The Potential of Artificial Intelligence to Detect Lymphovascular Invasion in Testicular Cancer

LVI-PathNet: Segmentation-classification pipeline for detection of lymphovascular invasion in whole slide images of lung adenocarcinoma

Lymphovascular invasion (LVI) in lung cancer is a significant prognostic factor that influences treatment and outcomes, yet its reliable detection is challenging due to interobserver variability. This study aims to develop a deep learning model for LVI detection using whole slide images (WSIs) and evaluate its effectiveness within a pathologist's information system. Experienced pathologists annotated blood vessels and invading tumor cells in 162 WSIs of non-mucinous lung adenocarcinoma sourced from two external and one internal datasets. Two models were trained to segment vessels and identify images with LVI features. DeepLabV3+ model achieved an Intersection-over-Union of 0.8840 and an area under the receiver operating characteristic curve (AUC-ROC) of 0.9869 in vessel segmentation. For LVI classification, the ensemble model achieved a F1-score of 0.9683 and an AUC-ROC of 0.9987. The model demonstrated robustness and was unaffected by variations in staining and image quality. The pilot study showed that pathologists' evaluation time for LVI detecting decreased by an average of 16.95%, and by 21.5% in "hard cases". The model facilitated consistent diagnostic assessments, suggesting potential for broader applications in detecting pathological changes in blood vessels and other lung pathologies.

EHMT2/G9a and EZH2: Epimarkers in testicular germ cell tumors

BACKGROUND

Testicular germ cell tumors remain the most frequent solid malignancies in young males. Despite excellent prognosis, the fact that only 60% of patients at diagnosis have elevated serum tumor markers (dependent on stage and histology) and the poor quality of life of patients who develop resistance to chemotherapy cannot be neglected. Consequently, it is mandatory to bring out novel biomarkers.

OBJECTIVES

The main goal was to evaluate EZH2 and EHMT2/G9a immunoexpression in a well-characterized patients' cohort of primary and metastatic testicular germ cell tumors, seeking associations with clinicopathological features and discovering differential immunoexpression patterns among specific subtypes.

MATERIALS AND METHODS

First, an in silico analysis of the Cancer Genome Atlas database was performed regarding EZH2 and EHMT2/G9a. Then, immunohistochemistry for EZH2 and EHMT2/G9a was carried out in a cohort of testicular germ cell tumor patients, comprising 155 chemo-naïve primary tumors and 11 chemo-treated metastases. Immunoexpression was evaluated using a digital pathology analysis software.

RESULTS

Higher EZH2 and EHMT2/G9a expression levels were found in non-seminoma in the in silico analysis, particularly in embryonal carcinoma. Through digital pathology analysis, non-seminomas showed significantly higher EZH2 and EHMT2/G9a immunoexpression, with embryonal carcinoma showing higher expression. Moreover, mixed tumors with 50% or more of embryonal carcinoma component revealed the highest nuclei positivity for both biomarkers. Cisplatin-exposed metastases demonstrated a higher EZH2-positive nuclei and H-score, as well as higher EHMT2/G9a-positive nuclei.

DISCUSSION AND CONCLUSION

Overall, our data suggest that EZH2 and EHMT2/G9a might be associated with greater aggressiveness and, eventually, involved in the metastatic setting, paving the way for testing targeted therapies.

Ensemble Deep Learning Model to Predict Lymphovascular Invasion in Gastric Cancer

Lymphovascular invasion (LVI) is one of the most important prognostic factors in gastric cancer as it indicates a higher likelihood of lymph node metastasis and poorer overall outcome for the patient. Despite its importance, the detection of LVI(+) in histopathology specimens of gastric cancer can be a challenging task for pathologists as invasion can be subtle and difficult to discern. Herein, we propose a deep learning-based LVI(+) detection method using H&E-stained whole-slide images. The ConViT model showed the best performance in terms of both AUROC and AURPC among the classification models (AUROC: 0.9796; AUPRC: 0.9648). The AUROC and AUPRC of YOLOX computed based on the augmented patch-level confidence score were slightly lower (AUROC: -0.0094; AUPRC: -0.0225) than those of the ConViT classification model. With weighted averaging of the patch-level confidence scores, the ensemble model exhibited the best AUROC, AUPRC, and F1 scores of 0.9880, 0.9769, and 0.9280, respectively. The proposed model is expected to contribute to precision medicine by potentially saving examination-related time and labor and reducing disagreements among pathologists.

A robust model training strategy using hard negative mining in a weakly labeled dataset for lymphatic invasion in gastric cancer

Gastric cancer is a significant public health concern, emphasizing the need for accurate evaluation of lymphatic invasion (LI) for determining prognosis and treatment options. However, this task is time-consuming, labor-intensive, and prone to intra- and interobserver variability. Furthermore, the scarcity of annotated data presents a challenge, particularly in the field of digital pathology. Therefore, there is a demand for an accurate and objective method to detect LI using a small dataset, benefiting pathologists. In this study, we trained convolutional neural networks to classify LI using a four-step training process: (1) weak model training, (2) identification of false positives, (3) hard negative mining in a weakly labeled dataset, and (4) strong model training. To overcome the lack of annotated datasets, we applied a hard negative mining approach in a weakly labeled dataset, which contained only final diagnostic information, resembling the typical data found in hospital databases, and improved classification performance. Ablation studies were performed to simulate the lack of datasets and severely unbalanced datasets, further confirming the effectiveness of our proposed approach. Notably, our results demonstrated that, despite the small number of annotated datasets, efficient training was achievable, with the potential to extend to other image classification approaches used in medicine.

Deep Learning for Subtypes Identification of Pure Seminoma of the Testis

The most critical step in the clinical diagnosis workflow is the pathological evaluation of each tumor sample. Deep learning is a powerful approach that is widely used to enhance diagnostic accuracy and streamline the diagnosis process. In our previous study using omics data, we identified 2 distinct subtypes of pure seminoma. Seminoma is the most common histological type of testicular germ cell tumors (TGCTs). Here we developed a deep learning decision making tool for the identification of seminoma subtypes using histopathological slides. We used all available slides for pure seminoma samples from The Cancer Genome Atlas (TCGA). The developed model showed an area under the ROC curve of 0.896. Our model not only confirms the presence of 2 distinct subtypes within pure seminoma but also unveils the presence of morphological differences between them that are imperceptible to the human eye.

Built to Last? Reproducibility and Reusability of Deep Learning Algorithms in Computational Pathology

Recent progress in computational pathology has been driven by deep learning. While code and data availability are essential to reproduce findings from preceding publications, ensuring a deep learning model's reusability is more challenging. For that, the codebase should be well-documented and easy to integrate into existing workflows and models should be robust toward noise and generalizable toward data from different sources. Strikingly, only a few computational pathology algorithms have been reused by other researchers so far, let alone employed in a clinical setting. To assess the current state of reproducibility and reusability of computational pathology algorithms, we evaluated peer-reviewed articles available in PubMed, published between January 2019 and March 2021, in 5 use cases: stain normalization; tissue type segmentation; evaluation of cell-level features; genetic alteration prediction; and inference of grading, staging, and prognostic information. We compiled criteria for data and code availability and statistical result analysis and assessed them in 160 publications. We found that only one-quarter (41 of 160 publications) made code publicly available. Among these 41 studies, three-quarters (30 of 41) analyzed their results statistically, half of them (20 of 41) released their trained model weights, and approximately a third (16 of 41) used an independent cohort for evaluation. Our review is intended for both pathologists interested in deep learning and researchers applying algorithms to computational pathology challenges. We provide a detailed overview of publications with published code in the field, list reusable data handling tools, and provide criteria for reproducibility and reusability.

Artificial Intelligence in Urooncology: What We Have and What We Expect

INTRODUCTION

Artificial intelligence is transforming healthcare by driving innovation, automation, and optimization across various fields of medicine. The aim of this study was to determine whether artificial intelligence (AI) techniques can be used in the diagnosis, treatment planning, and monitoring of urological cancers.

METHODOLOGY

We conducted a thorough search for original and review articles published until 31 May 2022 in the PUBMED/Scopus database. Our search included several terms related to AI and urooncology. Articles were selected with the consensus of all authors.

RESULTS

Several types of AI can be used in the medical field. The most common forms of AI are machine learning (ML), deep learning (DL), neural networks (NNs), natural language processing (NLP) systems, and computer vision. AI can improve various domains related to the management of urologic cancers, such as imaging, grading, and nodal staging. AI can also help identify appropriate diagnoses, treatment options, and even biomarkers. In the majority of these instances, AI is as accurate as or sometimes even superior to medical doctors.

CONCLUSIONS

AI techniques have the potential to revolutionize the diagnosis, treatment, and monitoring of urologic cancers. The use of AI in urooncology care is expected to increase in the future, leading to improved patient outcomes and better overall management of these tumors.

The Present and Future of Artificial Intelligence in Urological Cancer

Artificial intelligence has drawn more and more attention for both research and application in the field of medicine. It has considerable potential for urological cancer detection, therapy, and prognosis prediction due to its ability to choose features in data to complete a particular task autonomously. Although the clinical application of AI is still immature and faces drawbacks such as insufficient data and a lack of prospective clinical trials, AI will play an essential role in individualization and the whole management of cancers as research progresses. In this review, we summarize the applications and studies of AI in major urological cancers, including tumor diagnosis, treatment, and prognosis prediction. Moreover, we discuss the current challenges and future applications of AI.

Biomarkers of disease recurrence in stage I testicular germ cell tumours

Stage I testicular cancer is a disease restricted to the testicle. After orchiectomy, patients are considered to be without disease; however, the tumour is prone to relapse in ~4-50% of patients. Current predictive markers of relapse, which are tumour size and invasion to rete testis (in seminoma) or lymphovascular invasion (in non-seminoma), have limited clinical utility and are unable to correctly predict relapse in a substantial proportion of patients. Adjuvant therapeutic strategies based on available biomarkers can lead to overtreatment of 50-85% of patients. Discovery and implementation of novel biomarkers into treatment decision making will help to reduce the burden of adjuvant treatments and improve patient selection for adjuvant therapy.

Multi-modality artificial intelligence in digital pathology

In common medical procedures, the time-consuming and expensive nature of obtaining test results plagues doctors and patients. Digital pathology research allows using computational technologies to manage data, presenting an opportunity to improve the efficiency of diagnosis and treatment. Artificial intelligence (AI) has a great advantage in the data analytics phase. Extensive research has shown that AI algorithms can produce more up-to-date and standardized conclusions for whole slide images. In conjunction with the development of high-throughput sequencing technologies, algorithms can integrate and analyze data from multiple modalities to explore the correspondence between morphological features and gene expression. This review investigates using the most popular image data, hematoxylin-eosin stained tissue slide images, to find a strategic solution for the imbalance of healthcare resources. The article focuses on the role that the development of deep learning technology has in assisting doctors' work and discusses the opportunities and challenges of AI.

Decoding germ cell tumours for clinicians

PURPOSE OF REVIEW

Germ-cell tumours of the testis affect predominantly younger males aged between 15 and 40 years, with nearly 74,500 new cases estimated globally in 2020. Their rarity and the complex morphology, mean that, in nonexpert hands, there is a significant risk of misdiagnosis of both type and staging of these neoplasms.

RECENT FINDINGS

There have been significant changes in the 2016 WHO classification of Testicular tumours that need to be understood by both pathologists and clinicians for streamlining management. Standardised structured reporting guidelines and discussion at the multidisciplinary-team meetings lead to subsequently better health outcomes and patient safety.

SUMMARY

Therefore, communication with high-quality reports and understanding of clinicians of what constitutes an adequate report, is the key to ensure proper management of these patients. We attempt to discuss the key updates and pathological features that influence management and need to be communicated with clarity and precision.

Digital Pathology Transformation in a Supraregional Germ Cell Tumour Network

Background: In this article we share our experience of creating a digital pathology (DP) supraregional germ cell tumour service, including full digitisation of the central laboratory. Methods: DP infrastructure (Philips) was deployed across our hospital network to allow full central digitisation with partial digitisation of two peripheral sites in the supraregional testis germ cell tumour network. We used a survey-based approach to capture the quantitative and qualitative experiences of the multidisciplinary teams involved. Results: The deployment enabled case sharing for the purposes of diagnostic reporting, second opinion, and supraregional review. DP was seen as a positive step forward for the departments involved, and for the wider germ cell tumour network, and was completed without significant issues. Whilst there were challenges, the transition to DP was regarded as worthwhile, and examples of benefits to patients are already recognised. Conclusion: Pathology networks, including highly specialised services, such as in this study, are ideally suited to be digitised. We highlight many of the benefits but also the challenges that must be overcome for such clinical transformation. Overall, from the survey, the change was seen as universally positive for our service and highlights the importance of engagement of the whole team to achieve success.