Artificial intelligence based liver portal tract region identification and quantification with transplant biopsy whole-slide images

Yu, Hanyi; Sharifai, Nima; Jiang, Kun; Wang, Fusheng; Teodoro, George; Farris, Alton B.; Kong, Jun

doi:10.1016/j.compbiomed.2022.106089

Cited by 8 publications

(6 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Their study was chiefly limited by a small sample of donor liver from a single institution and the presence of selection bias in the test for association with EAD. Yu et al [ 51 ] designed a Multiple Up-sampling and Spatial Attention guided UNet model (MUSA-UNet) to segment liver portal tract regions in liver WSI that correlates with the stage of liver fibrosis. The dataset consisted of 53 WSIs, 30 of which were used for training and 23 for testing.…”

Section: Resultsmentioning

confidence: 99%

Artificial Intelligence Advances in Transplant Pathology

Rahman,

Yilmaz,

Albadri

et al. 2023

Bioengineering

View full text Add to dashboard Cite

Transplant pathology plays a critical role in ensuring that transplanted organs function properly and the immune systems of the recipients do not reject them. To improve outcomes for transplant recipients, accurate diagnosis and timely treatment are essential. Recent advances in artificial intelligence (AI)-empowered digital pathology could help monitor allograft rejection and weaning of immunosuppressive drugs. To explore the role of AI in transplant pathology, we conducted a systematic search of electronic databases from January 2010 to April 2023. The PRISMA checklist was used as a guide for screening article titles, abstracts, and full texts, and we selected articles that met our inclusion criteria. Through this search, we identified 68 articles from multiple databases. After careful screening, only 14 articles were included based on title and abstract. Our review focuses on the AI approaches applied to four transplant organs: heart, lungs, liver, and kidneys. Specifically, we found that several deep learning-based AI models have been developed to analyze digital pathology slides of biopsy specimens from transplant organs. The use of AI models could improve clinicians’ decision-making capabilities and reduce diagnostic variability. In conclusion, our review highlights the advancements and limitations of AI in transplant pathology. We believe that these AI technologies have the potential to significantly improve transplant outcomes and pave the way for future advancements in this field.

show abstract

Section: Resultsmentioning

confidence: 99%

Artificial Intelligence Advances in Transplant Pathology

Rahman,

Yilmaz,

Albadri

et al. 2023

Bioengineering

View full text Add to dashboard Cite

show abstract

“…It is noteworthy that the single-stage Unet model and its variants are easily trainable with few annotated images, and they typically do not overfit. However, for high-resolution images, such as whole-slide images (WSI), where the dimensions of the medical images are a few thousand pixels per side, resizing such images to smaller dimensions to fit a Unet model or its variants may result in poor segmentation results [38]. In such scenarios, splitting the images into smaller patches, followed by training the Unet model and its variants, can improve the segmentation performance, as shown in [21].…”

Section: Discussionmentioning

confidence: 99%

NUMSnet: Nested-U Multi-Class Segmentation Network for 3D Medical Image Stacks

Roychowdhury

2023

Information

View full text Add to dashboard Cite

The semantic segmentation of 3D medical image stacks enables accurate volumetric reconstructions, computer-aided diagnostics and follow-up treatment planning. In this work, we present a novel variant of the Unet model, called the NUMSnet, that transmits pixel neighborhood features across scans through nested layers to achieve accurate multi-class semantic segmentation with minimal training data. We analyzed the semantic segmentation performance of the NUMSnet model in comparison with several Unet model variants in the segmentation of 3–7 regions of interest using only 5–10% of images for training per Lung-CT and Heart-CT volumetric image stack. The proposed NUMSnet model achieves up to 20% improvement in segmentation recall, with 2–9% improvement in Dice scores for Lung-CT stacks and 2.5–16% improvement in Dice scores for Heart-CT stacks when compared to the Unet++ model. The NUMSnet model needs to be trained with ordered images around the central scan of each volumetric stack. The propagation of image feature information from the six nested layers of the Unet++ model are found to have better computation and segmentation performance than the propagation of fewer hidden layers or all ten up-sampling layers in a Unet++ model. The NUMSnet model achieves comparable segmentation performance to previous works while being trained on as few as 5–10% of the images from 3D stacks. In addition, transfer learning allows faster convergence of the NUMSnet model for multi-class semantic segmentation from pathology in Lung-CT images to cardiac segmentation in Heart-CT stacks. Thus, the proposed model can standardize multi-class semantic segmentation for a variety of volumetric image stacks with a minimal training dataset. This can significantly reduce the cost, time and inter-observer variability associated with computer-aided detection and treatment.

show abstract

“…Twenty articles were reviewed through full text screening (Table 3) [34][35][36][37][38][39][40][41][42][43][44][45][46][47][48][49][50][51][52][53]. As for tumoral studies, none used prospectively collected data.…”

Section: Non-tumoralmentioning

confidence: 99%

“…As for tumoral studies, none used prospectively collected data. The algorithms primary goal was either segmentation (4/20) [34][35][36][37], classification (15/20) [38][39][40][41][42][43][44][45][46][47][48][49][50][51][52] or prediction (1/20) [53]. The most prevalent thematic included inflammation detection and quantification, especially in Non-Alcoholic SteatoHepatitis (NASH) (6/20) and fibrosis detection and grading (4/20).…”

Section: Non-tumoralmentioning

confidence: 99%

Artificial Intelligence-Based Opportunities in Liver Pathology—A Systematic Review

et al. 2023

View full text Add to dashboard Cite

Background: Artificial Intelligence (AI)-based Deep Neural Networks (DNNs) can handle a wide range of applications in image analysis, ranging from automated segmentation to diagnostic and prediction. As such, they have revolutionized healthcare, including in the liver pathology field. Objective: The present study aims to provide a systematic review of applications and performances provided by DNN algorithms in liver pathology throughout the Pubmed and Embase databases up to December 2022, for tumoral, metabolic and inflammatory fields. Results: 42 articles were selected and fully reviewed. Each article was evaluated through the Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) tool, highlighting their risks of bias. Conclusions: DNN-based models are well represented in the field of liver pathology, and their applications are diverse. Most studies, however, presented at least one domain with a high risk of bias according to the QUADAS-2 tool. Hence, DNN models in liver pathology present future opportunities and persistent limitations. To our knowledge, this review is the first one solely focused on DNN-based applications in liver pathology, and to evaluate their bias through the lens of the QUADAS2 tool.

show abstract

Artificial intelligence based liver portal tract region identification and quantification with transplant biopsy whole-slide images

Cited by 8 publications

References 40 publications

Artificial Intelligence Advances in Transplant Pathology

Artificial Intelligence Advances in Transplant Pathology

NUMSnet: Nested-U Multi-Class Segmentation Network for 3D Medical Image Stacks

Artificial Intelligence-Based Opportunities in Liver Pathology—A Systematic Review

Contact Info

Product

Resources

About