Automatic semantic segmentation of EHG recordings by deep learning: An approach to a screening tool for use in clinical practice

• Published in: Computer methods and programs in biomedicine 2024-09, Vol.254, p.108317, Article 108317
• Main Authors: Nieto-del-Amor, Félix, Ye-Lin, Yiyao, Monfort-Ortiz, Rogelio, Diago-Almela, Vicente Jose, Modrego-Pardo, Fernando, Martinez-de-Juan, Jose L., Hao, Dongmei, Prats-Boluda, Gema
• Format: Article
• Language: English
• Subjects: Deep learning; Electrohysterography; Preterm delivery prediction; Semantic segmentation; Signal processing; Uterine myoelectric activity
• ISSN: 0169-2607; 1872-7565; 1872-7565
• DOI: 10.1016/j.cmpb.2024.108317

•A deep learning-based automatic semantic segmentation of EHG recordings is proposed.•A screening tool for physiological EHG epoch segmentation in clinical practice.•The best architecture for detecting physiological epochs was UNET 3+ with 91.4 % AUC.•Automatic and double-blind segmentation perform similarly in preterm labor detection. Preterm delivery is an important factor in the disease burden of the newborn and infants worldwide. Electrohysterography (EHG) has become a promising technique for predicting this condition, thanks to its high degree of sensitivity. Despite the technological progress made in predicting preterm labor, its use in clinical practice is still limited, one of the main barriers being the lack of tools for automatic signal processing without expert supervision, i.e. automatic screening of motion and respiratory artifacts in EHG records. Our main objective was thus to design and validate an automatic system of segmenting and screening the physiological segments of uterine origin in EHG records for robust characterization of uterine myoelectric activity, predicting preterm labor and help to promote the transferability of the EHG technique to clinical practice. For this, we combined 300 EHG recordings from the TPEHG DS database and 69 EHG recordings from our own database (Ci2B-La Fe) of women with singleton gestations. This dataset was used to train and evaluate U-Net, U-Net++, and U-Net 3+ for semantic segmentation of the physiological and artifacted segments of EHG signals. The model's predictions were then fine-tuned by post-processing. U-Net 3+ outperformed the other models, achieving an area under the ROC curve of 91.4 % and an average precision of 96.4 % in detecting physiological activity. Thresholds from 0.6 to 0.8 achieved precision from 93.7 % to 97.4 % and specificity from 81.7 % to 94.5 %, detecting high-quality physiological segments while maintaining a trade-off between recall and specificity. Post-processing improved the model's adaptability by fine-tuning both the physiological and corrupted segments, ensuring accurate artifact detection while maintaining physiological segment integrity in EHG signals. As automatic segmentation proved to be as effective as double-blind manual segmentation in predicting preterm labor, this automatic segmentation tool fills a crucial gap in the existing preterm delivery prediction system workflow by eliminating the need for double-blind segmentation by experts and facilitates the practica