Search arXivSearch

arXiv · 2201.00636

Improving Feature Extraction from Histopathological Images Through A Fine-tuning ImageNet Model

Abstract

Due to lack of annotated pathological images, transfer learning has been the predominant approach in the field of digital pathology.Pre-trained neural networks based on ImageNet database are often used to extract "off the shelf" features, achieving great success in predicting tissue types, molecular features, and clinical outcomes, etc. We hypothesize that fine-tuning the pre-trained models using histopathological images could further improve feature extraction, and downstream prediction performance.We used 100,000 annotated HE image patches for colorectal cancer (CRC) to finetune a pretrained Xception model via a twostep approach.The features extracted from finetuned Xception (FTX2048) model and Imagepretrained (IMGNET2048) model were compared through: (1) tissue classification for HE images from CRC, same image type that was used for finetuning; (2) prediction of immunerelated gene expression and (3) gene mutations for lung adenocarcinoma (LUAD).Fivefold cross validation was used for model performance evaluation. The extracted features from the finetuned FTX2048 exhibited significantly higher accuracy for predicting tisue types of CRC compared to the off the shelf feature directly from Xception based on ImageNet database. Particularly, FTX2048 markedly improved the accuracy for stroma from 87% to 94%. Similarly, features from FTX2048 boosted the prediction of transcriptomic expression of immunerelated genesin LUAD. For the genes that had signigicant relationships with image fetures, the features fgrom the finetuned model imprroved the prediction for the majority of the genes. Inaddition, fetures from FTX2048 improved prediction of mutation for 5 out of 9 most frequently mutated genes in LUAD.

Explore related subjects

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Xingyu Li, Min Cen, Jinfeng Xu, Hong Zhang, Xu Steven Xu. 2022-01-03. Improving Feature Extraction from Histopathological Images Through A Fine-tuning ImageNet Model. https://arxiv.org/abs/2201.00636

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

Hyperspectral Image Restoration and Super-resolution with Physics-Aware Deep Learning for Biomedical Applications

Hyperspectral imaging is a powerful bioimaging tool which can uncover novel insights, thanks to its sensitivity to the intrinsic properties of materials. However, this enhanced contrast comes at the cost of system complexity, constrained by an inherent trade-off between spatial, spectral, and temporal resolution. To overcome this limitation, we present a self-supervised deep learning-based approach that restores and enhances pixel resolution post-acquisition without requiring external training data beyond the images to be restored. Fine-tuned using metrics aligned with the imaging model, our physics-aware method achieves a 16$\times$ pixel super-resolution enhancement and a 12$\times$ imaging speedup without the need of additional training data for transfer learning. Applied to both synthetic and experimental data from five different sample types, including healthy and diseased tissues, we demonstrate that the model preserves biological integrity, as we did not detect systematic loss of biological features or biologically consequential hallucinations in tested datasets. We also concretely demonstrate the model's ability to reveal disease-associated metabolic changes that would otherwise remain undetectable. Furthermore, we provide physical insights into the model's inner workings, paving the way for future refinements that could potentially reveal novel high resolution features in an explainable manner. All methods are available as open-source software on GitHub.

eess.IV

OASIS: Online Adaptive Video Compression via Closed-loop Feedback Control

Computer vision systems are a key building block in an autonomous vehicle, responsible for a range of perception tasks. However, they incur massive data transmission over long communication links from multiple cameras, creating a critical bandwidth and energy bottleneck. Although conventional codecs such as H.264 can reduce data rates, they are ill-suited for real-time vision systems due to high processing latency and energy consumption, as well as their reliance on static user-defined compression settings. In light of these challenges, we propose OASIS, an adaptive video compression framework that integrates lightweight in-sensor compression with task-aware compression ratio control. Based on the real-time task performance, it dynamically updates the optimal compression ratio. Experimental results demonstrate that OASIS generalizes across multiple vision tasks, achieving on average a 6x data compression, 5.8x reduction in link power consumption, and 2.5x reduction in link latency, with at most 1.5% performance degradation.

eess.IV

Echo-E$^3$Net: Efficient Endocardial Spatio-Temporal Network for Ejection Fraction Estimation

Left ventricular ejection fraction (LVEF) is a primary marker of cardiac function. However, routine estimation from endocardial measurements requires manual delineation at end-diastole (ED) and end-systole (ES), a process that is time-consuming and subject to inter-observer variability. Reliable automation is especially valuable for point-of-care ultrasound (POCUS), where computational resources are limited and acquisition quality varies. We propose Echo-E$^3$Net, an anatomy-guided spatio-temporal network that explicitly embeds cardiac anatomy into LVEF prediction. A dual-phase Endocardial Border Detector (E$^2$CBD) uses phase-specific cross-attention to localize ED/ES endocardial landmarks and produce phase-aware landmark embeddings, while an Endocardial Feature Aggregator (E$^2$FA) fuses these embeddings with global statistical descriptors of deep feature maps to refine EF regression. Training is guided by a lightweight geometric loss that uses ED and ES endocardial landmarks to regularize EF prediction. On EchoNet-Dynamic and a PSAX subset of EchoNet-Pediatric, Echo-E$^3$Net attains competitive performance using only 1.55M parameters and 8.05 GFLOPs, an order-of-magnitude compute reduction versus recent baselines, supporting real-time deployment. Our code is publicly available at https://github.com/moeinheidari7829/Echo-E3Net.

eess.IV