Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Vision Models for Medical Imaging: A Hybrid Approach for PCOS Detection from Ultrasound Scans

Md Mahmudul Hoque, Md Mehedi Hassain, Muntakimur Rahaman, Md. Towhidul Islam, Shaista Rani, Md Sharif Mollah

TL;DR

This work targets automated PCOS detection from ovarian ultrasound images using hybrid CNN-Transformer architectures. It introduces two ensembles, DenConST and DenConREST, with DenConREST (combining EfficientNetV2, ResNet18, DenseNet121, Swin Transformer, and ConvNeXt) achieving a peak accuracy of 98.23% and a recall near 100% on a Kaggle-derived dataset. The study demonstrates that aggregating diverse feature extractors yields superior diagnostic performance compared with individual CNNs or transformers, offering a robust tool for screening in resource-limited clinical settings. Future directions include multicenter validation and multimodal (biomarker-inclusive) approaches to further enhance clinical applicability.

Abstract

Polycystic Ovary Syndrome (PCOS) is the most familiar endocrine illness in women of reproductive age. Many Bangladeshi women suffer from PCOS disease in their older age. The aim of our research is to identify effective vision-based medical image analysis techniques and evaluate hybrid models for the accurate detection of PCOS. We introduced two novel hybrid models combining convolutional and transformer-based approaches. The training and testing data were organized into two categories: "infected" (PCOS-positive) and "noninfected" (healthy ovaries). In the initial stage, our first hybrid model, 'DenConST' (integrating DenseNet121, Swin Transformer, and ConvNeXt), achieved 85.69% accuracy. The final optimized model, 'DenConREST' (incorporating Swin Transformer, ConvNeXt, DenseNet121, ResNet18, and EfficientNetV2), demonstrated superior performance with 98.23% accuracy. Among all evaluated models, DenConREST showed the best performance. This research highlights an efficient solution for PCOS detection from ultrasound images, significantly improving diagnostic accuracy while reducing detection errors.

Vision Models for Medical Imaging: A Hybrid Approach for PCOS Detection from Ultrasound Scans

TL;DR

This work targets automated PCOS detection from ovarian ultrasound images using hybrid CNN-Transformer architectures. It introduces two ensembles, DenConST and DenConREST, with DenConREST (combining EfficientNetV2, ResNet18, DenseNet121, Swin Transformer, and ConvNeXt) achieving a peak accuracy of 98.23% and a recall near 100% on a Kaggle-derived dataset. The study demonstrates that aggregating diverse feature extractors yields superior diagnostic performance compared with individual CNNs or transformers, offering a robust tool for screening in resource-limited clinical settings. Future directions include multicenter validation and multimodal (biomarker-inclusive) approaches to further enhance clinical applicability.

Abstract

Polycystic Ovary Syndrome (PCOS) is the most familiar endocrine illness in women of reproductive age. Many Bangladeshi women suffer from PCOS disease in their older age. The aim of our research is to identify effective vision-based medical image analysis techniques and evaluate hybrid models for the accurate detection of PCOS. We introduced two novel hybrid models combining convolutional and transformer-based approaches. The training and testing data were organized into two categories: "infected" (PCOS-positive) and "noninfected" (healthy ovaries). In the initial stage, our first hybrid model, 'DenConST' (integrating DenseNet121, Swin Transformer, and ConvNeXt), achieved 85.69% accuracy. The final optimized model, 'DenConREST' (incorporating Swin Transformer, ConvNeXt, DenseNet121, ResNet18, and EfficientNetV2), demonstrated superior performance with 98.23% accuracy. Among all evaluated models, DenConREST showed the best performance. This research highlights an efficient solution for PCOS detection from ultrasound images, significantly improving diagnostic accuracy while reducing detection errors.
Paper Structure (12 sections, 2 equations, 4 figures, 1 table)

This paper contains 12 sections, 2 equations, 4 figures, 1 table.

Table of Contents

  1. Introduction
  2. Methodology
  3. Data Collection
  4. Image Preprocessing
  5. Model Architecture
  6. Training Configuration and Optimization
  7. Hybrid Model Development
  8. Evaluation Methodology
  9. Implementation Details
  10. Results Analysis
  11. Discussion
  12. Conclusion

Figures (4)

  • Figure 1: System Architecture
  • Figure 2: PCOS infected and noninfected ultrasound images
  • Figure 3: DenConREST Architecture
  • Figure 4: Confusion Matrix of DenConREST Model