Segmentation and Classification of Melanoma and Nevus in Whole Slide Images

Zon, Mike van; Stathonikos, Nikolas; Blokx, Willeke A.M.; Komina, Selim; Maas, Sybren L. N.; Pluim, Josien P. W.; Diest, Paul J. van; Veta, Mitko

doi:10.1109/isbi45749.2020.9098487

Cited by 13 publications

(5 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Pathology imaging provides an important view of cancer tissue and has been widely used in diagnosing primary and metastatic cancers [ 67 , 68 , 69 ]. Eight cell types were segmented and counted from the pathology images and the percentage of each cell type among all the detected cells was denoted as the image feature of this cell type for the corresponding sample.…”

Section: Resultsmentioning

confidence: 99%

Integration of lncRNAs, Protein-Coding Genes and Pathology Images for Detecting Metastatic Melanoma

Liu

Fan

et al. 2022

Genes

View full text Add to dashboard Cite

Melanoma is a lethal skin disease that develops from moles. This study aimed to integrate multimodal data to predict metastatic melanoma, which is highly aggressive and difficult to treat. The proposed EnsembleSKCM method evaluated the prediction performances of long noncoding RNAs (lncRNAs), protein-coding messenger genes (mRNAs) and pathology images (images) for metastatic melanoma. Feature selection was used to screen for metastatic biomarkers in the lncRNA and mRNA datasets. The integrated EnsembleSKCM model was built based on the weighted results of the lncRNA-, mRNA- and image-based models. EnsembleSKCM achieved 0.9444 in the prediction accuracy of metastatic melanoma and outperformed the single-modal prediction models based on the lncRNA, mRNA and image data. The experimental data suggest the importance of integrating the complementary information from the three data modalities. WGCNA was used to analyze the relationship of molecular-level features and image features, and the results show connections between them. Another cohort was used to validate our prediction.

show abstract

Section: Resultsmentioning

confidence: 99%

Integration of lncRNAs, Protein-Coding Genes and Pathology Images for Detecting Metastatic Melanoma

Liu

Fan

et al. 2022

Genes

View full text Add to dashboard Cite

show abstract

“…In terms of the results with different training approaches, it is clear that the use of a supervised approach leads to better results with fewer data. 39 , 56 , 60 However, the use of a weakly supervised approach also showed great results in huge datasets. 8 The main problem with the weakly supervised approach was the need for huge datasets, which can be provided more easily, not requiring pathologist annotations, and binary problems to be solved, but Mercan et al 34 proposed a multi-class weakly supervised method with reasonable precision with an average size dataset.…”

Section: Discussionmentioning

confidence: 99%

Artificial intelligence as a tool for diagnosis in digital pathology whole slide images: A systematic review

Rodriguez

Rodriguez²,

Silva³

et al. 2022

Journal of Pathology Informatics

View full text Add to dashboard Cite

“…Segmentation-based methods. These approaches use semantic information about tissues in a WSI to produce an image-level decision [16]- [20]. Typically, these approaches have three steps: (1) produce a tissue-level semantic segmentation mask using CNNs for an input WSI, (2) extract features, such as distribution of tissues, from these semantic masks, and (3) produce an image-level decision using the features extracted from the semantic masks.…”

Section: Related Workmentioning

confidence: 99%

Scale-Aware Transformers for Diagnosing Melanocytic Lesions

Wu¹,

Mehta

Nofallah

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Diagnosing melanocytic lesions is one of the most challenging areas of pathology with extensive intra-and inter-observer variability. The gold standard for a diagnosis of invasive melanoma is the examination of histopathological whole slide skin biopsy images by an experienced dermatopathologist. Digitized whole slide images offer novel opportunities for computer programs to improve the diagnostic performance of pathologists. In order to automatically classify such images, representations that reflect the content and context of the input images are needed. In this paper, we introduce a novel self-attention-based network to learn representations from digital whole slide images of melanocytic skin lesions at multiple scales. Our model softly weighs representations from multiple scales, allowing it to discriminate between diagnosis-relevant and -irrelevant information automatically. Our experiments show that our method outperforms five other state-of-the-art whole slide image classification methods by a significant margin. Our method also achieves comparable performance to 187 practicing U.S. pathologists who interpreted the same cases in an independent study. To facilitate relevant research, full training and inference code will be made publicly available.

show abstract

Segmentation and Classification of Melanoma and Nevus in Whole Slide Images

Cited by 13 publications

References 11 publications

Integration of lncRNAs, Protein-Coding Genes and Pathology Images for Detecting Metastatic Melanoma

Integration of lncRNAs, Protein-Coding Genes and Pathology Images for Detecting Metastatic Melanoma

Artificial intelligence as a tool for diagnosis in digital pathology whole slide images: A systematic review

Scale-Aware Transformers for Diagnosing Melanocytic Lesions

Contact Info

Product

Resources

About