A Randomized Trial of PHOTOdynamic Surgery in Non–Muscle-Invasive Bladder Cancer

Heer, Rakesh; Lewis, Rebecca; Vadiveloo, Thenmalar; Yu, Ge; Mariappan, Paramananthan; Cresswell, Joanne; McGrath, John; Nabi, Ghulam; Mostafid, Hugh; Lazarowicz, Henry; Kelly, John D.; Duncan, Anne; Penegar, Steven; Breckons, Matt; Wilson, Laura; Clark, Emma; Feber, Andrew; Orozco-Leal, Giovany; Tandoğdu, Zafer; Taylor, Ernest; N’Dow, James; Norrie, John; Ramsay, Craig; Rice, Stephen; Vale, Luke; MacLennan, Graeme; Hall, Emma

doi:10.1056/evidoa2200092

Cited by 31 publications

(11 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Despite reported benefit in improved tumor detection, adoption of BLC remains limited due to the increased cost of specialized cystoscopic equipment and imaging agent, as well as clinical workflow demand to instill the imaging agent into the bladder 1 hour in advance of BLC. Moreover, a recent randomized controlled trial of BLC versus WLC failed to demonstrate a benefit to recurrence-free survival at 3 years, but did confer some additional cost (Heer et al 2022). Cost-effective, noninvasive, and easily adoptable adjunct imaging technologies are needed to address the diagnostic shortcomings of both WLC and BLC.…”

Section: Introductionmentioning

confidence: 99%

Tumor detection under cystoscopy with transformer-augmented deep learning algorithm

Jia,

Shkolyar,

Laurie

et al. 2023

Phys. Med. Biol.

View full text Add to dashboard Cite

Objective. Accurate tumor detection is critical in cystoscopy to improve bladder cancer resection and decrease recurrence. Advanced deep learning algorithms hold the potential to improve the performance of standard white-light cystoscopy (WLC) in a noninvasive and cost-effective fashion. The purpose of this work is to develop a cost-effective, transformer-augmented deep learning algorithm for accurate detection of bladder tumors in WLC and to assess its performance on archived patient data. Approach. ‘CystoNet-T’, a deep learning-based bladder tumor detector, was developed with a transformer-augmented pyramidal CNN architecture to improve automated tumor detection of WLC. CystoNet-T incorporated the self-attention mechanism by attaching transformer encoder modules to the pyramidal layers of the feature pyramid network (FPN), and obtained multi-scale activation maps with global features aggregation. Features resulting from context augmentation served as the input to a region-based detector to produce tumor detection predictions. The training set was constructed by 510 WLC frames that were obtained from cystoscopy video sequences acquired from 54 patients. The test set was constructed based on 101 images obtained from WLC sequences of 13 patients. Main results. CystoNet-T was evaluated on the test set with 96.4 F1 and 91.4 AP (Average Precision). This result improved the benchmark of Faster R-CNN and YOLO by 7.3 points in F1 and 3.8 points in AP. The improvement is attributed to the strong ability of global attention of CystoNet-T and better feature learning of the pyramids architecture throughout the training. The model was found to be particularly effective in highlighting the foreground information for precise localization of the true positives while favorably avoiding false alarms Significance. We have developed a deep learning algorithm that accurately detects bladder tumors in WLC. Transformer-augmented AI framework promises to aid in clinical decision-making for improved bladder cancer diagnosis and therapeutic guidance.

show abstract

Section: Introductionmentioning

confidence: 99%

Tumor detection under cystoscopy with transformer-augmented deep learning algorithm

Jia,

Shkolyar,

Laurie

et al. 2023

Phys. Med. Biol.

View full text Add to dashboard Cite

show abstract

“…Since WLC may miss at least 20% of bladder cancers [3], adjunct image modality like photodynamic diagnosis (PDD), or blue light cystoscopy (BLC) can be indicated to increase the detection sensitivity of cystoscopy [4]. Although BLC results in a better sensitivity for bladder tumors (80-99%) than WLC (70-90%), both image modalities suffer from poor to moderate specificities (34-70%) [5][6][7] and the additive benefit of BLC for recurrence free survival is limited [8].…”

Section: Introductionmentioning

confidence: 99%

Potential of educational cystoscopy atlas for augmented intelligence

Eminaga

Laurie

Lee

et al. 2023

Advanced Biomedical and Clinical Diagnostic and Surgical Guidance Systems XXI

View full text Add to dashboard Cite

Background: Cystoscopy is a common urological procedure for evaluation and treatment of diseases of the lower urinary tract. Cystoscopic recognition of cancerous and benign lesions of the bladder may be challenging given the wide spectrum of pathology and the experience of the urologist. Although computer-aided detection tools hold the potential to improve the urologist's performance, compiling a comprehensive dataset to train such tools remain a challenge. Educational cystoscopy atlas represents an alternative strategy to overcome this challenge. Materials and Methods:Mimicking the human behavior, we utilized an educational cystoscopy atlas to develop deep learning models for lesion detection. We applied a total of 312 images representing 7 major urologic findings from a cystoscopy atlas. A random image augmentation was applied to these images and included color contrast manipulation, image flipping and shearing. We utilized a neural architecture search to determine the optimal model design; For each case, we examined the area under the receiver operating characteristic (AUROC), the specificity, sensitivity, the positive predictive value (PPV) and the negative predictive value (NPV) and to classify frames according to the cancer presence status on 68 cystoscopy videos. Results:The median per-case AUROC for the frame classification was 0.680 by a median specificity of 0.312 and a median sensitivity of 0.867. At frame level, the median per-case PPV was 0.347 and the median per-case NPV was 0.837. All lesions were correctly flagged by our model. Conclusion:Our results unravel the potential utility of educational cystoscopy atlas for augmented intelligence.

show abstract

“…Although BLC results in a better sensitivity for bladder tumors (92.3-99%) than WLC (80-90%), both image modalities suffer from poor specificities (34-70%) [5][6][7]. In a recent randomized-controlled trial, BLC failed to demonstrate a benefit to recurrence free survival [8]. BLC requires instillation of a photo-sensitive fluorescence agent, costly specialized equipment, and additional provider training and experience.…”

Section: Introductionmentioning

confidence: 99%

Sequential modeling for cystoscopic image classification

Laurie

Eminaga

Shkolyar

et al. 2023

Advanced Photonics in Urology 2023

View full text Add to dashboard Cite

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.

show abstract

A Randomized Trial of PHOTOdynamic Surgery in Non–Muscle-Invasive Bladder Cancer

Cited by 31 publications

References 26 publications

Tumor detection under cystoscopy with transformer-augmented deep learning algorithm

Tumor detection under cystoscopy with transformer-augmented deep learning algorithm

Potential of educational cystoscopy atlas for augmented intelligence

Sequential modeling for cystoscopic image classification

Contact Info

Product

Resources

About