Breast cancer afflicts millions of women in the United States and worldwide, of whom about a half to two-thirds will undergo breast conserving surgery (BCS) or lumpectomy.^1,2 The goal of BCS is to completely remove the tumor with a narrow rim/margin of normal, unaffected breast tissue while preserving as much normal tissue as possible. Although outcomes have improved over the last decade, women with positive margins (cancer cells at the surface of the surgical specimen) still have at least a twofold increased risk of cancer recurrence,^{3 – 5} and thus, are often recommended to undergo additional surgery to achieve clear margins. Additional surgery is associated with additional discomfort, surgical complications, worse cosmesis, and additional emotional stress, time, and financial burdens to patients and their caregivers.^6,7 The current re-excision rate of BCS in the United States is 14% to 18% and highly variable among surgeons, ranging from 0% to 92%.^{2,8 – 12} One reason why women with positive margins need to undergo re-excision surgery is that definitive pathologic margin status is typically not available until several days after surgery.

Microscopy with ultraviolet surface excitation (MUSE) is increasingly studied for intraoperative assessment of tumor margins during breast-conserving surgery to reduce the re-excision rate. Here we report a two-step classification approach using texture analysis of MUSE images to automate the margin detection. A study dataset consisting of MUSE images from 66 human breast tissues was constructed for model training and validation. Features extracted using six texture analysis methods were investigated for tissue characterization, and a support vector machine was trained for binary classification of image patches within a full image based on selected feature subsets. A weighted majority voting strategy classified a sample as tumor or normal. Using the eight most predictive features ranked by the maximum relevance minimum redundancy and Laplacian scores methods has achieved a sample classification accuracy of 92.4% and 93.0%, respectively. Local binary pattern alone has achieved an accuracy of 90.3%.

Endotracheal tube (ETT) intubation is a medical procedure routinely used for achieving mechanical ventilation in critically ill patients. Appropriate ETT placement is crucial as undetected tube migration may cause multiple complications or even fatalities. Therefore, prompt detection of unplanned movement of the ETT and immediate action to restore proper placement are essential to ensure patient safety. Despite this necessity, there is not a widely adopted tool for real-time assessment of ETT displacement. We have developed a device, a dual-camera endotracheal tube or DC-ETT, to address this unmet clinical need. This device uses a near-infrared (NIR) LED and a side-firing optical fiber embedded in the side of an ETT to light up the tracheal tissue and a visible and NIR camera module for the displacement detection. The NIR camera tracks the movement of the NIR pattern on the skin, while the visible camera is used to correct the body movements. The efficacy of the DC-ETT was assessed in two piglets with a linear displacement sensor as reference. A mean discrepancy of less than 0.5 mm between the DC-ETT and reference sensor was observed within a displacement range of ±15 mm. The results suggest that the DC-ETT can potentially provide a simple and cost-effective solution for real-time monitoring of ETT displacements in operating rooms, intensive care units, and emergency departments.

SignificanceAccurate transfer of annotations from histological images to fluorescence images is essential in developing deep learning (DL)-based optical imaging systems for intraoperative assessment of tumor margins. Manual annotation is time-consuming, prone to interobserver variability, and impractical for large-scale datasets.AimWe present a semi-automated method that can effectively transfer tumor annotations from pathologist-annotated hematoxylin and eosin (H&E) images to fluorescence images captured using microscopy with ultraviolet surface excitation (MUSE). This method is not intended for intraoperative use but rather to facilitate the creation of annotated datasets for DL model development.ApproachOur semi-automated method consists of nonrigid image registration, outline extraction and refinement, and annotation transfer. The method was applied to H&E and MUSE image pairs from 35 breast and lung tissue samples. Manual annotations in MUSE images were used as the ground truth for evaluation.ResultsThe proposed method achieved a Dice score coefficient of 0.87±0.07, convolutional-neural-network-based feature similarity of 0.94±0.04, and a normalized Hausdorff distance of 0.15±0.06 across the dataset.ConclusionThese results demonstrate that the method provides a fast and accurate solution for generating annotated MUSE datasets necessary for training DL algorithms for intraoperative tumor margin detection.

SignificanceEndotracheal intubation is a common approach for airway management in critically ill patients. However, the position of the endotracheal tube (ETT) may be altered during the procedure due to head movements. Accidental displacement or dislodge of the ETT may reduce the airflow, leading to moderate to severe complications, and in some cases even fatality. Therefore, timely detection of changes in ETT position in the trachea is critical to ensure immediate and intermediate interventions to maintain the ETT in the proper position. Currently, there are no widely utilized tools for real-time monitoring of ETT positions.AimThe goal of this study is to develop a cost-effective and easy-to-use near-infrared (NIR) device, named Opt-ETT, capable of continuously monitoring the ETT position in the trachea of a patient.ApproachA side-firing fiber is attached to the side of the ETT to illuminate the trachea tissue with NIR light, and a detector board containing five phototransistors is affixed to the chest skin to measure the intensity of diffusely transmitted light. Displacement of the ETT is estimated using second-order polynomial fitting to the ratios of the phototransistor readings. Monte Carlo simulations, ex vivo experiment on porcine tissue, and in vivo experiments using a swine model have been conducted to assess the feasibility of the device.ResultsThe design of the Opt-ETT device has been verified by the Monte Carlo simulations and ex vivo experiment. The estimation of displacement from in vivo experiments using the Opt-ETT exhibited a high degree of agreement with that measured by a reference sensor, with a discrepancy between −1.0 to +1.5 mm within a displacement range from −15 to +15 mm.ConclusionsThe Opt-ETT device provides a potentially cost-effective solution for real-time and continuous monitoring of ETT position in patient during an intubation procedure.

Significance: Over 80% of cervical cancer cases occur in lower-to-middle income countries (LMIC’s). This is partly because current screening techniques lack affordability, accessibility, and/or reliability for use in LMIC’s. Aim: To develop an optical technique for cervical cancer screening that is affordable, accessible, and reliable for use in LMIC’s. Approach: We developed a portable diffuse reflectance spectroscopy (DRS) system, which costs [ ] USD to manufacture, and employs a Raspberry Pi to extract the absorption ([ ]) and reduced scattering ([ ]) coefficients of biological tissue. The system was subject to travel and intentional rough handling. It was further used to capture 320 DRS spectra taken from 64 tissue-mimicking phantoms. Two users collected phantom data, one “expert”, and one “novice” in biomedical optics. The system was also used to collect 335 spectra from colon, small intestine, and rectal tissue of a fresh ex vivo porcine specimen. A previously described artificial intelligence model was used to extract optical properties, and a GradientBoostingClassifier identified the organ of origin for ex vivo spectra. Results: System alignment was robust to intentional rough handling and travel. Phantom [ ] and [ ] were predicted with average root-mean square error of [ ], regardless of user. Regarding ex vivo data, the system predicted the organ of origin with 80–90% accuracy. Statistical differences between predicted [ ] were observed in all three organs ([ ]–0.03), and between [ ] in two organs ([ ]–0.07). Conclusions: The DRS system has the potential to be affordable, reliable, and accessible for cervical screening in LMIC’s.