This study reports a method for the detection of mechanical signaling anomalies in cardiac tissue through the use of deep learning and the design of two anomaly detectors. In contrast to anomaly classifiers, anomaly detectors allow accurate identification of the time position of the anomaly. The first detector used a recurrent neural network (RNN) of long short-term memory (LSTM) type, while the second used an autoencoder. Mechanical contraction data present several challanges, including high presence of noise due to the biological variability in the contraction response, noise introduced by the data acquisition chain and a wide variety of anomalies. Therefore, we present a robust deep-learning-based anomaly detection framework that addresses these main issues, which are difficult to address with standard unsupervised learning techniques. For the time series recording, an experimental model was designed in which signals of cardiac mechanical contraction (right and left atria) of a CD-1 mouse could be acquired in an automatic organ bath, reproducing the physiological conditions. In order to train the anomaly detection models and validate their performance, a database of synthetic signals was designed (n = 800 signals), including a wide range of anomalous events observed in the experimental recordings. The detector based on the LSTM neural network was the most accurate. The performance of this detector was assessed by means of experimental mechanical recordings of cardiac tissue of the right and left atria.