Matches in SemOpenAlex for { <https://semopenalex.org/work/W4324132519> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W4324132519 abstract "Background: Cystoscopy is a common endoscopic procedure to examine the lower urinary tract, particularly the bladder, for potential tumors, lesions, or other sources of hematuria. Cystoscopy has recognized shortcomings including missed tumors and differentiation of benign from cancerous lesions. Clinical outcomes are affected by variable provider experience. Deep learning models have been proposed to address these issues. Because real-time cystoscopy consists of sequential frames, we explored a novel class of DL models to classify frames of bladder tumors using sequential inputs. Materials and Methods: We considered four state-of-the-art sequential models (SlowFast, Multiscale Vision Transformers, X3D, and CNN-LSTM). Models were trained with different sequence lengths. The development set consisted of 196 10-second video clips from 76 cystoscopies (70 patients). The validation set consisted of 68 full-length cystoscopy videos with 216,870 frames (60 patients) were annotated for pathologically confirmed bladder tumors. Model performance was measured according to sensitivity, specificity, and AUC at the frame-level for detection of region of interest (ROI). We also collected the inference time for each model to assess real-time feasibility. Results: Model performance varied by model architecture and sequence length. We defined three new evaluation metrics: per-ROI accuracy, per-block sensitivity, and per-block specificity. The best performing model (X3D) with a sequence length of 8 achieved a per-ROI sensitivity of 100%, per-block sensitivity of 94.7%, and per-block specificity of 80.0%. X3D also provided the best trade-off between accuracy and efficiency. Conclusion: Sequential modeling has the potential to accurately classify a wide variety of bladder tumors in a real-time setting." @default.
- W4324132519 created "2023-03-15" @default.
- W4324132519 creator A5003413325 @default.
- W4324132519 creator A5017505168 @default.
- W4324132519 creator A5020136401 @default.
- W4324132519 creator A5040092574 @default.
- W4324132519 creator A5055415605 @default.
- W4324132519 creator A5061741626 @default.
- W4324132519 creator A5065153826 @default.
- W4324132519 creator A5071759528 @default.
- W4324132519 creator A5087105596 @default.
- W4324132519 creator A5088044242 @default.
- W4324132519 date "2023-03-14" @default.
- W4324132519 modified "2023-10-17" @default.
- W4324132519 title "Sequential modeling for cystoscopic image classification" @default.
- W4324132519 cites W1572827793 @default.
- W4324132519 cites W2112229406 @default.
- W4324132519 cites W2126938607 @default.
- W4324132519 cites W2138925237 @default.
- W4324132519 cites W2302501749 @default.
- W4324132519 cites W2787110013 @default.
- W4324132519 cites W2806489088 @default.
- W4324132519 cites W3110795479 @default.
- W4324132519 cites W4252240752 @default.
- W4324132519 cites W4252684946 @default.
- W4324132519 cites W4300089637 @default.
- W4324132519 cites W4307043455 @default.
- W4324132519 doi "https://doi.org/10.1117/12.2649334" @default.
- W4324132519 hasPublicationYear "2023" @default.
- W4324132519 type Work @default.
- W4324132519 citedByCount "1" @default.
- W4324132519 countsByYear W43241325192023 @default.
- W4324132519 crossrefType "proceedings-article" @default.
- W4324132519 hasAuthorship W4324132519A5003413325 @default.
- W4324132519 hasAuthorship W4324132519A5017505168 @default.
- W4324132519 hasAuthorship W4324132519A5020136401 @default.
- W4324132519 hasAuthorship W4324132519A5040092574 @default.
- W4324132519 hasAuthorship W4324132519A5055415605 @default.
- W4324132519 hasAuthorship W4324132519A5061741626 @default.
- W4324132519 hasAuthorship W4324132519A5065153826 @default.
- W4324132519 hasAuthorship W4324132519A5071759528 @default.
- W4324132519 hasAuthorship W4324132519A5087105596 @default.
- W4324132519 hasAuthorship W4324132519A5088044242 @default.
- W4324132519 hasConcept C115961682 @default.
- W4324132519 hasConcept C153180895 @default.
- W4324132519 hasConcept C154945302 @default.
- W4324132519 hasConcept C41008148 @default.
- W4324132519 hasConcept C75294576 @default.
- W4324132519 hasConceptScore W4324132519C115961682 @default.
- W4324132519 hasConceptScore W4324132519C153180895 @default.
- W4324132519 hasConceptScore W4324132519C154945302 @default.
- W4324132519 hasConceptScore W4324132519C41008148 @default.
- W4324132519 hasConceptScore W4324132519C75294576 @default.
- W4324132519 hasLocation W43241325191 @default.
- W4324132519 hasOpenAccess W4324132519 @default.
- W4324132519 hasPrimaryLocation W43241325191 @default.
- W4324132519 hasRelatedWork W133358225 @default.
- W4324132519 hasRelatedWork W1577137544 @default.
- W4324132519 hasRelatedWork W1988312369 @default.
- W4324132519 hasRelatedWork W2041525275 @default.
- W4324132519 hasRelatedWork W2508908072 @default.
- W4324132519 hasRelatedWork W2509146328 @default.
- W4324132519 hasRelatedWork W2537156416 @default.
- W4324132519 hasRelatedWork W2742991909 @default.
- W4324132519 hasRelatedWork W2996038082 @default.
- W4324132519 hasRelatedWork W7626849 @default.
- W4324132519 isParatext "false" @default.
- W4324132519 isRetracted "false" @default.
- W4324132519 workType "article" @default.