![]() ![]() ![]() Third, we use tumor depth as an auxiliary task to improve grade classification in a multitask learning framework. Second, we introduce a novel ordinal ranking constraint on the patch attention network to ensure that higher-grade tumor regions are assigned higher attention. First, we leverage spatial and semantic proximity to define a WSI graph that encodes both local and non-local dependencies between tumor regions and leverage graph attention convolution to derive contextual patch features. We propose three key innovations to address general as well as cSCC-specific challenges in tumor grading. The proposed model, RACR-MIL, transforms each WSI into a bag of tiled patches and leverages attention-based multiple-instance learning to assign a WSI-level grade. We propose an automated weakly-supervised grading approach for cSCC WSIs that is trained using WSI-level grade and does not require fine-grained tumor annotations. It is diagnosed by manual multi-class tumor grading using a tissue whole slide image (WSI), which is subjective and suffers from inter-pathologist variability. ![]() * Accepted at 2023 MICCAI FAIMI WorkshopĬutaneous squamous cell cancer (cSCC) is the second most common skin cancer in the US. Finally, we recommend further research on robust ITA estimation and diverse dataset acquisition with skin tone annotation to facilitate conclusive fairness assessments of artificial intelligence tools in dermatology. Moreover, we investigate the causes of such large discrepancy among these approaches and find that the lack of diversity in the ISIC18 dataset limits its use as a testbed for fairness analysis. Our analyses reveal a high disagreement among previously published studies demonstrating the risks of ITA-based skin tone estimation methods. In this work, we review and compare four ITA-based approaches of skin tone classification on the ISIC18 dataset, a common benchmark for assessing skin cancer classification fairness in the literature. These angles are then categorised into skin tones that are subsequently used to analyse fairness in skin cancer classification. Briefly, ITA calculates an angle based on pixels extracted from skin images taking into account the lightness and yellow-blue tints. To date, such skin tone labels have been estimated prior to fairness analysis in independent studies using the Individual Typology Angle (ITA). However, the absence of skin tone labels in public datasets hinders building a fair classifier. Addressing fairness in lesion classification from dermatological images is crucial due to variations in how skin diseases manifest across skin tones. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |