# Ranking Loss and Sequestering Learning for Reducing Image Search Bias in Histopathology

arXiv: https://arxiv.org/abs/2304.08498 · HTML: https://mlsanity.com/paper/2304.08498/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 62 references that are in the map.
- First posted on arXiv 15 Apr 2023.

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification](https://mlsanity.com/paper/2106.00908/) (2021)
- [AMC: AutoML for Model Compression and Acceleration on Mobile Devices](https://mlsanity.com/paper/1802.03494/) (2018)
- [Quantifying the effects of data augmentation and stain color normalization in convolutional neural networks for computational pathology](https://mlsanity.com/paper/1902.06543/) (2019)
- [Searching for Activation Functions](https://mlsanity.com/paper/1710.05941/) (2017)
- [Neural Architecture Optimization](https://mlsanity.com/paper/1808.07233/) (2018)
- [A Deeper Look at Dataset Bias](https://mlsanity.com/paper/1505.01257/) (2015)
- [Machine learning methods for histopathological image analysis](https://mlsanity.com/paper/1709.00786/) (2017)
- [A Decade Survey of Content Based Image Retrieval using Deep Learning](https://mlsanity.com/paper/2012.00641/) (2020)
- [Whole-Slide Mitosis Detection in H&E Breast Histology Using PHH3 as a Reference to Train Distilled Stain-Invariant Convolutional Networks](https://mlsanity.com/paper/1808.05896/) (2018)
- [Detecting Cancer Metastases on Gigapixel Pathology Images](https://mlsanity.com/paper/1703.02442/) (2017)
- [Fine-Tuning and Training of DenseNet for Histopathology Image Representation Using TCGA Diagnostic Slides](https://mlsanity.com/paper/2101.07903/) (2021)
- [Deep learning-based survival prediction for multiple cancer types using histopathology images](https://mlsanity.com/paper/1912.07354/) (2019)
- [Similar Image Search for Histopathology: SMILY](https://mlsanity.com/paper/1901.11112/) (2019)
- [Representation Learning of Histopathology Images using Graph Neural Networks](https://mlsanity.com/paper/2004.07399/) (2020)
- [SpinalNet: Deep Neural Network with Gradual Input](https://mlsanity.com/paper/2007.03347/) (2020)
- [Boosted EfficientNet: Detection of Lymph Node Metastases in Breast Cancer Using Convolutional Neural Network](https://mlsanity.com/paper/2010.05027/) (2020)
- [Evolutionary Computation in Action: Feature Selection for Deep Embedding Spaces of Gigapixel Pathology Images](https://mlsanity.com/paper/2303.00943/) (2023)

## Built on by (most cited first, 3 of 3)

- [Towards More Transparent and Accurate Cancer Diagnosis with an Unsupervised CAE Approach](https://mlsanity.com/paper/2305.11728/) (2023)
- [A Preliminary Investigation into Search and Matching for Tumour Discrimination in WHO Breast Taxonomy Using Deep Networks](https://mlsanity.com/paper/2308.11162/) (2023)
- [Selection of Distinct Morphologies to Divide & Conquer Gigapixel Pathology Images](https://mlsanity.com/paper/2311.09902/) (2023)

## Abstract (arXiv)

Recently, deep learning has started to play an essential role in healthcare applications, including image search in digital pathology. Despite the recent progress in computer vision, significant issues remain for image searching in histopathology archives. A well-known problem is AI bias and lack of generalization. A more particular shortcoming of deep models is the ignorance toward search functionality. The former affects every model, the latter only search and matching. Due to the lack of ranking-based learning, researchers must train models based on the classification error and then use the resultant embedding for image search purposes. Moreover, deep models appear to be prone to internal bias even if using a large image repository of various hospitals. This paper proposes two novel ideas to improve image search performance. First, we use a ranking loss function to guide feature extraction toward the matching-oriented nature of the search. By forcing the model to learn the ranking of matched outputs, the representation learning is customized toward image search instead of learning a class label. Second, we introduce the concept of sequestering learning to enhance the generalization of feature extraction. By excluding the images of the input hospital from the matched outputs, i.e., sequestering the input domain, the institutional bias is reduced. The proposed ideas are implemented and validated through the largest public dataset of whole slide images. The experiments demonstrate superior results compare to the-state-of-art.