Kathryn V. Isaac’s research while affiliated with University of British Columbia and other places

This Surgical Innovation explores the potential that wearable augmented reality devices have for improving intraoperative imaging, patient outcomes, and surgical workflows.

Introduction Up to one-fifth of breast cancer survivors will develop chronic breast cancer-related lymphoedema (BCRL). To date, complex physical decongestion therapy (CDT) is the gold standard of treatment. However, it is mainly symptomatic and often ineffective in preventing BCRL progression. Lymphovenous anastomosis (LVA) and vascularised lymph node transfer (VLNT) are microsurgical techniques that aim to restore lymphatic drainage. This international randomised trial aims to evaluate advantages of microsurgical interventions plus CDT versus CDT alone for BCRL treatment. Methods and analysis The effectiveness of LVA and/or VLNT in combination with CDT, which may be combined with liposuction, versus CDT alone will be evaluated in routine practice across the globe. Patients with BCRL will be randomly allocated to either surgical or conservative therapy. The primary end point of this trial is the patient-reported quality of life (QoL) outcome ‘lymphoedema-specific QoL’, which will be assessed 15 months after randomisation. Secondary end points are further patient-reported outcomes (PROs), arm volume measurements, economic evaluations and imaging at different time points. A long-term follow-up will be conducted up to 10 years after randomisation. A total of 280 patients will be recruited in over 20 sites worldwide. Ethics and dissemination This study will be conducted in compliance with the Declaration of Helsinki and the International Council for Harmonisation-Good Clinical Practice (ICH-GCP) E6 guideline. Ethical approval has been obtained by the lead ethics committee ‘Ethikkommission Nordwest- und Zentralschweiz’ (2023-00733, 22 May 2023). Ethical approval from local authorities will be sought for all participating sites. Regardless of outcomes, the findings will be published in a peer-reviewed medical journal. Metadata detailing the dataset’s type, size and content will be made available, along with the full study protocol and case report forms, in public repositories in compliance with the Findability, Accessibility, Interoperability and Reuse principles. Trial registration number NCT05890677 .

Objectives This is a protocol for a Cochrane Review (intervention). The objectives are as follows: To assess the effects of microsurgery versus complex physical decongestive therapy in people with chronic breast cancer‐related lymphoedema.

Introduction: Breast cancer care requires both oncologists and plastic surgeons. Coordinating these specialists and combining extirpative and reconstructive procedures before adjunctive therapies can cause delays in care. For patients with less advanced disease, surgery is performed before adjunctive therapies, requiring early specialist coordination and the possibility of surgical complications. We compare these patients to those with more advanced disease requiring adjunctive therapies before surgery. Methods: A retrospective chart review identified 337 post-mastectomy + immediate breast reconstruction (IBR) patients. Patients were divided into surgery first (SF) and neoadjuvant chemotherapy (NC) first groups with reconstructive subgroups. Wait times between care pathway milestones were compiled and compared to national standards. Results: SF experienced longer wait times from consultation to treatment initiation (47 ± 51.5 vs 22 ± 22, P<.001) and from first to second treatment modality (62 ± 35 vs 39 ± 17, P<.001). Furthermore, only 29% of SF met the standard of receiving treatment within 4 weeks from consultation compared to 63% of NC ( P<.001). Within subgroups, SF alloplastic reconstructions had shorter wait times compared to SF autologous reconstructions. For SF, only 31% of alloplastic and 24% of autologous reconstruction initiated treatment within 4 weeks of consultation. Conclusion: In this cohort of Canadian breast cancer patients, those receiving surgery first experienced prolonged wait times to treatment, particularly with autologous reconstruction. Patients should be informed of the potential impact on adjunctive therapies when considering reconstructive modality.

PURPOSE Breast cancer relapses are rarely collected by cancer registries because of logistical and financial constraints. Hence, we investigated natural language processing (NLP), enhanced with state-of-the-art deep learning transformer tools and large language models, to automate relapse identification in the text of computed tomography (CT) reports. METHODS We analyzed follow-up CT reports from patients diagnosed with breast cancer between January 1, 2005, and December 31, 2014. The reports were curated and annotated for the presence or absence of local, regional, and distant breast cancer relapses. We performed 10-fold cross-validation to evaluate models identifying different types of relapses in CT reports. Model performance was assessed with classification metrics, reported with 95% confidence intervals. RESULTS In our data set of 1,445 CT reports, 799 (55.3%) described any relapse, 72 (5.0%) local relapses, 97 (6.7%) regional relapses, and 743 (51.4%) distant relapses. The any-relapse model achieved an accuracy of 89.6% (87.8-91.1), with a sensitivity of 93.2% (91.4-94.9) and a specificity of 84.2% (80.9-87.1). The local relapse model achieved an accuracy of 94.6% (93.3-95.7), a sensitivity of 44.4% (32.8-56.3), and a specificity of 97.2% (96.2-98.0). The regional relapse model showed an accuracy of 93.6% (92.3-94.9), a sensitivity of 70.1% (60.0-79.1), and a specificity of 95.3% (94.2-96.5). Finally, the distant relapse model demonstrated an accuracy of 88.1% (86.2-89.7), a sensitivity of 91.8% (89.9-93.8), and a specificity of 83.7% (80.5-86.4). CONCLUSION We developed NLP models to identify local, regional, and distant breast cancer relapses from CT reports. Automating the identification of breast cancer relapses can enhance data collection about patient outcomes.

Augmented reality (AR) systems for surgical navigation provides the capability to project preoperative CT scans and segmented anatomical structures directly into the surgeon’s field of view, along with virtual displays akin to traditional monitors. Utilizing the Meta Quest 3 consumer AR headset, we found that it can achieve clinically acceptable accuracy in surgical navigation for deep inferior epigastric perforator (DIEP) surgeries. Notably, the Quest 3 can operate independently thanks to a novel registration technique employing hand tracking, suitable for use in sterile environments. The DIEP flap is a widely favored option for autologous breast reconstructions. Intraoperatively, the perforator arteries are selected to maximize tissue perfusion and minimize donor site morbidity. Conventionally, preoperative CT angiograms are used to locate perforators and visualize vessel courses, thus reducing DIEP flap harvest time and complication rates. Though, there are currently very limited means to reliably translate information found on preoperative imaging for use in the operating theater. The Meta Quest 3 was trialed in three DIEP flap surgeries by displaying segmented deep inferior epigastric arteries and DIEP arteries during preoperative and intraoperative phases of surgery. The AR projections facilitated the visualization of the DIEP arteries and efficient pedicle dissection by guiding the placement and length of the fascial incision. Furthermore, this work supports the hypothesis that AR will improve flap design, reduce harvest time, and improve safety during DIEP flap harvesting.

e13591 Background: Relapse is a major concern for oncologists and breast cancer survivors that necessitates additional treatment and often leads to mortality. Cancer registries routinely track cancer mortality, but few monitor for relapse because of logistical challenges and prohibitive costs. In this context, Natural Language Processing (NLP) is a promising tool. Merging artificial intelligence with linguistics, NLP can rapidly analyze vast volumes of text in electronic health records. This capability of NLP is particularly valuable for Computed Tomography (CT) scans used in breast cancer care. CT scans are routinely used to characterize breast cancer progression and are described in transcribed dictations by radiologists. We aimed to apply NLP to these text reports to identify breast cancer relapses. Objective: To automate breast cancer relapse detection and classification in CT text reports using NLP. Methods: We analyzed 1,445 CT text reports from patients diagnosed with breast cancer between January 1, 2005, and December 31, 2014. These reports underwent manual review by trained human annotators. Text was annotated to identify terminology defining local, regional, and distant breast cancer relapses. Annotated reports were partitioned into a training-validation set (90% cohort) and a test set (10% cohort) for NLP model development. Results: In our dataset of 1,445 CT text reports, 72 (5.0%) were classified as local relapse, 97 (6.7%) as regional relapse, and 743 (51.4%) as distant relapse. The performance of our NLP model using the training-validation dataset can be summarized by the following metrics and 95% confidence intervals: 94% (±3.2) accuracy for detection and 96% (±2.9) accuracy for classification. The performance of our NLP model was confirmed using the test dataset, with 90% (±4.5) accuracy for detection and 91% (±6.3) accuracy for classification. For reference, all metrics are outlined (Table). Conclusions: Our model for identifying regional and distant relapses in CT reports had excellent performance, but had lower sensitivity for local relapses, posing a risk of false negatives. Automating the identification and classification of breast cancer relapses, if used retrospectively, can enhance cancer registry data about patient outcomes and, if used prospectively, holds the potential for enhancing patient care. [Table: see text]