Deep learning-based quality-controlled spleen assessment from ultrasound images

TY - JOUR

T1 - Deep learning-based quality-controlled spleen assessment from ultrasound images

AU - Yuan, Zhen

AU - Puyol-Antón, Esther

AU - Jogeesvaran, Haran

AU - Smith, Nicola

AU - Inusa, Baba

AU - King, Andrew P.

N1 - Funding Information: This work was supported by the Wellcome/EPSRC Centre for Medical Engineering [WT 203148/Z/16/Z]. The support provided by China Scholarship Council during PhD programme of Zhen Yuan in King’s College London is acknowledged. Publisher Copyright: © 2022 Elsevier Ltd

PY - 2022/7

Y1 - 2022/7

N2 - Objective: Splenomegaly (abnormal splenic enlargement) is a potentially life-threatening condition that occurs in a range of clinical scenarios, including in patients suffering from Sickle cell disease (SCD). Therefore, spleen size assessments from ultrasound imaging are commonly performed in SCD clinics, and typically involve measuring the length of the spleen. However, the current workflow is prone to intra- and inter-observer variability and is dependent on the experience of the sonographer. Our objective was to automate the spleen length measurement process. Methods: Two deep learning-based approaches were investigated to achieve automated spleen length measurement from ultrasound images. One is a segmentation-based approach, where we trained a modified U-Net to obtain a spleen segmentation and then applied post-processing to measure the spleen length from the segmentation. The second approach is based on direct regression of spleen length. We also incorporated a quality control (QC) model to help less experienced sonographers ensure the quality of ultrasound images before measurement. Results: Our best model (segmentation-based approach) reached a mean percentage length error (MPLE) of 4.58% on good quality images, which is within the range of human expert inter-observer variability (5.78%). After including bad quality images, the incorporation of the QC step resulted in a significant reduction in MPLE (from 5.76% to 4.88%). Conclusion: Automated, quality-controlled spleen length measurement from ultrasound has been achieved with human-level accuracy. Significance: This proposed framework has the potential to assist in making robust and accurate assessments of the spleen, especially in settings where there is a lack of experienced sonographers.

AB - Objective: Splenomegaly (abnormal splenic enlargement) is a potentially life-threatening condition that occurs in a range of clinical scenarios, including in patients suffering from Sickle cell disease (SCD). Therefore, spleen size assessments from ultrasound imaging are commonly performed in SCD clinics, and typically involve measuring the length of the spleen. However, the current workflow is prone to intra- and inter-observer variability and is dependent on the experience of the sonographer. Our objective was to automate the spleen length measurement process. Methods: Two deep learning-based approaches were investigated to achieve automated spleen length measurement from ultrasound images. One is a segmentation-based approach, where we trained a modified U-Net to obtain a spleen segmentation and then applied post-processing to measure the spleen length from the segmentation. The second approach is based on direct regression of spleen length. We also incorporated a quality control (QC) model to help less experienced sonographers ensure the quality of ultrasound images before measurement. Results: Our best model (segmentation-based approach) reached a mean percentage length error (MPLE) of 4.58% on good quality images, which is within the range of human expert inter-observer variability (5.78%). After including bad quality images, the incorporation of the QC step resulted in a significant reduction in MPLE (from 5.76% to 4.88%). Conclusion: Automated, quality-controlled spleen length measurement from ultrasound has been achieved with human-level accuracy. Significance: This proposed framework has the potential to assist in making robust and accurate assessments of the spleen, especially in settings where there is a lack of experienced sonographers.

KW - Deep learning

KW - Segmentation

KW - Sickle cell disease

KW - Spleen ultrasound image

KW - Splenomegaly

UR - http://www.scopus.com/inward/record.url?scp=85129538333&partnerID=8YFLogxK

U2 - 10.1016/j.bspc.2022.103724

DO - 10.1016/j.bspc.2022.103724

M3 - Article

AN - SCOPUS:85129538333

SN - 1746-8094

VL - 76

JO - Biomedical Signal Processing and Control

JF - Biomedical Signal Processing and Control

M1 - 103724

ER -