Pulmonary nodule false positive screening method based on multi-task learning

Abstract

The invention provides a pulmonary nodule false positive screening method based on multi-task learning. The method comprises the following steps: 1, acquiring an initial CT image of a lung to be detected through a CT detector, and preprocessing the three-dimensional initial CT image to obtain a standard CT image; 2, slicing the standard CT image, and inputting a CT slice with a fixed size into a candidate nodule detection model to obtain a candidate nodule; 3, marking positive nodules and false positive nodules of the candidate nodules obtained in the step 2, and inputting the marked nodules into a multi-task model to obtain benign and malignant classification of the candidate nodules and a reconstructed input image; the method is characterized in that a doctor is helped to complete auxiliary diagnosis work by utilizing computer-aided detection and utilizing cross technologies such as digital images, computer vision and pattern recognition. By means of the computer-aided diagnosis technology, the suspected nodule area can be detected from the CT image quickly and accurately, the workload of the doctor can be reduced, and meanwhile, the film reading accuracy and efficiency can be improved.

Description

technical field [0001] The invention relates to the field of pulmonary nodule screening, in particular to a multi-task learning-based false positive screening method for pulmonary nodules. Background technique [0002] Lung cancer is currently one of the diseases with the highest morbidity and mortality in the world, and with the process of industrialization and the aggravation of environmental pollution and other issues, the morbidity and mortality of lung cancer are still rising. Compared with other cancers, the biological characteristics of lung cancer are very complex. The early symptoms of lung cancer are mild and the onset time is short, so it is not easy to be found in the early stage. Once diagnosed as advanced lung cancer, the patient will miss the best time for treatment. Early diagnosis and treatment can usually greatly improve the survival rate of patients. [0003] Lung cancer exists in the form of pulmonary nodules in the early stage. With the continuous devel...

AI Technical Summary

Problems solved by technology

[0003] Lung cancer exists in the form of pulmonary nodules in the early stage. With the continuous development of medical imaging technology, the location and shape of lung lesions can be clearly observed from CT images. The diagnosis must be carefully examined and comprehensively analyzed. Manual examination by doctors only consumes a lot of time and energy. The huge amount of CT image reading greatly increases the work intensity of doctors, and it is easy to cause fatigue. This will lead to a decline in reading efficiency and quality, resulting in a certain probability of misdiagnosis, missed diagnosis, etc., and doctors have a certain degree of subjectivity in the diagnosis of pulmonary nodules

At present, most of the existing automatic detection systems for pulmonary nodules use traditional machine learning methods and two-dimensional images. Usually, some spatial context information of the lungs is lost, and the results produced on different slices are different, and it is easy to cause detection errors

Images