Hyperspectral imaging for tissue classification, a way toward smart laparoscopic colorectal surgery.

In the last decades, laparoscopic surgery has become the gold standard in patients with colorectal cancer. To overcome the drawback of reduced tactile feedback, real-time tissue classification could be of great benefit. In this ex vivo study, hyperspectral imaging (HSI) was used to distinguish tumor tissue from healthy surrounding tissue. A sample of fat, healthy colorectal wall, and tumor tissue was collected per patient and imaged using two hyperspectral cameras, covering the wavelength range from 400 to 1700 nm. The data were randomly divided into a training (75%) and test (25%) set. After feature reduction, a quadratic classifier and support vector machine were used to distinguish the three tissue types. Tissue samples of 32 patients were imaged using both hyperspectral cameras. The accuracy to distinguish the three tissue types using both hyperspectral cameras was 0.88 (STD = 0.13) on the test dataset. When the accuracy was determined per patient, a mean accuracy of 0.93 (STD = 0.12) was obtained on the test dataset. This study shows the potential of using HSI in colorectal cancer surgery for fast tissue classification, which could improve clinical outcome. Future research should be focused on imaging entire colon/rectum specimen and the translation of the technique to an intraoperative setting.

Detection of breast cancer by surface-enhanced laser desorption/ionization time-of-flight mass spectrometry tissue and serum protein profiling.

AIM: Novel diagnostic breast cancer markers have been extensively searched for in the proteome, using, among others, surface-enhanced laser desorption/ionization time-of-flight mass spectrometry (SELDI-TOF MS). Thus far, the majority of SELDI-TOF MS studies have investigated samples originating from biorepositories, which hampers biomarker discovery as they likely suffer from variable adherence to collection protocols. MATERIAL AND METHODS: We investigated breast cancer (n=75) and control (n=26) serum and tissue samples, collected prospectively by rigorous adherence to a strictly defined protocol. Sera were collected preoperatively and postoperatively, and serum and tissue samples were analyzed by SELDI-TOF MS using the IMAC30 Ni and Q10 pH 8 array. RESULTS: Three serum peaks were significantly associated with breast cancer, while in tissue, 27 discriminative peaks were detected. Several peak clusters gradually increased or decreased in intensity from healthy to benign to cancer, or with increasing cancer stage. The constructed classification trees had a tenfold cross-validated performance of 67% to 87%. Two tissue peaks were identified as N-terminal albumin fragments. These are likely to have been generated by (breast) cancer-specific proteolytic activity in the tumor microenvironment. CONCLUSIONS: These albumin fragment scan potentially provide insights into the pathophysiological mechanisms associated with, or underlying, breast cancer, and aid in improving breast cancer diagnosis.