RESUMEN
BACKGROUND AND OBJECTIVE: Image-guided surgical navigation (IGSN) can enhance surgical precision and safety. The expansion of minimally invasive surgery has increased the demand for integration of these navigation systems into robot-assisted surgery. Our objective was to evaluate the integration of electromagnetic tracking with IGSN in robot-assisted sentinel lymph node biopsy (SLNB). METHODS: We conducted a prospective feasibility study to test the use of IGSN in SLNB. In total, 25 patients scheduled for SLNB at The Netherlands Cancer Institute were included (March 2022 to March 2023). SLNB using IGSN was performed using a standardised technique with a da Vinci robot (Intuitive Surgical, Sunnyvale, CA, USA) in four-arm configuration. Feasibility was determined as the percentage of sentinel nodes (SNs) successfully identified via IGSN. Successful SN resection was defined as SNs correctly localised via navigation and validated ex vivo with a gamma probe. Surgeon feedback on the robot-assisted IGSN workflow was evaluated using the System Usability Scale (SUS). KEY FINDINGS AND LIMITATIONS: In accordance with the protocol, the first five patients were used for workflow optimisation, and the subsequent 20 patients were included in the analysis. IGSN led to successful identification of 91% (50/55) of the SNs. There were no complications associated with navigation. The surgeon feedback (SUS) was 60.9, with lowest scores reported for the user interface and workflow integration. CONCLUSIONS: IGSN during robot-assisted surgery was feasible and safe. The technique allowed identification and removal of predefined small pelvic lymph nodes. PATIENT SUMMARY: We carried out a study on the feasibility of imaging-guided navigation in robot-assisted prostate surgery. Our results show that this technique is feasible, safe, and effective.
RESUMEN
Significance: The accurate correlation between optical measurements and pathology relies on precise image registration, often hindered by deformations in histology images. We investigate an automated multi-modal image registration method using deep learning to align breast specimen images with corresponding histology images. Aim: We aim to explore the effectiveness of an automated image registration technique based on deep learning principles for aligning breast specimen images with histology images acquired through different modalities, addressing challenges posed by intensity variations and structural differences. Approach: Unsupervised and supervised learning approaches, employing the VoxelMorph model, were examined using a dataset featuring manually registered images as ground truth. Results: Evaluation metrics, including Dice scores and mutual information, demonstrate that the unsupervised model exceeds the supervised (and manual) approaches significantly, achieving superior image alignment. The findings highlight the efficacy of automated registration in enhancing the validation of optical technologies by reducing human errors associated with manual registration processes. Conclusions: This automated registration technique offers promising potential to enhance the validation of optical technologies by minimizing human-induced errors and inconsistencies associated with manual image registration processes, thereby improving the accuracy of correlating optical measurements with pathology labels.
Asunto(s)
Procesamiento de Imagen Asistido por Computador , Humanos , Procesamiento de Imagen Asistido por Computador/métodos , Aprendizaje Profundo , Femenino , Mama/diagnóstico por imagen , Neoplasias de la Mama/diagnóstico por imagen , Neoplasias de la Mama/patología , Algoritmos , Imagen Multimodal/métodosRESUMEN
This study aims to evaluate several defined specimen parameters that would allow to determine the surgical accuracy of breast-conserving surgeries (BCS) in a representative population of patients. These specimen parameters could be used to compare surgical accuracy when using novel technologies for intra-operative BCS guidance in the future. Different specimen parameters were determined among 100 BCS patients, including the ratio of specimen volume to tumor volume (resection ratio) with different optimal margin widths (0 mm, 1 mm, 2 mm, and 10 mm). Furthermore, the tumor eccentricity [maximum tumor-margin distance - minimum tumor-margin distance] and the relative tumor eccentricity [tumor eccentricity ÷ pathological tumor diameter] were determined. Different patient subgroups were compared using Wilcoxon rank sum tests. When using a surgical margin width of 0 mm, 1 mm, 2 mm, and 10 mm, on average, 19.16 (IQR 44.36), 9.94 (IQR 18.09), 6.06 (IQR 9.69) and 1.35 (IQR 1.78) times the ideal resection volume was excised, respectively. The median tumor eccentricity among the entire patient population was 11.29 mm (SD = 3.99) and the median relative tumor eccentricity was 0.66 (SD = 2.22). Resection ratios based on different optimal margin widths (0 mm, 1 mm, 2 mm, and 10 mm) and the (relative) tumor eccentricity could be valuable outcome measures to evaluate the surgical accuracy of novel technologies for intra-operative BCS guidance.
RESUMEN
BACKGROUND: Hepatic arterial infusion pump chemotherapy combined with systemic chemotherapy (HAIP-SYS) for liver-only colorectal liver metastases (CRLMs) has shown promising results but has not been adopted worldwide. This study evaluated the feasibility of HAIP-SYS in the Netherlands. METHODS: This was a single-arm phase II study of patients with CRLMs who received HAIP-SYS consisting of floxuridine with concomitant systemic FOLFOX or FOLFIRI. Main inclusion and exclusion criteria were borderline resectable or unresectable liver-only metastases, suitable arterial anatomy and no previous local treatment. Patients underwent laparotomy for pump implantation and primary tumour resection if in situ. Primary end point was feasibility, defined as ≥70% of patients completing two cycles of HAIP-SYS. Sample size calculations led to 31 patients. Secondary outcomes included safety and tumour response. RESULTS: Thirty-one patients with median 13 CRLMs (i.q.r. 6-23) were included. Twenty-eight patients (90%) received two HAIP-SYS cycles. Three patients did not get two cycles due to extrahepatic disease at pump placement, definitive pathology of a recto-sigmoidal squamous cell carcinoma, and progressive disease. Five patients experienced grade 3 surgical or pump device-related complications (16%) and 11 patients experienced grade ≥3 chemotherapy toxicity (38%). At first radiological evaluation, disease control rate was 83% (24/29 patients) and hepatic disease control rate 93% (27/29 patients). At 6 months, 19 patients (66%) had experienced grade ≥3 chemotherapy toxicity and the disease control rate was 79%. CONCLUSION: HAIP-SYS for borderline resectable and unresectable CRLMs was feasible and safe in the Netherlands. This has led to a successive multicentre phase III randomized trial investigating oncological benefit (EUDRA-CT 2023-506194-35-00). Current trial registration number: clinicaltrials.gov (NCT04552093).
Asunto(s)
Carcinoma de Células Escamosas , Neoplasias Colorrectales , Neoplasias Hepáticas , Humanos , Estudios de Factibilidad , Neoplasias Hepáticas/tratamiento farmacológico , Neoplasias Hepáticas/cirugía , Bombas de InfusiónRESUMEN
(1) Background: Hyperspectral imaging has emerged as a promising margin assessment technique for breast-conserving surgery. However, to be implicated intraoperatively, it should be both fast and capable of yielding high-quality images to provide accurate guidance and decision-making throughout the surgery. As there exists a trade-off between image quality and data acquisition time, higher resolution images come at the cost of longer acquisition times and vice versa. (2) Methods: Therefore, in this study, we introduce a deep learning spatial-spectral reconstruction framework to obtain a high-resolution hyperspectral image from a low-resolution hyperspectral image combined with a high-resolution RGB image as input. (3) Results: Using the framework, we demonstrate the ability to perform a fast data acquisition during surgery while maintaining a high image quality, even in complex scenarios where challenges arise, such as blur due to motion artifacts, dead pixels on the camera sensor, noise from the sensor's reduced sensitivity at spectral extremities, and specular reflections caused by smooth surface areas of the tissue. (4) Conclusion: This gives the opportunity to facilitate an accurate margin assessment through intraoperative hyperspectral imaging.
Asunto(s)
Artefactos , Mastectomía Segmentaria , Movimiento (Física)RESUMEN
Purpose: Training and evaluation of the performance of a supervised deep-learning model for the segmentation of hepatic tumors from intraoperative US (iUS) images, with the purpose of improving the accuracy of tumor margin assessment during liver surgeries and the detection of lesions during colorectal surgeries. Approach: In this retrospective study, a U-Net network was trained with the nnU-Net framework in different configurations for the segmentation of CRLM from iUS. The model was trained on B-mode intraoperative hepatic US images, hand-labeled by an expert clinician. The model was tested on an independent set of similar images. The average age of the study population was 61.9 ± 9.9 years. Ground truth for the test set was provided by a radiologist, and three extra delineation sets were used for the computation of inter-observer variability. Results: The presented model achieved a DSC of 0.84 (p=0.0037), which is comparable to the expert human raters scores. The model segmented hypoechoic and mixed lesions more accurately (DSC of 0.89 and 0.88, respectively) than hyper- and isoechoic ones (DSC of 0.70 and 0.60, respectively) only missing isoechoic or >20 mm in diameter (8% of the tumors) lesions. The inclusion of extra margins of probable tumor tissue around the lesions in the training ground truth resulted in lower DSCs of 0.75 (p=0.0022). Conclusion: The model can accurately segment hepatic tumors from iUS images and has the potential to speed up the resection margin definition during surgeries and the detection of lesion in screenings by automating iUS assessment.
RESUMEN
The validation of newly developed optical tissue-sensing techniques for tumor detection during cancer surgery requires an accurate correlation with the histological results. Additionally, such an accurate correlation facilitates precise data labeling for developing high-performance machine learning tissue-classification models. In this paper, a newly developed Point Projection Mapping system will be introduced, which allows non-destructive tracking of the measurement locations on tissue specimens. Additionally, a framework for accurate registration, validation, and labeling with the histopathology results is proposed and validated on a case study. The proposed framework provides a more-robust and accurate method for the tracking and validation of optical tissue-sensing techniques, which saves time and resources compared to the available conventional techniques.
RESUMEN
Significance: Accurately distinguishing tumor tissue from normal tissue is crucial to achieve complete resections during soft tissue sarcoma (STS) surgery while preserving critical structures. Incomplete tumor resections are associated with an increased risk of local recurrence and worse patient prognosis. Aim: We evaluate the performance of diffuse reflectance spectroscopy (DRS) to distinguish tumor tissue from healthy tissue in STSs. Approach: DRS spectra were acquired from different tissue types on multiple locations in 20 freshly excised sarcoma specimens. A k-nearest neighbors classification model was trained to predict the tissue types of the measured locations, using binary and multiclass approaches. Results: Tumor tissue could be distinguished from healthy tissue with a classification accuracy of 0.90, sensitivity of 0.88, and specificity of 0.93 when well-differentiated liposarcomas were included. Excluding this subtype, the classification performance increased to an accuracy of 0.93, sensitivity of 0.94, and specificity of 0.93. The developed model showed a consistent performance over different histological subtypes and tumor locations. Conclusions: Automatic tissue discrimination using DRS enables real-time intra-operative guidance, contributing to more accurate STS resections.
Asunto(s)
Sarcoma , Humanos , Análisis Espectral/métodos , Pronóstico , Sarcoma/diagnóstico por imagen , Sarcoma/cirugíaRESUMEN
PURPOSE: Accuracy of image-guided liver surgery is challenged by deformation of the liver during the procedure. This study aims at improving navigation accuracy by using intraoperative deep learning segmentation and nonrigid registration of hepatic vasculature from ultrasound (US) images to compensate for changes in liver position and deformation. METHODS: This was a single-center prospective study of patients with liver metastases from any origin. Electromagnetic tracking was used to follow US and liver movement. A preoperative 3D model of the liver, including liver lesions, and hepatic and portal vasculature, was registered with the intraoperative organ position. Hepatic vasculature was segmented using a reduced 3D U-Net and registered to preoperative imaging after initial alignment followed by nonrigid registration. Accuracy was assessed as Euclidean distance between the tumor center imaged in the intraoperative US and the registered preoperative image. RESULTS: Median target registration error (TRE) after initial alignment was 11.6 mm in 25 procedures and improved to 6.9 mm after nonrigid registration (p = 0.0076). The number of TREs above 10 mm halved from 16 to 8 after nonrigid registration. In 9 cases, registration was performed twice after failure of the first attempt. The first registration cycle was completed in median 11 min (8:00-18:45 min) and a second in 5 min (2:30-10:20 min). CONCLUSION: This novel registration workflow using automatic vascular detection and nonrigid registration allows to accurately localize liver lesions. Further automation in the workflow is required in initial alignment and classification accuracy.
Asunto(s)
Aprendizaje Profundo , Neoplasias Hepáticas , Humanos , Movimientos de los Órganos , Estudios Prospectivos , Neoplasias Hepáticas/diagnóstico por imagen , Neoplasias Hepáticas/cirugía , Imagenología Tridimensional/métodosRESUMEN
Tumor boundary identification during colorectal cancer surgery can be challenging, and incomplete tumor removal occurs in approximately 10% of the patients operated for advanced rectal cancer. In this paper, a deep learning framework for automatic tumor segmentation in colorectal ultrasound images was developed, to provide real-time guidance on resection margins using intra-operative ultrasound. A colorectal ultrasound dataset was acquired consisting of 179 images from 74 patients, with ground truth tumor annotations based on histopathology results. To address data scarcity, transfer learning techniques were used to optimize models pre-trained on breast ultrasound data for colorectal ultrasound data. A new custom gradient-based loss function (GWDice) was developed, which emphasizes the clinically relevant top margin of the tumor while training the networks. Lastly, ensemble learning methods were applied to combine tumor segmentation predictions of multiple individual models and further improve the overall tumor segmentation performance. Transfer learning outperformed training from scratch, with an average Dice coefficient over all individual networks of 0.78 compared to 0.68. The new GWDice loss function clearly decreased the average tumor margin prediction error from 1.08 mm to 0.92 mm, without compromising the segmentation of the overall tumor contour. Ensemble learning further improved the Dice coefficient to 0.84 and the tumor margin prediction error to 0.67 mm. Using transfer and ensemble learning strategies, good tumor segmentation performance was achieved despite the relatively small dataset. The developed US segmentation model may contribute to more accurate colorectal tumor resections by providing real-time intra-operative feedback on tumor margins.
RESUMEN
During breast-conserving surgeries, it remains challenging to accomplish adequate surgical margins. We investigated different numbers of fibers for fiber-optic diffuse reflectance spectroscopy to differentiate tumorous breast tissue from healthy tissue ex vivo up to 2 mm from the margin. Using a machine-learning classification model, the optimal performance was obtained using at least three emitting fibers (Matthew's correlation coefficient (MCC) of 0.73), which was significantly higher compared to the performance of using a single-emitting fiber (MCC of 0.48). The percentage of correctly classified tumor locations varied from 75% to 100% depending on the tumor percentage, the tumor-margin distance and the number of fibers.
RESUMEN
With the shift towards organ preserving treatment strategies in rectal cancer it has become increasingly important to accurately discriminate between a complete and good clinical response after neoadjuvant chemoradiotherapy (CRT). Standard of care imaging techniques such as CT and MRI are well equipped for initial staging of rectal tumors, but discrimination between a good clinical and complete response remains difficult due to their limited ability to detect small residual vital tumor fragments. To identify new promising imaging techniques that could fill this gap, it is crucial to know the size and invasion depth of residual vital tumor tissue since this determines the requirements with regard to the resolution and imaging depth of potential new optical imaging techniques. We analyzed 198 pathology slides from 30 rectal cancer patients with a Mandard tumor regression grade 2 or 3 after CRT that underwent surgery. For each patient we determined response pattern, size of the largest vital tumor fragment or bulk and the shortest distance from the vital tumor to the luminal surface. The response pattern was shrinkage in 14 patients and fragmentation in 16 patients. For both groups combined, the largest vital tumor fragment per patient was smaller than 1mm for 38% of patients, below 0.2mm for 12% of patients and for one patient as small as 0.06mm. For 29% of patients the vital tumor remnant was present within the first 0.01mm from the luminal surface and for 87% within 0.5mm. Our results explain why it is difficult to differentiate between a good clinical and complete response in rectal cancer patients using endoscopy and MRI, since in many patients submillimeter tumor fragments remain below the luminal surface. To detect residual vital tumor tissue in all patients included in this study a technique with a spatial resolution of 0.06mm and an imaging depth of 8.9mm would have been required. Optical imaging techniques offer the possibility of detecting majority of these cases due to the potential of both high-resolution imaging and enhanced contrast between tissue types. These techniques could thus serve as a complimentary tool to conventional methods for rectal cancer response assessment.
RESUMEN
(1) Background: Assessing the resection margins during breast-conserving surgery is an important clinical need to minimize the risk of recurrent breast cancer. However, currently there is no technique that can provide real-time feedback to aid surgeons in the margin assessment. Hyperspectral imaging has the potential to overcome this problem. To classify resection margins with this technique, a tissue discrimination model should be developed, which requires a dataset with accurate ground-truth labels. However, establishing such a dataset for resection specimens is difficult. (2) Methods: In this study, we therefore propose a novel approach based on hyperspectral unmixing to determine which pixels within hyperspectral images should be assigned to the ground-truth labels from histopathology. Subsequently, we use this hyperspectral-unmixing-based approach to develop a tissue discrimination model on the presence of tumor tissue within the resection margins of ex vivo breast lumpectomy specimens. (3) Results: In total, 372 measured locations were included on the lumpectomy resection surface of 189 patients. We achieved a sensitivity of 0.94, specificity of 0.85, accuracy of 0.87, Matthew's correlation coefficient of 0.71, and area under the curve of 0.92. (4) Conclusion: Using this hyperspectral-unmixing-based approach, we demonstrated that the measured locations with hyperspectral imaging on the resection surface of lumpectomy specimens could be classified with excellent performance.
RESUMEN
In vivo tissue imaging is an essential tool for medical diagnosis, surgical guidance, and treatment. However, specular reflections caused by glossy tissue surfaces can significantly degrade image quality and hinder the accuracy of imaging systems. In this work, we further the miniaturisation of specular reflection reduction techniques using micro cameras, which have the potential to act as intra-operative supportive tools for clinicians. In order to remove these specular reflections, two small form factor camera probes, handheld at 10 mm footprint and miniaturisable to 2.3 mm, are developed using different modalities, with line-of-sight to further miniaturisation. (1) The sample is illuminated via multi-flash technique from four different positions, causing a shift in reflections which are then filtered out in a post-processing image reconstruction step. (2) The cross-polarisation technique integrates orthogonal polarisers onto the tip of the illumination fibres and camera, respectively, to filter out the polarisation maintaining reflections. These form part of a portable imaging system that is capable of rapid image acquisition using different illumination wavelengths, and employs techniques that lend themselves well to further footprint reduction. We demonstrate the efficacy of the proposed system with validating experiments on tissue-mimicking phantoms with high surface reflection, as well as on excised human breast tissue. We show that both methods can provide clear and detailed images of tissue structures along with the effective removal of distortion or artefacts caused by specular reflections. Our results suggest that the proposed system can improve the image quality of miniature in vivo tissue imaging systems and reveal underlying feature information at depth, for both human and machine observers, leading to better diagnosis and treatment outcomes.
RESUMEN
The authors wish to make the following corrections to this paper [...].
RESUMEN
Optical technologies are widely used for tissue sensing purposes. However, maneuvering conventional probe designs with flat-tipped fibers in narrow spaces can be challenging, for instance during pelvic colorectal cancer surgery. In this study, a compact side-firing fiber probe was developed for tissue discrimination during colorectal cancer surgery using diffuse reflectance spectroscopy. The optical behavior was compared to flat-tipped fibers using both Monte Carlo simulations and experimental phantom measurements. The tissue classification performance was examined using freshly excised colorectal cancer specimens. Using the developed probe and classification algorithm, an accuracy of 0.92 was achieved for discriminating tumor tissue from healthy tissue.
RESUMEN
INTRODUCTION: Anastomotic leakage after gastrointestinal surgery has a high impact on patient's quality of life and its origin is associated with inadequate perfusion. Imaging photoplethysmography (iPPG) is a noninvasive imaging technique that measures blood-volume changes in the microvascular tissue bed and detects changes in tissue perfusion. MATERIALS AND METHODS: Intraoperative iPPG imaging was performed in 29 patients undergoing an open segment resection of the small intestine or colon. During each surgery, imaging was performed on fully perfused (true positives) and ischemic intestines (true negatives) and the anastomosis (unknowns). Imaging consisted of a 30-s video from which perfusion maps were extracted, providing detailed information about blood flow within the intestine microvasculature. To detect the predictive capabilities of iPPG, true positive and true negative perfusion conditions were used to develop two different perfusion classification methods. RESULTS: iPPG-derived perfusion parameters were highly correlated with perfusion-perfused or ischemic-in intestinal tissues. A perfusion confidence map distinguished perfused and ischemic intestinal tissues with 96% sensitivity and 86% specificity. Anastomosis images were scored as adequately perfused in 86% of cases and 14% inconclusive. The cubic-Support Vector Machine achieved 90.9% accuracy and an area under the curve of 96%. No anastomosis-related postoperative complications were encountered in this study. CONCLUSIONS: This study shows that noninvasive intraoperative iPPG is suitable for the objective assessment of small intestine and colon anastomotic perfusion. In addition, two perfusion classification methods were developed, providing the first step in an intestinal perfusion prediction model.
Asunto(s)
Procedimientos Quirúrgicos del Sistema Digestivo , Fotopletismografía , Humanos , Fotopletismografía/efectos adversos , Calidad de Vida , Anastomosis Quirúrgica/efectos adversos , Procedimientos Quirúrgicos del Sistema Digestivo/efectos adversos , Fuga Anastomótica/etiología , Perfusión/efectos adversos , Verde de IndocianinaRESUMEN
BACKGROUND AND AIMS: Screening for colorectal cancer (CRC) aims to decrease CRC incidence and mortality. Biennial fecal immunochemical test screening started in the Netherlands in 2014 for individuals 55-75 years of age. This study investigated the effect of screening on stage-specific incidence, with focus on stage III and IV CRC. METHODS: Inhabitants diagnosed with CRC in 2009-2018 were included. CRC incidence per stage, year, and detection method (ie, screen-detected vs clinically detected) was evaluated. Patient, tumor, and treatment characteristics, and survival of patients with stage III and IV CRC, were compared according to the detection method. RESULTS: Included were 140,649 CRCs in 136,882 patients. An initial peak of stage I-III CRC diagnoses after initiation of screening was followed by a continuous decrease within screening-eligible ages. Total CRC incidence remained higher than before screening, although stage II and IV CRC incidence decreased below prescreening levels. Screen-detected CRCs were significantly more frequently located in the left-sided colon (stage III; 43.7% vs 30.9%; stage IV: 45.1% vs 36.1%), and the primary tumor resection rate was higher (stage III colon: 99.8% vs 99.0%, rectum: 97.3% vs 89.7%; stage IV colon: 65.4% vs 56.6%, rectum: 47.3% vs 33.5%). Patients with screen-detected stage IV CRC had significantly more often single-organ metastases (74.5% vs 57.0%; P < .001) and more frequently received treatment with curative intent (colon: 41.3% vs 27.4%; rectum: 33.8% vs 24.6%). Overall survival significantly improved for patients with screen-detected CRCs (stage III: P < .001; stage IV: P < .001). CONCLUSIONS: Five years after the start of a nationwide CRC screening program, a decrease in stage II and IV CRC incidence was observed. Patients with screen-detected stage III and stage IV CRC had less extensive disease and improved survival compared with those with clinically detected CRC.
Asunto(s)
Neoplasias Colorrectales , Detección Precoz del Cáncer , Humanos , Incidencia , Detección Precoz del Cáncer/métodos , Neoplasias Colorrectales/diagnóstico , Tamizaje Masivo/métodos , Países Bajos/epidemiologíaRESUMEN
Significance: Hyperspectral reflectance imaging can be used in medicine to identify tissue types, such as tumor tissue. Tissue classification algorithms are developed based on, e.g., machine learning or principle component analysis. For the development of these algorithms, data are generally preprocessed to remove variability in data not related to the tissue itself since this will improve the performance of the classification algorithm. In hyperspectral imaging, the measured spectra are also influenced by reflections from the surface (glare) and height variations within and between tissue samples. Aim: To compare the ability of different preprocessing algorithms to decrease variations in spectra induced by glare and height differences while maintaining contrast based on differences in optical properties between tissue types. Approach: We compare eight preprocessing algorithms commonly used in medical hyperspectral imaging: standard normal variate, multiplicative scatter correction, min-max normalization, mean centering, area under the curve normalization, single wavelength normalization, first derivative, and second derivative. We investigate conservation of contrast stemming from differences in: blood volume fraction, presence of different absorbers, scatter amplitude, and scatter slope-while correcting for glare and height variations. We use a similarity metric, the overlap coefficient, to quantify contrast between spectra. We also investigate the algorithms for clinical datasets from the colon and breast. Conclusions: Preprocessing reduces the overlap due to glare and distance variations. In general, the algorithms standard normal variate, min-max, area under the curve, and single wavelength normalization are the most suitable to preprocess data used to develop a classification algorithm for tissue classification. The type of contrast between tissue types determines which of these four algorithms is most suitable.
Asunto(s)
Imágenes Hiperespectrales , Máquina de Vectores de Soporte , Algoritmos , Análisis de Componente Principal , Espectroscopía Infrarroja CortaRESUMEN
Achieving an adequate resection margin during breast-conserving surgery remains challenging due to the lack of intraoperative feedback. Here, we evaluated the use of hyperspectral imaging to discriminate healthy tissue from tumor tissue in lumpectomy specimens. We first used a dataset obtained on tissue slices to develop and evaluate three convolutional neural networks. Second, we fine-tuned the networks with lumpectomy data to predict the tissue percentages of the lumpectomy resection surface. A MCC of 0.92 was achieved on the tissue slices and an RMSE of 9% on the lumpectomy resection surface. This shows the potential of hyperspectral imaging to classify the resection margins of lumpectomy specimens.