From quantitative metrics to clinical success: assessing the utility of deep learning for tumor segmentation in breast surgery.

PURPOSE: Preventing positive margins is essential for ensuring favorable patient outcomes following breast-conserving surgery (BCS). Deep learning has the potential to enable this by automatically contouring the tumor and guiding resection in real time. However, evaluation of such models with respect to pathology outcomes is necessary for their successful translation into clinical practice. METHODS: Sixteen deep learning models based on established architectures in the literature are trained on 7318 ultrasound images from 33 patients. Models are ranked by an expert based on their contours generated from images in our test set. Generated contours from each model are also analyzed using recorded cautery trajectories of five navigated BCS cases to predict margin status. Predicted margins are compared with pathology reports. RESULTS: The best-performing model using both quantitative evaluation and our visual ranking framework achieved a mean Dice score of 0.959. Quantitative metrics are positively associated with expert visual rankings. However, the predictive value of generated contours was limited with a sensitivity of 0.750 and a specificity of 0.433 when tested against pathology reports. CONCLUSION: We present a clinical evaluation of deep learning models trained for intraoperative tumor segmentation in breast-conserving surgery. We demonstrate that automatic contouring is limited in predicting pathology margins despite achieving high performance on quantitative metrics.

Real-time automatic tumor segmentation for ultrasound-guided breast-conserving surgery navigation.

PURPOSE: Ultrasound-based navigation is a promising method in breast-conserving surgery, but tumor contouring often requires a radiologist at the time of surgery. Our goal is to develop a real-time automatic neural network-based tumor contouring process for intraoperative guidance. Segmentation accuracy is evaluated by both pixel-based metrics and expert visual rating. METHODS: This retrospective study includes 7318 intraoperative ultrasound images acquired from 33 breast cancer patients, randomly split between 80:20 for training and testing. We implement a u-net architecture to label each pixel on ultrasound images as either tumor or healthy breast tissue. Quantitative metrics are calculated to evaluate the model's accuracy. Contour quality and usability are also assessed by fellowship-trained breast radiologists and surgical oncologists. Additionally, the viability of using our u-net model in an existing surgical navigation system is evaluated by measuring the segmentation frame rate. RESULTS: The mean dice similarity coefficient of our u-net model is 0.78, with an area under the receiver-operating characteristics curve of 0.94, sensitivity of 0.95, and specificity of 0.67. Expert visual ratings are positive, with 93% of responses rating tumor contour quality at or above 7/10, and 75% of responses rating contour quality at or above 8/10. Real-time tumor segmentation achieved a frame rate of 16 frames-per-second, sufficient for clinical use. CONCLUSION: Neural networks trained with intraoperative ultrasound images provide consistent tumor segmentations that are well received by clinicians. These findings suggest that neural networks are a promising adjunct to alleviate radiologist workload as well as improving efficiency in breast-conserving surgery navigation systems.

Real-time electromagnetic navigation for breast-conserving surgery using NaviKnife technology: A matched case-control study.

Breast-conserving surgery (BCS) is a mainstay in breast cancer treatment. For nonpalpable breast cancers, current strategies have limited accuracy, contributing to high positive margin rates. We developed NaviKnife, a surgical navigation system based on real-time electromagnetic (EM) tracking. The goal of this study was to confirm the feasibility of intraoperative EM navigation in patients with nonpalpable breast cancer and to assess the potential value of surgical navigation. We recruited 40 patients with ultrasound visible, single, nonpalpable lesions, undergoing BCS. Feasibility was assessed by equipment functionality and sterility, acceptable duration of the operation, and surgeon feedback. Secondary outcomes included specimen volume, positive margin rate, and reoperation outcomes. Study patients were compared to a control group by a matched case-control analysis. There was no equipment failure or breach of sterility. The median operative time was 66 (44-119) minutes with NaviKnife vs 65 (34-158) minutes for the control (P = .64). NaviKnife contouring time was 3.2 (1.6-9) minutes. Surgeons rated navigation as easy to setup, easy to use, and useful in guiding nonpalpable tumor excision. The mean specimen volume was 95.4 ± 73.5 cm3 with NaviKnife and 140.7 ± 100.3 cm3 for the control (P = .01). The positive margin rate was 22.5% with NaviKnife and 28.7% for the control (P = .52). The re-excision specimen contained residual disease in 14.3% for NaviKnife and 50% for the control (P = .28). Our results demonstrate that real-time EM navigation is feasible in the operating room for BCS. Excisions performed with navigation result in the removal of less breast tissue without compromising postive margin rates.