Patherea: Cell Detection and Classification for the 2020s

• URL: http://arxiv.org/abs/2412.16425v1
• Date: Sat, 21 Dec 2024 01:23:58 GMT
• Title: Patherea: Cell Detection and Classification for the 2020s
• Authors: Dejan Štepec, Maja Jerše, Snežana Đokić, Jera Jeruc, Nina Zidar, Danijel Skočaj,
• Abstract summary: Patherea is a framework for point-based cell detection and classification. It provides a complete solution for developing and evaluating state-of-the-art approaches.
• Score: 0.0
• License:
• Abstract: This paper presents a Patherea, a framework for point-based cell detection and classification that provides a complete solution for developing and evaluating state-of-the-art approaches. We introduce a large-scale dataset collected to directly replicate a clinical workflow for Ki-67 proliferation index estimation and use it to develop an efficient point-based approach that directly predicts point-based predictions, without the need for intermediate representations. The proposed approach effectively utilizes point proposal candidates with the hybrid Hungarian matching strategy and a flexible architecture that enables the usage of various backbones and (pre)training strategies. We report state-of-the-art results on existing public datasets - Lizard, BRCA-M2C, BCData, and the newly proposed Patherea dataset. We show that the performance on existing public datasets is saturated and that the newly proposed Patherea dataset represents a significantly harder challenge for the recently proposed approaches. We also demonstrate the effectiveness of recently proposed pathology foundational models that our proposed approach can natively utilize and benefit from. We also revisit the evaluation protocol that is used in the broader field of cell detection and classification and identify the erroneous calculation of performance metrics. Patherea provides a benchmarking utility that addresses the identified issues and enables a fair comparison of different approaches. The dataset and the code will be publicly released upon acceptance.

Related papers

• Rethinking the Effectiveness of Graph Classification Datasets in Benchmarks for Assessing GNNs [7.407592553310068]
  We propose an empirical protocol based on a fair benchmarking framework to investigate the performance discrepancy between simple methods and GNNs. We also propose a novel metric to quantify the dataset effectiveness by considering both dataset complexity and model performance. Our findings shed light on the current understanding of benchmark datasets, and our new platform could fuel the future evolution of graph classification benchmarks.
  arXiv  Detail & Related papers  (2024-07-06T08:33:23Z)
• Minimally Supervised Learning using Topological Projections in Self-Organizing Maps [55.31182147885694]
  We introduce a semi-supervised learning approach based on topological projections in self-organizing maps (SOMs) Our proposed method first trains SOMs on unlabeled data and then a minimal number of available labeled data points are assigned to key best matching units (BMU) Our results indicate that the proposed minimally supervised model significantly outperforms traditional regression techniques.
  arXiv  Detail & Related papers  (2024-01-12T22:51:48Z)
• When is Off-Policy Evaluation (Reward Modeling) Useful in Contextual Bandits? A Data-Centric Perspective [64.73162159837956]
  evaluating the value of a hypothetical target policy with only a logged dataset is important but challenging. We propose DataCOPE, a data-centric framework for evaluating a target policy given a dataset. Our empirical analysis of DataCOPE in the logged contextual bandit settings using healthcare datasets confirms its ability to evaluate both machine-learning and human expert policies.
  arXiv  Detail & Related papers  (2023-11-23T17:13:37Z)
• Sample Complexity of Preference-Based Nonparametric Off-Policy Evaluation with Deep Networks [58.469818546042696]
  We study the sample efficiency of OPE with human preference and establish a statistical guarantee for it. By appropriately selecting the size of a ReLU network, we show that one can leverage any low-dimensional manifold structure in the Markov decision process.
  arXiv  Detail & Related papers  (2023-10-16T16:27:06Z)
• Open-Set Domain Adaptation with Visual-Language Foundation Models [51.49854335102149]
  Unsupervised domain adaptation (UDA) has proven to be very effective in transferring knowledge from a source domain to a target domain with unlabeled data. Open-set domain adaptation (ODA) has emerged as a potential solution to identify these classes during the training phase.
  arXiv  Detail & Related papers  (2023-07-30T11:38:46Z)
• Going beyond research datasets: Novel intent discovery in the industry setting [60.90117614762879]
  This paper proposes methods to improve the intent discovery pipeline deployed in a large e-commerce platform. We show the benefit of pre-training language models on in-domain data: both self-supervised and with weak supervision. We also devise the best method to utilize the conversational structure (i.e., question and answer) of real-life datasets during fine-tuning for clustering tasks, which we call Conv.
  arXiv  Detail & Related papers  (2023-05-09T14:21:29Z)
• Comparison of Model-Free and Model-Based Learning-Informed Planning for PointGoal Navigation [10.797100163772482]
  We compare state-of-the-art Deep Reinforcement Learning based approaches with Partially Observable Markov Decision Process (POMDP) formulation of the point goal navigation problem. We show comparable, though slightly worse performance than the SOTA DD-PPO approach, yet with far fewer data.
  arXiv  Detail & Related papers  (2022-12-17T05:23:54Z)
• Cluster-level pseudo-labelling for source-free cross-domain facial expression recognition [94.56304526014875]
  We propose the first Source-Free Unsupervised Domain Adaptation (SFUDA) method for Facial Expression Recognition (FER) Our method exploits self-supervised pretraining to learn good feature representations from the target data. We validate the effectiveness of our method in four adaptation setups, proving that it consistently outperforms existing SFUDA methods when applied to FER.
  arXiv  Detail & Related papers  (2022-10-11T08:24:50Z)
• A Recommendation Approach based on Similarity-Popularity Models of Complex Networks [1.385805101975528]
  This work proposes a novel recommendation method based on complex networks generated by a similarity-popularity model to predict ones. We first construct a model of a network having users and items as nodes from observed ratings and then use it to predict unseen ratings. The proposed approach is implemented and experimentally compared against baseline and state-of-the-art recommendation methods on 21 datasets from various domains.
  arXiv  Detail & Related papers  (2022-09-29T11:00:06Z)
• Multi-view Data Classification with a Label-driven Auto-weighted Strategy [32.581793437017716]
  We propose an auto-weighted strategy to evaluate the importance of views from a label perspective. Based on this strategy, we propose a transductive semi-supervised auto-weighted multi-view classification model. The proposed method achieves optimal or sub-optimal classification accuracy at the lowest computational cost.
  arXiv  Detail & Related papers  (2022-01-03T15:27:54Z)
• Deep Adversarial Domain Adaptation Based on Multi-layer Joint Kernelized Distance [30.452492118887182]
  Domain adaptation refers to the learning scenario that a model learned from the source data is applied on the target data. The distribution discrepancy between source data and target data can substantially affect the adaptation performance. A deep adversarial domain adaptation model based on a multi-layer joint kernelized distance metric is proposed.
  arXiv  Detail & Related papers  (2020-10-09T02:32:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.