A deep learning-based precision and automatic kidney segmentation system using efficient feature pyramid networks in computed tomography images

Hsiao, Chiu-Han; Lin, Ping-Cherng; Chung, Li-An; Lin, Frank Yeong-Sung; Yang, Feng-Jung; Yang, Shan-Yi; Wu, Cho‐Kai; Huang, Yennun; Sun, Tzu-Lung

doi:10.1016/j.cmpb.2022.106854

Cited by 21 publications

(16 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is especially important for MRI where minor improvements in the imaging technology are periodically implemented and need to be incorporated into the model. Unlike prior reports attempting to fully automate organ volume measurements into ADPKD with accuracy approaching manual contouring [22][23][24][25][26][27][28][29][30][31][32][33][34][35], this research demonstrates superior measurement reproducibility over manual contouring that can readily adapt to technological advances. Since the deep learning server is within the PACS firewall, technologists can rapidly transfer images to the server for running the inference.…”

Section: Discussionmentioning

confidence: 93%

“…This eliminates the need to manually draw every contour of the cystic kidneys, [ 22 ] thereby increasing the efficiency of accurate TKV measurement. Table 1 summarizes the existing literature for deep learning-based organ volume measurements in ADPKD using CT [ 23 , 24 , 25 , 26 , 27 ], ultrasound [ 28 ] and MRI [ 22 , 29 , 30 , 31 , 32 , 33 , 34 , 35 ]. MRI has the advantage over CT of not requiring ionizing radiation, which is particularly important, for these organ volume measurements are repeated many times over the patient’s lifetime, and MRI has higher resolution compared to ultrasound.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning Automation of Kidney, Liver, and Spleen Segmentation for Organ Volume Measurements in Autosomal Dominant Polycystic Kidney Disease

et al. 2022

View full text Add to dashboard Cite

Organ volume measurements are a key metric for managing ADPKD (the most common inherited renal disease). However, measuring organ volumes is tedious and involves manually contouring organ outlines on multiple cross-sectional MRI or CT images. The automation of kidney contouring using deep learning has been proposed, as it has small errors compared to manual contouring. Here, a deployed open-source deep learning ADPKD kidney segmentation pipeline is extended to also measure liver and spleen volumes, which are also important. This 2D U-net deep learning approach was developed with radiologist labeled T2-weighted images from 215 ADPKD subjects (70% training = 151, 30% validation = 64). Additional ADPKD subjects were utilized for prospective (n = 30) and external (n = 30) validations for a total of 275 subjects. Image cropping previously optimized for kidneys was included in training but removed for the validation and inference to accommodate the liver which is closer to the image border. An effective algorithm was developed to adjudicate overlap voxels that are labeled as more than one organ. Left kidney, right kidney, liver and spleen labels had average errors of 3%, 7%, 3%, and 1%, respectively, on external validation and 5%, 6%, 5%, and 1% on prospective validation. Dice scores also showed that the deep learning model was close to the radiologist contouring, measuring 0.98, 0.96, 0.97 and 0.96 on external validation and 0.96, 0.96, 0.96 and 0.95 on prospective validation for left kidney, right kidney, liver and spleen, respectively. The time required for manual correction of deep learning segmentation errors was only 19:17 min compared to 33:04 min for manual segmentations, a 42% time saving (p = 0.004). Standard deviation of model assisted segmentations was reduced to 7, 5, 11, 5 mL for right kidney, left kidney, liver and spleen respectively from 14, 10, 55 and 14 mL for manual segmentations. Thus, deep learning reduces the radiologist time required to perform multiorgan segmentations in ADPKD and reduces measurement variability.

show abstract

Section: Discussionmentioning

confidence: 93%

Section: Introductionmentioning

confidence: 99%

Deep Learning Automation of Kidney, Liver, and Spleen Segmentation for Organ Volume Measurements in Autosomal Dominant Polycystic Kidney Disease

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Initially, Yolov7 was used for image preprocessing to target only the kidney. After this, they used deep CNNs to recognize a kidney stone in the applied input image 30 . DL is a subset of ML that is motivated by the arrangement and operation of intelligence 31 .…”

Section: Related Workmentioning

confidence: 99%

“…After this, they used deep CNNs to recognize a kidney stone in the applied input image. 30 DL is a subset of ML that is motivated by the arrangement and operation of intelligence. 31 DL algorithms have been efficaciously applied to computer vision, and it has become a common practice to employ these algorithms to analyze medical pictures.…”

Section: Related Workmentioning

confidence: 99%

End‐to‐end light‐weighted deep‐learning model for abnormality classification in kidney CT images

Karthikeyan,

Kishore,

Sajin

2024

Int J Imaging Syst Tech

View full text Add to dashboard Cite

Kidney disease is a major health problem that affects millions of people around the world. Human kidney problems can be diagnosed with the help of computed tomography (CT), which creates cross‐sectional slices of the organ. A deep end‐to‐end convolutional neural network (CNN) model is proposed to help radiologists detect and characterize kidney problems in CT scans of patients. This has the potential to improve diagnostic accuracy and efficiency, which in turn benefits patient care. Our strategy involves teaching a suggested deep end‐to‐end CNN to distinguish between healthy and diseased kidneys. The recommended CNN is trained using a standard CT image library that has been annotated to show kidney stones, cysts, and tumors. The model can then be used to detect kidney abnormalities in fresh CT scans, which may enhance the effectiveness and speed with which diagnoses are made. A total of 1812 pictures were used, each one a unique cross‐sectional CT scan of the patient. Our model has a detection rate of 99.17% in CT scan validation tests. We employed a different dataset with a total of 5077 normal samples, 3709 cyst samples, 1377 stone samples, and 2283 tumor samples. In tests, our model proved to be 99.68% accurate. The suggested framework has been validated by applying it to the clinical dataset, resulting in 99% accuracy in predictions. As low‐cost and portable CT scanners become more commonplace, the described concept may soon be employed outside of a hospital environment, at the point of treatment, or even in the patient's own home.

show abstract

“…IOU is the result of the division of the “area of overlap” by the “area of union”. 17 Another way to quantify the accuracy of object detection is the Dice coefficient (or Sørensen–Dice coefficient), which is calculated by dividing the area of union by the total number of pixels in the individual areas. 18 …”

Section: Current Statusmentioning

confidence: 99%

Role of artificial intelligence in diagnosing Barrett’s esophagus-related neoplasia

2023

View full text Add to dashboard Cite

Barrett’s esophagus is associated with an increased risk of adenocarcinoma. Thorough screening during endoscopic surveillance is crucial to improve patient prognosis. Detecting and characterizing dysplastic or neoplastic Barrett’s esophagus during routine endoscopy are challenging, even for expert endoscopists. Artificial intelligence-based clinical decision support systems have been developed to provide additional assistance to physicians performing diagnostic and therapeutic gastrointestinal endoscopy. In this article, we review the current role of artificial intelligence in the management of Barrett’s esophagus and elaborate on potential artificial intelligence in the future.

show abstract

A deep learning-based precision and automatic kidney segmentation system using efficient feature pyramid networks in computed tomography images

Cited by 21 publications

References 13 publications

Deep Learning Automation of Kidney, Liver, and Spleen Segmentation for Organ Volume Measurements in Autosomal Dominant Polycystic Kidney Disease

Deep Learning Automation of Kidney, Liver, and Spleen Segmentation for Organ Volume Measurements in Autosomal Dominant Polycystic Kidney Disease

End‐to‐end light‐weighted deep‐learning model for abnormality classification in kidney CT images

Role of artificial intelligence in diagnosing Barrett’s esophagus-related neoplasia

Contact Info

Product

Resources

About