Whole slide imaging (WSI) scanner differences influence optical and computed properties of digitized prostate cancer histology

Duenweg, Savannah; Bobholz, Samuel; Lowman, Allison; Stebbins, Margaret; Winiarz, Aleksandra; Nath, Biprojit; Kyereme, Fitzgerald; Iczkowski, Kenneth A.; LaViolette, Peter S.

doi:10.1016/j.jpi.2023.100321

Cited by 7 publications

(3 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since previous studies have demonstrated how the optical and computed properties of WSIs are affected by technical differences in slide scanners, potentially influencing the performance of AI-based tools [9], we found it necessary to evaluate our model's performance using WSIs obtained from different scanners. Duenweng et al [10] demonstrated that the optical and computed properties of WSI from different scanners can affect AI-based tools, particularly when applied to low-resolution images (i.e., low magnification). In our study, we worked (for both training and validation of the model) on patches obtained at an intermediate magnification (20×), which ensured that the performance of our model was not adversely affected by the differing properties of the two scanners.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Development of an Artificial-Intelligence-Based Tool for Automated Assessment of Cellularity in Bone Marrow Biopsies in Ph-Negative Myeloproliferative Neoplasms

D’Abbronzo,

D’Antonio,

De Chiara

et al. 2024

Cancers

View full text Add to dashboard Cite

The cellularity assessment in bone marrow biopsies (BMBs) for the diagnosis of Philadelphia chromosome (Ph)-negative myeloproliferative neoplasms (MPNs) is a key diagnostic feature and is usually performed by the human eyes through an optical microscope with consequent inter-observer and intra-observer variability. Thus, the use of an automated tool may reduce variability, improving the uniformity of the evaluation. The aim of this work is to develop an accurate AI-based tool for the automated quantification of cellularity in BMB histology. A total of 55 BMB histological slides, diagnosed as Ph- MPN between January 2018 and June 2023 from the archives of the Pathology Unit of University “Luigi Vanvitelli” in Naples (Italy), were scanned on Ventana DP200 or Epredia P1000 and exported as whole-slide images (WSIs). Fifteen BMBs were randomly selected to obtain a training set of AI-based tools. An expert pathologist and a trained resident performed annotations of hematopoietic tissue and adipose tissue, and annotations were exported as .tiff images and .png labels with two colors (black for hematopoietic tissue and yellow for adipose tissue). Subsequently, we developed a semantic segmentation model for hematopoietic tissue and adipose tissue. The remaining 40 BMBs were used for model verification. The performance of our model was compared with an evaluation of the cellularity of five expert hematopathologists and three trainees; we obtained an optimal concordance between our model and the expert pathologists’ evaluation, with poorer concordance for trainees. There were no significant differences in cellularity assessments between two different scanners.

show abstract

Section: Discussionmentioning

confidence: 99%

“…Recently, an AI-supported diagnostic tool for prostate cancer based on digitized pathology slides (Paige Prostate) was approved by the FDA [8]. Despite these regulatory processes, variability in scanner performance has been shown to influence AI-based assessments [9,10].…”

Section: Introductionmentioning

confidence: 99%

Development of an Artificial-Intelligence-Based Tool for Automated Assessment of Cellularity in Bone Marrow Biopsies in Ph-Negative Myeloproliferative Neoplasms

D’Abbronzo,

D’Antonio,

De Chiara

et al. 2024

Cancers

View full text Add to dashboard Cite

show abstract

“…The digital scanner for the Whole Slide Image (WSI), opens the doors for computer vision to tackle the analysis of the WSI to reduce diagnosis time. Whole Slide Image (WSI) is a way of laboratory steps to get histopathological images, either by examining them manually under the microscope or by digitalizing the slide with different magnifications by special scanners (Duenweg et al, 2023). Many reviews have discussed the history of histopathological image analysis and the different machinelearning techniques used (Bhargava and Madabhushi, 2016;Shen et al, 2017;Gurcan et al, 2009;Litjens et al, 2017;Xing and Yang, 2016) and we will describe the WSI analysis using different pathology-oriented applications based on machine learning techniques.…”

Section: Introductionmentioning

confidence: 99%

Challenges of Breast Cancer Detection Based on Histopathology Images

Youssef,

Youssif,

Behaidy

2024

Journal of Computer Science

View full text Add to dashboard Cite

Artificial Intelligence (AI) is rapidly evolving every day to become increasingly potent and dependable. AI systems are becoming more sophisticated and are being utilized across various domains with the goal of enhancing human existence. Within the healthcare system, artificial intelligence finds application in handling and documenting large volumes of medical data, conducting analyses of healthcare systems, advancing pharmaceutical development, and aiding physicians in decision-making processes. Machines excel over humans in executing repetitive tasks consistently and reliably. In addition, the performance has recently been enhanced by the emersion of deep learning techniques. Breast cancer presents a significant danger to women globally as it reached 25.4% of new cases diagnosed with cancer types. Its danger increases with its ability to spread outside the breast through blood vessels and lymph vessels. The availability of histopathological images and the advancement in AI and machine learning techniques give new horizons for more investigation and studies of breast histopathology images. In this study, we demonstrate the different steps for detecting and classifying breast cancer through a journey from the preparation of breast tissue specimens to classification clarifying the different techniques used. Furthermore, we will discuss the challenges and solutions for histopathology images and the automated systems used.

show abstract

A highly accurate and semi-automated method for quantifying spherical microplastics based on digital slide scanners and image processing

Tang,

Yao,

Dong

et al. 2024

Environmental Research

View full text Add to dashboard Cite

Whole slide imaging (WSI) scanner differences influence optical and computed properties of digitized prostate cancer histology

Cited by 7 publications

References 41 publications

Development of an Artificial-Intelligence-Based Tool for Automated Assessment of Cellularity in Bone Marrow Biopsies in Ph-Negative Myeloproliferative Neoplasms

Development of an Artificial-Intelligence-Based Tool for Automated Assessment of Cellularity in Bone Marrow Biopsies in Ph-Negative Myeloproliferative Neoplasms

Challenges of Breast Cancer Detection Based on Histopathology Images

A highly accurate and semi-automated method for quantifying spherical microplastics based on digital slide scanners and image processing

Contact Info

Product

Resources

About