Development and validation of a diagnostic model based on artificial intelligence for diagnosing pancreatic cancer.
The global incidence and mortality rates of pancreatic cancer have been on the rise in recent decades. At the same time, pancreatic cancer occupies a leading position among malignant neoplasms, which are often first detected at advanced stages, which significantly worsens the prognosis for patients. In this regard, it is important to create automated systems capable of accurately segmenting and diagnosing pancreatic tumors at an early stage. A diagnostic model based on U-Net is proposed and evaluated, aimed at improving the accuracy of automatic segmentation of medical images for segmentation of the pancreas and identification of malignant changes in computed tomography (CT) images.
The diagnostic model of the algorithm was based on the U-Net architecture, and image texture indices were used as control features. The neural network algorithm was trained using CT data from 310 patients with pancreatic neoplasms. Segmentation datasets from 280 pancreatic cancer studies from an open source, Memorial Sloan Kettering Cancer Center, was used to segment medical images and train the algorithm. Manual segmentation of medical images obtained at Regional Clinical Hospital of the Kaliningrad was performed using specialized three-dimensional (3D) Slicer software: CT images of 30 patients with pancreatic neoplasms. Diagnoses in the patient group were confirmed by morphological diagnostics, including examination of biopsy samples and/or surgical material. Four types of indicators were used to quantify segmentation results: Dice similarity coefficient (DSC), accuracy, sensitivity, and specificity.
The diagnostic model achieved an accuracy of 88% in the classification of pancreatic cancer, and the DSC segmentation accuracy factor was 70%, demonstrating sensitivity of 98% and specificity of 98%. The results obtained emphasize the effectiveness of CT image analysis for the diagnosis of pancreatic malignancies using a neural network algorithm that uses textural features of medical images. In the course of the work, a number of limitations were identified: obtaining false positive results during segmentation, a limited number of medical images and clinical data that may affect the representativeness of the developed diagnostic model. Nevertheless, the results show the prospects for integrating artificial intelligence (AI) technologies into clinical practice, which can significantly improve diagnostic efficiency.
The use of neural network algorithms based on the textural features of medical images has significant potential in the field of clinical decision support systems. Despite certain limitations in the course of work, the using textural features for training neural networks will increase the accuracy of diagnosis of pancreatic malignancies and will play an important role in determining patient management strategies and monitoring the effectiveness of prescribed treatment methods. It is necessary to further study additional textural characteristics, utilize 3D models, and include more clinical data to improve the accuracy of the diagnostic model when differentiating malignant tumors from healthy tissues.
The diagnostic model of the algorithm was based on the U-Net architecture, and image texture indices were used as control features. The neural network algorithm was trained using CT data from 310 patients with pancreatic neoplasms. Segmentation datasets from 280 pancreatic cancer studies from an open source, Memorial Sloan Kettering Cancer Center, was used to segment medical images and train the algorithm. Manual segmentation of medical images obtained at Regional Clinical Hospital of the Kaliningrad was performed using specialized three-dimensional (3D) Slicer software: CT images of 30 patients with pancreatic neoplasms. Diagnoses in the patient group were confirmed by morphological diagnostics, including examination of biopsy samples and/or surgical material. Four types of indicators were used to quantify segmentation results: Dice similarity coefficient (DSC), accuracy, sensitivity, and specificity.
The diagnostic model achieved an accuracy of 88% in the classification of pancreatic cancer, and the DSC segmentation accuracy factor was 70%, demonstrating sensitivity of 98% and specificity of 98%. The results obtained emphasize the effectiveness of CT image analysis for the diagnosis of pancreatic malignancies using a neural network algorithm that uses textural features of medical images. In the course of the work, a number of limitations were identified: obtaining false positive results during segmentation, a limited number of medical images and clinical data that may affect the representativeness of the developed diagnostic model. Nevertheless, the results show the prospects for integrating artificial intelligence (AI) technologies into clinical practice, which can significantly improve diagnostic efficiency.
The use of neural network algorithms based on the textural features of medical images has significant potential in the field of clinical decision support systems. Despite certain limitations in the course of work, the using textural features for training neural networks will increase the accuracy of diagnosis of pancreatic malignancies and will play an important role in determining patient management strategies and monitoring the effectiveness of prescribed treatment methods. It is necessary to further study additional textural characteristics, utilize 3D models, and include more clinical data to improve the accuracy of the diagnostic model when differentiating malignant tumors from healthy tissues.
Authors
Paramzin Paramzin, Kakotkin Kakotkin, Burkin Burkin, Ponimash Ponimash, Nikitin Nikitin, Agapov Agapov
View on Pubmed