Accurate diagnostic tissue segmentation and concurrent disease subtyping with small datasets
Purpose: To provide a flexible, end-to-end platform for visually distinguishing diseased from undiseased tissue in a medical image, in particular pathology slides, and classifying diseased regions by subtype. Highly accurate results are obtained using small training datasets and reduced-scale source...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-01-01
|
| Series: | Journal of Pathology Informatics |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S215335392200774X |
| _version_ | 1811177282164752384 |
|---|---|
| author | Steven J. Frank |
| author_facet | Steven J. Frank |
| author_sort | Steven J. Frank |
| collection | DOAJ |
| description | Purpose: To provide a flexible, end-to-end platform for visually distinguishing diseased from undiseased tissue in a medical image, in particular pathology slides, and classifying diseased regions by subtype. Highly accurate results are obtained using small training datasets and reduced-scale source images that can be easily shared. Approach: An ensemble of lightweight convolutional neural networks (CNNs) is trained on different subsets of images derived from a relatively small number of annotated whole-slide histopathology images (WSIs). The WSIs are first reduced in scale in a manner that preserves anatomic features critical to analysis while also facilitating convenient handling and storage. The segmentation and subtyping tasks are performed sequentially on the reduced-scale images using the same basic workflow: generating and sifting tiles from the image, then classifying each tile with an ensemble of appropriately trained CNNs. For segmentation, the CNN predictions are combined using a function to favor a selected similarity metric, and a mask or map for a a candidate image is produced from tiles whose combined predictions exceed a decision boundary. For subtyping, the resulting mask is applied to the candidate image, and new tiles are derived from the unoccluded regions. These are classified by the subtyping CNNs to produce an overall subtype prediction. Results and conclusion: This approach was applied successfully to two very different datasets of large WSIs, one (PAIP2020) involving multiple subtypes of colorectal cancer and the other (CAMELYON16) single-type breast cancer metastases. Scored using standard similarity metrics, the segmentations outperformed more complex models typifying the state of the art. |
| first_indexed | 2024-04-10T22:59:07Z |
| format | Article |
| id | doaj.art-74ece0eb4dd54240b414d14b4cc75220 |
| institution | Directory Open Access Journal |
| issn | 2153-3539 |
| language | English |
| last_indexed | 2024-04-10T22:59:07Z |
| publishDate | 2023-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of Pathology Informatics |
| spelling | doaj.art-74ece0eb4dd54240b414d14b4cc752202023-01-14T04:26:37ZengElsevierJournal of Pathology Informatics2153-35392023-01-0114100174Accurate diagnostic tissue segmentation and concurrent disease subtyping with small datasetsSteven J. Frank0Corresponding author.; Med*A-Eye Technologies, Framingham, MA 01702, United StatesPurpose: To provide a flexible, end-to-end platform for visually distinguishing diseased from undiseased tissue in a medical image, in particular pathology slides, and classifying diseased regions by subtype. Highly accurate results are obtained using small training datasets and reduced-scale source images that can be easily shared. Approach: An ensemble of lightweight convolutional neural networks (CNNs) is trained on different subsets of images derived from a relatively small number of annotated whole-slide histopathology images (WSIs). The WSIs are first reduced in scale in a manner that preserves anatomic features critical to analysis while also facilitating convenient handling and storage. The segmentation and subtyping tasks are performed sequentially on the reduced-scale images using the same basic workflow: generating and sifting tiles from the image, then classifying each tile with an ensemble of appropriately trained CNNs. For segmentation, the CNN predictions are combined using a function to favor a selected similarity metric, and a mask or map for a a candidate image is produced from tiles whose combined predictions exceed a decision boundary. For subtyping, the resulting mask is applied to the candidate image, and new tiles are derived from the unoccluded regions. These are classified by the subtyping CNNs to produce an overall subtype prediction. Results and conclusion: This approach was applied successfully to two very different datasets of large WSIs, one (PAIP2020) involving multiple subtypes of colorectal cancer and the other (CAMELYON16) single-type breast cancer metastases. Scored using standard similarity metrics, the segmentations outperformed more complex models typifying the state of the art.http://www.sciencedirect.com/science/article/pii/S215335392200774XDigital pathologyTissue segmentationDeep learningWhole slide images |
| spellingShingle | Steven J. Frank Accurate diagnostic tissue segmentation and concurrent disease subtyping with small datasets Journal of Pathology Informatics Digital pathology Tissue segmentation Deep learning Whole slide images |
| title | Accurate diagnostic tissue segmentation and concurrent disease subtyping with small datasets |
| title_full | Accurate diagnostic tissue segmentation and concurrent disease subtyping with small datasets |
| title_fullStr | Accurate diagnostic tissue segmentation and concurrent disease subtyping with small datasets |
| title_full_unstemmed | Accurate diagnostic tissue segmentation and concurrent disease subtyping with small datasets |
| title_short | Accurate diagnostic tissue segmentation and concurrent disease subtyping with small datasets |
| title_sort | accurate diagnostic tissue segmentation and concurrent disease subtyping with small datasets |
| topic | Digital pathology Tissue segmentation Deep learning Whole slide images |
| url | http://www.sciencedirect.com/science/article/pii/S215335392200774X |
| work_keys_str_mv | AT stevenjfrank accuratediagnostictissuesegmentationandconcurrentdiseasesubtypingwithsmalldatasets |