A ConvLSTM-based model for predicting thermal damage during laser interstitial thermal therapy

<i>Objective.</i>Accurate prediction of thermal damage extent is essential for effective and precise thermal therapy, especially in brain laser interstitial thermal therapy (LITT). Immediate postoperative contrast-enhanced T1-weighted imaging (CE-T1WI) is the primary method for clinically assessing<i>in vivo</i>thermal damage after image-guided LITT. CE-T1WI reveals a hyperintense enhancing rim surrounding the target lesion, which serves as a key radiological marker for evaluating the thermal damage extent. Although widely used in clinical practice, traditional thermal damage models rely on empirical parameters from<i>in vitro</i>experiments, which can lead to inaccurate predictions of thermal damage<i>in vivo</i>. Additionally, these models predict only two tissue states (damaged or undamaged), failing to capture three tissue states observed on post-CE-T1WI images, highlighting the need for improved thermal damage prediction methods.<i>Approach.</i>This study proposes a novel convolutional long short-term memory-based model that utilizes intraoperative temperature distribution history data measured by magnetic resonance temperature imaging (MRTI) during LITT to predict the enhancing rim on post-CE-T1WI images. This method was implemented and evaluated on retrospective data from 56 patients underwent brain LITT.<i>Main results.</i>The proposed model effectively predicts the enhancing rim on postoperative images, achieving an average dice similarity coefficient of 0.82 (±0.063) on the test dataset. Furthermore, it generates real-time predicted thermal damage area variation trends that closely resemble those of the traditional thermal damage model, suggesting potential for real-time prediction of thermal damage extent.<i>Significance.</i>This method could provide a valuable tool for visualizing and assessing intraoperative thermal damage extent.