Clinical practice has revealed ambiguities in PI-RADS v2.1 scoring, but a limited number of studies are available that validate the interreader and intrareader reproducibility of the mpMRI PI-RADS lexicon. We decomposed the PI-RADS rules into a set of common data elements to evaluate the inter- and intraobserver agreement in assessing the individual features included in the PI-RADS lexicon. Six radiologists (three highly experienced, three less experienced) in two sessions independently read thirty-two lesions in the peripheral and transition zone using the structured reporting tool, blinded to clinical MRI indication. The highest agreement between radiologists was observed for the abnormality detection, the evaluation of the type of signal intensity, and the characteristic of benign prostatic hyperplasia. Moderate agreement was reported for dynamic contrast-enhanced images. This resulted in a decrease in abnormality detection (PA = 76.5%) and enhancement indication (PA = 77.3%). The lowest agreement was observed for highly subjective features: shape, signal intensity level, and type of lesion margins. The results indicate the limitations of the PI-RADS v2.1 lexicon in relation to interreader and intrareader reproducibility. We have demonstrated that it is possible to develop structured reporting systems standardized according to the PI-RADS lexicon.

BACKGROUND. Managing women in pregnancy or labour is becoming a serious challenge because of delayed conception age and higher morbidity. The main negative factor is increasing numbers of overweight and obese women. Fatty tissue significantly biases the detection of uterine contractions by tocography, which is routinely used in obstetrical wards. Thus, the FDA approved an alternative method called electrohysterography (EHG) and recommended it for women with an over-normal BMI. However, almost all published methods of labour prediction based on EHG signals use a “black-box model” approach, i.e., increasingly numerically complex signal features and classification algorithms that are chosen a priori, without any physiological rationale behind them. This makes using these algorithms difficult in obstetrical practice. AIM. The aim of the study was to show that a simple classifier based on a single and physiologically interpretable parameter can predict uterine contractions during labour with an accuracy comparable to advanced classifiers. METHODS. An obstetrical interpretable EHG parameter was introduced called the uterine activity index. To avoid the influence of confounding factors associated with preterm labour and imbalanced signal sets, this classifier was evaluated using the private, retrospective database of EHG signals registered for 45 women in the third trimester of a pregnancy, and 31 women in the second stage of labour with a normal BMI. The classifier, based on the logistic regression model, was tested using the bootstrap method. RESULTS. The bootstrapping mean (95% confidence interval) of the AUC ROC estimated for the 200 bootstrap samples was 0.96 (0.91–0.99). This accuracy was slightly better for EHG signals in comparison to predictions based on classical tocography. CONCLUSIONS. The obtained results confirm that a simple physiologically explained classifier can be considered in commercial applications of electrohysterography. However, its clinical significance should be evaluated through properly designed randomised clinical trials.

Reinforcement learning (RL) is one of three basic machine learning paradigms, alongside supervised learning and unsupervised learning. Reinforcement learning algorithms have become very popular in simple computer games and games like chess and GO. However, playing classical arcade fighting games would be challenging because of the complexity of the command system (the character makes moves according to the sequence of input) and combo system. In this paper, a creation of a game environment of The King of Fighters ’97 (KOF ’97), which implements the open gym env interface, is described. Based on the characteristics of the game, an innovative approach to represent the observations from the last few steps has been proposed, which guarantees the preservation of Markov’s property. The observations are coded using the “one-hot encoding” technique to form a binary vector, while the sequence of stacked vectors from successive steps creates a binary image. This image encodes the character’s input and behavioural pattern, which are then retrieved and recognized by the CNN network. A network structure based on the Advantage Actor-Critic network was proposed. In the experimental verification, the RL agent performing basic combos and complex moves (including the so-called “desperation moves”) was able to defeat characters using the highest level of AI built into the game.