RESUMO
INTRODUCTION AND AIM: The technology, named 'deep learning' is the promising result of the last two decades of development in computer science. It poses an unavoidable challenge for medicine, how to understand, apply and adopt the - today not fully explored - possibilities that have become available by these new methods. METHOD: It is a gift and a mission, since the exponentially growing volume of raw data (from imaging, laboratory, therapy diagnostics or therapy interactions, etc.) did not solve until now our wished and aimed goal to treat patients according to their personal status and setting or specific to their tumor and disease. RESULTS: Currently, as a responsible health care provider and financier, we face the problem of supporting suboptimal procedures and protocols either at individual or at community level. The problem roots in the overwhelming amount of data and, at the same time, the lack of targeted information for treatment. We expect from the deep learning technology an aid which helps to reinforce and extend the human-human cooperations in patient-doctor visits. We expect that computers take over the tedious work allowing to revive the core of healing medicine: the insightful meeting and discussion between patients and medical experts. CONCLUSION: We should learn the revelational possibilities of deep learning techniques that can help to overcome our recognized finite capacities in data processing and integration. If we, doctors and health care providers or decision makers, are able to abandon our fears and prejudices, then we can utilize this new tool not only in imaging diagnostics but also for daily therapies (e.g., immune therapy). The paper aims to make a great mind to do this. Orv Hetil. 2019; 160(4): 138-143.
Assuntos
Inteligência Artificial , Aprendizado Profundo , Mamografia , Interface Usuário-Computador , Humanos , Hungria , Motivação , Relações Médico-PacienteRESUMO
In the last two decades, Computer Aided Detection (CAD) systems were developed to help radiologists analyse screening mammograms, however benefits of current CAD technologies appear to be contradictory, therefore they should be improved to be ultimately considered useful. Since 2012, deep convolutional neural networks (CNN) have been a tremendous success in image recognition, reaching human performance. These methods have greatly surpassed the traditional approaches, which are similar to currently used CAD solutions. Deep CNN-s have the potential to revolutionize medical image analysis. We propose a CAD system based on one of the most successful object detection frameworks, Faster R-CNN. The system detects and classifies malignant or benign lesions on a mammogram without any human intervention. The proposed method sets the state of the art classification performance on the public INbreast database, AUC = 0.95. The approach described here has achieved 2nd place in the Digital Mammography DREAM Challenge with AUC = 0.85. When used as a detector, the system reaches high sensitivity with very few false positive marks per image on the INbreast dataset. Source code, the trained model and an OsiriX plugin are published online at https://github.com/riblidezso/frcnn_cad .
Assuntos
Neoplasias da Mama/diagnóstico , Neoplasias da Mama/patologia , Aprendizado Profundo , Diagnóstico por Computador/métodos , Detecção Precoce de Câncer/métodos , Mamografia/métodos , Neoplasias da Mama/classificação , Confiabilidade dos Dados , Bases de Dados Factuais , Feminino , Humanos , Aprendizado de Máquina , Programas de Rastreamento , Redes Neurais de Computação , Curva ROCRESUMO
BACKGROUND: Mutation of the p53 gene is detectable in most cases of gastric cancer, as it is the most common genetic alteration in human malignancies. It is also well documented that Helicobacter pylori infection plays an important role in gastric carcinogenesis. There is still no clarification, however, concerning how genetic instability influences the homeostasis of gastric epithelium. We have studied the effect of H. pylori infection on apoptosis of the antral epithelium in the presence/absence of intestinal metaplasia and the expression of the p53 oncoprotein. The relationship between these two processes is analysed. METHODS: Antral biopsies were taken from 36 patients who underwent routine upper endoscopy (17 men, 19 women, mean age 61.0 years). The biopsies were fixed in formalin and embedded in paraffin. Patients were classified into two histological groups: (1) as chronic gastritis without intestinal metaplasia (n = 19), and (2) chronic gastritis with intestinal metaplasia (n = 17). An immunohistochemical method was used to detect the expression of p53 oncoprotein, and the terminal transferase mediated dUTP nick end-labelling (TUNEL) method was used to detect apoptotic cells. RESULTS: In the absence of intestinal metaplasia, both the apoptotic index (0.0272 +/- 0.011 vs 0.0128 +/- 0.006) and expresssion of p53 (35.55 +/- 31.16 vs 18.33 +/- 19.65) were significantly higher in H. pylori positive cases compared to H. pylori negative cases. In the presence of intestinal metaplasia, p53 expression was further increased (P < 0.05), but apoptosis was similar to that observed in H. pylori negative gastritis without intestinal metaplasia. In the presence of intestinal metaplasia, H. pylori infection did not influence apoptosis (0.013 +/- 0.004 vs 0.011 +/- 0.004), or p53 ratio (70.16 +/- 22.54 vs 68.50 +/- 28.96). In the sequence of gastritis-intestinal metaplasia the two indices show a close negative correlation (P < 0.05). CONCLUSION: In the absence of intestinal metaplasia H. pylori infection increases both apoptotic activity and expression of p53 oncoprotein in the gastric mucosa. The lack of increased apoptosis with a higher p53 expression in the presence of intestinal metaplasia suggests an increased genetic instability and also may suggest that mutation of the p53 gene is an early step in the multistep process of gastric carcinogenesis.
Assuntos
Apoptose/genética , Gastrite/genética , Genes p53/genética , Infecções por Helicobacter , Helicobacter pylori , Intestinos/patologia , Idoso , Feminino , Mucosa Gástrica/patologia , Gastrite/microbiologia , Gastrite/patologia , Expressão Gênica/genética , Humanos , Marcação In Situ das Extremidades Cortadas/métodos , Masculino , Metaplasia , Pessoa de Meia-Idade , Mutação/genética , Proteínas Oncogênicas/análiseRESUMO
Our aim was to compare the expression of EGFR and proliferative cell nuclear antigen (PCNA) in different histological and endoscopic diagnostic groups, in cases of Helicobacter pylori infection, in vivo. Paraffin embedded human gastric biopsy samples (86) were analysed by EGFR and PCNA immunohistochemistry and classified both on the basis of histology and endoscopic findings. In normal epithelia (NE), a positive correlation was found between PCNA and EGFR and in H. pylori-negative gastritis with and without intestinal metaplasia (P < 0.01). On the other hand, a negative correlation was detected between the two immunohistochemical findings in H. pylori-associated gastritis with intestinal metaplasia (HPGIM) and in the atrophic gastritis (AG) group. In HPGIM the percentage of EGFR-positive cells was significantly lower (32.4 +/- 30.4) when compared to either the NE (50.3 +/- 23.7) or H. pylori-negative gastritis with intestinal metaplasia (HNGIM) (48.3 +/- 23.7). In AG, EGFR was significantly lower when compared to the NE (P < 0.05). Based on the endoscopic findings, a significant decrease of EGFR expression was found in gastric ulcer cases as compared to NE, gastritis or erosion cases (P < 0.01). PCNA showed no significant alterations between the NE and gastritis, AG groups. The presence of H. pylori has an inverse effect on PCNA and EGFR expression in HPGIM.