Artificial Intelligence Assists in the Detection of Blood Vessels in Whole Slide Images: Practical Benefits for Oncological Pathology

Multiple-Instance Learning for thyroid gland disease classification: A hands-on experience

The morphological diagnosis of thyroid gland neoplasms presents a dual challenge: it requires the expertise of highly trained specialists and considerable time, particularly when evaluating multiple whole slide images (WSIs) from a single patient. The integration of artificial intelligence (AI) techniques into the diagnostic workflow is a hot area of research. However, most studies rely on meticulously curated datasets, the preparation of which is both costly and fraught with complexities. This paper investigates the development of machine learning models using weakly-annotated "real-world" data, devoid of the selective preprocessing typical in common research datasets. Our study demonstrates that a Multiple-Instance Learning (MIL) model, trained on a weak patient-level annotations of 1102 patients encompassing 5104 WSIs, successfully discriminates between benign and malignant conditions at the patient level, achieving an average test set F1-Score of 0.85 with a standard deviation of 0.05. This study is, to our knowledge, the first to report findings from an AI model trained on patient-level data without prior labeling refinement. Additionally, we identify potential pitfalls in data quality that could induce model overfitting, such as the inadvertent inclusion of dye used to highlight resection margins, which correlates with the target variable. We also assessed the impact of detailed slide-level versus coarse patient-level annotations on classification accuracy using a smaller, more precisely annotated dataset of 36 laboratory cases (91 WSIs). The results indicate that detailed annotations substantially enhance classification performance in smaller datasets.

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.

Photoplethysmography-Based Angiography of Skin Tumors in Arbitrary Areas of Human Body

Noninvasive, rapid, and robust diagnostic techniques for clinical screening of tumors located in arbitrary areas of the human body are in demand. To address this challenge, we analyzed the feasibility of photoplethysmography-based angiography for assessing vascular structures within malignant and benign tumors. The proposed hardware and software were approved in a clinical study involving 30 patients with tumors located in the legs, torso, arms, and head. High-contrast and detailed vessel maps within both benign and malignant tumors were obtained. We demonstrated that capillary maps are consistent and can be interpreted using well-established dermoscopic criteria for vascular morphology. Vessel mapping provides valuable details, which may not be available in dermoscopic images and can aid in determining whether a tumor is benign or malignant. We believe that the proposed approach may become a valuable tool in the preliminary cancer diagnosis and is suitable for large-scale screening.

ML-driven segmentation of microvascular features during histological examination of tissue-engineered vascular grafts

Introduction

The development of next-generation tissue-engineered medical devices such as tissue-engineered vascular grafts (TEVGs) is a leading trend in translational medicine. Microscopic examination is an indispensable part of animal experimentation, and histopathological analysis of regenerated tissue is crucial for assessing the outcomes of implanted medical devices. However, the objective quantification of regenerated tissues can be challenging due to their unusual and complex architecture. To address these challenges, research and development of advanced ML-driven tools for performing adequate histological analysis appears to be an extremely promising direction.

Methods

We compiled a dataset of 104 representative whole slide images (WSIs) of TEVGs which were collected after a 6-month implantation into the sheep carotid artery. The histological examination aimed to analyze the patterns of vascular tissue regeneration in TEVGs in situ. Having performed an automated slicing of these WSIs by the Entropy Masker algorithm, we filtered and then manually annotated 1,401 patches to identify 9 histological features: arteriole lumen, arteriole media, arteriole adventitia, venule lumen, venule wall, capillary lumen, capillary wall, immune cells, and nerve trunks. To segment and quantify these features, we rigorously tuned and evaluated the performance of six deep learning models (U-Net, LinkNet, FPN, PSPNet, DeepLabV3, and MA-Net).

Results

After rigorous hyperparameter optimization, all six deep learning models achieved mean Dice Similarity Coefficients (DSC) exceeding 0.823. Notably, FPN and PSPNet exhibited the fastest convergence rates. MA-Net stood out with the highest mean DSC of 0.875, demonstrating superior performance in arteriole segmentation. DeepLabV3 performed well in segmenting venous and capillary structures, while FPN exhibited proficiency in identifying immune cells and nerve trunks. An ensemble of these three models attained an average DSC of 0.889, surpassing their individual performances.

Conclusion

This study showcases the potential of ML-driven segmentation in the analysis of histological images of tissue-engineered vascular grafts. Through the creation of a unique dataset and the optimization of deep neural network hyperparameters, we developed and validated an ensemble model, establishing an effective tool for detecting key histological features essential for understanding vascular tissue regeneration. These advances herald a significant improvement in ML-assisted workflows for tissue engineering research and development.

Application of an artificial intelligence for quantitative analysis of endothelial capillary beds in vitro

BACKGROUND

The use of endothelial cell cultures has become fundamental to study angiogenesis. Recent advances in artificial intelligences (AI) offer opportunities to develop automated assessment methods in medical research, analyzing larger datasets.

OBJECTIVE

The aim of this study was to compare the application of AI with a manual method to morphometrically quantify in vitro angiogenesis.

METHODS

Co-cultures of human microvascular endothelial cells and fibroblasts were incubated mimicking endothelial capillary-beds. An AI-software was trained for segmentation of endothelial capillaries on anti-CD31-labeled light microscope crops. Number of capillaries and branches and average capillary diameter were measured by the AI and manually on 115 crops.

RESULTS

The crops were analyzed faster by the AI than manually (3 minutes vs 1 hour per crop). Using the AI, systematically more capillaries (mean 48/mm2 vs 27/mm2) and branches (mean 23/mm2 vs 11/mm2) were counted than manually. Both methods had a strong linear relationship in counting capillaries and branches (r-capillaries = 0.88, r-branches = 0.89). No correlation was found for measurements of the diameter (r-diameter = 0.15).

CONCLUSIONS

The present AI reduces the time required for quantitative analysis of angiogenesis on large datasets, and correlates well with manual analysis.

A Comprehensive Look at In Vitro Angiogenesis Image Analysis Software

One of the complex challenges faced presently by tissue engineering (TE) is the development of vascularized constructs that accurately mimic the extracellular matrix (ECM) of native tissue in which they are inserted to promote vessel growth and, consequently, wound healing and tissue regeneration. TE technique is characterized by several stages, starting from the choice of cell culture and the more appropriate scaffold material that can adequately support and supply them with the necessary biological cues for microvessel development. The next step is to analyze the attained microvasculature, which is reliant on the available labeling and microscopy techniques to visualize the network, as well as metrics employed to characterize it. These are usually attained with the use of software, which has been cited in several works, although no clear standard procedure has been observed to promote the reproduction of the cell response analysis. The present review analyzes not only the various steps previously described in terms of the current standards for evaluation, but also surveys some of the available metrics and software used to quantify networks, along with the detection of analysis limitations and future improvements that could lead to considerable progress for angiogenesis evaluation and application in TE research.