RESUMO
BACKGROUND: Colorectal cancer has a high incidence rate worldwide, with over 1.8 million new cases and 880,792 deaths in 2018. Fortunately, its early detection significantly increases the survival rate, reaching a cure rate of 90% when diagnosed at a localized stage. Colonoscopy is the gold standard technique for detection and removal of colorectal lesions with potential to evolve into cancer. When polyps are found in a patient, the current procedure is their complete removal. However, in this process, gastroenterologists cannot assure complete resection and clean margins which are given by the histopathology analysis of the removed tissue, which is performed at laboratory. AIMS: In this paper, we demonstrate the capabilities of multiphoton microscopy (MPM) technology to provide imaging biomarkers that can be extracted by deep learning techniques to identify malignant neoplastic colon lesions and distinguish them from healthy, hyperplastic, or benign neoplastic tissue, without the need for histopathological staining. MATERIALS AND METHODS: To this end, we present a novel MPM public dataset containing 14,712 images obtained from 42 patients and grouped into 2 classes. A convolutional neural network is trained on this dataset and a spatially coherent predictions scheme is applied for performance improvement. RESULTS: We obtained a sensitivity of 0.8228 ± 0.1575 and a specificity of 0.9114 ± 0.0814 on detecting malignant neoplastic lesions. We also validated this approach to estimate the self-confidence of the network on its own predictions, obtaining a mean sensitivity of 0.8697 and a mean specificity of 0.9524 with the 18.67% of the images classified as uncertain. CONCLUSIONS: This work lays the foundations for performing in vivo optical colon biopsies by combining this novel imaging technology together with deep learning algorithms, hence avoiding unnecessary polyp resection and allowing in situ diagnosis assessment.
RESUMO
BACKGROUND: The results obtained to date concerning food groups, diet quality and colorectal cancer (CRC) risk vary according to criteria used and the study populations. AIM: To study the relationships between food groups, diet quality and CRC risk, in an adult population of the Basque Country (North of Spain). METHODS: This observational study included 308 patients diagnosed with CRC and 308 age- and sex-matched subjects as controls. During recruitment, dietary, anthropometric, lifestyle, socioeconomic, demographic and health status information was collected. Adherence to the dietary recommendations was evaluated utilizing the Healthy Eating Index for the Spanish Diet and the MedDietScore. Conditional logistic regressions were used to evaluate the associations of food group intakes, diet quality scores, categorized in tertiles, with CRC risk. RESULTS: The adjusted models for potential confounding factors showed a direct association between milk and dairy products consumption, in particular high-fat cheeses [odds ratio (OR) third tertile vs first tertile = 1.87, 95% confidence intervals (CI): 1.11-3.16], and CRC risk. While the consumption of fiber-containing foods, especially whole grains (OR third tertile vs first tertile = 0.62, 95%CI: 0.39-0.98), and fatty fish (OR third tertile vs first tertile = 0.53, 95%CI: 0.27-0.99) was associated with a lower risk for CRC. Moreover, higher MD adherence was associated with a reduced CRC risk in adjusted models (OR third tertile vs first tertile = 0.40, 95%CI: 0.20-0.80). CONCLUSION: Direct associations were found for high-fat cheese, whereas an inverse relation was reported for fiber-containing foods and fatty fish, as well as adherence to a Mediterranean dietary pattern.