AIxURO URINE CYTOLOGY CLINICAL STUDIES
USCAP 2026 Oral Presentation
AI-Powered Urine Cytology: Redefining Diagnostic Precision and Workflow at PathNet
Resources and News
Educational resources and news from AIxMed to keep you informed
and up-to-date on our AI empowered digital cytology solutions.
and up-to-date on our AI empowered digital cytology solutions.
.png)
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.
AIxURO URINE CYTOLOGY CLINICAL STUDIES
March 2026
USCAP 2026 Oral Presentation
AI-Powered Urine Cytology: Redefining Diagnostic Precision and Workflow at PathNet
USCAP 2026 Oral Presentation
AI-Powered Urine Cytology: Redefining Diagnostic Precision and Workflow at PathNet
STUDY DESIGN:
RESULTS:
The implementation of AIxURO™ at PathNet has delivered a comprehensive set of clinical and operational advantages by bridging the gap between digital pathology and automated analytical software. By integrating this tool into the daily workflow, the laboratory realized several key benefits:
Strategic Clinical Uses
- Cyto-Histo Correlation: The platform serves as a powerful additional tool for correlating cytology findings with surgical pathology results.
- Quality Control Review: AIxURO™ provides a robust QC layer, acting as atireless "second set of eyes" to confirm results and reduce human fatigue.
- Educational Advancement: The digitized data and statistical analysis offer a modernized platform for the training and education of cytologists, residents and fellows.
Operational and Patient Benefits
- Cost-Effectiveness: Patients benefit from a reduction in unnecessary and expensive ancillary testing, such as UroVysion FISH, as the AI's precision assists in increased diagnostic confidence.
- Workflow Efficiency: The laboratory observed an increase in both cytologist and pathologist efficiency, particularly through the use of superior digital imaging.
- Ergonomics and Reliability: Beyond technical accuracy, the transition to digital analysis improved the physical ergonomics for cytologists and ensured the consistent confirmation of negative cases.
CONCLUSIONS:
PathNet’s success proves that the future of pathology lies in the synergy between human expertise and machine learning. By embedding AI within the existing digital workflow, PathNet has empowered its staff to work more efficiently and comfortably while setting a new global standard for patient care.
AIxURO URINE CYTOLOGY CLINICAL STUDIES
March 2026
USCAP 2026 Oral Presentation
Objective Precision in the Caribbean: CorePlus and the Future of AI-Driven Pathology
USCAP 2026 Oral Presentation
Objective Precision in the Caribbean: CorePlus and the Future of AI-Driven Pathology
STUDY DESIGN:
RESULTS:
The laboratory conducted a comprehensive validation study involving 117 cases across a wide range of diagnostic categories (benign, AUC, HGUC). The results showed:
- High Concordance: A 93.7% concordance rate between manual microscopy and the AI-driven
- Statistical Robustness: High sensitivity (90.4%) and specificity (94.1%),demonstrating the AI's ability to accurately identify HGUC cases while maintaining low false-positive rates.evaluation.
CONCLUSIONS:
CorePlus has demonstrated that private laboratories can lead the way in adopting advanced AI technology. By prioritizing patient care and investing in digital tools, the lab has achieved unprecedented efficiency and diagnostic precision.
AIxURO URINE CYTOLOGY CLINICAL STUDIES
March 2026
USCAP 2026 Oral Presentation
Digital Cytopathology in the Heart of Europe: A Bioptická Laboratoř Experience
USCAP 2026 Oral Presentation
Digital Cytopathology in the Heart of Europe: A Bioptická Laboratoř Experience
STUDY DESIGN:
RESULTS:
The implementation of the AI-driven workflow resulted in significant improvements:
- Increased Speed: Pathologists reported a 30% to 50% increase in workflow speed, with the diagnosis of benign cases often reduced to mere seconds.
- Enhanced Sensitivity: The AI was slightly biased toward sensitivity, ensuring that atypical cells were prioritized for review.
- Objective Data: The system provides quantitative metrics for atypical and suspicious cells, removing subjectivity from the diagnostic process.
- Improved Efficiency: The reduction in screening time allowed the lab to free up capacity for growth without compromising accuracy.
CONCLUSIONS:
Clinical use of AIxURO resulted in a 30–50% faster overall read time, improved sensitivity with moreobjective data for atypical cases, and a noticeably better user experience. The system is easy to use,avoids unnecessary features, integrates well with glass slides, and supports increased efficiency andgrowth in routine clinical practice.
March 2026
AI-Powered Urine Cytology: Redefining Diagnostic Precision and Workflow at PathNet
STUDY DESIGN:
RESULTS:
The implementation of AIxURO™ at PathNet has delivered a comprehensive set of clinical and operational advantages by bridging the gap between digital pathology and automated analytical software. By integrating this tool into the daily workflow, the laboratory realized several key benefits:
Strategic Clinical Uses
- Cyto-Histo Correlation: The platform serves as a powerful additional tool for correlating cytology findings with surgical pathology results.
- Quality Control Review: AIxURO™ provides a robust QC layer, acting as atireless "second set of eyes" to confirm results and reduce human fatigue.
- Educational Advancement: The digitized data and statistical analysis offer a modernized platform for the training and education of cytologists, residents and fellows.
Operational and Patient Benefits
- Cost-Effectiveness: Patients benefit from a reduction in unnecessary and expensive ancillary testing, such as UroVysion FISH, as the AI's precision assists in increased diagnostic confidence.
- Workflow Efficiency: The laboratory observed an increase in both cytologist and pathologist efficiency, particularly through the use of superior digital imaging.
- Ergonomics and Reliability: Beyond technical accuracy, the transition to digital analysis improved the physical ergonomics for cytologists and ensured the consistent confirmation of negative cases.
CONCLUSIONS:
PathNet’s success proves that the future of pathology lies in the synergy between human expertise and machine learning. By embedding AI within the existing digital workflow, PathNet has empowered its staff to work more efficiently and comfortably while setting a new global standard for patient care.
March 2026
AIxURO URINE CYTOLOGY CLINICAL STUDIES
USCAP 2026 Oral Presentation
Objective Precision in the Caribbean: CorePlus and the Future of AI-Driven Pathology
Objective Precision in the Caribbean: CorePlus and the Future of AI-Driven Pathology
STUDY DESIGN:
RESULTS:
The laboratory conducted a comprehensive validation study involving 117 cases across a wide range of diagnostic categories (benign, AUC, HGUC). The results showed:
- High Concordance: A 93.7% concordance rate between manual microscopy and the AI-driven
- Statistical Robustness: High sensitivity (90.4%) and specificity (94.1%),demonstrating the AI's ability to accurately identify HGUC cases while maintaining low false-positive rates.evaluation.
CONCLUSIONS:
CorePlus has demonstrated that private laboratories can lead the way in adopting advanced AI technology. By prioritizing patient care and investing in digital tools, the lab has achieved unprecedented efficiency and diagnostic precision.
March 2026
AIxURO URINE CYTOLOGY CLINICAL STUDIES
USCAP 2026 Oral Presentation
Digital Cytopathology in the Heart of Europe: A Bioptická Laboratoř Experience
Digital Cytopathology in the Heart of Europe: A Bioptická Laboratoř Experience
STUDY DESIGN:
RESULTS:
The implementation of the AI-driven workflow resulted in significant improvements:
- Increased Speed: Pathologists reported a 30% to 50% increase in workflow speed, with the diagnosis of benign cases often reduced to mere seconds.
- Enhanced Sensitivity: The AI was slightly biased toward sensitivity, ensuring that atypical cells were prioritized for review.
- Objective Data: The system provides quantitative metrics for atypical and suspicious cells, removing subjectivity from the diagnostic process.
- Improved Efficiency: The reduction in screening time allowed the lab to free up capacity for growth without compromising accuracy.
CONCLUSIONS:
Clinical use of AIxURO resulted in a 30–50% faster overall read time, improved sensitivity with moreobjective data for atypical cases, and a noticeably better user experience. The system is easy to use,avoids unnecessary features, integrates well with glass slides, and supports increased efficiency andgrowth in routine clinical practice.
March 2026
AIxTHY THYROID FINE NEEDLE ASPIRATION CLINICAL STUDIES
USCAP 2026 Oral Presentation
AIxTHY Digital Cytopathology Platform Improves Diagnostic Accuracy and Reduces Nondiagnostic Interpretations in Thyroid Fine-Needle Aspiration Cytology
AIxTHY Digital Cytopathology Platform Improves Diagnostic Accuracy and Reduces Nondiagnostic Interpretations in Thyroid Fine-Needle Aspiration Cytology
STUDY DESIGN:
- A total of 100 ThinPrep thyroid FNAC cases with established ground truth cytologic diagnoses (The Bethesda System for Reporting Thyroid Cytopathology) using a consensus of the original cytology report interpretation and the surgical pathology findings were analyzed:
- 5 TBS-I, 35 TBS-II, 15 TBS-III, 15 TBS-IV, and 30 TBS-VI cases
- Each case was digitized into single-layer whole-slide images (WSIs) using Leica AT2 or 3DHISTECH scanners.
- The AIxTHY algorithm was applied to identify abnormal cells and quantify cytomorphologic features on each WSI.
- Eight independent reviewers (3 cytopathologists, 5 cytologists) assessed each case under two arms, separated by a two-week washout period:
- Arm 1- Microscopy only
- Arm 2- AI-assisted digital review
- Performance Metrics: Comparison of study diagnosis with ground truth cytology diagnosis for two arms across 800 total reads.
- Diagnostic agreement for TBS categorization
- Reclassification of TBS category
- Binary reclassification of the TBS-I reads from microscopy by AI-assisted review
RESULTS:
- In the Nondiagnostic (TBS-I) category, microscopy (Arm 1) achieved 80.0% (32/40) agreement with the ground truth, but to our surprise, AI-assisted review (Arm 2) reduced nondiagnostic calls to 57.5% (23/40).
- Agreement for indeterminate TBS-III cases increased from 29.2% (35/120) in the microscopy arm to 46.7% (56/120) in the AI-assisted review arm.
- Overall, TBS-I reads decreased from 10.0% (80/800) in microscopy to 6.8% (54/800) in AI-assisted review, representing a 32.5% relative reduction (26 fewer TBS-I interpretations).
- Binary reclassification of the 80 TBS-I reads from microscopy (TBS-II as negative; TBS-III+ as positive) showed that AI-assisted review 2 reclassified:
- 12 as negative (32.1% specificity gain) and
- 4 as positive (40.0% sensitivity gain),
- thereby improving overall diagnostic accuracy and interpretive confidence for previously indeterminate cases.
CONCLUSIONS:
- AI-assisted review reduced nondiagnostic (TBS-I) interpretations originally rendered by microscopy and improved diagnostic accuracy in thyroid FNAC.
- By reclassifying TBS-I cases into actionable Bethesda categories, AIxTHY enhanced both specificity and sensitivity.
- Reassignment to a benign or malignant diagnoses expedites definitive care.
- These results highlight the potential of AIxTHY as an effective adjunct for digital cytology workflows, supporting more reliable and efficient thyroid FNAC interpretation.
March 2026
AIxURO URINE CYTOLOGY CLINICAL STUDIES
USCAP 2026 Poster Preentation
Mitigating Visual Fatigue in Urine Cytology: AIxURO, an AI-Driven Review Platform, Improves Diagnostic Accuracy and Efficiency
Mitigating Visual Fatigue in Urine Cytology: AIxURO, an AI-Driven Review Platform, Improves Diagnostic Accuracy and Efficiency
STUDY DESIGN:
- 100 urine cytology cases were selected, comprising 60 positive and 40 negative diagnoses for bladder cancer.
- Each slide was digitized into a whole-slide image (WSI) using a Hamamatsu S360 scanner.
- AIxURO was applied to detect abnormal urothelial cells and quantify cytomorphologic features on each WSI.
- Four cytologists independently reviewed all cases under microscopy and AI-assisted review (AIxURO) arms, separated by a washout period, and data was pooled for 400 reads/arm.
- Visual fatigue was assessed using the Computer Vision Syndrome Questionnaire (CVS-Q), which rates 16 ocular and visual symptoms by frequency and intensity (total score of 0–32; scores ≥6 indicate CVS).
- Performance Metrics: Comparison of study diagnosis with ground truth cytology diagnosis for two arms across 400 total read.
- Binary diagnostic accuracy (positive: AUC and above; negative: NHGUC)
- Mean diagnostic turnaround time (second)
RESULTS:
- In CVS-Q evaluation, microscopy produced higher mean scores than AIxURO at both the first 50 (5.8 vs. 1.2) and last 50 (10.5 vs. 2.8) reads, indicating greater visual fatigue with microscopy.
- CVS-Q scores progressively increased during microscopy (the mean score: 1.8 to 10.5), reaching levels consistent with CVS, whereas only one reviewer exceeded the CVS threshold after 100 reads in AIxURO.
- These results indicate that AIxURO reduces both the likelihood and severity of visual fatigue.
- In diagnostic performance, AIxURO achieved higher sensitivity (0.975 vs. 0.867) and accuracy (0.960 vs. 0.890), with substantially shorter mean turnaround time (24.2 seconds vs. 80.3 seconds) compared with microscopy, indicating improved accuracy and efficiency with AI assistance.
CONCLUSIONS:
- Compared with microscopy, AIxURO was associated with lower CVS-Q scores, reflecting reduced visual fatigue, along with higher diagnostic accuracy and shorter reporting times.
- These findings support integrating the AI platform into routine cytology practice to enhance user comfort, reduce occupational visual strain, and improve diagnostic performance.
November 2025
THE PARIS SYSTEM FOR URINE CYTOLOGY NUCLEAR TO CYTOPLASMIC RATIO
ASC Oral Presentation
The Paris Study: Multicenter Retrospective Analysis of Artificial Intelligence-Quantified Nuclear-to-Cytoplasmic Ratios and Nuclear Areas in Confirmed Bladder Cancer Urology Specimens
The Paris Study: Multicenter Retrospective Analysis of Artificial Intelligence-Quantified Nuclear-to-Cytoplasmic Ratios and Nuclear Areas in Confirmed Bladder Cancer Urology Specimens
STUDY DESIGN:
- A total of 541 specimens from biopsy-confirmed urothelial carcinoma cases were collected from five hospitals (four in the U.S., one in Taiwan).
- Slides were digitized using Hamamatsu S360 scanner. After excluding 88 slides with poor image quality, 453 WSIs were analyzed, including:
- 75 Cytospin
- 317 ThinPrep
- 61 SurePath [CytoRich]
- AIxURO subcategorized atypia based on The Paris System (TPS) 2.0 criteria (N/C ratio and nuclear features):
- Higher cancer risk (suspicious)
- Lower cancer risk (atypical)
- Median numbers of suspicious, top 24 high-risk suspicious, and atypical cells, along with their N/C ratios and nuclear areas, were statistically compared across three preparations.
RESULTS:
- AIxURO analyzed 100,312 suspicious cells (including 8,672 top 24 suspicious cells) and 535,021 atypical cells from 453 WSIs.
- SurePath contained significantly more suspicious cells (1.07 cells/mm²) compared to Cytospin (0.32 cells/mm²) and ThinPrep (0.12 cells/mm²).
- Cytospin showed the highest atypical cell numbers (8.28 cells/mm²) versus SurePath (5.43 cells/mm²) and ThinPrep (1.53 cells/mm²).
- Consistent N/C ratios were observed across preparations for suspicious (0.660–0.666), top 24 suspicious (0.676–0.687), and atypical cells (0.568–0.576).
- Nuclear areas for suspicious and atypical cells were significantly larger in SurePath (102.8 µm², 79.3 µm²) compared to ThinPrep (100.4 µm², 75.6 µm²) and Cytospin (93.7 µm², 69.2 µm²).
CONCLUSIONS:
- AIxURO consistently quantified N/C ratios across diverse cyto preparations and institutions, supporting the broad applicability of TPS.
- The median N/C ratio of suspicious cells was consistently below 0.7, while nuclear area emerged as a significant indicator of malignancy risk, highlighting the potential of AI in refining clinical diagnostic criteria.
November 2025
AIxURO URINE CYTOLOGY CLINICAL STUDIES
ASC Poster Presentation
AI-Driven Logistic Regression Models for Bladder Cancer Prediction: A Pilot Study Quantifying Atypical Urothelial Cells with Cytomorphometric Features
AI-Driven Logistic Regression Models for Bladder Cancer Prediction: A Pilot Study Quantifying Atypical Urothelial Cells with Cytomorphometric Features
STUDY DESIGN:
- 2,607 specimens, previously classified by The Paris System (TPS), were analyzed using AIxURO.
- AIxURO subcategorized cells into suspicious cells (SCs) and atypical cells (ACs) based on the degree of atypia and measurements:
- Abnormal cell counts standardized to the sample area (cells/mm 2 )
- Mean N/C ratio
- Mean nuclear area
- Five logistic regression models were developed for each cell category using different combinations of cytomorphometric parameters.
- Two binary diagnostic cohorts were constructed:
- Screening cohort (AUC/SHGUC/HGUC as positive)
- Surveillance cohort (SHGUC/HGUC as positive, excluding AUC)
- Screening cohort (AUC/SHGUC/HGUC as positive)
- Model performance was assessed using:
- Receiver operating characteristic (ROC) curves
- Optimal cutoffs determined by Youden’s index
- Sensitivity and specificity
- Receiver operating characteristic (ROC) curves
RESULTS:
- Screening cohort: ACs demonstrated higher sensitivity (59.4% vs. 54.4%) but lower specificity (93.7% vs. 94.9%) compared to SCs.
- Logarithmic-transformed (log) cell counts improved sensitivity (SCs: 54.4% to 66.4%; ACs: 59.4% to 78.3%) but reduced specificity (SCs: 94.9% to 84.3%; ACs: 93.7% to 77.4%).
- Incorporating the N/C ratio or nuclear area slightly improved performance.
- Surveillance cohort: SCs achieved the highest specificity (96.2%), while log SCs and combined models improved sensitivity but reduced specificity.
CONCLUSIONS:
- For screening purposes, the log ACs incorporating the nuclear area model achieved the highest sensitivity (78.9%).
- For surveillance purposes, the SCs model demonstrated the highest specificity (96.2%).
- These preliminary results support the need for larger-scale studies to further investigate and validate logistic regression models for the clinical application of AIxURO.
October 2025
AIxTHY THYROID FINE NEEDLE ASPIRATION CLINICAL STUDIES
Pathology Visions Oral Presentation
Redefining Thyroid Cytology with AIxTHY: Improved Accuracy and Efficiency in FNAC Interpretation
Redefining Thyroid Cytology with AIxTHY: Improved Accuracy and Efficiency in FNAC Interpretation
STUDY DESIGN:
- 100 thyroid ThinPrep slides categorized forground truth diagnosis (The Bethesda System for Reporting Thyroid Cytopathology) using a consensus of the original cytology report interpretation and the surgical pathology findings. All cases had a surgical result except Nondiagnostic cases.
- Urine slides were digitized as single-layer (S-WSIs)and 7-Z-layer (7-WSIs) WSIs by the 3D-Histech scanner and analyzed with AI-assistance software (AIxTHY)
- 5 reviewers including 3 cytopathologist (CP) and5 cytologists (CT) evaluated slides with a 2-week washout period between research arms:
- Arm 1- Microscopy only
- Arm 2- S-WSI with AIxTHY-assistance
- Arm 3- 7-WSI with AIxTHY-assistance
- Performance Metrics:
Comparison of study diagnosis with ground truth cytology diagnosis for 3 Arms across 500 total reads.
- Binary diagnostic accuracy (positive: TBS-III and above; negative: TBS-II)
- TBS category concordance (TBS-I~VI)
- Mean diagnostic turnaround time (second)
RESULTS:
- Sensitivity: Improved with AIxTHY (Arm 2: 81.3%;Arm 3: 83.0%) compared with microscopy (Arm 1: 68.7%; p < 0.001); no difference between AI-assisted arms (p = 0.522).
- Specificity: Slightly lower with AIxTHY (Arm 2:68.0%; Arm 3: 65.7%) than microscopy (73.1%), significant for Arm 1 vs. Arm 3(p = 0.049).
- Overall Accuracy: Increased from 70.3%(microscopy) to 76.4–76.6% (AIxTHY; p = 0.004).
- Diagnostic Efficiency: Mean review time reduced by 32.8% (163.6 s → 109.9 s; p < 0.001).
- TBS Concordance: Overall comparable (Arm 1:52.4%; Arm 2: 51.4%; Arm 3: 53.5%).
- Higher agreement for indeterminate TBS-III with AIxTHY (44–53%) vs. microscopy (25%).
- Nondiagnostic (TBS-I) Rates: Decreased from10.8% to 6.4–5.6%, representing a 41–48% reduction.
- Several TBS-I cases were reclassified to TBS-II or ≥TBS-III under AI-assisted review.
CONCLUSIONS:
AIxTHY improved sensitivity, diagnostic accuracy, and efficiency while reducing review time and nondiagnostic rates, with minimal impact on specificity. These results support its role in streamlining thyroid FNAC workflows through AI-assisted digital cytopathology
May 2025
AIxURO URINE CYTOLOGY CLINICAL STUDIES
ICC 2025 Oral Presentation
AIxURO: Enhancing Diagnostic Accuracy in Bladder Caner Detection with AI-Assisted Urine Cytology
AIxURO: Enhancing Diagnostic Accuracy in Bladder Caner Detection with AI-Assisted Urine Cytology
STUDY DESIGN:
- Retrospective study using 200 ThinPrep urine cytology slides.
- Ground truth: NHGUC (n=100), AUC (n=35), SHGUC (n=32), HGUC (n=33).
- Slides digitized using: (1) Mikroscan SLxCyto( Mikroscan-WSIs); (2) Customized Huron scanner (Huron-WSIs).
- WSIs were analyzed using AIxURO, a disease-specific AI algorithm for bladder cancer.
- Three-arm blinded review by 1 cytopathologist and 2 cytologists, with 2-week washout periods:
- Arm 1: Conventional microscopy
- Arm 2: AIxURO with Mikroscan-WSIs
- Arm 3: AIxURO with Huron-WSIs
- Performance Metrics:
- Comparison of study diagnosis with urine cytology ground truth diagnosis (n=200) for 3 arms, using following threshold: AUC+(AUC, SHGUC and HGUC) cases as positive; NHGUC cases as negative.
- Assessment of agreement between study diagnoses and surgical pathology-confirmed bladder cancer (n=72) among the three arms.
- Evaluation of bladder cancer prediction in hematuria-indicated cases (n=16) across the three arms.
RESULTS:
- Urine cytology ground truth cases: Arm 2 and Arm3 exhibited higher sensitivity (85.0% and 88.3%) compared to Arm 1 (79.3%) with comparable accuracy across all arms (Arm 1: 86.8%, Arm 2: 85.3%, Arm 3: 85.3%).
- Biopsy-confirmed bladder cancer cases: Arm 2 and Arm 3 showed improved sensitivity (92.0% and 93.2%) and accuracy (82.9% and 82.4%) compared to Arm 1 (84.6% sensitivity, 78.2% accuracy).
- Hematuria cases: Arms 2 and 3 achieved superior sensitivity (96.7% and 100.0%) and accuracy (89.6% and 91.7%) compared to Arm 1 (90.0% sensitivity, 85.4% accuracy).
CONCLUSIONS:
AIxURO consistently enhanced diagnostic sensitivity and maintained accuracy across multiple scanners, outperforming microscopy in detecting bladder cancer. It demonstrated strong predictive performance in high-risk subgroups, supporting its utility in real-world clinical workflows and digital cytology integration.
Upcoming Events
Upcoming event
American Urological Association -Visit us at the Lumea Booth (#547)
15
-
18
May 2026
Washington, DC
May
15
-
18
,
2026
No items found.
Latest news
March 2026
USCAP 2026 Video Recording
Objective Precision in the Caribbean: CorePlus and the Future of AI-Driven Pathology March 2026
USCAP 2026 Video Recording
Digital Cytopathology in the Heart of Europe: A Bioptická Laboratoř ExperienceFebruary 2026
January 2026
November 2025
EINPresswire
AIxMed and ASCT PartnershipNovember 2025
November 2024
American Society of Cytopathology (ASC)
Dr. Barbara Crothers is the recipient of the ASC’s highest award- 2024 Papanicolaou AwardApril 2024
