# Contrastive Deep Encoding Enables Uncertainty-aware Machine-learning-assisted Histopathology

Source: [Contrastive Deep Encoding Enables Uncertainty-aware Machine-learning-assisted Histopathology](<https://www.sota2.com/research/paper/68fa708e1e209131cea4bbbc>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T06:26:19.199Z

Authors: Nirhoshan Sivaroopan, Chamuditha Jayanga, Chalani Ekanayake, Hasindri Watawana, Jathurshan Pradeepkumar, Mithunjha Anandakumar, Ranga Rodrigo, Chamira U. S. Edussooriya, Dushan N. Wadduwage

Published: 2023-09-13T17:37:19.000Z

## Abstract

Deep neural network models can learn clinically relevant features from millions of histopathology images. However generating high-quality annotations to train such models for each hospital, each cancer type, and each diagnostic task is prohibitively laborious. On the other hand, terabytes of training data -- while lacking reliable annotations -- are readily available in the public domain in some cases. In this work, we explore how these large datasets can be consciously utilized to pre-train deep networks to encode informative representations. We then fine-tune our pre-trained models on a fraction of annotated training data to perform specific downstream tasks. We show that our approach can reach the state-of-the-art (SOTA) for patch-level classification with only 1-10% randomly selected annotations compared to other SOTA approaches. Moreover, we propose an uncertainty-aware loss function, to quantify the model confidence during inference. Quantified uncertainty helps experts select the best instances to label for further training. Our uncertainty-aware labeling reaches the SOTA with significantly fewer annotations compared to random labeling. Last, we demonstrate how our pre-trained encoders can surpass current SOTA for whole-slide image classification with weak supervision. Our work lays the foundation for data and task-agnostic pre-trained deep networks with quantified uncertainty.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2309.07113>)

[PDF](<https://arxiv.org/pdf/2309.07113.pdf>)
