CNN-based tumor progression prediction after thermal ablation with CT imaging

M. Taghavi; M. Maas; F.C.R. Staal; R.G.H. Beets-Tan; S. Benson

doi:10.1117/12.2611516

CNN-based tumor progression prediction after thermal ablation with CT imaging

M. Taghavi, M. Maas, F.C.R. Staal, R.G.H. Beets-Tan, S. Benson^*

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceeding › Academic › peer-review

Abstract

Local tumor progression (LTP) after ablation treatment in colorectal liver metastases (CRLM) has a detrimental impact on the outcome for patients with advanced colorectal cancer. The ability to predict or even identify LTP at the earliest opportunity is critical to personalise follow-up and subsequent treatment. We present a study of 79 patients (120 lesions) with CRLM who underwent thermal ablation treatment, in which a multi-channel model that identifies patients with LTP from baseline and restaging computed tomography (CT) scans. The study made use of transfer learning strategies in association with a 3-fold cross validation. The area under the receiveroperating characteristic curve was found to be 0.72 (95% confidence interval [CI]: 0.64-0.79), demonstrating that the model was able to generate prognostic features from the CT images.

Original language	English
Title of host publication	MEDICAL IMAGING 2022: COMPUTER-AIDED DIAGNOSIS
Editors	K Drukker, KM Iftekharuddin
Publisher	SPIE-INT SOC OPTICAL ENGINEERING
Number of pages	6
Volume	12033
ISBN (Print)	9781510649415
DOIs	https://doi.org/10.1117/12.2611516
Publication status	Published - 2022
Event	Conference on Medical Imaging - Computer-Aided Diagnosis - San Diego, United States Duration: 20 Feb 2022 → 27 Mar 2022

Publication series

Series	Proceedings of SPIE
Number	1203335
Volume	12033
ISSN	0277-786X

Conference

Conference	Conference on Medical Imaging - Computer-Aided Diagnosis
Country/Territory	United States
City	San Diego
Period	20/02/22 → 27/03/22

Keywords

Ablation
deep-learning
CT

Access to Document

10.1117/12.2611516

Cite this

@inproceedings{d185687c61f343ae97d394589742662d,

title = "CNN-based tumor progression prediction after thermal ablation with CT imaging",

abstract = "Local tumor progression (LTP) after ablation treatment in colorectal liver metastases (CRLM) has a detrimental impact on the outcome for patients with advanced colorectal cancer. The ability to predict or even identify LTP at the earliest opportunity is critical to personalise follow-up and subsequent treatment. We present a study of 79 patients (120 lesions) with CRLM who underwent thermal ablation treatment, in which a multi-channel model that identifies patients with LTP from baseline and restaging computed tomography (CT) scans. The study made use of transfer learning strategies in association with a 3-fold cross validation. The area under the receiveroperating characteristic curve was found to be 0.72 (95% confidence interval [CI]: 0.64-0.79), demonstrating that the model was able to generate prognostic features from the CT images.",

keywords = "Ablation, deep-learning, CT",

author = "M. Taghavi and M. Maas and F.C.R. Staal and R.G.H. Beets-Tan and S. Benson",

note = "Publisher Copyright: {\textcopyright} 2022 SPIE.; Conference on Medical Imaging - Computer-Aided Diagnosis ; Conference date: 20-02-2022 Through 27-03-2022",

year = "2022",

doi = "10.1117/12.2611516",

language = "English",

isbn = "9781510649415",

volume = "12033",

series = "Proceedings of SPIE",

publisher = "SPIE-INT SOC OPTICAL ENGINEERING",

number = "1203335",

editor = "K Drukker and KM Iftekharuddin",

booktitle = "MEDICAL IMAGING 2022: COMPUTER-AIDED DIAGNOSIS",

}

Taghavi, M, Maas, M, Staal, FCR, Beets-Tan, RGH & Benson, S 2022, CNN-based tumor progression prediction after thermal ablation with CT imaging. in K Drukker & KM Iftekharuddin (eds), MEDICAL IMAGING 2022: COMPUTER-AIDED DIAGNOSIS. vol. 12033, 120335, SPIE-INT SOC OPTICAL ENGINEERING, Proceedings of SPIE, no. 1203335, vol. 12033, Conference on Medical Imaging - Computer-Aided Diagnosis, San Diego, California, United States, 20/02/22. https://doi.org/10.1117/12.2611516

CNN-based tumor progression prediction after thermal ablation with CT imaging. / Taghavi, M.; Maas, M.; Staal, F.C.R. et al.
MEDICAL IMAGING 2022: COMPUTER-AIDED DIAGNOSIS. ed. / K Drukker; KM Iftekharuddin. Vol. 12033 SPIE-INT SOC OPTICAL ENGINEERING, 2022. 120335 (Proceedings of SPIE; No. 1203335, Vol. 12033).

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceeding › Academic › peer-review

TY - GEN

T1 - CNN-based tumor progression prediction after thermal ablation with CT imaging

AU - Taghavi, M.

AU - Maas, M.

AU - Staal, F.C.R.

AU - Beets-Tan, R.G.H.

AU - Benson, S.

PY - 2022

Y1 - 2022

N2 - Local tumor progression (LTP) after ablation treatment in colorectal liver metastases (CRLM) has a detrimental impact on the outcome for patients with advanced colorectal cancer. The ability to predict or even identify LTP at the earliest opportunity is critical to personalise follow-up and subsequent treatment. We present a study of 79 patients (120 lesions) with CRLM who underwent thermal ablation treatment, in which a multi-channel model that identifies patients with LTP from baseline and restaging computed tomography (CT) scans. The study made use of transfer learning strategies in association with a 3-fold cross validation. The area under the receiveroperating characteristic curve was found to be 0.72 (95% confidence interval [CI]: 0.64-0.79), demonstrating that the model was able to generate prognostic features from the CT images.

AB - Local tumor progression (LTP) after ablation treatment in colorectal liver metastases (CRLM) has a detrimental impact on the outcome for patients with advanced colorectal cancer. The ability to predict or even identify LTP at the earliest opportunity is critical to personalise follow-up and subsequent treatment. We present a study of 79 patients (120 lesions) with CRLM who underwent thermal ablation treatment, in which a multi-channel model that identifies patients with LTP from baseline and restaging computed tomography (CT) scans. The study made use of transfer learning strategies in association with a 3-fold cross validation. The area under the receiveroperating characteristic curve was found to be 0.72 (95% confidence interval [CI]: 0.64-0.79), demonstrating that the model was able to generate prognostic features from the CT images.

KW - Ablation

KW - deep-learning

KW - CT

U2 - 10.1117/12.2611516

DO - 10.1117/12.2611516

M3 - Conference article in proceeding

SN - 9781510649415

VL - 12033

T3 - Proceedings of SPIE

BT - MEDICAL IMAGING 2022: COMPUTER-AIDED DIAGNOSIS

A2 - Drukker, K

A2 - Iftekharuddin, KM

PB - SPIE-INT SOC OPTICAL ENGINEERING

T2 - Conference on Medical Imaging - Computer-Aided Diagnosis

Y2 - 20 February 2022 through 27 March 2022

ER -