The cytopathologist's role in developing and evaluating artificial intelligence in cytopathology practice

McAlpine, Ewen; Michelow, Pamela

doi:10.1111/cyt.12799

Cited by 24 publications

(38 citation statements)

References 19 publications

(33 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ensuring that cytologists do not impede the implementation of deep learning in cytology is of paramount importance and implementing AI in cytology will place added responsibility on cytologists [13]. Cytologists need to place themselves at the center of the development and validation of these technologies in cytology [1].…”

Section: Added Responsibility For Cytologistsmentioning

confidence: 99%

“…Understanding how an algorithm's performance is evaluated is also of paramount importance [13]. Commonly used metrics to assess algorithm performance include accuracy, precision, and recall, and the specific setting in which an algorithm will be employed is critical to understanding which of these metrics one should attempt to maximize when training an algorithm.…”

Section: Challenges With Algorithm Trainingmentioning

confidence: 99%

See 1 more Smart Citation

Challenges Developing Deep Learning Algorithms in Cytology

2020

View full text Add to dashboard Cite

Background: The incorporation of digital pathology into routine pathology practice is becoming more widespread. Definite advantages exist with respect to the implementation of artificial intelligence (AI) and deep learning in pathology, including cytopathology. However, there are also unique challenges in this regard. Summary: This review discusses cytology-specific challenges, including the need to implement digital cytology prior to AI; the large file sizes and increased acquisition times for whole slide images in cytology; the routine use of multiple stains, such as Papanicolaou and Romanowsky stains; the lack of high-quality annotated datasets on which to train algorithms; and the considerable computer resources required, in terms of both computer infrastructure and skilled personnel, for computing and storage of data. Global concerns regarding AI that are certainly applicable to cytology include the need for model validation and continued quality assurance, ethical issues such as the use of patient data in developing algorithms, the need to develop regulatory frameworks regarding what type of data can be utilized and ensuring cybersecurity during data collection and storage, and algorithm development. Key Messages: While AI will likely play a role in cytology practice in the future, applying this technology to cytology poses a unique set of challenges. A broad understanding of digital pathology and algorithm development is desirable to guide the development of algorithms, as well as the need to be cognizant of potential pitfalls to avoid when incorporating the technology in practice.

show abstract

Section: Added Responsibility For Cytologistsmentioning

confidence: 99%

Section: Challenges With Algorithm Trainingmentioning

confidence: 99%

Challenges Developing Deep Learning Algorithms in Cytology

2020

View full text Add to dashboard Cite

show abstract

“…[14] The emerging technology of whole slide imaging (WSI) [15,16] and artificial intelligence (AI) [17][18][19] applications are revolutionized in improving the efficiency of cytopathological examinations. [20,21] There are systems currently under investigation for analyzing BM smears, such as Vision Bone Marrow [22] and Scorpio Full Field BMA. [23] In this study, we take advantages of a high-resolution BM smear scanning device and advanced deep learning algorithms for cell classification.…”

Section: Introductionmentioning

confidence: 99%

Developing and Preliminary Validating an Automatic Cell Classification System for Bone Marrow Smears: a Pilot Study

Jin

Fu²,

Cao³

et al. 2020

J Med Syst

View full text Add to dashboard Cite

Bone marrow smear examination is an indispensable diagnostic tool in the evaluation of hematological diseases, but the process of manual differential count is labor extensive. In this study, we developed an automatic system with integrated scanning hardware and machine learning-based software to perform differential cell count on bone marrow smears to assist diagnosis. The initial development of the artificial neural network was based on 3000 marrow smear samples retrospectively archived from Sir Run Run Shaw Hospital affiliated to Zhejiang University School of Medicine between June 2016 and December 2018. The preliminary field validating test of the system was based on 124 marrow smears newly collected from the Second Affiliated Hospital of Harbin Medical University between April 2019 and November 2019. The study was performed in parallel of machine automatic recognition with conventional manual differential count by pathologists using the microscope. We selected representative 600,000 marrow cell images as training set of the algorithm, followed by random captured 30,867 cell images for validation. In validation, the overall accuracy of automatic cell classification was 90.1% (95% CI, 89.8–90.5%). In a preliminary field validating test, the reliability coefficient (ICC) of cell series proportion between the two analysis methods were high (ICC ≥ 0.883, P < 0.0001) and the results by the two analysis methods were consistent for granulocytes and erythrocytes. The system was effective in cell classification and differential cell count on marrow smears. It provides a useful digital tool in the screening and evaluation of various hematological disorders.

show abstract

“…the unavailability of decision criteria) that may lead to failure of identifying algorithmic errors. 10,27 In order to ensure high reliability, approaches that allow review of the algorithmic predictions by trained pathologists (computer-assisted diagnosis/prognosis) through visualization of algorithmic results as an overlay on the WSI have been recommended for future application. 10 First computer-assisted MC tools have been recently validated for human pathologists.…”

mentioning

confidence: 99%

Computer-Assisted Mitotic Count Using a Deep Learning-based Algorithm Improves Inter-Observer Reproducibility and Accuracy in canine cutaneous mast cell tumors

Bertram

Aubreville

Donovan

et al. 2021

Preprint

View full text Add to dashboard Cite

The mitotic count (MC) is an important histological parameter for prognostication of malignant neoplasms. However, it has inter- and intra-observer discrepancies due to difficulties in selecting the region of interest (MC-ROI) and in identifying/classifying mitotic figures (MFs). Recent progress in the field of artificial intelligence has allowed the development of high-performance algorithms that may improve standardization of the MC. As algorithmic predictions are not flawless, the computer-assisted review by pathologists may ensure reliability. In the present study we have compared partial (MC-ROI preselection) and full (additional visualization of MF candidate proposal and display of algorithmic confidence values) computer-assisted MC analysis to the routine (unaided) MC analysis by 23 pathologists for whole slide images of 50 canine cutaneous mast cell tumors (ccMCTs). Algorithmic predictions aimed to assist pathologists in detecting mitotic hotspot locations, reducing omission of MF and improving classification against imposters. The inter-observer consistency for the MC significantly increased with computer assistance (interobserver correlation coefficient, ICC = 0.92) compared to the unaided approach (ICC = 0.70). Classification into prognostic stratifications had a higher accuracy with computer assistance. The algorithmically preselected MC-ROIs had a consistently higher MCs than the manually selected MC-ROIs. Compared to a ground truth (developed with immunohistochemistry for phosphohistone H3), pathologist performance in detecting individual MF was augmented when using computer assistance (F1-score of 0.68 increased to 0.79) with a reduction in false negatives by 38%. The results of this study prove that computer assistance may lead to a more reproducible and accurate MCs in ccMCTs.

show abstract

The cytopathologist's role in developing and evaluating artificial intelligence in cytopathology practice

Cited by 24 publications

References 19 publications

Challenges Developing Deep Learning Algorithms in Cytology

Challenges Developing Deep Learning Algorithms in Cytology

Developing and Preliminary Validating an Automatic Cell Classification System for Bone Marrow Smears: a Pilot Study

Computer-Assisted Mitotic Count Using a Deep Learning-based Algorithm Improves Inter-Observer Reproducibility and Accuracy in canine cutaneous mast cell tumors

Contact Info

Product

Resources

About