Towards Improved Cervical Cancer Screening: Vision Transformer-Based Classification and Interpretability

• URL: http://arxiv.org/abs/2504.21340v1
• Date: Wed, 30 Apr 2025 05:59:56 GMT
• Title: Towards Improved Cervical Cancer Screening: Vision Transformer-Based Classification and Interpretability
• Authors: Khoa Tuan Nguyen, Ho-min Park, Gaeun Oh, Joris Vankerschaver, Wesley De Neve,
• Abstract summary: We propose a novel approach to cervical cell image classification for cervical cancer screening using the EVA-02 transformer model.<n>We developed a four-step pipeline: fine-tuning EVA-02, feature extraction, selecting important features through machine learning models, and training a new artificial neural network.<n>Our best model achieved an F1-score of 0.85227, outperforming the baseline EVA-02 model.
• Score: 1.0026364432018122
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: We propose a novel approach to cervical cell image classification for cervical cancer screening using the EVA-02 transformer model. We developed a four-step pipeline: fine-tuning EVA-02, feature extraction, selecting important features through multiple machine learning models, and training a new artificial neural network with optional loss weighting for improved generalization. With this design, our best model achieved an F1-score of 0.85227, outperforming the baseline EVA-02 model (0.84878). We also utilized Kernel SHAP analysis and identified key features correlating with cell morphology and staining characteristics, providing interpretable insights into the decision-making process of the fine-tuned model. Our code is available at https://github.com/Khoa-NT/isbi2025_ps3c.

Related papers

• A Hybrid Deep Learning CNN Model for Enhanced COVID-19 Detection from Computed Tomography (CT) Scan Images [0.0]
  Early detection of COVID-19 is crucial for effective treatment and controlling its spread.<n>This study proposes a novel hybrid deep learning model for detecting COVID-19 from CT scan images.<n>Our proposed model achieved an accuracy of 98.93%, outperforming the individual models in terms of precision, recall, F1 scores, and ROC curve performance.
  arXiv  Detail & Related papers  (2025-01-28T18:59:21Z)
• Comparative Performance Analysis of Transformer-Based Pre-Trained Models for Detecting Keratoconus Disease [0.0]
  This study compares eight pre-trained CNNs for diagnosing keratoconus, a degenerative eye disease. MobileNetV2 was the best accurate model in identifying keratoconus and normal cases with few misclassifications.
  arXiv  Detail & Related papers  (2024-08-16T20:15:24Z)
• Improving Machine Learning Based Sepsis Diagnosis Using Heart Rate Variability [0.0]
  This study aims to use heart rate variability (HRV) features to develop an effective predictive model for sepsis detection. A neural network model is trained on the HRV features, achieving an F1 score of 0.805, a precision of 0.851, and a recall of 0.763.
  arXiv  Detail & Related papers  (2024-08-01T01:47:29Z)
• Dense Feature Memory Augmented Transformers for COVID-19 Vaccination Search Classification [60.49594822215981]
  This paper presents a classification model for detecting COVID-19 vaccination related search queries. We propose a novel approach of considering dense features as memory tokens that the model can attend to. We show that this new modeling approach enables a significant improvement to the Vaccine Search Insights (VSI) task.
  arXiv  Detail & Related papers  (2022-12-16T13:57:41Z)
• Transformer Lesion Tracker [12.066026343488453]
  We propose a transformer-based approach, termed Transformer Lesion Tracker (TLT) We design a Cross Attention-based Transformer (CAT) to capture and combine both global and local information to enhance feature extraction. We conduct experiments on a public dataset to show the superiority of our method and find that our model performance has improved the average Euclidean center error by at least 14.3%.
  arXiv  Detail & Related papers  (2022-06-13T15:35:24Z)
• Dynamically-Scaled Deep Canonical Correlation Analysis [77.34726150561087]
  Canonical Correlation Analysis (CCA) is a method for feature extraction of two views by finding maximally correlated linear projections of them. We introduce a novel dynamic scaling method for training an input-dependent canonical correlation model.
  arXiv  Detail & Related papers  (2022-03-23T12:52:49Z)
• Improving Classification Model Performance on Chest X-Rays through Lung Segmentation [63.45024974079371]
  We propose a deep learning approach to enhance abnormal chest x-ray (CXR) identification performance through segmentations. Our approach is designed in a cascaded manner and incorporates two modules: a deep neural network with criss-cross attention modules (XLSor) for localizing lung region in CXR images and a CXR classification model with a backbone of a self-supervised momentum contrast (MoCo) model pre-trained on large-scale CXR data sets.
  arXiv  Detail & Related papers  (2022-02-22T15:24:06Z)
• Lung Cancer Lesion Detection in Histopathology Images Using Graph-Based Sparse PCA Network [93.22587316229954]
  We propose a graph-based sparse principal component analysis (GS-PCA) network, for automated detection of cancerous lesions on histological lung slides stained by hematoxylin and eosin (H&E) We evaluate the performance of the proposed algorithm on H&E slides obtained from an SVM K-rasG12D lung cancer mouse model using precision/recall rates, F-score, Tanimoto coefficient, and area under the curve (AUC) of the receiver operator characteristic (ROC)
  arXiv  Detail & Related papers  (2021-10-27T19:28:36Z)
• A multi-stage machine learning model on diagnosis of esophageal manometry [50.591267188664666]
  The framework includes deep-learning models at the swallow-level stage and feature-based machine learning models at the study-level stage. This is the first artificial-intelligence-style model to automatically predict CC diagnosis of HRM study from raw multi-swallow data.
  arXiv  Detail & Related papers  (2021-06-25T20:09:23Z)
• Cervical Cytology Classification Using PCA & GWO Enhanced Deep Features Selection [1.990876596716716]
  Cervical cancer is one of the most deadly and common diseases among women worldwide. We propose a fully automated framework that utilizes Deep Learning and feature selection. The framework is evaluated on three publicly available benchmark datasets.
  arXiv  Detail & Related papers  (2021-06-09T08:57:22Z)
• End-2-End COVID-19 Detection from Breath & Cough Audio [68.41471917650571]
  We demonstrate the first attempt to diagnose COVID-19 using end-to-end deep learning from a crowd-sourced dataset of audio samples. We introduce a novel modelling strategy using a custom deep neural network to diagnose COVID-19 from a joint breath and cough representation.
  arXiv  Detail & Related papers  (2021-01-07T01:13:00Z)

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.