Artificial Intelligence for Segmentation of Bladder Tumor Cystoscopic Images Performed by U-Net with Dilated Convolution

Mutaguchi, Jun; Morooka, Ken’ichi; Kobayashi, Seiichiro; Umehara, Aiko; Miyauchi, Satoru; Kinoshita, Fumio; Inokuchi, Junichi; Oda, Yoshinao; Kurazume, Ryo; Eto, Masatoshi

doi:10.1089/end.2021.0483

Cited by 15 publications

(10 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The U-Net architecture [ 76 ] is a convolutional neural network architecture, which has been widely used for the segmentation of medical images. To cite just a few, U-Nets have been used in the segmentation of osteosarcoma in computed tomography scans [ 80 ], lung tumors in CT scans [ 81 ], lesions of the breast in ultrasound images [ 82 ], tumors of the bladder in cystoscopic images [ 83 ], breast and fibroglandular tissue in magnetic resonance [ 84 ] and nuclei in hematoxylin and eosin-stained slices [ 85 ]. The essence of the U-Net architecture is a combination of downsampling steps (also known as the contracting path) obtained by convolutions and downsampling, which are followed by upsampling steps (also known as the expansive path) ( Figure 5 ).…”

Section: Materials and Methodsmentioning

confidence: 99%

Impact of Training Data, Ground Truth and Shape Variability in the Deep Learning-Based Semantic Segmentation of HeLa Cells Observed with Electron Microscopy

2023

View full text Add to dashboard Cite

This paper investigates the impact of the amount of training data and the shape variability on the segmentation provided by the deep learning architecture U-Net. Further, the correctness of ground truth (GT) was also evaluated. The input data consisted of a three-dimensional set of images of HeLa cells observed with an electron microscope with dimensions 8192×8192×517. From there, a smaller region of interest (ROI) of 2000×2000×300 was cropped and manually delineated to obtain the ground truth necessary for a quantitative evaluation. A qualitative evaluation was performed on the 8192×8192 slices due to the lack of ground truth. Pairs of patches of data and labels for the classes nucleus, nuclear envelope, cell and background were generated to train U-Net architectures from scratch. Several training strategies were followed, and the results were compared against a traditional image processing algorithm. The correctness of GT, that is, the inclusion of one or more nuclei within the region of interest was also evaluated. The impact of the extent of training data was evaluated by comparing results from 36,000 pairs of data and label patches extracted from the odd slices in the central region, to 135,000 patches obtained from every other slice in the set. Then, 135,000 patches from several cells from the 8192×8192 slices were generated automatically using the image processing algorithm. Finally, the two sets of 135,000 pairs were combined to train once more with 270,000 pairs. As would be expected, the accuracy and Jaccard similarity index improved as the number of pairs increased for the ROI. This was also observed qualitatively for the 8192×8192 slices. When the 8192×8192 slices were segmented with U-Nets trained with 135,000 pairs, the architecture trained with automatically generated pairs provided better results than the architecture trained with the pairs from the manually segmented ground truths. This suggests that the pairs that were extracted automatically from many cells provided a better representation of the four classes of the various cells in the 8192×8192 slice than those pairs that were manually segmented from a single cell. Finally, the two sets of 135,000 pairs were combined, and the U-Net trained with these provided the best results.

show abstract

Section: Materials and Methodsmentioning

confidence: 99%

Impact of Training Data, Ground Truth and Shape Variability in the Deep Learning-Based Semantic Segmentation of HeLa Cells Observed with Electron Microscopy

2023

View full text Add to dashboard Cite

show abstract

“…Prior studies of deep learning for cystoscopy images utilized still images, either captured directly by surgeons or extracted from cystoscopy videos to curate a cystoscopy atlas [6][7][8][9][10][11]. In these studies, the collection of still images for cystoscopy data followed a prede ned selection criteria of frames (e.g., a single frame with the best representation of the lesion, every 10th frame, the rst 30 frames) to reduce data dimensionality and redundancy; however, this approach considers cystoscopy data to be static, which is not re ective of the real-world condition and the dynamic streaming content, and therefore limits the ability to generate generalizable and relevant data.…”

Section: Discussionmentioning

confidence: 99%

“…Storage of cystoscopy images and videos, however, is uncommon due to lack of e cient infrastructure for storage and retrieval of large videos les. In addition to visual documentation, capturing cystoscopy images and videos could be useful for curation of educational cystoscopy atlases [4,5] and the development of computer-aided solutions for augmented endoscopic imaging [6][7][8][9][10][11].…”

Section: Introductionmentioning

confidence: 99%

An Efficient Framework for Video Documentation of Bladder Lesions for Cystoscopy: A Proof-of-Concept Study

Eminaga

Shkolyar

et al. 2022

J Med Syst

View full text Add to dashboard Cite

The identi cation of relevant frame sequences in an endoscopy video is labor-intensive and complicated by the poor data integrity of endoscopic information. We designed a surgeon-guided framework to e ciently manage the visual data from commonly performed bladder endoscopy (cystoscopy) videos.Screenshots of bladder lesions were captured during cystoscopy during transurethral resection of bladder tumor, then manually labeled according to case identi cation, date, lesion location, imaging modality, and pathology. The framework used the screenshot to search for and extract a corresponding 10-second video clip. Each video clip included a one-second space holder with a QR barcode informing the video content. The success of the framework was measured by the secondary use of these short clips and the reduction of storage volume required for video materials. From 86 cases, the framework successfully generated 249 video clips from 230 screenshots, with 14 erroneous video clips from 8 screenshots excluded. The HIPPA-compliant barcodes provided information of video contents with a 100% data completeness. A web-based educational gallery was curated with various diagnostic categories and annotated frame sequences. Compared with the unedited videos, the informative short video clips reduced the storage volume by 99.5%. In conclusion, our framework expedites the generation of visual contents with surgeon's instruction for cystoscopy and potential incorporation of video data towards applications including clinical documentation, education, and research.

show abstract

“…Gastrointestinal endoscopy AI technologies published during the same period were also referenced for comparison. Of the 384 articles identified, 8 [4,5 ▪▪ ,6–9,10 ▪ ,11 ▪▪ ] were original papers, 1 [12] was an editorial comment, 1 [13 ▪ ] was a review, and 6 [14–19] were conference abstracts related to cystoscopy.…”

Section: Methodsmentioning

confidence: 99%

Overview of current applications and trends in artificial intelligence for cystoscopy and transurethral resection of bladder tumours

Ikeda,

Nosato

2023

Current Opinion in Urology

View full text Add to dashboard Cite

Purpose of review Accurate preoperative and intraoperative identification and complete resection of bladder cancer is essential. Adequate postoperative follow-up and observation are important to identify early intravesical recurrence or progression. However, the accuracy of diagnosis and treatment is dependent on the knowledge and experience of the physicians. Artificial intelligence (AI) can be an important tool for physicians performing cystoscopies. Recent findings Reports published over the past year and a half have identified an adequate amount of cystoscopy datasets for deep learning, with rich datasets of multiple tumour types including images of flat, carcinoma-in-situ, and elevated lesions, and more diverse applications. In addition to detecting bladder tumours, AI can assist in diagnosing interstitial cystitis. Applications of AI using conventional white-light and also to bladder endoscopy with different image enhancement techniques and manufacturers is underway. A framework has also been proposed to standardise the management of clinical data from cystoscopy to aid education and AI development and to compare with gastrointestinal endoscopic AI. Although real-world clinical applications have lagged, technological developments are progressing. Summary AI-based cystoscopy is likely to become an important tool and is expected to have real-world clinical applications comprehensively linking AI and imaging, data management systems, and clinicians. Video abstract http://links.lww.com/COU/A45

show abstract

Artificial Intelligence for Segmentation of Bladder Tumor Cystoscopic Images Performed by U-Net with Dilated Convolution

Cited by 15 publications

References 24 publications

Impact of Training Data, Ground Truth and Shape Variability in the Deep Learning-Based Semantic Segmentation of HeLa Cells Observed with Electron Microscopy

Impact of Training Data, Ground Truth and Shape Variability in the Deep Learning-Based Semantic Segmentation of HeLa Cells Observed with Electron Microscopy

An Efficient Framework for Video Documentation of Bladder Lesions for Cystoscopy: A Proof-of-Concept Study

Overview of current applications and trends in artificial intelligence for cystoscopy and transurethral resection of bladder tumours

Contact Info

Product

Resources

About