Deep learning radiomics-based preoperative prediction of recurrence in chronic rhinosinusitis

Shaojuan He; Wei Chen; Xuehai Wang; Xinyu Xie; Fangying Liu; Xinyi Ma; Xuezhong Li; Anning Li; Xin Feng

doi:10.1016/j.isci.2023.106527

Deep learning radiomics-based preoperative prediction of recurrence in chronic rhinosinusitis

iScience. 2023 Mar 30;26(4):106527. doi: 10.1016/j.isci.2023.106527. eCollection 2023 Apr 21.

Authors

Shaojuan He^{1

2}, Wei Chen³, Xuehai Wang⁴, Xinyu Xie¹, Fangying Liu¹, Xinyi Ma¹, Xuezhong Li¹, Anning Li², Xin Feng¹

Affiliations

¹ Department of Otorhinolaryngology, Qilu Hospital of Shandong University, NHC Key Laboratory of Otorhinolaryngology (Shandong University), Jinan, China.
² Department of Radiology, Qilu Hospital of Shandong University, Jinan, China.
³ School and Hospital of Stomatology, Cheeloo College of Medicine, Shandong University, Jinan, China.
⁴ Department of Otorhinolaryngology, Weihai Municipal Hospital, Weihai, China.

Abstract

Chronic rhinosinusitis (CRS) is characterized by poor prognosis and propensity for recurrence even after surgery. Identification of those CRS patients with high risk of relapse preoperatively will contribute to personalized treatment recommendations. In this paper, we proposed a multi-task deep learning network for sinus segmentation and CRS recurrence prediction simultaneously to develop and validate a deep learning radiomics-based nomogram for preoperatively predicting recurrence in CRS patients who needed surgical treatment. 265 paranasal sinuses computed tomography (CT) images of CRS from two independent medical centers were analyzed to build and test models. The sinus segmentation model achieved good segmentation results. Furthermore, the nomogram combining a deep learning signature and clinical factors also showed excellent recurrence prediction ability for CRS. Our study not only facilitates a technique for sinus segmentation but also provides a noninvasive method for preoperatively predicting recurrence in patients with CRS.

Keywords: Health sciences; Machine learning; Medicine.