Analysis of the sensitivity of high‐grade squamous intraepithelial lesion Pap diagnosis and interobserver variability with the Hologic Genius Digital Diagnostics System DOI Creative Commons
Lakshmi Harinath, Esther Elishaev,

Yuhong Ye

et al.

Cancer Cytopathology, Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 5, 2024

Abstract Background Artificial intelligence (AI)–based systems are transforming cytopathology practice. The aim of this study was to evaluate the sensitivity high‐grade squamous intraepithelial lesion (HSIL) Papanicolaou (Pap) diagnosis assisted by Hologic Genius Digital Diagnostics System (GDDS). Methods A validation performed with 890 ThinPrep Pap tests GDDS independently. From set, a subset 183 cases originally interpreted as HSIL confirmed histologically were included in study. for detecting three cytopathologists calculated. Results Most classified atypical glandular cell/atypical cell–high grade not excluded (AGC/ASC‐H) and above all cytopathologists. Of these cases, 11.5% low‐grade (LSIL) pathologist (P‐A), 6% B (P‐B), 5.5% C (P‐C); 3.8%, 2.7%, 1.6% cell unknown significance (ASC‐US) P‐A, P‐B, P‐C, respectively. detection cervical neoplasia 2 (CIN2+) lesions 100% if ASC‐US (ASC‐US+) abnormalities counted among pathologists. CIN2+ 84.7%, 91.3%, 92.9% respectively, ASC‐H abnormalities. Kendall W coefficient 0.722, which indicated strong agreement between Conclusions New‐generation AI‐assisted test screening such have potential transform cytology In study, aided interpreting tests, good pathologists who interacted system.

Language: Английский

Digital Cytology Combined With Artificial Intelligence Compared to Conventional Microscopy for Anal Cytology: A Preliminary Study DOI Open Access

Renê Gerhard,

Cioly Rivero Colmenarez,

Corinne Selle

et al.

Cytopathology, Journal Year: 2025, Volume and Issue: unknown

Published: March 11, 2025

ABSTRACT Introduction Recent studies have shown that digital cytology (DC) coupled with artificial intelligence (AI) algorithms is a valid approach to the diagnosis of cervico‐vaginal lesions using liquid‐based (LBC). We evaluated use these methods for anal LBC specimens. Methods A series 124 slides previously diagnosed by conventional microscopy (CC) were reviewed DC/AI system generated gallery images. Diagnoses based on selected images, according 2014 Bethesda System Reporting Cervical Cytology, compared CC. Results Overall, CC and approaches detected similar number abnormal (ASC‐US+) cases (63 62 cases, respectively). observed an exact concordance between DC in 70 (57.9%) corresponding moderate agreement two (κ = 0.41, p < 0.001). 0.48, 0.001) was also found when positive stratified into ‘low‐grade’ (ASC‐US, LSIL) ‘high‐grade’ (ASC‐H, HSIL). The more higher severity HSIL: 9 2 respectively) than (3 classified as Conclusions ASC‐US+ both systems similar.

Language: Английский

Citations

0
Implementing 100% quality control in a cervical cytology workflow using whole slide images and artificial intelligence provided by the Techcyte SureView™ System DOI Creative Commons

Maria del Mar Rivera Rolon,

Erik Gustafson,

R.K. Cole

et al.

Cancer Cytopathology, Journal Year: 2025, Volume and Issue: 133(6)

Published: May 19, 2025

Abstract Background Recent advancements in digital pathology have extended into cytopathology. Laboratories screening cervical cytology specimens now choose between limited imaging options and traditional manual microscopy. The Techcyte SureView™ Cervical Cytology System, designed for cytopathology, was validated at CorePlus, a laboratory Puerto Rico, adopted as 100% quality control (QC) tool. Methods validation study included 1442 whole slide images (WSIs) from 1273 ThinPrep® 169 SurePath™ slides, digitized with the 3DHISTECH Panoramic 1000 DX scanner using dry water immersion scanning profiles. These WSIs were processed by system, board‐certified cytopathologist reviewing artificial intelligence (AI)‐identified objects of interest comparing them to light microscopy results. Results profile outperformed both detecting squamous glandular abnormalities. It achieved 97% accuracy, 82% sensitivity, 99% specificity, 98% negative predictive value, 86% positive value. Additionally, review time rapid. system has been operational several months, enhancing accuracy workflow efficiency. Conclusions This demonstrates that particularly through can improve performance. Successful led CorePlus integrate AI algorithm their QC tool, resulting improved benefiting professionals patients.

Language: Английский

Citations

0
Something old, something new: Cervical cytopathology in the new era DOI Creative Commons

Rawan Tahboub,

Javier Sanchez-Ortiz,

M.N. Lai

et al.

Human Pathology Reports, Journal Year: 2024, Volume and Issue: 37, P. 300756 - 300756

Published: Aug. 27, 2024

Language: Английский

Citations

2
Analysis of the sensitivity of high‐grade squamous intraepithelial lesion Pap diagnosis and interobserver variability with the Hologic Genius Digital Diagnostics System DOI Creative Commons
Lakshmi Harinath, Esther Elishaev,

Yuhong Ye

et al.

Cancer Cytopathology, Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 5, 2024

Abstract Background Artificial intelligence (AI)–based systems are transforming cytopathology practice. The aim of this study was to evaluate the sensitivity high‐grade squamous intraepithelial lesion (HSIL) Papanicolaou (Pap) diagnosis assisted by Hologic Genius Digital Diagnostics System (GDDS). Methods A validation performed with 890 ThinPrep Pap tests GDDS independently. From set, a subset 183 cases originally interpreted as HSIL confirmed histologically were included in study. for detecting three cytopathologists calculated. Results Most classified atypical glandular cell/atypical cell–high grade not excluded (AGC/ASC‐H) and above all cytopathologists. Of these cases, 11.5% low‐grade (LSIL) pathologist (P‐A), 6% B (P‐B), 5.5% C (P‐C); 3.8%, 2.7%, 1.6% cell unknown significance (ASC‐US) P‐A, P‐B, P‐C, respectively. detection cervical neoplasia 2 (CIN2+) lesions 100% if ASC‐US (ASC‐US+) abnormalities counted among pathologists. CIN2+ 84.7%, 91.3%, 92.9% respectively, ASC‐H abnormalities. Kendall W coefficient 0.722, which indicated strong agreement between Conclusions New‐generation AI‐assisted test screening such have potential transform cytology In study, aided interpreting tests, good pathologists who interacted system.

Language: Английский

Citations

2