Clinical application and improvement of a CNN‐based autosegmentation model for clinical target volumes in cervical cancer radiotherapy

Abstract

Objective: Clinical target volume (CTV) autosegmentation for cervical cancer is desirable for radiation therapy. Data heterogeneity and interobserver variability (IOV) limit the clinical adaptability of such methods. The adaptive method is proposed to improve the adaptability of CNN-based autosegmentation of CTV contours in cervical cancer. Methods: This study included 400 cervical cancer treatment planning cases with CTV delineated by radiation oncologists from three hospitals. The datasets were divided into five subdatasets (80 cases each). The cases in datasets 1, 2, and 3 were delineated by physicians A, B, and C, respectively. The cases in datasets 4 and 5 were delineated by multiple physicians. Dataset 1 was divided into training (50 cases), validation (10 cases), and testing (20 cases) cohorts, and they were used to construct the pretrained model. Datasets 2-5 were regarded as host datasets to evaluate the accuracy of the pretrained model. In the adaptive process, the pretrained model was fine-tuned to measure improvements by gradually adding more training cases selected from the host datasets. The accuracy of the autosegmentation model on each host dataset was evaluated using the corresponding test cases. The Dice similarity coefficient (DSC) and 95% Hausdorff distance (HD_95) were used to evaluate the accuracy. Results: Before and after adaptive improvements, the average DSC values on the host datasets were 0.818 versus 0.882, 0.763 versus 0.810, 0.727 versus 0.772, and 0.679 versus 0.789, which are improvements of 7.82%, 6.16%, 6.19%, and 16.05%, respectively. The average HD_95 values were 11.143 mm versus 6.853 mm,22.402 mm versus 14.076 mm,28.145 mm versus 16.437 mm, and 33.034 mm versus 16.441 mm,which are improvements of 37.94%,37.17%, 41.60%, and 50.23%, respectively. Conclusion:The proposed method improved the adaptability of the CNNbased autosegmentation model when applied to host datasets.

A Comparison Study Between CNN-Based Deformed Planning CT and CycleGAN-Based Synthetic CT Methods for Improving iCBCT Image Quality

“…In recent years, deep learning-based image processing methods have been widely applied to the field of medical imaging, including medical image segmentation ( 7 – 9 ), disease diagnosis ( 10 , 11 ), medical image denoising ( 12 ), and medical image translation ( 13 , 14 ). The development of deep learning technology has accelerated the process of clinical treatment and improved the mining of medical image information.…”

Evaluation of generalization ability for deep learning‐based auto‐segmentation accuracy in limited field of view CBCT of male pelvic region

“…[10][11][12] Researchers have conducted segmentation of soft tissue organs on CT and/or CBCT using neural encoding/decoding based on the CNN architecture, thereby exploiting supervised training. [13][14][15][16][17][18][19][20][21] The main requirement for this type of approach is anatomical correspondence between the input image (CT or CBCT), and the ground truth reference label. [13][14][15][16][17][18][19][20][21] Although CNNbased segmentation works well for full field of view (FOV) CBCT, [13][14][15][16][17]20,21 it is unknown whether CNNbased segmentation using limited FOV CBCT is possible.…”

“…Multiple investigators have reported that atlas‐based and convolutional neural network (CNN)‐based segmentation was successfully applied to CT and CBCT images, showing that the CNN‐based methods can provide greater segmentation accuracy and better efficiency than atlas‐based methods 10–12 . Researchers have conducted segmentation of soft tissue organs on CT and/or CBCT using neural encoding/decoding based on the CNN architecture, thereby exploiting supervised training 13–21 . The main requirement for this type of approach is anatomical correspondence between the input image (CT or CBCT), and the ground truth reference label 13–21 .…”

Multi-organ segmentation of CT via convolutional neural network: impact of training setting and scanner manufacturer

“…Although CNN-based segmentation is becoming more widely adopted in some radiotherapy workflows (Schreier et al 2020, Cha et al 2021, Chang et al 2021, it is not widely used in settings aiming to assess response to therapy in patients with advanced cancers. In addition, a number of uncertainties and unknowns remain to be sufficiently addressed.…”