Radiomics for Preoperative Jaw Cyst Differentiation

Official title

Preoperative Differentiation of Jaw Cystic Lesions Based on Radiomics From Computed Tomography Images: A Multicenter, Prospective Machine Learning Study

Overview

This study focuses on jawbone cystic lesions, including odontogenic tumors like ameloblastoma and various cysts. Treatment approaches differ; ameloblastomas often require surgical excision due to potential recurrence and metastasis, while cystic lesions may be treated with curettage and marsupialization. Accurate preoperative diagnosis is crucial for optimal treatment outcomes, as inappropriate choices can lead to delayed treatment or overtreatment, affecting patient quality of life. Currently, there is no standard protocol for differential diagnosis, highlighting the need for a predictive diagnostic model. The study will be a multicenter, prospective machine learning research involving 300 patients across 12 centers. It aims to enhance a previously developed predictive model that integrates machine learning with CT radiomics. Patients will be grouped based on imaging modalities, with data processed uniformly to improve diagnostic predictions. Inclusion criteria ensure comprehensive preoperative data, while exclusion criteria eliminate incomplete or previously treated cases. The study seeks to optimize the model's performance and provide valuable clinical insights.

Detailed description

Jawbone cystic lesions include odontogenic tumors and non-tumorous cystic lesions occurring within the jawbone, with ameloblastoma being the most common among the former, and odontogenic and non-odontogenic cysts among the latter. Currently, the treatment focus varies for different types of jawbone cystic lesions. Ameloblastomas, which may recur and metastasize, are primarily treated with surgical excision, while cystic lesions are more broadly treated with procedures like curettage and marsupialization. Therefore, accurate preoperative differential diagnosis of various jawbone lesions and the subsequent selection of appropriate treatment plans are crucial for achieving optimal patient outcomes. Inappropriate treatment choices may delay the condition or lead to overtreatment, affecting the patient's quality of life. At present, there is still a lack of an objective and accurate standard and differential diagnosis protocol for the treatment of jawbone cystic lesions, making the establishment of an objective and scientific preoperative diagnostic prediction model of significant clinical importance. In previous research, investigators successfully developed an effective predictive diagnostic model by integrating machine learning techniques with computed tomography (CT) radiomics, achieving a maximum AUC ( area under curve ) value \>0.8, indicating good predictive performance and clinical reference value. In the current study, investigators aim to conduct a multicenter, prospective machine learning study to further enhance the model's predictive diagnostic performance and assist clinical diagnosis and treatment.

This study is designed as a multicenter, prospective machine learning study, involving 300 patients with jawbone cystic lesions across 12 centers, as detailed in the list of collaborating institutions. Based on research group's previous investigation of the actual diagnostic and treatment conditions at each research center, investigators plan to utilize different types of imaging data for grouping according to the imaging examinations conducted, and to standardize the processing of imaging data from different units and types for subsequent work. Sun Yat-sen Memorial Hospital of Sun Yat-sen University will serve as the main center, with other institutions as sub-centers. The specific grouping is as follows: the spiral CT group includes six general hospitals; the cone beam CT (CBCT) group includes one general hospital and five specialized dental hospitals.

During the study, after enrolling participants who meet the inclusion criteria, investigators will collect maxillofacial CT imaging data, import them into the software (LIFEx version 6.30), and delineate the region of interest (ROI). Radiomic features within the ROI will be extracted using Pyradiomics software, selected, and used for preoperative diagnostic predictions with the existing model. After surgical treatment, the pathological results of the lesions will be tracked and recorded. If conditions permit, the model's predictive performance can be further optimized in phases during the study, or methodological adjustments and reconstructions of the predictive model can be attempted using all available data to achieve a more ideal preoperative diagnostic prediction.

Interventions

• Diagnostic test different types of computed tomography (CT) scans
  For enrolled patients with jaw cystic lesions, depending on their group, either a maxillofacial spiral CT scan or a cone beam CT scan is performed before surgical treatment.

Primary outcome measures

• Statistical Analysis Metrics for Machine Learning Model Predictions [Time frame: 2025.06-2026.01]

Eligibility criteria

Inclusion criteria

• first-time visitors who have not received other treatment interventions;
• participants with complete preoperative medical records, imaging examinations, and imaging data;
• participants who have undergone maxillofacial CT examination preoperatively, with complete CT data, no artifact interference in the lesion area, and a lesion size with the longest diameter of at least 2 cm;
• participants who can tolerate surgical treatment, with specimens sent for routine pathological examination after surgery.

Exclusion criteria

• incomplete medical records, such as missing specialized examination and treatment operation records;
• patients who received therapeutic operations at other hospitals at first diagnosis, not fully cured or with recurrence;
• patients who did not undergo CT examination preoperatively, with incomplete CT data, severe artifact interference in the lesion area, or lesion size not meeting requirements;
• lesions not submitted as specimens for examination during surgery, with no routine pathological examination;
• unclear postoperative pathology reports, or pathological diagnoses other than odontogenic cysts or non-solid ameloblastoma.

Criteria are shown verbatim from the registry (in English). Final eligibility is always assessed by the study center.

Healthy volunteers: No

Study design

Observational model

Cohort

Study locations

China · 1 center

• Sun Yat-sen Memorial Hospital,Sun Yat-sen University — Guangzhou

Publications

• Baumhoer D, Holler S. [Cystic lesions of the jaws]. Pathologe. 2018 Feb;39(1):71-84. doi: 10.1007/s00292-017-0402-x. German. PMID 29322252
• Effiom OA, Ogundana OM, Akinshipo AO, Akintoye SO. Ameloblastoma: current etiopathological concepts and management. Oral Dis. 2018 Apr;24(3):307-316. doi: 10.1111/odi.12646. Epub 2017 Mar 9. PMID 28142213
• Al-Moraissi EA, Kaur A, Gomez RS, Ellis E 3rd. Effectiveness of different treatments for odontogenic keratocyst: a network meta-analysis. Int J Oral Maxillofac Surg. 2023 Jan;52(1):32-43. doi: 10.1016/j.ijom.2022.09.004. Epub 2022 Sep 21. PMID 36150944
• Yoshiura K, Higuchi Y, Araki K, Shinohara M, Kawazu T, Yuasa K, Tabata O, Kanda S. Morphologic analysis of odontogenic cysts with computed tomography. Oral Surg Oral Med Oral Pathol Oral Radiol Endod. 1997 Jun;83(6):712-8. doi: 10.1016/s1079-2104(97)90325-5. PMID 9195629
• Neagu D, Escuder-de la Torre O, Vazquez-Mahia I, Carral-Roura N, Rubin-Roger G, Penedo-Vazquez A, Luaces-Rey R, Lopez-Cedrun JL. Surgical management of ameloblastoma. Review of literature. J Clin Exp Dent. 2019 Jan 1;11(1):e70-e75. doi: 10.4317/jced.55452. eCollection 2019 Jan. PMID 30697397
• Kreppel M, Zoller J. Ameloblastoma-Clinical, radiological, and therapeutic findings. Oral Dis. 2018 Mar;24(1-2):63-66. doi: 10.1111/odi.12702. PMID 29480593
• Yip SS, Aerts HJ. Applications and limitations of radiomics. Phys Med Biol. 2016 Jul 7;61(13):R150-66. doi: 10.1088/0031-9155/61/13/R150. Epub 2016 Jun 8. PMID 27269645
• Mayerhoefer ME, Materka A, Langs G, Haggstrom I, Szczypinski P, Gibbs P, Cook G. Introduction to Radiomics. J Nucl Med. 2020 Apr;61(4):488-495. doi: 10.2967/jnumed.118.222893. Epub 2020 Feb 14. PMID 32060219

Identifiers

NCT: NCT06579768 · SYSKY-2024-432-02

Primary sources (government registries)

• ClinicalTrials.gov (US NIH)

View this study on ClinicalTrials.gov ↗