A deep learning-based precision volume calculation approach for kidney and tumor segmentation on computed tomography images

•An lightweight ResNet-41 model is proposed for kidney segmentation in abdomen CT images.•An optimized kidney volume calculation system is proposed to determine the kidney volume precisely.•ResNet-41 and EfficientNet deep learning models are evaluated on the KiTS19 database and achieved a Dice score of 0.9648 for kidney segmentation and 0.7294 for all types of tumor detections, respectively.