THE PARIS SYSTEM FOR URINE CYTOLOGY NUCLEAR TO CYTOPLASMIC RATIO
USCAP 2025 Oral Presentation
Quantitative Analysis of the Paris System Cytomorphological Criteria in Digital Urinary Cytology Using Artificial Intelligence Algorithm
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.
AIxTHY THYROID FINE NEEDLE ASPIRATION CLINICAL STUDIES
March 2026
USCAP 2026 Oral Presentation
AIxTHY Digital Cytopathology Platform Improves Diagnostic Accuracy and Reduces Nondiagnostic Interpretations in Thyroid Fine-Needle Aspiration Cytology
USCAP 2026 Oral Presentation
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.
AIxURO URINE CYTOLOGY CLINICAL STUDIES
March 2026
USCAP 2026 Poster Preentation
Mitigating Visual Fatigue in Urine Cytology: AIxURO, an AI-Driven Review Platform, Improves Diagnostic Accuracy and Efficiency
USCAP 2026 Poster Preentation
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.
THE PARIS SYSTEM FOR URINE CYTOLOGY NUCLEAR TO CYTOPLASMIC RATIO
November 2025
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
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
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.
March 2025
Quantitative Analysis of the Paris System Cytomorphological Criteria in Digital Urinary Cytology Using Artificial Intelligence Algorithm
STUDY DESIGN:
- 296 urine cytology slides from confirmed biopsy-positive cases within six months (70 AUC, 65 SHGUC,161 HGUC)
- Slides digitized into WSIs with Leica AT2 scanner
- AI algorithm identified and categorized cells with high (suspicious) or low (atypical) malignancy risk based on The Paris System for Reporting Urinary Cytology (TPS) features; Top-24 category order-ranks 24 most abnormal cells
- Performance Metrics: Mean values of suspicious cells, atypical cells, and the top-24 cells (cells ranked by highest probability of malignancy) with TPS features compared across the three categories (HGUC, SHGUC, and AUC).
RESULTS:
- HGUC cases had significantly higher mean number of abnormal cells for top-24 cells (12.2 vs. 5.5 vs. 2.5), suspicious cells (91.6 vs. 13.1 vs. 2.7), and atypical cells (885.1 vs. 108.9 vs. 30.8) compared to SHGUC and AUC, respectively.
- Top-24 and suspicious cells displayed higher N:C ratio (0.65-0.66) and larger nuclear area (106-113 mm 2 ) than atypical cells (0.57 and 86-91 mm 2 ) across three categories.
- Percentage of cells with all 3 key TPS morphological features across 3 categories:
o Top-24 cells- 84%-95%
o Suspicious cells- 81%-91%
o Atypical cells- 22%-39%
- Critical distinguishing feature between suspicious and atypical was hyperchromasia
o 93% of suspicious cells
o 24%-40% of atypical cells.
- Percentage of top-24 / suspicious cells with all 3 TPS features:
o HGUC (95% / 91%)
o SHGUC (89% / 89%)
o AUC (84% / 81%)
CONCLUSIONS:
HGUC showed the highest numbers of abnormal urothelial cells compared to SHGUC and AUC. N/C ratio and nuclear sizes were larger in top-24 and suspicious cell categories compared to the atypical cell category. Hyperchromasia was the most important distinguishing morphologic feature between suspicious and atypical cells. HGUC had the highest % of top-24 and suspicious cells with all 3 TPS morphologic features, indicating that the AI algorithm correctly selected features predicting HGUC. These findings highlight AI’s potential to enhance accuracy and efficiency in bladder cancer diagnosis.
March 2025
WHOLE SLIDE IMAGE SCANNER STUDIES
USCAP 2025 Poster Presentation
Does Digital Scanner Selection Impact Urine Cytology Whole Slide Imaging? A Comparative Study of Five Commercial Digital Scanning Devices
Does Digital Scanner Selection Impact Urine Cytology Whole Slide Imaging? A Comparative Study of Five Commercial Digital Scanning Devices
STUDY DESIGN:
- Ten de-identified ThinPrep Urocyte slides with surgical concordance as gold standard/ground truth (4 NHGUC, 2 AUC, 1 SHGUC, 3 HGUC) digitized into WSIs using five digital imagers:
o Leica Aperio AT2
o Hamamatsu S360
o 3DHistech P1000
o Customized Huron WSI model
o Mikroscan SLxCyto
- AI algorithm was applied to the WSIs to detect suspicious cells (high-malignant risk) and atypical urothelial cells (low-malignant risk).
- 3 cytologists (CT) reported diagnosis on slides with 2-week washout period between arms:
o Arm 1- Microscopy only
o Arm 2- AI-assisted WSI review
- Performance Metrics:
o WSI conversion rate
o Comparison of binary (positive vs negative) diagnosis (AUC, SHGUC, and HGUC cases = positive) with ground truth diagnosis for 2 Arms
o Quantitative data analysis
RESULTS:
- All digital imagers achieved a 100% WSI conversion rate.
- In the binary diagnosis, AI-assisted WSI review demonstrated performance comparable to microscopy across all imagers
- Quantitative analysis revealed slight variations in key metrics, including suspicious/atypical cell numbers, nuclear-to-cytoplasmic (N:C) ratio, and nuclear area, among WSIs produced by different imagers
CONCLUSIONS:
First study to assess multiple digital pathology imagers for AI-assisted urine cytology. Results demonstrate that a disease-specific AI algorithm produces consistent diagnostic performance and quantitative analysis across different WSIs, supporting its potential to enhance diagnostic accuracy across imaging platforms.
March 2025
AIxTHY THYROID FINE NEEDLE ASPIRATION CLINICAL STUDIES
USCAP 2025 Oral Presentation
Assessing Role of Artificial Intelligence in Thyroid Cytology: A Feasibility Study in Clinical Practice
Assessing Role of Artificial Intelligence in Thyroid Cytology: A Feasibility Study in Clinical Practice
STUDY DESIGN:
• 100 thyroid ThinPrep slides categorized for ground 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 WSIs and analyzed with AI-assistance software (AIxTHY)
• 1 cytopathologist (CP) and 2 cytologists (CT) evaluated slides with a 2-week washout period between research arms:
o Arm 1- Microscopy only
o Arm 2- WSI only
o Arm 3- WSI with AI-assistance
• Performance Metrics: Comparison of study diagnosis with ground truth diagnosis for 3 Arms, using following cut-off values:
o Threshold 1: Negative = TBS II; Positive = V or VI (III and IV are indeterminate)
o Threshold 2: Negative = TBS II; Positive = IV, V, VI (III excluded)
o Threshold 3: Negative = TBS II (Benign); Positive = III, IV, V, VI (Atypia of undetermined significance, Follicular neoplasm, Suspicious for malignancy, Malignant)
o All TBS I (Nondiagnostic) cases were excluded from the study
RESULTS:
- Threshold 1 (TBS V+ as positive) showed highest accuracy and consensus with biopsy and cytology (Arm 1 = 100%; Arm 2 = 95.7%;Arm 3 = 100%)
- Threshold 3 (TBS III+ as positive) showed accuracy of Arm 1 = 75.8%; Arm 2 = 72.7%; Arm 3 = 72.9%
- For AI-assistance (Arm 3), Threshold TBS iV+ had higher Sensitivity (93.5%), Specificity (96.2%), PPV (96.6% and NPV (92.6%)than including atypia (TBS III+)(Sensitivity = 94.3%; Specificity = 78.9%; PPV= 83.2%; NPV = 92.6%; accuracy 87.0%)
- Using consensus cytology+biopsy reports to determine accuracy yielded higher accuracy, compared to lower accuracy with cytology diagnosis alone
CONCLUSIONS:
The accuracy of AI-assisted thyroid cytology diagnosis closelyapproximates microscopic accuracy, but dependent on the cut-off point for“negative” and “positive” results. The best diagnostic review concordance occurswhen both cytology and biopsy results serve as the “ground truth” for thestudy.
November 2024
THE PARIS SYSTEM FOR URINE CYTOLOGY NUCLEAR TO CYTOPLASMIC RATIO
Pathology Visions Oral Presentation
AI-Driven Comparative Study of Cell Characteristics in Urine Cytology with Biopsy Correlation
AI-Driven Comparative Study of Cell Characteristics in Urine Cytology with Biopsy Correlation
DPA 2024 Oral Presentation Crothers BA et al. Tungs’ Taichung MetroHarbor Hospital, Show Chwan Memorial Hospital, Taipei Veteran’s General Hospital, Taichung Veteran’s General Hospital
STUDY DESIGN:
- 242 urine cytology slides (74 AUC, 56 SHGUC, 112 HGUC) from patients with biopsy-confirmed HGUC within a 6-month window
- 162 (67%) Cytospin, 60 (25%) TP-UroCyte, 20 (8%) BD CytoRich
- 124,980 abnormal cells inferred by AI-assisted digital software system (AIxURO)
- 54% of biopsy proven CIS or HGUC cases had a cytology interpretation of AUC or SHGUC; 46% cytology interpretation of HGUC
- Evaluation of N/C ratios and nuclear sizes for the top 24 most abnormal cells, and for the categories of suspicious cells vs atypical cells, with statistical significance
RESULTS:
- Average N/C ratios:some text
- Top 24 abnormal cells = 0.66 (95% CI; 0.65-0.66)
- Suspicious cell category = 0.65 (95% CI; 0.64-0.65)
- Atypical cell category = 0.57 (95% CI; 0.57-0.57)(p < 0.0001)
- Average nuclear size:some text
- Top 24 abnormal cells = 108.1-116.8 µm2
- Atypical cell category = 86.3-87.7 µm2
- Significantly larger nuclear sizes occurred in the top 24 abnormal and suspicious cell categories than in atypical cells category
- Nuclear size of biopsy:CIS cells was significantly larger than those of biopsy:HGUC cells for all AI-categories
- Slightly more HGUC biopsy cases were cytologically interpreted as AUC or SHGUC than as HGUC
CONCLUSIONS:
AI-assistance demonstrates a predictable quantitative advantage for assessment of nuclear size and N/C ratio when assessing atypical and suspicious cells using The Paris System. The average N/C ratio is lower (0.66) than that suggested for HGUC/SHGUC (0.70) in TPS.
November 2024
AIxURO URINE CYTOLOGY CLINICAL STUDIES
Academic Article: International Urology and Nephrology
Artificial Intelligence Algorithms Enhance Urine Cytology Reporting Confidence In Postoperative Follow-up For Upper Urinary Tract Urothelial Carcinoma
Artificial Intelligence Algorithms Enhance Urine Cytology Reporting Confidence In Postoperative Follow-up For Upper Urinary Tract Urothelial Carcinoma
International Urology and Nephrology, 2024: https://doi.org/10.1007/s11255-024-04270-8 Chen CC, Yen TH, Li JR, et al.
STUDY DESIGN:
- 296 urine cytology slides from 113 patients with upper tract urothelial carcinoma, with matching pre- and post-operative cytology, pathology, and follow up for recurrence
- Comparison of cytology slides digitized and independently assessed by AIxURO to original cytology report
RESULTS:
- 88/113 (77.8%) patients had 1-2 cytology specimens preoperatively
- 44/204 (21.5%) positive cytology slides with 34/113 patients diagnosed with upper tract carcinoma (UTUC)
- Postop recurrence detected in 27/113 patients (23%) at average 190 days
- 34/56 slides (60.7%) were negative for UTUC
- 8/27 patients (29.6%) met criteria for early diagnosis of intravesical recurrence
- AIxURO identified 2 more patients (10/27; 37%) with early intravesical recurrence
CONCLUSIONS:
AI-assisted diagnostic imaging (AIxURO) enhanced detection of underdiagnosed urine cytology slides to capture early recurrence in UTUC.
November 2024
SOFTWARE OPTIMIZATION & VALIDATION STUDIES
ASC Oral Presentation
Total Abnormal Cells in Bladder Cancer Screening: The Role of Artificial Intelligence-Based Logistic Models in Urine Cytology
Total Abnormal Cells in Bladder Cancer Screening: The Role of Artificial Intelligence-Based Logistic Models in Urine Cytology
ASC 2024 Oral Presentation / Hwang YT et al. / National Taipei University
STUDY DESIGN:
An AI-based logistic regression model was developed to determine the optimal number of abnormal urothelial cells (HGUC, SGHUC, or AUC) required to accurately predict the presence of bladder cancer. The study goal was to evaluate the accuracy and effectiveness of the logistic models in predicting bladder cancer from clinical urine cytology test datasets.
- 2025 cytology slide images (471 positives, 1334 negatives) were analyzed by the AI algorithm
- Abnormal cells were categorized as suspicious (SHGUC+) or atypical (AUC)
- Preparation types: Cytospin, ThinPrep, BD CytoRich, and TP-Urocyte
- Cell numbers were standardized by preparation sample area (mm2)
- Calculations:
- Suspicious cell numbers
- Log of suspicious cell numbers
- Atypical cell numbers
- Log of atypical cell numbers
- Performance Metrics: Accuracy, sensitivity, specificity, ROC curve
RESULTS:
- Logistic model- suspicious cells: 91.69 Accuracy, 64.29 Sensitivity, 95.44 Specificity
- Log Suspicious cells: 65.33 Accuracy, 95.24 Sensitivity, 61.24 Specificity
- Logistic model-atypical cells: 94.27 Accuracy, 69.05 Sensitivity, 97.72 Specificity
- Log Atypical cells: 76.22 Accuracy, 88.1 Sensitivity, 74.59 Specificity
- Cell cut-off value per preparation type:some text
- Suspicious cutoff value: 0.189 (Cytospin 5 cells, TP 59, CytoRich 25, UroCyte 10
- Atypical cutoff value: 1.823 (Cytospin 52 cells, TP 573, 242 CytoRich, 49 UroCyte
CONCLUSIONS:
Suspicious cell cut-off values support TPS criteria, with more than 5 suspicious cells categorized as SHGUC or higher indicating high likelihood of HGUC
Atypical cell cut-off values can aid in identifying potential false-negative cases when suspicious cell numbers are below cut-off values but atypical numbers are higher.
November 2024
THE PARIS SYSTEM FOR URINE CYTOLOGY NUCLEAR TO CYTOPLASMIC RATIO
ASC Poster Presentation
How does artificial intelligence redefine N:C ratio thresholds for diagnosing high-grade urothelial carcinoma?
How does artificial intelligence redefine N:C ratio thresholds for diagnosing high-grade urothelial carcinoma?
ASC 2024 Poster Presentation Hang JF, Yang WL, Yeh CH et al. TVGHTE, Natl Tung University, Show Chwan Mem Hospital, Tungs MetroHarbor Hospital N:C ratio pilot study_2024
STUDY DESIGN:
- 109 urine cytology cytospin cases with surgically-confirmed HGUC, HGUC-CIS, “positive” or CIS within a 6 month pre-or post-urine collection window
- Digitally analyzed by AIxURO AI-deep learning software for N/C ratio and nuclear area for the cytologic specimen diagnoses of AUC, SHGUC, and HGUC
- Comparison of the cytologic and surgical diagnoses by mean cell numbers per slide, mean N/C ratio, and mean nuclear area (µm2)
RESULTS:
- Cell Quantification: AIxURO categorized fewer suspicious cells (mean 160.0) compared to atypical cells (mean 929.6)
- N/C Ratio and Nuclear Area: Suspicious cells had higher mean N/C ratio (0.66 vs 0.58) and higher mean nuclear area (107.2 vs 66,9 µm2) than atypical cells
- Mean N/C for suspicious cells across all biopsies = 0.65 to 0.68
- Larger nuclear areas were also noted in SHGUC (13.9% difference) and HGUC (24.4% difference)
- Carcinoma in situ (CIS) had the largest mean nuclear area for both suspicious (117.3 µm2) and atypical (101.1 µm2) cells
CONCLUSIONS:
A lower mean N/C ratio for suspicious cells as an indicator of biopsy-proven HGUC using TPS should be considered, especially for AI-assisted urine cytology software programs. AIxURO categorized suspicious cells have a higher nuclear area than categorized atypical cells. Very large nuclear areas may be an indicator of CIS.
November 2024
WHOLE SLIDE IMAGE SCANNER STUDIES
Pathology Visions Poster Presentation
Do different digital imagers used with the AIxURO system impact performance in urine cytology?
Do different digital imagers used with the AIxURO system impact performance in urine cytology?
DPA 2024 Poster Presentation / Abstract Yang WL, Yang WC, Huang SM, et al. Show Chwan Hospital and AIxMED (pilot studies 2 & 3)
STUDY DESIGN:
- 183 urine cytology slides (140 CytoRich, 43 SurePath), with expert panel consensus diagnoses as NHGUC (83), AUC (45), SHGUC (27), and HGUC (28)
- Slides scanned by Leica AT2 and Hamamatsu S360 digital scanners with images inferred by the AI algorithm (AIxURO), using The Paris System (TPS) 2.0 criteria
- AIxURO separated abnormal cells into “suspicious” and “atypical” categories for investigator review
- 3-Arm Study:
- 6 reviewers (1 cytopathologist and 5 cytologists) interpreted the slides using conventional microscopy only (Arm 1), Leica whole slide image (WSI) with AIxURO AI-assistance (Arm 2), and Hamamatsu WSI with AIxURO AI-assistance (Arm 3) with a 2-week wash-out period between reviews
RESULTS:
3294 total reviews (microscopy + WSI + AIxURO); binary distribution as positive (AUC, SHGUC, or HGUC) or negative (NHGUC)
- Sensitivity and Specificity of AIxURO with Leica: 85.0% and 90.0%
- Sensitivity and Specificity of AIxURO with Hamamatsu: 82.9% and 89.6%
- Sensitivity and Specificity of microscopy only: 83.7% and 89.4%
- Total Time for review of AIxURO with Leica: 37.4 seconds
- Total Time for Review of AIxURO with Hamamatsu: 53.1 seconds
- Total Time for Review of microscopy only: 82.0 seconds
- Reviewers (3) experienced with the AIxURO system had higher sensitivity (91.3% vs 78.7%) but lower specificity (87.7% vs 92.3%) and spent less time (30.6 sec vs 44.4 sec) than the 3 without experience
CONCLUSIONS:
Use of AI-assisted software (AIxURO) to classify abnormal urothelial cells into atypical or suspicious categories improved the overall sensitivity and specificity for a binary interpretation over conventional microscopy. Additionally, AI-assistance significantly reduced reporting time by 52.4% (AIxURO + Leica AT2) and 35.2% (AIxURO + Hamamatsu) compared to microscopy. Experienced users of AIxURO showed better overall performance, suggesting that training and experience with AI-assistance will improve performance.
November 2024
AIxURO URINE CYTOLOGY CLINICAL STUDIES
Pathology Visions Poster Presentation
Transforming bladder cancer diagnosis via AI-aided digital cytology integration in clinical workflow
Transforming bladder cancer diagnosis via AI-aided digital cytology integration in clinical workflow
DPA 2024 Poster Presentation / Abstract Sigfred Lajara, MD; Samer Khader, MD; Rajiv Dhir, MD; Daniel Geisler, MD; Jacqueline Cuda, SCT; Caroline Horne, SCT UPMC pilot study
STUDY DESIGN:
- 200 ThinPrep urine cytology slides (100 NHGUC, 35 AUC, 32 SHGUC, 33 HGUC) with diagnostic confirmation by 3 expert pathologists were digitized to WSIs using Mikroscan SLxCyto and analyzed by an AI-assisted program, AIxURO
- 1 cytopathologist (CP) and 2 cytologists (CT) reviewed urine slides or AI-assisted images with a 2-week washout period between reviews
- Arm 1: Microscopic review
- Arm 2: AI-assisted software (AIxURO) review
- Performance Metrics: Comparison of 2 diagnostic positive thresholds: AUC+ (AUC, SHGUC, and HGUC) and SHGUC+ (SHGUC and HGUC) and total time for interpretation
RESULTS:
- AI-assisted AIxURO showed higher sensitivity (85% vs 79.3%) but lower specificity (92% vs 98%) than microscopy overall, using AUC+ as the positive threshold
- AIxURO showed lower sensitivity (74.9% vs 76.9%) and specificity (96% vs 97.5%) than microscopy using SHGUC+ as the positive threshold.
- Review Time: AIxURO markedly reduced review time (37.4 s) compared to microscopy (102.6 s) overall. CTs spent almost double the time for microscopy (121.6 s) compared to the CP (64.6 s).
CONCLUSIONS:
AIxURO showed a 5.7% increase in sensitivity and 8.6% decrease in specificity compared to microscopy, suggesting that while AIxURO helps to ID more positive cases, it results in higher false positives. At SHGUC+ threshold, AIxURO showed a 2% decrease in sensitivity and 1.5% decrease in specificity, suggesting that reviewers diagnose more cases as AUC than with microscopy. AIxURO saves reviewers 63.5% of evaluation time compared to microscopy, at more consistent evaluation times. CTs spend substantially less evaluation time than CP using AIxURO.
Upcoming Events
No items found.
Latest news
February 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
