Deep Learning Accurately Quantifies Plasma Cell Percentages on CD138-Stained Bone Marrow Samples

Fu, Fred; Guenther, Angela; Sakhdari, Ali; McKee, Trevor D.; Xia, Daniel

doi:10.1016/j.jpi.2022.100011

Cited by 6 publications

(4 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors used an Aperio ScanScope XT scanner (Aperio Technologies, California, USA) for digitisation to generate whole-slide images (WSI) for the study. A similar study was done by Fu et al 16 using WSI.…”

Section: Introductionsupporting

confidence: 55%

“…19 Fu et al, have developed a web application that applies their developed convolutional neural network (CNN), which allows pathologists to upload single images from microscope cameras to obtain a percentage of plasma cells in real time based on the CD138-stained plasma cells on that image. 16 This technology could be used in resource-limited laboratories as an alternative to WSI if our method for selecting representative areas is included.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Evaluation of a new technique using artificial intelligence for quantification of plasma cells on CD138 immunohistochemistry

Gantana,

Nell,

Musekwa

et al. 2023

Int J Lab Hematology

View full text Add to dashboard Cite

IntroductionThe diagnosis of plasma cell neoplasms depends on the accurate quantification of plasma cells, traditionally done by immunohistochemical CD138 staining of bone marrow biopsies. Currently, there is no fully satisfactory reference method for this quantification. In our previous study, we compared the commonly used overview estimation method (method A) with a novel method for counting plasma cells in three representative areas (method B). Results showed comparable concordance parameters between the two methods. In this follow‐up study, we compared the previously evaluated methods with a digital analysis method (method C) that uses artificial intelligence in open‐source software, QuPath.MethodsArchived CD138 immunohistochemically stained trephine sections of bone marrow samples used in our previous study were used (n = 33). Reviewers selected three representative areas on each sample by taking images with a light microscope and camera. Digital analysis was performed using the positive cell detection function in QuPath. The entire process was repeated by each reviewer to test intraobserver concordance (concordance correlation coefficient [CCC]) in addition to interobserver concordance (intraclass correlation coefficient [ICC]).ResultsIntraobserver concordance of method C showed strong agreement for all reviewers with the lowest CCC = 0.854. Interobserver concordance for method C using ICC was 0.909 and 0.949. This showed high interobserver agreement with significant differences between method C and previously assessed method A (ICC = 0.793 and 0.713) and method B (ICC = 0.657 and 0.658).ConclusionWe were able to successfully count CD138‐positive plasma cells in bone marrow biopsies using artificial intelligence. This method is superior to both manual counting and overview estimation, regardless of tumour load.

show abstract

Section: Introductionsupporting

confidence: 55%

Section: Discussionmentioning

confidence: 99%

Evaluation of a new technique using artificial intelligence for quantification of plasma cells on CD138 immunohistochemistry

Gantana,

Nell,

Musekwa

et al. 2023

Int J Lab Hematology

View full text Add to dashboard Cite

show abstract

“…The evaluation of histology is, however, much more complex due to tissue architecture and the variation in object shape due to cutting effects. First attempts using ML have been made to identify and enumerate a single-cell lineage that was stained with specific antibodies, e.g., plasma cells (CD138) [ 15 , 16 ], or lymphoid and plasma cells (CD3, CD20, CD138, MUM1) [ 17 ]. More advanced studies used the morphological features in H&E-stained WSIs, without the addition of immunohistochemical stains, to discriminate between megakaryocytes, erythroid, and myeloid cells in patients with myeloproliferative disease [ 18 , 19 , 20 ].…”

Section: Applications Of Ai To Bm Histologymentioning

confidence: 99%

Artificial Intelligence in Bone Marrow Histological Diagnostics: Potential Applications and Challenges

2023

View full text Add to dashboard Cite

The expanding digitalization of routine diagnostic histological slides holds a potential to apply artificial intelligence (AI) to pathology, including bone marrow (BM) histology. In this perspective we describe potential tasks in diagnostics that can be supported, investigations that can be guided and questions that can be answered by the future application of AI on whole slide images of BM biopsies. These range from characterization of cell lineages and quantification of cells and stromal structures to disease prediction. First glimpses show an exciting potential to detect subtle phenotypic changes with AI that are due to specific genotypes. The discussion is illustrated by examples of current AI research using BM biopsy slides. In addition, we briefly discuss current challenges for implementation of AI-supported diagnostics.

show abstract

“…In terms of method fusion, a cell segmentation model combines marker-controlled watershed transform and deep learning methods [20]. For the problem of bone marrow cell identification and segmentation, there are also many related studies experimenting with deep learning methods, such as [21], which proposed to identify and segment CD138+ and CD138-stained cells in bone marrow cells using a semantic segmentation-based convolutional neural network.The authors in [4] proposed to use a YOLOv5 network-based bone marrow cell detection algorithm, trained by minimizing a novel loss function, and the results show that the proposed loss function effectively improves the performance of the algorithm. Ref.…”

Section: Introductionmentioning

confidence: 99%

GCT-UNET: U-Net Image Segmentation Model for a Small Sample of Adherent Bone Marrow Cells Based on a Gated Channel Transform Module

et al. 2022

View full text Add to dashboard Cite

Pathological diagnosis is considered to be declarative and authoritative. However, reading pathology slides is a challenging task. Different parts of the section are taken and read for different purposes and with different focuses, which further adds difficulty to the pathologist’s diagnosis. In recent years, the deep neural network has made great progress in the direction of computer vision and the main approach to image segmentation is the use of convolutional neural networks, through which the spatial properties of the data are captured. Among a wide variety of different network structures, one of the more representative ones is UNET with encoder and decoder structures. The biggest advantage of traditional UNET is that it can still perform well with a small number of samples, but because the information in the feature map is lost in the downsampling process of UNET, and a large amount of spatially accurate detailed information is lost in the decoding part. This makes it difficult to complete accurate segmentation of cell images with dense numbers and high adhesion. For this reason, we propose a new network structure based on UNET, which can be used to segment cell images by aggregating the global contextual information between different channels and assigning different weights to the corresponding channels through the gated adaptive mechanism, we improve the performance of UNET in the cell segmentation task and consider the use of unsupervised segmentation methods for secondary segmentation of the predicted results of our model, and the final results obtained are tested to meet the needs of the readers.

show abstract

Deep Learning Accurately Quantifies Plasma Cell Percentages on CD138-Stained Bone Marrow Samples

Cited by 6 publications

References 18 publications

Evaluation of a new technique using artificial intelligence for quantification of plasma cells on CD138 immunohistochemistry

Evaluation of a new technique using artificial intelligence for quantification of plasma cells on CD138 immunohistochemistry

Artificial Intelligence in Bone Marrow Histological Diagnostics: Potential Applications and Challenges

GCT-UNET: U-Net Image Segmentation Model for a Small Sample of Adherent Bone Marrow Cells Based on a Gated Channel Transform Module

Contact Info

Product

Resources

About