TY - GEN
T1 - A Deep Learning Model for the Automatic Detection of Malignancy in Effusion Cytology
AU - Aboobacker, Shajahan
AU - Vijayasenan, Deepu
AU - Sumam David, S.
AU - Suresh, Pooja K.
AU - Sreeram, Saraswathy
N1 - Publisher Copyright:
© 2020 IEEE.
Copyright:
Copyright 2020 Elsevier B.V., All rights reserved.
PY - 2020/8/21
Y1 - 2020/8/21
N2 - The excessive accumulation of fluid between layers of pleura covering lungs is known as pleural effusion. Pleural effusion may be due to various infections, inflammations or malignancy. The cytologists visually examine the microscopic slide to detect the malignant cells. The process is time-consuming, and interpretation of reactive cells and cells with ambiguous levels of atypia may differ between pathologists. Considerable research is happening towards the automation of fluid cytology reporting. We propose an integrated approach based on deep learning, where the network learns directly to detect the malignant cells in effusion cytology images. Architecture U-Net is used to learn the malignant and benign cells from the images and to detect the images that contain malignant cells. The model gives a precision of 0.96, recall of 0.96, and specificity of 0.97. The AUC of the ROC curve is 0.97. The model can be used as a screening tool and has a malignant cell detection rate of 0.96 with a low false alarm rate of 0.03.
AB - The excessive accumulation of fluid between layers of pleura covering lungs is known as pleural effusion. Pleural effusion may be due to various infections, inflammations or malignancy. The cytologists visually examine the microscopic slide to detect the malignant cells. The process is time-consuming, and interpretation of reactive cells and cells with ambiguous levels of atypia may differ between pathologists. Considerable research is happening towards the automation of fluid cytology reporting. We propose an integrated approach based on deep learning, where the network learns directly to detect the malignant cells in effusion cytology images. Architecture U-Net is used to learn the malignant and benign cells from the images and to detect the images that contain malignant cells. The model gives a precision of 0.96, recall of 0.96, and specificity of 0.97. The AUC of the ROC curve is 0.97. The model can be used as a screening tool and has a malignant cell detection rate of 0.96 with a low false alarm rate of 0.03.
UR - http://www.scopus.com/inward/record.url?scp=85097924032&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85097924032&partnerID=8YFLogxK
U2 - 10.1109/ICSPCC50002.2020.9259490
DO - 10.1109/ICSPCC50002.2020.9259490
M3 - Conference contribution
AN - SCOPUS:85097924032
T3 - ICSPCC 2020 - IEEE International Conference on Signal Processing, Communications and Computing, Proceedings
BT - ICSPCC 2020 - IEEE International Conference on Signal Processing, Communications and Computing, Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2020 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2020
Y2 - 21 August 2020 through 23 August 2020
ER -