Dataset Information

Image-Based Deep Learning Detection of High-Grade B-Cell Lymphomas Directly from Hematoxylin and Eosin Images.

ABSTRACT: Deep learning applications are emerging as promising new tools that can support the diagnosis and classification of different cancer types. While such solutions hold great potential for hematological malignancies, there have been limited studies describing the use of such applications in this field. The rapid diagnosis of double/triple-hit lymphomas (DHLs/THLs) involving MYC, BCL2 and/or BCL6 rearrangements is obligatory for optimal patient care. Here, we present a novel deep learning tool for diagnosing DHLs/THLs directly from scanned images of biopsy slides. A total of 57 biopsies, including 32 in a training set (including five DH lymphoma cases) and 25 in a validation set (including 10 DH/TH cases), were included. The DHL-classifier demonstrated a sensitivity of 100%, a specificity of 87% and an AUC of 0.95, with only two false positive cases, compared to FISH. The DHL-classifier showed a 92% predictive value as a screening tool for performing conventional FISH analysis, over-performing currently used criteria. The work presented here provides the proof of concept for the potential use of an AI tool for the identification of DH/TH events. However, more extensive follow-up studies are required to assess the robustness of this tool and achieve high performances in a diverse population.

SUBMITTER: Perry C

PROVIDER: S-EPMC10650414 | biostudies-literature | 2023 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Image-Based Deep Learning Detection of High-Grade B-Cell Lymphomas Directly from Hematoxylin and Eosin Images.

Perry Chava C Greenberg Orli O Haberman Shira S Herskovitz Neta N Gazy Inbal I Avinoam Assaf A Paz-Yaacov Nurit N Hershkovitz Dov D Avivi Irit I

Cancers 20231029 21

Deep learning applications are emerging as promising new tools that can support the diagnosis and classification of different cancer types. While such solutions hold great potential for hematological malignancies, there have been limited studies describing the use of such applications in this field. The rapid diagnosis of double/triple-hit lymphomas (DHLs/THLs) involving MYC, BCL2 and/or BCL6 rearrangements is obligatory for optimal patient care. Here, we present a novel dee ...[more]

PMID: 37958379

Similar Datasets

Project description:Single image super-resolution is an important computer vision task with applications including remote sensing, medical imaging, and surveillance. Modern work on super-resolution utilizes deep learning to synthesize high resolution (HR) images from low resolution images (LR). With the increased utilization of digitized whole slide images (WSI) in pathology workflows, digital pathology has emerged as a promising domain for super-resolution. Despite extensive existing research into super-resolution, there remain challenges specific to digital pathology. Here, we investigated image augmentation techniques for hematoxylin and eosin (H&E) WSI super-resolution and model generalizability across diverse tissue types. In addition, we investigated shortcomings with common quality metrics (peak signal-to-noise ratio (PSNR), structure similarity index (SSIM)) by conducting a perceptual quality survey for super-resolved pathology images. High performing deep super-resolution models were used to generate 20X HR images from LR images (5X or 10X equivalent) for 11 different tissues and 30 human evaluators were asked to score the quality of the generated versus the ground truth 20X HR images. The scores given by a human rater and the PSNR or the SSIM were compared to investigate the correlation between model training parameters. We found that models trained on multiple tissues generalized better than those trained on a single tissue type. We also found that PSNR correlated with perceptual quality (R = 0.26) less accurately than did SSIM (R = 0.64), suggesting that the SSIM quality metric is insufficient. The methods proposed in this study can be used to virtually magnify H&E images with better perceptual quality than interpolation methods (i.e., bicubic interpolation) commonly implemented in digital pathology software. The impact of deep SISR methods is more notable when scaling to 4X is needed, such as in the case of super-resolving a low magnification WSI from 10X to 40X.

Project description:Large-droplet macrovesicular steatosis (ld-MaS) in more than 30% of liver graft hepatocytes is a major risk factor for liver transplantation. An accurate assessment of the ld-MaS percentage is crucial for determining liver graft transplantability, which is currently based on pathologists' evaluations of hematoxylin and eosin (H&E)-stained liver histology specimens, with the predominant criteria being the relative size of the lipid droplets (LDs) and their propensity to displace a hepatocyte's nucleus to the cell periphery. Automated image analysis systems aimed at objectively and reproducibly quantifying ld-MaS do not accurately differentiate large LDs from small-droplet macrovesicular steatosis and do not take into account LD-mediated nuclear displacement; this leads to a poor correlation with pathologists' assessments. Here we present an improved image analysis method that incorporates nuclear displacement as a key image feature for segmenting and classifying ld-MaS from H&E-stained liver histology slides. 52,000 LDs in 54 digital images from 9 patients were analyzed, and the performance of the proposed method was compared against the performance of current image analysis methods and the ld-MaS percentage evaluations of 2 trained pathologists from different centers. We show that combining nuclear displacement and LD size information significantly improves the separation between large and small macrovesicular LDs (specificity?=?93.7%, sensitivity?=?99.3%) and the correlation with pathologists' ld-MaS percentage assessments (linear regression coefficient of determination?=?0.97). This performance vastly exceeds that of other automated image analyzers, which typically underestimate or overestimate pathologists' ld-MaS scores. This work demonstrates the potential of automated ld-MaS analysis in monitoring the steatotic state of livers. The image analysis principles demonstrated here may help to standardize ld-MaS scores among centers and ultimately help in the process of determining liver graft transplantability.

Dataset Information

Image-Based Deep Learning Detection of High-Grade B-Cell Lymphomas Directly from Hematoxylin and Eosin Images.

Publications

Image-Based Deep Learning Detection of High-Grade B-Cell Lymphomas Directly from Hematoxylin and Eosin Images.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets