There are approximately 1.8 million diagnoses of colorectal cancer, 1 million diagnoses of stomach cancer, and 0.6 million diagnoses of esophageal cancer each year globally. An automatic computer-assisted diagnostic (CAD) tool to rapidly detect colorectal and esophagogastric cancer tissue in optical images would be hugely valuable to a surgeon during an intervention. Based on a colon dataset with 12 patients and an esophagogastric dataset of 10 patients, several state-of-the-art machine learning methods have been trained to detect cancer tissue using hyperspectral imaging (HSI), including Support Vector Machines (SVM) with radial basis function kernels, Multi-Layer Perceptrons (MLP) and 3D Convolutional Neural Networks (3DCNN). A leave-one-patient-out cross-validation (LOPOCV) with and without combining these sets was performed. The ROC-AUC score of the 3DCNN was slightly higher than the MLP and SVM with a difference of 0.04 AUC. The best performance was achieved with the 3DCNN for colon cancer and esophagogastric cancer detection with a high ROC-AUC of 0.93. The 3DCNN also achieved the best DICE scores of 0.49 and 0.41 on the colon and esophagogastric datasets, respectively. These scores were significantly improved using a patient-specific decision threshold to 0.58 and 0.51, respectively. This indicates that, in practical use, an HSI-based CAD system using an interactive decision threshold is likely to be valuable. Experiments were also performed to measure the benefits of combining the colorectal and esophagogastric datasets (22 patients), and this yielded significantly better results with the MLP and SVM models.

Currently, colorectal cancer (CRC) is mainly identified via a visual assessment during colonoscopy, increasingly used artificial intelligence algorithms, or surgery. Subsequently, CRC is confirmed through a histopathological examination by a pathologist. Hyperspectral imaging (HSI), a non-invasive optical imaging technology, has shown promising results in the medical field. In the current study, we combined HSI with several artificial intelligence algorithms to discriminate CRC. Between July 2019 and May 2020, 54 consecutive patients undergoing colorectal resections for CRC were included. The tumor was imaged from the mucosal side with a hyperspectral camera. The image annotations were classified into three groups (cancer, CA; adenomatous margin around the central tumor, AD; and healthy mucosa, HM). Classification and visualization were performed based on a four-layer perceptron neural network. Based on a neural network, the classification of CA or AD resulted in a sensitivity of 86% and a specificity of 95%, by means of leave-one-patient-out cross-validation. Additionally, significant differences in terms of perfusion parameters (e.g., oxygen saturation) related to tumor staging and neoadjuvant therapy were observed. Hyperspectral imaging combined with automatic classification can be used to differentiate between CRC and healthy mucosa. Additionally, the biological changes induced by chemotherapy to the tissue are detectable with HSI.

Hyperspectral imaging (HSI) has been used in many fields of biomedical research and clinical applications in recent years.¹ Promising results were reported for the estimation of organ perfusion,^2,3 differentiation of anatomical structures,^4,5 wound assessment,^6,7 and the detection of cancerous tissue^{8 – 11} in animal experiments and clinical studies.¹² However, the majority of the described systems do not apply to current minimally invasive surgery. Supporting the estimation of tissue perfusion or detection of risk structures with spectral imaging would be particularly important in laparoscopic procedures where surgeons are limited to their visual impression.

Background: Thyroidectomy is one of the most commonly performed surgical procedures. The region of the neck has a very complex structural organization. It would be beneficial to introduce a tool that can assist the surgeon in tissue discrimination during the procedure. One such solution is the noninvasive and contactless technique, called hyperspectral imaging (HSI).Methods: To interpret the HSI data, we implemented a supervised classification method to automatically discriminate the parathyroid, the thyroid, and the recurrent laryngeal nerve from surrounding tissue(muscle, skin) and materials (instruments, gauze). A leave‐one‐patient‐out cross‐validation was performed.Results: The best performance was obtained using support vector machine (SVM) with a classification and visualization in less than 1.4 seconds. A mean patient accuracy of 68% ± 23% was obtained for all tissues and material types.Conclusions: The proposed method showed promising results and have to be confirmed on a larger cohort of patient data.

Background: Novel intraoperative imaging techniques, namely, hyperspectral (HSI) and fluorescence imaging (FI), are promising with respect to reducing severe postoperative complications, thus increasing patient safety. Both tools have already been used to evaluate perfusion of the gastric conduit after esophagectomy and before anastomosis. To our knowledge, this is the first study evaluating both modalities simultaneously during esophagectomy. Methods: In our pilot study, 13 patients, who underwent Ivor Lewis esophagectomy and gastric conduit reconstruction, were analyzed prospectively. HSI and FI were recorded before establishing the anastomosis in order to determine its optimum position. Results: No anastomotic leak occurred during this pilot study. In five patients, the imaging methods resulted in a more peripheral adaptation of the anastomosis. There were no significant differences between the two imaging tools, and no adverse events due to the imaging methods or indocyanine green (ICG) injection occurred. Conclusions: Simultaneous intraoperative application of both modalities was feasible and not time consuming. They are complementary with regard to the ideal anastomotic position and may contribute to better surgical outcomes. The impact of their simultaneous application will be proven in consecutive prospective trials with a large patient cohort.