Scholarlink

<p>Pharyngitis is a common cause of throat-related clinical presentation, yet image-based screening from throat photographs remains insufficiently standardized and often lacks rigorous, leakage-aware evaluation. Existing approaches are commonly limited by small datasets, single-representation models, and incomplete validation protocols, which can weaken confidence in reported generalization. To address this gap, this study proposes PharynFuseFormer, a hybrid transformer–CNN feature-fusion framework that combines multi-scale convolutional processing, attention-based contextual refinement, and channel-wise gating to jointly model local texture cues and broader spatial context for binary pharyngitis screening. Experiments were conducted on a curated dataset of 362 RGB throat images, comprising 147 Pharyngitis and 215 Non-Pharyngitis samples, with a development split of 329 images and a held-out test split of 33 images. Images were resized to 224 × 224 × 3, and augmentation was applied only within the development split to reduce leakage risk. Evaluation used stratified 5-fold cross-validation with statistical comparison against representative baselines. PharynFuseFormer achieved 99.10% training accuracy and 98.73% cross-validation accuracy, with an improvement of up to + 4.73% points (95% CI + 4.18 to + 5.28; Holm <i>p</i> = 1.06e − 05; Cohen’s d = 14.01). Qualitative analyses using Grad-CAM, final-layer feature maps, and averaged activation heatmaps were included to contextualize model behavior. Under the current experimental setting, these findings support transformer–CNN feature fusion as a promising approach for image-based pharyngitis screening, while further validation under diverse acquisition conditions remains necessary.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

PharynFuseFormer supports image based pharyngitis screening from throat photographs using transformer CNN feature fusion

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年6月2日

查看全文
  • Md Anwar Hossain,
  • Md Abedur Rahman,
  • Md Sahid Hossain,
  • Chandan Karmakar,
  • Md Sharifur Rahman,
  • Kallol Chakraborty Shekhor,
  • Nithesh Naik,
  • Abdul Basit

摘要

Pharyngitis is a common cause of throat-related clinical presentation, yet image-based screening from throat photographs remains insufficiently standardized and often lacks rigorous, leakage-aware evaluation. Existing approaches are commonly limited by small datasets, single-representation models, and incomplete validation protocols, which can weaken confidence in reported generalization. To address this gap, this study proposes PharynFuseFormer, a hybrid transformer–CNN feature-fusion framework that combines multi-scale convolutional processing, attention-based contextual refinement, and channel-wise gating to jointly model local texture cues and broader spatial context for binary pharyngitis screening. Experiments were conducted on a curated dataset of 362 RGB throat images, comprising 147 Pharyngitis and 215 Non-Pharyngitis samples, with a development split of 329 images and a held-out test split of 33 images. Images were resized to 224 × 224 × 3, and augmentation was applied only within the development split to reduce leakage risk. Evaluation used stratified 5-fold cross-validation with statistical comparison against representative baselines. PharynFuseFormer achieved 99.10% training accuracy and 98.73% cross-validation accuracy, with an improvement of up to + 4.73% points (95% CI + 4.18 to + 5.28; Holm p = 1.06e − 05; Cohen’s d = 14.01). Qualitative analyses using Grad-CAM, final-layer feature maps, and averaged activation heatmaps were included to contextualize model behavior. Under the current experimental setting, these findings support transformer–CNN feature fusion as a promising approach for image-based pharyngitis screening, while further validation under diverse acquisition conditions remains necessary.