Deep Learning Model based Ki-67 Index estimation with Automatically Labelled Data

Lakshmi, S.; Ritwik, Kotra Venkata Sai; Vijayasenan, Deepu; David, S Sumam; Sreeram, Saraswathy; Suresh, Pooja K

doi:10.1109/embc44109.2020.9175752

Cited by 2 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…CPATH systems use WSIs to segment tissue types (e.g., urothelium, connective tissue, or muscle) and/or identify cell characteristics (e.g., nuclei, cytoplasm) [ 24 , 25 , 26 ]. Segmented tissue can be used for classification, for example, normal vs. tumor tissue, grading, or staging.…”

Section: Resultsmentioning

confidence: 99%

“…Nevertheless, detecting molecular alterations in clinical practice is hindered by high costs and complexity, highlighting the need for alternative, affordable, and rapid methods. CPATH methods have shown promising results in detecting molecular alterations and are relatively cheap and fast [ 4 , 25 , 31 , 34 , 65 ]. Therefore, CPATH can be used as a pre-selection tool to determine eligibility for molecular testing and, ultimately, help with bridging the gap between molecular identification techniques and clinical practice.…”

Section: Resultsmentioning

confidence: 99%

“…Cell nuclei were segmented with an average accuracy of 93%, and the Ki-67 index was calculated with a margin error of 2.1%. Manual labeling of cell nuclei to train the algorithm was a limitation of this study, addressed in a subsequent study by the same group through the use of automatically labeled data [ 25 ]. Their improved algorithm achieved an 89% accuracy in segmenting cell nuclei, with the Ki-67 index measured with a 0.4% error.…”

Section: Resultsmentioning

confidence: 99%

See 2 more Smart Citations

Artificial Intelligence in Digital Pathology for Bladder Cancer: Hype or Hope? A Systematic Review

Khoraminia,

Fuster,

Kanwal

et al. 2023

Cancers

View full text Add to dashboard Cite

Bladder cancer (BC) diagnosis and prediction of prognosis are hindered by subjective pathological evaluation, which may cause misdiagnosis and under-/over-treatment. Computational pathology (CPATH) can identify clinical outcome predictors, offering an objective approach to improve prognosis. However, a systematic review of CPATH in BC literature is lacking. Therefore, we present a comprehensive overview of studies that used CPATH in BC, analyzing 33 out of 2285 identified studies. Most studies analyzed regions of interest to distinguish normal versus tumor tissue and identify tumor grade/stage and tissue types (e.g., urothelium, stroma, and muscle). The cell’s nuclear area, shape irregularity, and roundness were the most promising markers to predict recurrence and survival based on selected regions of interest, with >80% accuracy. CPATH identified molecular subtypes by detecting features, e.g., papillary structures, hyperchromatic, and pleomorphic nuclei. Combining clinicopathological and image-derived features improved recurrence and survival prediction. However, due to the lack of outcome interpretability and independent test datasets, robustness and clinical applicability could not be ensured. The current literature demonstrates that CPATH holds the potential to improve BC diagnosis and prediction of prognosis. However, more robust, interpretable, accurate models and larger datasets—representative of clinical scenarios—are needed to address artificial intelligence’s reliability, robustness, and black box challenge.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Artificial Intelligence in Digital Pathology for Bladder Cancer: Hype or Hope? A Systematic Review

Khoraminia,

Fuster,

Kanwal

et al. 2023

Cancers

View full text Add to dashboard Cite

show abstract

“…This indicates that assessing KI by means of algorithms is more reliable than assessing it based on human experience alone. The software often relies on color deconvolution algorithms to detect DAB chromogen-stained (brown) and hematoxylin-stained (blue) cell nuclei [11][12][13] . However, the staining results of the nuclei of tumor cells and non-tumor cells, such as lymphocytes and stromal cells, can cause KI to be underestimated or overestimated.…”

Section: Introductionmentioning

confidence: 99%

Consecutive Cytokeratin Immunochemistry-Supervised Algorithm for Predicting Tumor Areas in Ki67 Breast Cancer Images

Wu,

Chang,

Tsai

et al. 2024

Preprint

View full text Add to dashboard Cite

Automatic Ki67 index (KI) assessment has become popular in breast cancer research; however, the results are easily influenced by non-tumor cells. This can be addressed by using neural networks to predict tumor areas. Compared to human annotation, cytokeratin immunostaining can more accurately highlight epithelial regions and provide reliable ground truth. We built an immunohistochemistry (IHC)-supervised neural network using the ground truth extracted from consecutive cytokeratin-stained slides, which could predict the tumor area in Ki67 images of breast cancer. The effect of masks on KI quantification was evaluated in 20 patients with breast carcinoma. Set A (three cases) was used to measure the similarity of adjacent whole-slide images (WSIs). A UNet++ (with an EfficientNet-b7 backbone) model was built using Set B (67 cases) for tumor area prediction. The KI in Set C (20 cases) was quantified with and without the application of tumor-area masks, and the KI difference was computed. The mean intersection over union of the epithelial masks extracted from adjacent cytokeratin sections was 0.72 (0.68–0.76). After training and validating in 49 cases, the intersection over union in the test set was 0.44–0.73. At the tile image-level, KI difference was − 42.5–41.7%. Images with the highest difference usually contained numerous lymphocytes or vessels, and the masks prevented disguised cells from being counted. At the WSI-level, the hotspot location changed in 18/20 cases, but hotspot KI changed insignificantly (− 1.0% on average). The global KI changed less (0.9% on average). Thus, consecutive IHC staining provides substantial, precise, and reliable ground truths that trained the algorithm efficiently. This IHC-supervised training workflow can be applied to other targets by replacing IHC antibodies. Furthermore, the virtual tumor areas improved Ki67 counting by excluding the non-tumor areas at the tile image-level, although the effect on the WSI-level was insignificant.

show abstract

Deep Learning Model based Ki-67 Index estimation with Automatically Labelled Data

Cited by 2 publications

References 14 publications

Artificial Intelligence in Digital Pathology for Bladder Cancer: Hype or Hope? A Systematic Review

Artificial Intelligence in Digital Pathology for Bladder Cancer: Hype or Hope? A Systematic Review

Consecutive Cytokeratin Immunochemistry-Supervised Algorithm for Predicting Tumor Areas in Ki67 Breast Cancer Images

Contact Info

Product

Resources

About