Parameterized Extraction of Tiles in Multilevel Gigapixel Images

Wetteland, Rune; Engan, Kjersti; Eftesol, Trygve

doi:10.1109/ispa52656.2021.9552104

Cited by 5 publications

(5 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tiles of size 256×256 were extracted from annotated regions at 400x magnification. Tiles at different magnifications were extracted so that the center of the tile remains the same for all views, as described in [25]. An example of this can be seen in Fig.…”

Section: Methodsmentioning

confidence: 99%

Invasive Cancerous Area Detection in Non-Muscle Invasive Bladder Cancer Whole Slide Images

Fuster

Khoraminia

Kiraz

et al. 2022

2022 IEEE 14th Image, Video, and Multidimensional Signal Processing Workshop (IVMSP)

Self Cite

View full text Add to dashboard Cite

Bladder cancer patients' stratification into risk groups relies on grade, stage and clinical factors. For non-muscle invasive bladder cancer, T1 tumours that invade the subepithelial tissue are high-risk lesions with a high probability to progress into an aggressive muscle-invasive disease. Detecting invasive cancerous areas is the main factor for dictating the treatment strategy for the patient. However, defining invasion is often subject to intra/interobserver variability among pathologists, thus leading to over or undertreatment. Computer-aided diagnosis systems can help pathologists reduce overheads and erratic reproducibility. We propose a multi-scale model that detects invasive cancerous areas patterns across the whole slide image. The model extracts tiles of different tissue types at multiple magnification levels and processes them to predict invasive patterns based on local and regional information for accurate T1 staging. Our proposed method yields an F1 score of 71.9, in controlled settings 74.9, and without infiltration 90.0.

show abstract

Section: Methodsmentioning

confidence: 99%

Invasive Cancerous Area Detection in Non-Muscle Invasive Bladder Cancer Whole Slide Images

Fuster

Khoraminia

Kiraz

et al. 2022

2022 IEEE 14th Image, Video, and Multidimensional Signal Processing Workshop (IVMSP)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Square patches of different sizes are commonly used. Smaller sizes are often used for DL models [41] to reduce the computational burden and to avoid excessive information within the patch. In some cases, bigger patch sizes might be needed to capture whole histopathological areas such as complete glands [40].…”

Section: Wsi Handlingmentioning

confidence: 99%

“…While this technique can mimic how the pathologists work when zooming in and out to get details or context, it requires complex models in order to be able to handle the different levels [38], [42]. To cover the entire WSI, patches are usually extracted using a sliding window with or without overlapping between patches [41]. If annotation masks are available, the patching can be performed only within ROI [43] or labeled areas, reducing the amount of irrelevant patches.…”

Section: Wsi Handlingmentioning

confidence: 99%

“…The extracted patches often become the actual dataset, substituting the use of the WSIs [44]. An alternative approach is patching "on-the-fly" [9], where a WSI-specific list of patch coordinates is stored [41], [42]. The extra storage required for different patching configurations is reduced because the patches must not be saved separately, and the flexibility for posterior processing is more flexible in terms of size, resolution, and overlapping.…”

Section: Wsi Handlingmentioning

confidence: 99%

“…The best patching option should be chosen according to the task, model, memory, and computational constraints, and is a trade-off between these requirements [9]. Patching details are often briefly mentioned in research papers, but any subsequent steps will be affected by the patching procedure, making reproducible patching critical for reproducible research [41].…”

Section: Wsi Handlingmentioning

confidence: 99%

See 2 more Smart Citations

The Devil is in the Details: Whole Slide Image Acquisition and Processing for Artifacts Detection, Color Variation, and Data Augmentation: A Review

et al. 2022

Self Cite

View full text Add to dashboard Cite

Whole Slide Images (WSI) are widely used in histopathology for research and the diagnosis of different types of cancer. The preparation and digitization of histological tissues leads to the introduction of artifacts and variations that need to be addressed before the tissues are analyzed. WSI preprocessing can significantly improve the performance of computational pathology systems and is often used to facilitate human or machine analysis. Color processing techniques are usually the main concern, while other areas are frequently ignored. In this paper, we present a detailed study of the state-of-the-art in three different areas of WSI preprocessing: Artifacts detection, color variation, and the emerging field of pathology-specific data augmentation. We include a summary of evaluation techniques along with a discussion of possible limitations and future research directions for new methods.

show abstract

Automatic Diagnostic Tool for Predicting Cancer Grade in Bladder Cancer Patients Using Deep Learning

et al. 2021

View full text Add to dashboard Cite

The most common type of bladder cancer is urothelial carcinoma, which is among the cancer types with the highest recurrence rate and lifetime treatment cost per patient. Diagnosed patients are stratified into risk groups, mainly based on grade and stage. However, it is well known that correct grading of bladder cancer suffers from intra-and interobserver variability and inconsistent reproducibility between pathologists, potentially leading to under-or overtreatment of the patients. The economic burden, unnecessary patient suffering, and additional load on the health care system illustrate the importance of developing new tools to aid pathologists. We propose a pipeline, called TRI grade , that will identify diagnostic relevant regions in the whole-slide image (WSI) and collectively predict the grade of the current WSI. The system consists of two main models, trained on weak slide-level grade labels. First, a WSI is segmented into the different tissue classes (urothelium, stroma, muscle, blood, damaged tissue, and background). Next, tiles are extracted from the diagnostic relevant urothelium tissue from three magnification levels (25x, 100x, and 400x) and processed sequentially by a convolutional neural network (CNN) based model. Ten models were trained for the slide-level grading experiment, where the best model achieved an F1-score of 0.90 on a test set consisting of 50 WSIs. The best model was further evaluated on a smaller segmentation test set, consisting of 14 WSIs where low-and high-grade regions were annotated by a pathologist. The TRI grade pipeline achieved an average F1-score of 0.91 for both the low-grade and high-grade classes.INDEX TERMS Automated cancer grading, bladder cancer, convolutional neural networks, multiscale classification, urothelial carcinoma, weakly labelled data, whole-slide image.

show abstract

Parameterized Extraction of Tiles in Multilevel Gigapixel Images

Cited by 5 publications

References 17 publications

Invasive Cancerous Area Detection in Non-Muscle Invasive Bladder Cancer Whole Slide Images

Invasive Cancerous Area Detection in Non-Muscle Invasive Bladder Cancer Whole Slide Images

The Devil is in the Details: Whole Slide Image Acquisition and Processing for Artifacts Detection, Color Variation, and Data Augmentation: A Review

Automatic Diagnostic Tool for Predicting Cancer Grade in Bladder Cancer Patients Using Deep Learning

Contact Info

Product

Resources

About