# Fine-Tuning and Training of DenseNet for Histopathology Image Representation Using TCGA Diagnostic Slides

arXiv: https://arxiv.org/abs/2101.07903 · HTML: https://mlsanity.com/paper/2101.07903/

## Key facts

- Cited by 52 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Jan 2021.

## Built on by (most cited first, 30 of 52)

- [HEST-1k: A Dataset for Spatial Transcriptomics and Histology Image Analysis](https://mlsanity.com/paper/2406.16192/) (2024)
- [Dynamic Graph Representation with Knowledge-aware Attention for Histopathology Whole Slide Image Analysis](https://mlsanity.com/paper/2403.07719/) (2024)
- [A General-Purpose Self-Supervised Model for Computational Pathology](https://mlsanity.com/paper/2308.15474/) (2023)
- [HIGT: Hierarchical Interaction Graph-Transformer for Whole Slide Image Analysis](https://mlsanity.com/paper/2309.07400/) (2023)
- [Rotation-Agnostic Image Representation Learning for Digital Pathology](https://mlsanity.com/paper/2311.08359/) (2023)
- [Local Attention Graph-based Transformer for Multi-target Genetic Alteration Prediction](https://mlsanity.com/paper/2205.06672/) (2022)
- [Learning image representations for anomaly detection: application to discovery of histological alterations in drug development](https://mlsanity.com/paper/2210.07675/) (2022)
- [Low-resource finetuning of foundation models beats state-of-the-art in histopathology](https://mlsanity.com/paper/2401.04720/) (2024)
- [Equipping Computational Pathology Systems with Artifact Processing Pipelines: A Showcase for Computation and Performance Trade-offs](https://mlsanity.com/paper/2403.07743/) (2024)
- [Free Lunch in Pathology Foundation Model: Task-specific Model Adaptation with Concept-Guided Feature Enhancement](https://mlsanity.com/paper/2411.09894/) (2024)
- [Aligning Knowledge Concepts to Whole Slide Images for Precise Histopathology Image Analysis](https://mlsanity.com/paper/2411.18101/) (2024)
- [MulGT: Multi-task Graph-Transformer with Task-aware Knowledge Injection and Domain Knowledge-driven Pooling for Whole Slide Image Analysis](https://mlsanity.com/paper/2302.10574/) (2023)
- [Improving Feature Extraction from Histopathological Images Through A Fine-tuning ImageNet Model](https://mlsanity.com/paper/2201.00636/) (2022)
- [When is a Foundation Model a Foundation Model](https://mlsanity.com/paper/2309.11510/) (2023)
- [Analysis and Validation of Image Search Engines in Histopathology](https://mlsanity.com/paper/2401.03271/) (2024)
- [Automatic Multi-Stain Registration of Whole Slide Images in Histopathology](https://mlsanity.com/paper/2107.14292/) (2021)
- [Pay Attention with Focus: A Novel Learning Scheme for Classification of Whole Slide Images](https://mlsanity.com/paper/2106.06623/) (2021)
- [LILE: Look In-Depth before Looking Elsewhere -- A Dual Attention Network using Transformers for Cross-Modal Information Retrieval in Histopathology Archives](https://mlsanity.com/paper/2203.01445/) (2022)
- [Generating and Weighting Semantically Consistent Sample Pairs for Ultrasound Contrastive Learning](https://mlsanity.com/paper/2212.04097/) (2022)
- [Evolutionary Computation in Action: Feature Selection for Deep Embedding Spaces of Gigapixel Pathology Images](https://mlsanity.com/paper/2303.00943/) (2023)
- [GRASP: GRAph-Structured Pyramidal Whole Slide Image Representation](https://mlsanity.com/paper/2402.03592/) (2024)
- [Histopathological Image Classification with Cell Morphology Aware Deep Neural Networks](https://mlsanity.com/paper/2407.08625/) (2024)
- [Creating an Atlas of Normal Tissue for Pruning WSI Patching Through Anomaly Detection](https://mlsanity.com/paper/2310.03106/) (2023)
- [Diagnostic Text-guided Representation Learning in Hierarchical Classification for Pathological Whole Slide Image](https://mlsanity.com/paper/2411.10709/) (2024)
- [Feature-interactive Siamese graph encoder-based image analysis to predict STAS from histopathology images in lung cancer](https://mlsanity.com/paper/2411.15274/) (2024)
- [MetaLR: Meta-tuning of Learning Rates for Transfer Learning in Medical Imaging](https://mlsanity.com/paper/2206.01408/) (2022)
- [Active Learning Enhances Classification of Histopathology Whole Slide Images with Attention-based Multiple Instance Learning](https://mlsanity.com/paper/2303.01342/) (2023)
- [Ranking Loss and Sequestering Learning for Reducing Image Search Bias in Histopathology](https://mlsanity.com/paper/2304.08498/) (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)
- [Benchmarking Histopathology Foundation Models for Ovarian Cancer Bevacizumab Treatment Response Prediction from Whole Slide Images](https://mlsanity.com/paper/2407.20596/) (2024)

## Abstract (arXiv)

Feature vectors provided by pre-trained deep artificial neural networks have become a dominant source for image representation in recent literature. Their contribution to the performance of image analysis can be improved through finetuning. As an ultimate solution, one might even train a deep network from scratch with the domain-relevant images, a highly desirable option which is generally impeded in pathology by lack of labeled images and the computational expense. In this study, we propose a new network, namely KimiaNet, that employs the topology of the DenseNet with four dense blocks, fine-tuned and trained with histopathology images in different configurations. We used more than 240,000 image patches with 1000x1000 pixels acquired at 20x magnification through our proposed "highcellularity mosaic" approach to enable the usage of weak labels of 7,126 whole slide images of formalin-fixed paraffin-embedded human pathology samples publicly available through the The Cancer Genome Atlas (TCGA) repository. We tested KimiaNet using three public datasets, namely TCGA, endometrial cancer images, and colorectal cancer images by evaluating the performance of search and classification when corresponding features of different networks are used for image representation. As well, we designed and trained multiple convolutional batch-normalized ReLU (CBR) networks. The results show that KimiaNet provides superior results compared to the original DenseNet and smaller CBR networks when used as feature extractor to represent histopathology images.