Up to 35% of breast-conserving surgeries fail to resect all the tumors completely. Ideally, machine learning methods using the iKnife data, which uses Rapid Evaporative Ionization Mass Spectrometry (REIMS), can be utilized to predict tissue type in real-time during surgery, resulting in better tumor resections. As REIMS data is heterogeneous and weakly labeled, and datasets are often small, model performance and reliability can be adversely affected. Self-supervised training and uncertainty estimation of the prediction can be used to mitigate these challenges by learning the signatures of input data without their label as well as including predictive confidence in output reporting. We first design an autoencoder model using a reconstruction pretext task as a self-supervised pretraining step without considering tissue type. Next, we construct our uncertainty-aware classifier using the encoder part of the model with Masksembles layers to estimate the uncertainty associated with its predictions. The pretext task was trained on 190 burns collected from 34 patients from Basal Cell Carcinoma iKnife data. The model was further trained on breast cancer data comprising of 200 burns collected from 15 patients. Our proposed model shows improvement in sensitivity and uncertainty metrics of 10% and 15.7% over the baseline, respectively. The proposed strategies lead to improvements in uncertainty calibration and overall performance, toward reducing the likelihood of incomplete resection, supporting removal of minimal non-neoplastic tissue, and improved model reliability during surgery. Future work will focus on further testing the model on intraoperative data and additional exvivo data following collection of more breast samples.
Glioblastoma Multiforme (GBM) is the most common and most lethal primary brain tumor in adults with a five-year survival rate of 5%. The current standard of care and survival rate have remained largely unchanged due to the degree of difficulty in surgically removing these tumors, which plays a crucial role in survival, as better surgical resection leads to longer survival times. Thus, novel technologies need to be identified to improve resection accuracy. Our study features a curated database of GBM and normal brain tissue specimens, which we used to train and validate a multi-instance learning model for GBM detection via rapid evaporative ionization mass spectrometry. This method enables real-time tissue typing. The specimens were collected by a surgeon, reviewed by a pathologist, and sampled with an electrocautery device. The dataset comprised 276 normal tissue burns and 321 GBM tissue burns. Our multi-instance learning model was adapted to identify the molecular signatures of GBM, and we employed a patient-stratified four-fold cross-validation approach for model training and evaluation. Our models demonstrated robustness and outperformed baseline models with an improved AUC of 0.95 and accuracy of 0.95 in correctly classifying GBM and normal brain. This study marks the first application of deep learning to REIMS data for brain tumor tissue characterization. This study sets the foundation for investigating more clinically relevant questions where intraoperative tissue detection in neurosurgery is pertinent.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.