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

BACKGROUND AND OBJECTIVE: 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. METHODS: 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. RESULTS: 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. CONCLUSIONS: 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 practical clinical use of EHG. This work potentially contributes to the early detection of authentic preterm labor women and will allow clinicians to design individual patient strategies for maternal health surveillance systems and predict adverse pregnancy outcomes.

Inversión uterina puerperal: experiencia en nuestro centro / Puerperal uterine inversion: a single-center experience

Objetivo. Evaluar la incidencia, la evolución y el riesgo de recurrencia en casos de inversión uterina puerperal en nuestro centro. Material y métodos. Estudio retrospectivo. Veintidós casos de inversión uterina puerperal entre enero del 1993 y diciembre del 2013. Se analizan los diferentes riesgos. Resultados. Pacientes: edad media: 28 años (18-41); 19 nulíparas (86%); 4 pacientes presentaban cirugía uterina anterior (18%). Trabajo de parto: 6 finalizaron la gestación mediante cesárea (27%), y 16 (73%) vía vaginal. Peso medio de los recién nacidos: 3.111 g (2.130-3.950); 8 casos de retención de placenta (36,4%) y 3 atonías uterinas (13,6%). Tipo inversión: 100% aguda. Complicaciones y manejo: hemorragia severa en 7 pacientes; 20 casos (91%) se resolvieron mediante maniobra de Johnson; 2 histerectomías (9%). No hubo muertes ni recurrencias. Conclusiones. La nuliparidad y la retención de placenta fueron factores de riesgo importantes en nuestro estudio. La precocidad en el diagnóstico y el tratamiento es de vital importancia. La cirugía debe ser la última opción (AU)

Objective. To assess the incidence, outcomes, and risk of recurrence of puerperal uterine inversion in our hospital. Material and methods. A retrospective study was carried out in 22 cases of puerperal uterine inversion from January 1993 to December 2013 in our hospital. We analyzed different risk factors. Results. The mean age of the patients was 28 years (18-41). Nineteen (86%) were nulliparous. Four (18%) had undergone previous uterine surgery. Delivery was through cesarean section in 6 patients (27%) and through the vaginal route in 16 (73%). The mean birthweight was 3111 grams (2130-3950). Retained placenta occurred in 8 patients (36.4%) and uterine atony in 3 (13.6%). Uterine inversion was acute in all patients. Complications and management consisted of severe hemorrhage in 7 patients, 20 cases (91%) were resolved by the Johnson procedure, and 22 hysterectomies (9%) were performed. There were no deaths and no recurrences. Conclusions. In our study, important risk factors were nulliparity and placenta accreta. Early diagnosis and treatment are of the utmost importance. Surgery should be the last option (AU)

Leiomiomatosis múltiple y gestación. Cesárea e histerectomía programadas / Multiple leiomyomatosis and pregnancy. Planned cesarean hysterectomy

La concurrencia de miomas uterinos en la gestación es del 0,3-2,6%, aun menor en el caso de la leiomiomatosis múltiple, e implica complicaciones obstétricas y sistémicas en la gestante. La cesárea más histerectomía programada es un procedimiento que no aumenta la morbimortalidad materna y disminuye las posibles complicaciones puerperales. Exponemos los casos de 2 pacientes, con gestaciones a término y con indicación obstétrica de cesárea e indicación ginecológica de histerectomía. En ambas se practicaron las 2 intervenciones en un mismo acto quirúrgico. Las pacientes no presentaron ningún tipo de complicación postoperatoria y el tiempo de estancia hospitalaria total se vio reducido al 50%

The prevalence of leiomyomas in pregnant women ranges from 0.3 to 2.6% while that of multiple uterine leiomyomatosis is even lower. These myomas provoke obstetric and systemic complications in pregnant women. Planned cesarean hysterectomy does not increase maternal morbidity and mortality rates and reduces puerperal complications. We present two cases of pregnant women at term with an obstetric indication for cesarean section and a gynecological indication for hysterectomy. Both procedures were performed in the same intervention. There were no postoperative complications and hospital stay was reduced by 50% (AU)