of pathological response rate in neoadjuvant therapy for gastric cancer

With the annual increase in the incidence and mortality rates of gastric cancer, it has gradually become one of the significant threats to human health. Approximately 90% of gastric cancer patients are diagnosed with adenocarcinoma. Although the 5-year survival rate for early-stage gastric cancer can exceed 90%, due to its concealed symptoms, less than half of the patients are eligible for radical surgical treatment upon diagnosis. For gastric cancer patients receiving palliative treatment, the current expected survival time is only about one year. In China, the majority of gastric cancer patients, accounting for about 80% of the total, are in the locally advanced stage. For these patients, radical surgery remains the primary treatment option; however, surgery alone is often inadequate in controlling tumor progression. In the pivotal MAGIC study, the recurrence rate was as high as 75%, and similar results were obtained in the French ACCORD07-FFCD9703 study. Numerous clinical trials are currently exploring preoperative neoadjuvant therapy for patients with locally advanced gastric cancer. Data indicates that preoperative neoadjuvant therapy can not only reduce the size of the local tumor but also shrink surrounding lymph nodes, thereby downstaging the tumor and improving the R0 resection rate. Additionally, it can decrease tumor cell activity and eliminate potential micrometastases. The emergence of various immunotherapies has ushered in a new era for neoadjuvant treatment options for gastric cancer.

Advancements in Digital Cytopathology Since COVID-19: Insights from a Narrative Review of Review Articles

Background/Objectives: The integration of digitalization in cytopathology is an emerging field with transformative potential, aiming to enhance diagnostic precision and operational efficiency. This narrative review of reviews (NRR) seeks to identify prevailing themes, opportunities, challenges, and recommendations related to the process of digitalization in cytopathology. Methods: Utilizing a standardized checklist and quality control procedures, this review examines recent advancements and future implications in this domain. Twenty-one review studies were selected through a systematic process. Results: The results highlight key emerging trends, themes, opportunities, challenges, and recommendations in digital cytopathology. First, the study identifies pivotal themes that reflect the ongoing technological transformation, guiding future focus areas in the field. A major trend is the integration of artificial intelligence (AI), which is increasingly critical in improving diagnostic accuracy, streamlining workflows, and assisting decision making. Notably, emerging AI technologies like large language models (LLMs) and chatbots are expected to provide real-time support and automate tasks, though concerns around ethics and privacy must be addressed. The reviews also emphasize the need for standardized protocols, comprehensive training, and rigorous validation to ensure AI tools are reliable and effective across clinical settings. Lastly, digital cytopathology holds significant potential to improve healthcare accessibility, especially in remote areas, by enabling faster, more efficient diagnoses and fostering global collaboration through telepathology. Conclusions: Overall, this study highlights the transformative impact of digitalization in cytopathology, improving diagnostic accuracy, efficiency, and global accessibility through tools like whole-slide imaging and telepathology. While artificial intelligence plays a significant role, the broader focus is on integrating digital solutions to enhance workflows and collaboration. Addressing challenges such as standardization, training, and ethical considerations is crucial to fully realize the potential of these advancements.

Integration of AI-Assisted in Digital Cervical Cytology Training: A Comparative Study

OBJECTIVE

This study aimed to investigate the supporting role of artificial intelligence (AI) in digital cervical cytology training.

METHODS

A total of 104 trainees completed both manual reading and AI-assisted reading tests following the AI-assisted digital training regimen. The interpretation scores and the testing time in different groups were compared. Also, the consistency, sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) of diagnoses were further analysed through the confusion matrix and inconsistency evaluation.

RESULTS

The mean interpretation scores were significantly higher in the AI-assisted group compared with the manual reading group (81.97 ± 16.670 vs. 67.98 ± 21.469, p < 0.001), accompanied by a reduction in mean interpretation time (32.13 ± 11.740 min vs. 11.36 ± 4.782 min, p < 0.001). The proportion of trainees' results with complete consistence (Category O) were improved from 0.645 to 0.803 and the averaged pairwise κ scores were improved from 0.535 (moderate) to 0.731 (good) with AI assistance. The number of correct answers, accuracies, sensitivities, specificities, PPV, NPV and κ scores of most class-specific diagnoses (NILM, Fungi, HSV, LSIL, HSIL, AIS, AC) also improved with AI assistance. Moreover, 97.8% (89/91) of trainees reported substantial improvement in cervical cytology interpretation ability, and all participants (100%, 91/91) expressed a strong willingness to integrate AI-assisted diagnosis into their future practice.

CONCLUSIONS

The utilisation of an AI-assisted digital cervical cytology training platform positively impacted trainee performance and received high satisfaction and acceptance among clinicians, suggesting its potential as a valuable adjunct to medical education.

Colorectal cancer classification using weakly annotated whole slide images: Multiple instance learning optimization study

Colorectal cancer (CRC) is considered one of the most deadly cancer types nowadays. It is rapidly increasing due to many factors, such as unhealthy lifestyles, water and food pollution, aging, and medical diagnosis development. Detecting CRC in its early stages can help stop its growth by providing the necessary treatments, thereby saving many people's lives. There are various tests that doctors can perform to diagnose CRC; however, biopsy using histopathological images is considered the "gold standard" for CRC diagnosis. Deep learning techniques can now be leveraged to build computer-aided diagnosis (CAD) systems that can affirm if an input sample shows any symptoms of cancer and determine its stage and location with an acceptable degree of confidence. In this research, we utilize deep learning to study the CRC classification problem using weakly annotated histopathological whole slide images (WSIs). We relax the constraints of the multiple instance learning (MIL) algorithm and primarily propose WSI-label prediction functions to be integrated with MIL, which significantly enhances the performance of WSI-level classification. We also applied efficient preprocessing techniques that output a computationally power-efficient dataset representation and performed multiple experiments to compose the most efficient CAD system. Our study introduces a notable improvement over the results obtained by the baseline research where we achieved an accuracy of 93.05% compared to 84.17%. Furthermore, our results using only the weakly annotated WSIs outperformed the baseline results that are based on performing initial pre-training using a strongly annotated part of the dataset.

Artificial intelligence for diagnosis and predictive biomarkers in Non-Small cell lung cancer Patients: New promises but also new hurdles for the pathologist

The rapid development of artificial intelligence (AI) based tools in pathology laboratories has brought forward unlimited opportunities for pathologists. Promising AI applications used for accomplishing diagnostic, prognostic and predictive tasks are being developed at a high pace. This is notably true in thoracic oncology, given the significant and rapid therapeutic progress made recently for lung cancer patients. Advances have been based on drugs targeting molecular alterations, immunotherapies, and, more recently antibody-drug conjugates which are soon to be introduced. For over a decade, many proof-of-concept studies have explored the use of AI algorithms in thoracic oncology to improve lung cancer patient care. However, despite the enthusiasm in this domain, the set-up and use of AI algorithms in daily practice of thoracic pathologists has not been operative until now, due to several constraints. The purpose of this review is to describe the potential but also the current barriers of AI applications in routine thoracic pathology for non-small cell lung cancer patient care and to suggest practical solutions for rapid future implementation.

Mismatch repair deficiency and its relationship with histopathological features in gastric cancer patients

Gastric cancer is a common malignancy disease with a poor prognosis. Deficient mismatch repair is a prognostic and predictive marker of response to systemic therapies. However, deficient mismatch repair frequency and the relationship between this status and microscopic characteristics are inconsistent across nations. We aimed to determine the rate of deficient mismatch repair and its association with histopathological features in gastric cancer patients. A cross-sectional study was conducted on 226 gastric cancer patients treated at Hue University of Medicine and Pharmacy Hospital and Hue Central Hospital from June 2020 to January 2024. Mismatch repair protein expression was evaluated using immunohistochemical staining, and any absence of mismatch repair proteins was regarded as deficient mismatch repair. The deficient mismatch repair rate was 12.8%. Deficient mismatch repair appeared to be more frequent in the intestinal subtype of Lauren classification odds ratio (OR) = 4.767 (95% confidence interval [CI], 1.086-20.921; p = 0.039), tubular/papillary adenocarcinoma (OR = 5.25; 95% CI, 1.185-23.251; p = 0.029), mucinous adenocarcinoma (OR = 6.19; 95% CI, 1.113-34.445; p = 0.037), and differentiated type (OR = 3.24; 95% CI, 1.324-7.931; p = 0.01). No statistically significant association was detected with histopathological features according to the Tumor Location-Modified Lauren classification and mucinous secreting morphology. Deficient mismatch repair status was unusual in gastric cancer. The degree of cell differentiation and microscopic characteristics based on the World Health Organization and Lauren classification could all impact the predictive power for microsatellite-instable status.

Tumor stroma ratio, tumor stroma maturity, tumor-infiltrating immune cells in relation to prognosis, and neoadjuvant therapy response in esophagogastric junction adenocarcinoma

Accurate predictions on prognosis and neoadjuvant therapy response are crucial for esophagogastric junction adenocarcinoma (EGJA) patients. Therefore, we aimed to investigate the predictive abilities of several indicators, including tumor stroma ratio (TSR), tumor stroma maturity (TSM), and the density and spatial distribution of tumor-infiltrating immune cells (TIICs), such as T cells, B cells, and tumor-associated macrophages (TAMs). Resection and biopsy specimens of a total of 695 patients were included, obtained from the National Cancer Center (NCC) and The Cancer Genome Atlas (TCGA) cohorts. TSR and TSM were evaluated based on histological assessment. TIICs were quantified by QuPath following immunohistochemical (IHC) staining in resection specimens, while the Klintrup-Mäkinen (KM) grade was employed for evaluating TIIC in biopsy specimens. Patients with high stromal levels or immature stroma had relatively worse prognoses. Furthermore, high CD8+T cell count in the tumor periphery, as well as low CD68+ TAM count either in the tumor center or in the tumor periphery, was an independent favorable prognostic factor. Significantly, the combination model incorporating TSM and CD163+TAMs emerged as an independent prognostic factor in both two independent cohorts (HR 3.644, 95% CI 1.341-9.900, p = 0.011 and HR 1.891, 95% CI 1.195-2.99, p = 0.006, respectively). Additionally, high stromal levels in preoperative biopsies correlated with poor neoadjuvant therapy response (p < 0.05). In conclusion, our findings suggest that TSR, TSM, CD8+T cell, CD68+TAMs, and CD163+TAMs predict the prognosis to some extent in patients with EGJA. Notably, the combined model incorporating TSM and CD163+TAM can contribute significantly to prognostic stratification. Additionally, high stromal levels evaluated in preoperative biopsy specimens correlated with poor neoadjuvant therapy response.

Therapeutic Targeting of PARP Expression and Glycolysis Rate-Limiting Enzymes in Breast Cancer Patients

BACKGROUND

Breast cancer is a heterogeneous disease characterized by diverse biochemical, histological, and clinical features. PARP1 and glycolysis rate-limiting enzymes play critical roles in cancer progression, making them promising therapeutic targets.

AIM

This study aimed to evaluate the expression levels of PARP1 and key glycolytic enzymes (HK, PFK, and PK) in breast cancer patients and assess their potential as therapeutic indicators.

MATERIALS AND METHODS

A total of 120 participants (60 breast cancer patients and 60 healthy controls) were included in the study. Blood samples were collected to measure PARP1 expression and the levels of glycolytic enzymes using ELISA. Statistical analyses were performed to compare the two groups.

RESULTS

PARP1 expression and glycolytic enzyme levels (HK, PFK, and PK) were significantly higher in breast cancer patients compared to healthy controls (p < 0.0001).

CONCLUSION

The overexpression of PARP1 and key glycolytic enzymes indicates their involvement in breast cancer progression and underscores their potential as therapeutic targets and biomarkers.

Development and validation of a deep learning model for morphological assessment of myeloproliferative neoplasms using clinical data and digital pathology

The subjectivity of morphological assessment and the overlapping pathological features of different subtypes of myeloproliferative neoplasms (MPNs) make accurate diagnosis challenging. To improve the pathological assessment of MPNs, we developed a diagnosis model (fusion model) based on the combination of bone marrow whole-slide images (deep learning [DL] model) and clinical parameters (clinical model). Thousand and fifty-one MPN and non-MPN patients were divided into the training, internal testing and one internal and two external validation cohorts (the combined validation cohort). In the combined validation cohort, fusion model achieved higher areas under curve (AUCs) than clinical or DL model or both for MPNs and subtype identification. Compared with haematopathologists with different experience, clinical model achieved AUC which was comparable to seniors and higher than juniors (p = 0.0208) for polycythaemia vera. The AUCs of fusion model were comparable to seniors and higher than juniors for essential thrombocytosis (p = 0.0141), prefibrotic primary myelofibrosis (p = 0.0085) and overt primary myelofibrosis (p = 0.0330) identification. In conclusion, the performances of our proposed models are equivalent to senior haematopathologists and better than juniors, providing a new perspective on the utilization of DL algorithms in MPN morphological assessment.

Automated recognition and segmentation of lung cancer cytological images based on deep learning

Compared with histological examination of lung cancer, cytology is less invasive and provides better preservation of complete morphology and detail. However, traditional cytological diagnosis requires an experienced pathologist to evaluate all sections individually under a microscope, which is a time-consuming process with low interobserver consistency. With the development of deep neural networks, the You Only Look Once (YOLO) object-detection model has been recognized for its impressive speed and accuracy. Thus, in this study, we developed a model for intraoperative cytological segmentation of pulmonary lesions based on the YOLOv8 algorithm, which labels each instance by segmenting the image at the pixel level. The model achieved a mean pixel accuracy and mean intersection over union of 0.80 and 0.70, respectively, on the test set. At the image level, the accuracy and area under the receiver operating characteristic curve values for malignant and benign (or normal) lesions were 91.0% and 0.90, respectively. In addition, the model was deemed suitable for diagnosing pleural fluid cytology and bronchoalveolar lavage fluid cytology images. The model predictions were strongly correlated with pathologist diagnoses and the gold standard, indicating the model's ability to make clinical-level decisions during initial diagnosis. Thus, the proposed method is useful for rapidly localizing lung cancer cells based on microscopic images and outputting image interpretation results.

Artificial Intelligence and Whole Slide Imaging Assist in Thyroid Indeterminate Cytology: A Systematic Review

INTRODUCTION

Thyroid cytopathology, particularly in cases of atypia of undetermined significance/follicular lesions of undetermined significance (AUS/FLUS), suffers from suboptimal sensitivity and specificity challenges. Recent advancements in digital pathology and artificial intelligence (AI) hold promise for enhancing diagnostic accuracy. This systematic review included studies that focused on diagnostic accuracy in AUS/FLUS cases using AI, whole slide imaging (WSI), or both.

METHODS

Of the 176 studies from 2000 to 2023, 13 met the inclusion criteria. The datasets range from 145 to 964 WSIs, with an overall number of 494 AUS cases ranging from eight to 254. Five studies used convolutional neural networks (CNNs), and two used artificial neural networks (ANNs). The preparation methods included Romanowsky-stained smears either alone or combined with Papanicolaou-stained or H&E and liquid-based cytology (ThinPrep). The scanner models that were used for scanning the slides varied, including Leica/Aperio, Alyuda Neurointelligence Cupertino, and PANNORAMIC™ Desk Scanner. Classifiers used include Feedforward Neural Networks (FFNNs), Two-Layer Feedforward Neural Networks (2L-FFNNs), Classifier Machine Learning Algorithm (MLA), Visual Geometry Group 11 (VGG11), Gradient Boosting Trees (GBT), Extra Trees Classifier (ETC), YOLOv4, EfficientNetV2-L, Back-Propagation Multi-Layer Perceptron (BP MLP), and MobileNetV2.

RESULTS

The available studies have shown promising results in differentiating between thyroid lesions, including AUS/FLUS. AI can be especially effective in removing sources of errors such as subjective assessment, variation in staining, and algorithms. CNN has been successful in processing WSI data and identifying diagnostic features with minimal human supervision. ANNs excelled in integrating structured clinical data with image-derived features, particularly when paired with WSI, enhancing diagnostic accuracy for indeterminate thyroid lesions.

CONCLUSION

A combined approach using both CNN and ANN can take advantage of their strengths. While AI and WSI integration shows promise in improving diagnostic accuracy and reducing uncertainty in indeterminate thyroid cytology, challenges such as the lack of standardization need to be addressed.

Deep learning methods for improving the accuracy and efficiency of pathological image analysis

This study presents a novel integration of two advanced deep learning models, U-Net and EfficientNetV2, to achieve high-precision segmentation and rapid classification of pathological images. A key innovation is the development of a new heatmap generation algorithm, which leverages meticulous image preprocessing, data enhancement strategies, ensemble learning, attention mechanisms, and deep feature fusion techniques. This algorithm not only produces highly accurate and interpretatively rich heatmaps but also significantly improves the accuracy and efficiency of pathological image analysis. Unlike existing methods, our approach integrates these advanced techniques into a cohesive framework, enhancing its ability to reveal critical features in pathological images. Rigorous experimental validation demonstrated that our algorithm excels in key performance indicators such as accuracy, recall rate, and processing speed, underscoring its potential for broader applications in pathological image analysis and beyond.

Deep learning model to diagnose cardiac amyloidosis from haematoxylin/eosin-stained myocardial tissue

Aims

Amyloid deposition in myocardial tissue is a definitive feature for diagnosing cardiac amyloidosis, though less invasive imaging modalities such as bone tracer cardiac scintigraphy and cardiac magnetic resonance imaging have been established as first steps for its diagnosis. This study aimed to develop a deep learning model to support the diagnosis of cardiac amyloidosis from haematoxylin/eosin (HE)-stained myocardial tissue.

Methods and results

This single-centre retrospective observational study enrolled 166 patients who underwent myocardial biopsies between 2008 and 2022, including 76 patients diagnosed with cardiac amyloidosis and 90 with other diagnoses. A deep learning model was developed to output the probabilities of cardiac amyloidosis for all the small patches cutout from each myocardial specimen. The developed model highlighted the area in the stained images as highly suspicious, corresponding to where Dylon staining marked amyloid deposition, and discriminated the patches in the evaluation dataset with an area under the curve of 0.965. Provided that the diagnostic criterion for cardiac amyloidosis was defined as a median probability of cardiac amyloidosis >50% in all patches, the model achieved perfect performance in discriminating patients with cardiac amyloidosis from those without it, with an area under the curve of 1.0.

Conclusion

A deep learning model was developed to diagnose cardiac amyloidosis from HE-stained myocardial tissue accurately. Although further prospective validation of this model using HE-stained myocardial tissues from multiple centres is needed, it may help minimize the risk of missing cardiac amyloidosis and maximize the utility of histological diagnosis in clinical practice.

Accuracy of machine learning in diagnosing microsatellite instability in gastric cancer: A systematic review and meta-analysis

BACKGROUND

Significant challenges persist in the early identification of microsatellite instability (MSI) within current clinical practice. In recent years, with the growing utilization of machine learning (ML) in the diagnosis and management of gastric cancer (GC), numerous researchers have explored the effectiveness of ML methodologies in detecting MSI. Nevertheless, the predictive value of these approaches still lacks comprehensive evidence. Accordingly, this study was carried out to consolidate the accuracy of ML in the prompt detection of MSI in GC.

METHODS

PubMed, the Cochrane Library, the Web of Science, and Embase were retrieved up to March 20, 2024. The risk of bias in the encompassed studies was evaluated utilizing a risk assessment tool for predictive models. Models were then subjected to subgroup analysis based on the modeling variables.

RESULTS

A total of 12 studies, encompassing 11,912 patients with GC, satisfied the predefined inclusion criteria. ML models established in these studies were primarily based on pathological images, clinical features, and radiomics. The results suggested that in the validation sets, the pathological image-based models had a synthesized c-index of 0.86 [95 % CI (0.83-0.89)], with sensitivity and specificity being 0.86 [95 % CI (0.76-0.92)] and 0.83 [95 % CI (0.78-0.87)], respectively; radiomics feature-based models achieved respective values of 0.87 [95 % CI (0.81-0.92)], 0.77 [95 % CI (0.70-0.83)] and 0.81 [95 % CI (0.74-0.87)]; radiomics feature-based models + clinical feature-based models achieved respective values of 0.87 [95 % CI (0.81-0.93)], 0.78 [95 % CI (0.70-0.84)] and 0.79 [95 % CI (0.69-0.86)].

CONCLUSIONS

ML has demonstrated optimal performance in detecting MSI in GC and could serve as a prospective early adjunctive detection tool for MSI in GC. Future research should contemplate minimally invasive or non-invasive, readily collectible, and efficient predictors to augment the predictive accuracy of ML.

State-of-the-art performance of deep learning methods for pre-operative radiologic staging of colorectal cancer lymph node metastasis: a scoping review

OBJECTIVES

To assess the current state-of-the-art in deep learning methods applied to pre-operative radiologic staging of colorectal cancer lymph node metastasis. Specifically, by evaluating the data, methodology and validation of existing work, as well as the current use of explainable AI in this fast-moving domain.

DESIGN

Scoping review.

DATA SOURCES

Academic databases MEDLINE, Embase, Scopus, IEEE Xplore, Web of Science and Google Scholar were searched with a date range of 1 January 2018 to 1 February 2024.

ELIGIBILITY CRITERIA

Includes any English language research articles or conference papers published since 2018 which have applied deep learning methods for feature extraction and classification of colorectal cancer lymph nodes on pre-operative radiologic imaging.

DATA EXTRACTION AND SYNTHESIS

Key results and characteristics for each included study were extracted using a shared template. A narrative synthesis was then conducted to qualitatively integrate and interpret these findings.

RESULTS

This scoping review covers 13 studies which met the inclusion criteria. The deep learning methods had an area under the curve score of 0.856 (0.796 to 0.916) for patient-level lymph node diagnosis and 0.904 (0.841 to 0.967) for individual lymph node assessment, given with a 95% confidence interval. Most studies have fundamental limitations including unrepresentative data, inadequate methodology, poor model validation and limited explainability techniques.

CONCLUSIONS

Deep learning methods have demonstrated the potential for accurately diagnosing colorectal cancer lymph nodes using pre-operative radiologic imaging. However, several methodological and validation flaws such as selection bias and lack of external validation make it difficult to trust the results. This review has uncovered a research gap for robust, representative and explainable deep learning methods that are end-to-end from automatic lymph node detection to the diagnosis of lymph node metastasis.

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.

Artificial intelligence in cytopathological applications for cancer: a review of accuracy and analytic validity

BACKGROUND

Cytopathological examination serves as a tool for diagnosing solid tumors and hematologic malignancies. Artificial intelligence (AI)-assisted methods have been widely discussed in the literature for increasing sensitivity, specificity and accuracy in the diagnosis of cytopathological clinical samples. Many of these tools are also used in clinical practice. There is a growing body of literature describing the role of AI in clinical settings, particularly in improving diagnostic accuracy and providing predictive and prognostic insights.

METHODS

A comprehensive search for this systematic review was conducted using databases Google, PUBMED (n = 450) and Google Scholar (n = 1067) with the keywords "Artificial Intelligence" AND "cytopathological" and "fine needle aspiration" AND "Deep Learning" AND "Machine Learning" AND "Hematologic Disorders" AND "Lung Cancer" AND "Pap Smear" and "cervical cancer screening" AND "Thyroid Cancer" AND "Breast Cancer" and "Sensitivity" and "Specificity". The search focused on literature reviews and systematic reviews published in English language between 2020 and 2024. PRISMA guidelines were adhered to with studies included and excluded as depicted in a flowchart. 417 results were screened with 34 studies were chosen for this review.

RESULTS

In the screening of patients with cervical cancer, bone marrow and peripheral blood smears and benign and malignant lesions in the lung, AI-assisted methods, particularly machine learning and deep learning (a subset of machine learning) methods, were applied to cytopathological data. These methods yielded greater diagnostic accuracy, specificity and sensitivity and decreased interobserver variability. Data sets were collected for both training and validation. Human machine combined performance was also found to be comparable to standalone performance in comparison with medical performance as well.

CONCLUSIONS

The use of AI in the analysis of cytopathological samples in research and clinical settings is increasing, and the involvement of pathologists in AI workflows is becoming increasingly important.

AI in Cytopathology: A Narrative Umbrella Review on Innovations, Challenges, and Future Directions

The integration of artificial intelligence (AI) in cytopathology is an emerging field with transformative potential, aiming to enhance diagnostic precision and operational efficiency. This umbrella review seeks to identify prevailing themes, opportunities, challenges, and recommendations related to AI in cytopathology. Utilizing a standardized checklist and quality control procedures, this review examines recent advancements and future implications of AI technologies in this domain. Twenty-one review studies were selected through a systematic process. AI has demonstrated promise in automating and refining diagnostic processes, potentially reducing errors and improving patient outcomes. However, several critical challenges need to be addressed to realize the benefits of AI fully. This review underscores the necessity for rigorous validation, ongoing empirical data on diagnostic accuracy, standardized protocols, and effective integration with existing clinical workflows. Ethical issues, including data privacy and algorithmic bias, must be managed to ensure responsible AI applications. Additionally, high costs and substantial training requirements present barriers to widespread AI adoption. Future directions highlight the importance of applying successful integration strategies from histopathology and radiology to cytopathology. Continuous research is needed to improve model interpretability, validation, and standardization. Developing effective strategies for incorporating AI into clinical practice and establishing comprehensive ethical and regulatory frameworks will be crucial for overcoming these challenges. In conclusion, while AI holds significant promise for advancing cytopathology, its full potential can only be achieved by addressing challenges related to validation, cost, and ethics. This review provides an overview of current advancements, identifies ongoing challenges, and offers a roadmap for the successful integration of AI into diagnostic cytopathology, informed by insights from related fields.

Optimization of diagnosis and treatment of hematological diseases via artificial intelligence

Background

Optimizing the diagnosis and treatment of hematological diseases is a challenging yet crucial research area. Effective treatment plans typically require the comprehensive integration of cell morphology, immunology, cytogenetics, and molecular biology. These plans also consider patient-specific factors such as disease stage, age, and genetic mutation status. With the advancement of artificial intelligence (AI), more "AI + medical" application models are emerging. In clinical practice, many AI-assisted systems have been successfully applied to the diagnosis and treatment of hematological diseases, enhancing precision and efficiency and offering valuable solutions for clinical practice.

Objective

This study summarizes the research progress of various AI-assisted systems applied in the clinical diagnosis and treatment of hematological diseases, with a focus on their application in morphology, immunology, cytogenetics, and molecular biology diagnosis, as well as prognosis prediction and treatment.

Methods

Using PubMed, Web of Science, and other network search engines, we conducted a literature search on studies from the past 5 years using the main keywords "artificial intelligence" and "hematological diseases." We classified the clinical applications of AI systems according to the diagnosis and treatment. We outline and summarize the current advancements in AI for optimizing the diagnosis and treatment of hematological diseases, as well as the difficulties and challenges in promoting the standardization of clinical diagnosis and treatment in this field.

Results

AI can significantly shorten turnaround times, reduce diagnostic costs, and accurately predict disease outcomes through applications in image-recognition technology, genomic data analysis, data mining, pattern recognition, and personalized medicine. However, several challenges remain, including the lack of AI product standards, standardized data, medical-industrial collaboration, and the complexity and non-interpretability of AI systems. In addition, regulatory gaps can lead to data privacy issues. Therefore, more research and improvements are needed to fully leverage the potential of AI to promote standardization of the clinical diagnosis and treatment of hematological diseases.

Conclusion

Our results serve as a reference point for the clinical diagnosis and treatment of hematological diseases and the development of AI-assisted clinical diagnosis and treatment systems. We offer suggestions for further development of AI in hematology and standardization of clinical diagnosis and treatment.

Diagnostic utility of transfer learning by using convolutional neural network for cytological diagnosis of malignant effusions

INTRODUCTION

Cytological analysis of effusion specimens provides critical information regarding the diagnosis and staging of malignancies, thus guiding their treatment and subsequent monitoring. Keeping in view the challenges encountered in the morphological interpretation, we explored convolutional neural networks (CNNs) as an important tool for the cytological diagnosis of malignant effusions.

MATERIALS AND METHODS

A retrospective review of patients at our institute, over 3.5 years yielded a dataset of 342 effusion samples and 518 images with known diagnoses. Cytological examination and cell block preparation were performed to establish correlation with the gold standard, histopathology. We developed a deep learning model using PyTorch, fine-tuned it on a labelled dataset, and evaluated its diagnostic performance using test samples.

RESULTS

The model exhibited encouraging results in the distinction of benign and malignant effusions with area under curve (AUC) of 0.8674, F-measure or F1 score which denotes the harmonic mean of precision and recall, to be 0.8678 thus, demonstrating optimal accuracy of our CNN model.

CONCLUSION

The study highlights the promising potential of transfer learning in enhancing the clinical pathology laboratory efficiency when dealing with malignant effusions.

Tumor budding in pre-neoadjuvant biopsy and post-neoadjuvant resection specimens is associated with poor prognosis in intrahepatic cholangiocarcinoma-a cohort study of 147 cases by modified ITBCC criteria

Tumor budding (TB) has been associated with poor survival in a variety of cancers including intrahepatic cholangiocarcinoma (iCCA). As tumor histomorphological features are significantly altered after neoadjuvant therapy (NAT), our study aims to assess the prognostic significance of TB in iCCA patients before and after NAT, by the modified International Tumor Budding Consensus Conference (ITBCC) criteria. 147 NAT-treated iCCA cases were included in this study. In biopsy specimens obtained before NAT, the TB-positive subgroup had lower overall survival (OS) in univariate analysis (P = 0.010). In resection specimens obtained after NAT, the TB-positive subgroup had reduced OS (P = 0.002) and recurrence-free survival (RFS) (P = 0.013) in univariate analysis. In multivariate analysis including TNM stage, lymphovascular invasion and perineural invasion, TB-positive in post-NAT resection was also found as an independent prognostic factor for both OS and RFS (OS, HR, 3.005; 95% CI, 1.333-6.775, P = 0.008; RFS, HR, 1.748; 95% CI, 1.085-2.816, P = 0.022). In conclusion, assessing the presence of TB by modified ITBCC criteria provides robust prognostic information in the NAT setting of iCCA patients and can be considered to be included in routine pathological reporting.

Artificial intelligence-based automated determination in breast and colon cancer and distinction between atypical and typical mitosis using a cloud-based platform

Artificial intelligence (AI) technology in pathology has been utilized in many areas and requires supervised machine learning. Notably, the annotations that define the ground truth for the identification of different confusing process pathologies, vary from study to study. In this study, we present our findings in the detection of invasive breast cancer for the IHC/ISH assessment system, along with the automated analysis of each tissue layer, cancer type, etc. in colorectal specimens. Additionally, models for the detection of atypical and typical mitosis in several organs were developed using existing whole-slide image (WSI) sets from other AI projects. All H&E slides were scanned by different scanners with a resolution of 0.12-0.50 μm/pixel, and then uploaded to a cloud-based AI platform. Convolutional neural networks (CNN) training sets consisted of invasive carcinoma, atypical and typical mitosis, and colonic tissue elements (mucosa-epithelium, lamina propria, muscularis mucosa, submucosa, muscularis propria, subserosa, vessels, and lymph nodes). In total, 59 WSIs from 59 breast cases, 217 WSIs from 54 colon cases, and 28 WSIs from 23 different types of tumor cases with relatively higher amounts of mitosis were annotated for the training. The harmonic average of precision and sensitivity was scored as F1 by AI. The final AI models of the Breast Project showed an F1 score of 94.49% for Invasive carcinoma. The mitosis project showed F1 scores of 80.18%, 97.40%, and 97.68% for mitosis, atypical, and typical mitosis layers, respectively. Overall F1 scores for the current results of the colon project were 90.02% for invasive carcinoma, 94.81% for the submucosa layer, and 98.02% for vessels and lymph nodes. After the training and optimization of the AI models and validation of each model, external validators evaluated the results of the AI models via blind-reader tasks. The AI models developed in this study were able to identify tumor foci, distinguish in situ areas, define colonic layers, detect vessels and lymph nodes, and catch the difference between atypical and typical mitosis. All results were exported for integration into our in-house applications for breast cancer and AI model development for both whole-block and whole-slide image-based 3D imaging assessment.

Applications of artificial intelligence in digital pathology for gastric cancer

Gastric cancer is one of the most common cancers and is one of the leading causes of cancer-related deaths in worldwide. Early diagnosis and treatment are essential for a positive outcome. The integration of artificial intelligence in the pathology field is increasingly widespread, including histopathological images analysis. In recent years, the application of digital pathology technology emerged as a potential solution to enhance the understanding and management of gastric cancer. Through sophisticated image analysis algorithms, artificial intelligence technologies facilitate the accuracy and sensitivity of gastric cancer diagnosis and treatment and personalized therapeutic strategies. This review aims to evaluate the current landscape and future potential of artificial intelligence in transforming gastric cancer pathology, so as to provide ideas for future research.

Image Analysis in Histopathology and Cytopathology: From Early Days to Current Perspectives

Both pathology and cytopathology still rely on recognizing microscopical morphologic features, and image analysis plays a crucial role, enabling the identification, categorization, and characterization of different tissue types, cell populations, and disease states within microscopic images. Historically, manual methods have been the primary approach, relying on expert knowledge and experience of pathologists to interpret microscopic tissue samples. Early image analysis methods were often constrained by computational power and the complexity of biological samples. The advent of computers and digital imaging technologies challenged the exclusivity of human eye vision and brain computational skills, transforming the diagnostic process in these fields. The increasing digitization of pathological images has led to the application of more objective and efficient computer-aided analysis techniques. Significant advancements were brought about by the integration of digital pathology, machine learning, and advanced imaging technologies. The continuous progress in machine learning and the increasing availability of digital pathology data offer exciting opportunities for the future. Furthermore, artificial intelligence has revolutionized this field, enabling predictive models that assist in diagnostic decision making. The future of pathology and cytopathology is predicted to be marked by advancements in computer-aided image analysis. The future of image analysis is promising, and the increasing availability of digital pathology data will invariably lead to enhanced diagnostic accuracy and improved prognostic predictions that shape personalized treatment strategies, ultimately leading to better patient outcomes.

A predictive model and rapid multi-dynamic algorithm developed based on tumor-stroma percentage in gastric cancer: a retrospective, observational study

Background

Tumor-stroma percentage (TSP) is a prognostic risk factor in numerous solid tumors. Despite this, the prognostic significance of TSP in gastric cancer (GC) remains underexplored. Through the development of a personalized predictive model and a semi-automatic identification system, our study aimed to fully unlock the predictive potential of TSP in GC.

Methods

We screened GC patients from Shanghai General Hospital (SGH) between 2012 and 2019 to develop and validate a nomogram. Univariate and multivariate Cox proportional hazards regression analyses were employed to identify independent prognostic factors influencing the prognosis for GC patients. The nomogram was further validated externally by using a cohort from Bengbu Medical College (BMC). All patients underwent radical gastrectomy, with those diagnosed with locally advanced GC receiving adjuvant chemotherapy. The primary outcome measured was overall survival (OS). The semi-automatic identification of the TSP was achieved through a computer-aided detection (CAD) system, denoted as TSP-cad, while TSP identified by pathologists was labeled as TSP-visual.

Results

A total of 813 GC patients from SGH and 59 from BMC were enrolled in our study. TSP-visual was identified as an adverse prognostic factor for OS in GC and was found to be associated with pathological Tumor Node Metastasis staging system (pTNM) stage, T stage, N stage, perineural invasion (PNI), lymphovascular invasion (LVI), TSP-visual, tumor size, and other factors. Multivariate Cox regression using the training cohort revealed that TSP-visual (hazard ratio [HR], 2.042; 95% confidential interval [CI], 1.485-2.806; P < 0.001), N stage (HR, 2.136; 95% CI, 1.343-3.397; P = 0.010), PNI (HR , 1.791; 95% CI, 1.270-2.526; P = 0.001), and LVI (HR, 1.482; 95% CI, 1.021-2.152; P = 0.039) were independent predictors. These factors were incorporated into a novel nomogram, which exhibited strong predictive accuracy for 5-year OS in the training, internal validation, and external validation cohorts (area under the curve = 0.744, 0.759, and 0.854, respectively). The decision curve analysis of the nomogram and concordance indexes across the three cohorts outperformed the traditional pTNM (P < 0.05). Additionally, TSP-cad assessment using a rapid multi-dynamic algorithm demonstrated good agreement with TSP-visual.

Conclusions

The novel nomogram based on TSP could effectively identify individuals at risk of a poor prognosis among patients with GC. TSP-cad is anticipated to enhance the evaluation process of TSP.

Model for detecting metastatic deposits in lymph nodes of colorectal carcinoma on digital/ non-WSI images

INTRODUCTION

Colorectal cancer (CRC) constitutes around 10% of global cancer diagnoses and death due to cancer. Treatment involves the surgical resection of the tumor and regional lymph nodes. Assessment of multiple lymph node demands meticulous examination by skilled pathologists, which can be arduous, prompting consideration for an artificial intelligence (AI)-supported workflow due to the growing number of slides to be examined, demanding heightened precision and the global shortage of pathologists.

METHOD

This was a retrospective cross-sectional study including digital images of glass slides containing sections of positive and negative lymph nodes obtained from radical resection of primary CRC. Lymph nodes from 165 previously diagnosed cases were selected from Agha Khan University Hospital, from Jan 2021 to Jan 2022. The images were prepared at 10X and uploaded into an open source software, Q path and deep learning model Ensemble was applied for the identification of tumor deposits in lymph node.

RESULTS

Out of the 87 positive lymph nodes detected by AI, 73(84%) were true positive and 14(16%) were false positive. The total number of negative lymph nodes detected by AI was 78. Out of these, 69(88.5%) were true negative and 9 (11.5%) were false negative. The sensitivity was 89% and specificity 83.1%. The odds ratio was 40 with a confidence interval of 16.26-98.3. P-value was < 0.05 (< 0.0001).

CONCLUSION

Though it was a small study but its results were really appreciating and we encourage more such studies with big sample data in future.

Poly (Adp-Ribose) Polymerase-1 (PARP-1) Is a Good Prognostic Marker for Pancreatic/Periampullary Cancers

BACKGROUND

Periampullary cancer (PAC) is highly aggressive with no effective adjuvant therapy or prognostic markers. Recently, poly (ADP-ribose) polymerase-1 (PARP-1) has emerged as a target in solid cancers, and its relationship with epithelial-mesenchymal transition (EMT) has been observed. However, the relationship between PARP-1 and EMT in PAC has not explored well.

MATERIALS AND METHODS

We assessed the prognostic significance of PARP-1 in 190 PACs patients and correlated it with EMT markers, including FGF8, FGFR4, MMP2, MMP3, Snail, and ZEB1. Immunohistochemistry for PARP-1 and EMT markers was performed using a tissue microarray.

RESULTS

PARP-1 and FGF8 expression were associated with better survival unlike other solid cancers ( P = 0.006 and P = 0.003), and MMP3 and ZEB1 expression were associated with poor prognosis in multivariate and survival analyses ( P = 0.009 and P < 0.001). In addition, PARP-1 is related negatively to Snail but not related with other EMT markers, implying an independent mechanism between PARP-1 and EMT in PACs. PARP-1 and FGF8 are independent good survival markers in PACs unlike other solid cancers.

CONCLUSIONS

PARP-1 and FGF8 in PACs could not be related to the EMT pathway but must be rather understood in light of similar cancer-protective roles. Further studies are required on EMT-associated immune markers in PACs.

Are the tumor microenvironment characteristics of pretreatment biopsy specimens of colorectal cancer really effectively predict the efficacy of neoadjuvant therapy: A retrospective multicenter study

More and more studies had pointed out that the tumor microenvironment characteristics based on colorectal cancer (CRC) pretreatment biopsy specimens could effectively predict the efficacy of neoadjuvant therapy, but under hematoxylin and eosin (HE) staining, whether the tumor microenvironment characteristics observed by pathologists could predict the efficacy of neoadjuvant therapy remains to be discussed. We collected 106 CRC patients who received neoadjuvant treatment and surgical resection from 3 hospitals. The number of mitosis, inflammation degree, desmoplastic reaction (DR), necrosis, tumor-stroma ratio (TSR) and tumor budding (TB) of CRC pretreatment biopsy specimens were observed under HE staining, and the degree of tumor pathological remission of CRC surgical specimens after neoadjuvant treatment was evaluated. According to the tumor regression grade (TRG), patients were divided into good-responders (TRG 0-1) and non-responders (TRG 2-3). All data were analyzed with SPSS software (version 23.0) to evaluate the correlation between the number of mitosis, inflammation degree, DR, necrosis, TSR and TB in pretreatment biopsy samples and the treatment effect. In univariate analysis, mitosis (P = .442), inflammation degree (P = .951), DR (P = .186), necrosis (P = .306), TSR (P = .672), and TB (P = .327) were not associated with the response to neoadjuvant therapy. However, we found that for colon cancer, rectal cancer was more likely to benefit from neoadjuvant therapy (P = .024). In addition, we further analyzed the impact of mitosis, inflammation degree, DR, necrosis, TSR and TB on neoadjuvant therapy in rectal cancer, and found that there was no predictive effect. By analyzing the characteristics of tumor microenvironment of CRC pretreatment biopsy specimens under HE staining, such as mitosis, inflammation degree, DR, necrosis, TSR and TB, it was impossible to effectively predict the efficacy of neoadjuvant therapy for CRC.

Artificial Intelligence Recognition Model Using Liquid-Based Cytology Images to Discriminate Malignancy and Histological Types of Non-Small-Cell Lung Cancer

INTRODUCTION

Artificial intelligence image recognition has applications in clinical practice. The purpose of this study was to develop an automated image classification model for lung cancer cytology using a deep learning convolutional neural network (DCNN).

METHODS

Liquid-based cytology samples from 8 normal parenchymal (N), 22 adenocarcinoma (ADC), and 15 squamous cell carcinoma (SQCC) surgical specimens were prepared, and 45 Papanicolaou-stained slides were scanned using whole-slide imaging. The final dataset of 9,141 patches consisted of 2,737 N, 4,756 ADC, and 1,648 SQCC samples. Densenet-121 was used as the DCNN to classify N versus malignant (ADC+SQCC) and ADC versus SQCC images. AdamW optimizer and 5-fold cross-validation were used in the training.

RESULTS

For malignancy prediction, the sensitivity, specificity, and accuracy were 0.97, 0.85, and 0.94, respectively, in the patch-level classification, and 0.92, 0.88, and 0.91, respectively, in the case-level classification. For SQCC prediction, the sensitivity, specificity, and accuracy were 0.86, 0.91, and 0.90, respectively, in the patch-level classification and 0.73, 0.82, and 0.78, respectively, in the case-level classification.

CONCLUSION

The DCNN model performed excellently in predicting malignancy and histological types of lung cancer. This model may be useful for predicting cytopathological diagnosis in clinical situations by reinforcing training.

Enhanced Immunohistochemistry Interpretation with a Machine Learning-Based Expert System

BACKGROUND

In recent decades, machine-learning (ML) technologies have advanced the management of high-dimensional and complex cancer data by developing reliable and user-friendly automated diagnostic tools for clinical applications. Immunohistochemistry (IHC) is an essential staining method that enables the identification of cellular origins by analyzing the expression of specific antigens within tissue samples. The aim of this study was to identify a model that could predict histopathological diagnoses based on specific immunohistochemical markers.

METHODS

The XGBoost learning model was applied, where the input variable (target variable) was the histopathological diagnosis and the predictors (independent variables influencing the target variable) were the immunohistochemical markers.

RESULTS

Our study demonstrated a precision rate of 85.97% within the dataset, indicating a high level of performance and suggesting that the model is generally reliable in producing accurate predictions.

CONCLUSIONS

This study demonstrated the feasibility and clinical efficacy of utilizing the probabilistic decision tree algorithm to differentiate tumor diagnoses according to immunohistochemistry profiles.

Deciphering the divergent transcriptomic landscapes of cervical cancer cells grown in 3D and 2D cell culture systems

Cervical cancer remains a significant health challenge for women worldwide, with a disproportionate impact on developing regions like sub-Saharan Africa. Taking advantage of recent advancements in developing suitable preclinical models to study cell proliferation, differentiation, and gene expression, we used RNA sequencing to compare the transcriptomic profiles of SiHa cervical cancer cells grown in 3D versus 2D culture systems. Pathway analysis of 3D cultures revealed upregulation of immune activation, angiogenesis, and tissue remodeling pathways. The high expression of cytokines, chemokines, matrix metalloproteinases, and immediate early genes, suggests that 3D cultures replicate the tumor microenvironment better than 2D monolayer cultures. HPV gene expression analysis further demonstrated higher expression levels of HPV16 E1, E2, E6, and E7 genes in 3D versus 2D cultures. Further, by using a set of linear models, we identified 79 significantly differentially expressed genes in 3D culture compared to 2D culture conditions, independent of HPV16 viral gene effects. We subsequently validated five of these genes at the protein level in both the SiHa cell line and a newly developed, patient-derived cervical cancer cell line. In addition, correlation analysis identified 26 human genes positively correlated with viral genes across 2D and 3D culture conditions. The top five 3D versus 2D differentially expressed and HPV-correlated genes were validated via qRT-PCR in our patient derived cell line. Altogether, these findings suggest that 3D cultures provide superior model systems to explore mechanisms of immune evasion, cancer progression and antiviral therapeutics.

Deciphering the Role of BRAFV600E Immunohistochemistry in Breast Lesions: A Comprehensive Review

The BRAFV600E mutation has been extensively studied in various cancers, but its role in breast lesions remains less understood. Immunohistochemistry (IHC) has emerged as a valuable tool for detecting BRAFV600E expression in breast tissue, aiding in diagnosis and prognosis. This comprehensive review examines the significance of BRAFV600E IHC in breast lesions, encompassing its frequency, association with clinicopathological features, and potential clinical implications. We summarize key findings, emphasizing their utility in diagnosis, prognosis prediction, and treatment response assessment. Additionally, we discuss implications for clinical practice, highlighting the need for integrating BRAFV600E IHC into diagnostic algorithms. Recommendations for future research include larger-scale studies to validate findings, optimize detection techniques, and explore therapeutic interventions targeting BRAFV600E in breast cancer. This review contributes to understanding the molecular landscape of breast lesions and informs clinical decision-making in their management.

Validation of digital image slides for diagnosis in cervico-vaginal cytology

OBJECTIVE

To test the diagnostic concordance between microscopic (MI) and digital (DG) observation of cervico-vaginal (CV) cytology in a validation study of the technique.

METHODS

Five cytotechnologists (CT) reviewed 888 routine CV cytology cases from the Cervical Pathology Unit of our center over a 2-week period of time. The cases were first observed by MI and at the end of the day the cases were observed by DG.

STATISTICAL ANALYSIS USED

Agreement calculated using the Kappa index.

RESULTS

Most of the diagnoses corresponded to benign (64%) or inflammatory conditions (14%) and 24% corresponded to the intraepithelial lesion or malignancy (ILM) category. The overall kappa coefficient of concordance was strong (0.87). Among the different CTs it was almost perfect in two, strong in two and moderate in one. In 18 cases (10%) there were discrepancies between techniques in the category of ILM. In 10 (56%) cases there was an overdiagnosis in DG and in 8 (44%) an overdiagnosis in MI. Only in two cases, the diagnostic discrepancy exceeded one degree of difference between lesions, and they were ASCUS or AGUS for DG and CIN 2 for MI.

CONCLUSIONS

In this validation test in which routine cases during a two-week period have been used, observing the cases with both techniques on the same day, we have obtained a strong degree of concordance. The discordances obtained have not been considered relevant.

Possible benefits, challenges, pitfalls, and future perspective of using ChatGPT in pathology

The much-hyped artificial intelligence (AI) model called ChatGPT developed by Open AI can have great benefits for physicians, especially pathologists, by saving time so that they can use their time for more significant work. Generative AI is a special class of AI model, which uses patterns and structures learned from existing data and can create new data. Utilizing ChatGPT in Pathology offers a multitude of benefits, encompassing the summarization of patient records and its promising prospects in Digital Pathology, as well as its valuable contributions to education and research in this field. However, certain roadblocks need to be dealt like integrating ChatGPT with image analysis which will act as a revolution in the field of pathology by increasing diagnostic accuracy and precision. The challenges with the use of ChatGPT encompass biases from its training data, the need for ample input data, potential risks related to bias and transparency, and the potential adverse outcomes arising from inaccurate content generation. Generation of meaningful insights from the textual information which will be efficient in processing different types of image data, such as medical images, and pathology slides. Due consideration should be given to ethical and legal issues including bias.

Revolutionizing Pathology with Artificial Intelligence: Innovations in Immunohistochemistry

Artificial intelligence (AI) is a reality of our times, and it has been successfully implemented in all fields, including medicine. As a relatively new domain, all efforts are directed towards creating algorithms applicable in most medical specialties. Pathology, as one of the most important areas of interest for precision medicine, has received significant attention in the development and implementation of AI algorithms. This focus is especially important for achieving accurate diagnoses. Moreover, immunohistochemistry (IHC) serves as a complementary diagnostic tool in pathology. It can be further augmented through the application of deep learning (DL) and machine learning (ML) algorithms for assessing and analyzing immunohistochemical markers. Such advancements can aid in delineating targeted therapeutic approaches and prognostic stratification. This article explores the applications and integration of various AI software programs and platforms used in immunohistochemical analysis. It concludes by highlighting the application of these technologies to pathologies such as breast, prostate, lung, melanocytic proliferations, and hematologic conditions. Additionally, it underscores the necessity for further innovative diagnostic algorithms to assist physicians in the diagnostic process.

RARPKB: a knowledge-guide decision support platform for personalized robot-assisted surgery in prostate cancer

BACKGROUND

Robot-assisted radical prostatectomy (RARP) has emerged as a pivotal surgical intervention for the treatment of prostate cancer (PCa). However, the complexity of clinical cases, heterogeneity of PCa, and limitations in physician expertise pose challenges to rational decision-making in RARP. To address these challenges, the authors aimed to organize the knowledge of previously complex cohorts and establish an online platform named the RARP knowledge base (RARPKB) to provide reference evidence for personalized treatment plans.

MATERIALS AND METHODS

PubMed searches over the past two decades were conducted to identify publications describing RARP. The authors collected, classified, and structured surgical details, patient information, surgical data, and various statistical results from the literature. A knowledge-guided decision-support tool was established using MySQL, DataTable, ECharts, and JavaScript. ChatGPT-4 and two assessment scales were used to validate and compare the platform.

RESULTS

The platform comprised 583 studies, 1589 cohorts, 1 911 968 patients, and 11 986 records, resulting in 54 834 data entries. The knowledge-guided decision support tool provide personalized surgical plan recommendations and potential complications on the basis of patients' baseline and surgical information. Compared with ChatGPT-4, RARPKB outperformed in authenticity (100% vs. 73%), matching (100% vs. 53%), personalized recommendations (100% vs. 20%), matching of patients (100% vs. 0%), and personalized recommendations for complications (100% vs. 20%). Postuse, the average System Usability Scale score was 88.88±15.03, and the Net Promoter Score of RARPKB was 85. The knowledge base is available at: http://rarpkb.bioinf.org.cn .

CONCLUSIONS

The authors introduced the pioneering RARPKB, the first knowledge base for robot-assisted surgery, with an emphasis on PCa. RARPKB can assist in personalized and complex surgical planning for PCa to improve its efficacy. RARPKB provides a reference for the future applications of artificial intelligence in clinical practice.