The rising prevalence of mental health disorders, particularly depression, highlights the need for improved approaches in therapeutic interventions. Traditional psychotherapy relies on subjective assessments, which can vary across therapists and sessions, making it challenging to track emotional progression and therapy effectiveness objectively. Leveraging the advancements in Natural Language Processing (NLP) and domain-specific Large Language Models (LLMs), this study introduces nBERT, a fine-tuned Bidirectional Encoder Representations from the Transformers (BERT) model integrated with the NRC Emotion Lexicon, to elevate emotion recognition in psychotherapy transcripts. The goal of this study is to provide a computational framework that aids in identifying emotional patterns, tracking patient-therapist emotional alignment, and assessing therapy outcomes. Addressing the challenge of emotion classification in text-based therapy sessions, where non-verbal cues are absent, nBERT demonstrates its ability to extract nuanced emotional insights from unstructured textual data, providing a data-driven approach to enhance mental health assessments. Trained on a dataset of 2021 psychotherapy transcripts, the model achieves an average precision of 91.53%, significantly outperforming baseline models. This capability not only improves diagnostic accuracy but also supports the customization of therapeutic strategies. By automating the interpretation of complex emotional dynamics in psychotherapy, nBERT exemplifies the transformative potential of NLP and LLMs in revolutionizing mental health care. Beyond psychotherapy, the framework enables broader LLM applications in the life sciences, including personalized medicine and precision healthcare.

Pyramid-based deformable registration networks achieve strong accuracy by decomposing complex deformations into a stack of subfields. However, most methods only rely on a single-step prediction at each scale and lack explicit modeling of intra-level motion ambiguity. Additionally, Transformer-based methods typically require millions of parameters. Such limitations restrict their ability to deploy, and jointly handle large displacements and subtle local motions. We propose ESR-Net, a parameter-efficient and motion-aware registration network that introduces an Exploratory Self-Refinement Module (ESRM) at each decoder level. A four-stage design in ESRM explicitly captures, guides, evaluates, and refines diverse motion possibilities rather than relying on a direct deformation estimation. In particular, ESRM first predicts motion-aware offset fields via spatial-channel attention, then dynamically relocates and updates warped moving features via deformable convolution, estimates confidence-aware weights by comparing updated moving and fixed features, and finally performs confidence-weighted fusion of multiple offset candidates to produce refined contextual representations and deformation subfields. This design enables ESR-Net to jointly capture intra-level motion diversity and inter-level dependencies, allowing it to handle both large displacements and subtle local deformations with high precision in a purely convolutional and lightweight manner. Extensive experiments on three 3D brain MRI datasets and one lung CT dataset show that ESR-Net outperforms popular CNN-based, Transformer-based, and pyramid-based methods while requiring only 0.60M parameters. These results demonstrate that explicit exploratory self-refinement offers an efficient and effective alternative to heavy Transformer-based registration models. Our code is publicly available at https://github.com/YoboY23420/ESR-Net.

The remaining useful life (RUL) of complex mechanical systems is the primary aspect of prognostics and health management, which is critical for ensuring reliability and safety. Recent developments have shifted towards a data-driven approach, emphasizing empirical insights over expert opinions. The similarity-based data-driven approach operates on the premise that systems with similar historical behaviors will likely exhibit similar future behaviors, making it suitable for RUL estimation. Conventionally, most similarity-based approaches utilize all historical data to identify reference systems for RUL estimations. However, not all historical events within a system hold equal significance for RUL. Certain events have a substantial impact on the remaining lifespan of a system. These significant and impactful events are called degradation events (DEs) in this study. Based on the hypothesis that systems undergoing similar DEs may share the same RUL, this study presents an innovative framework for RUL estimation that leverages only the DEs of a test system to identify reference systems that have experienced similar DEs. Furthermore, the model incorporates novel strategies for adjusting the RUL of the reference system based on the initial wear and degradation rates, thereby improving estimation accuracy. The effectiveness of the proposed model, in comparison with similar state-of-the-art models, is demonstrated through experiments on widely recognized jet engine datasets provided by NASA and bearing degradation data from the XJTU-SY.