Dataset Information

Deep Learning Model for Grading Metastatic Epidural Spinal Cord Compression on Staging CT.

ABSTRACT:

Background

Metastatic epidural spinal cord compression (MESCC) is a disastrous complication of advanced malignancy. Deep learning (DL) models for automatic MESCC classification on staging CT were developed to aid earlier diagnosis.

Methods

This retrospective study included 444 CT staging studies from 185 patients with suspected MESCC who underwent MRI spine studies within 60 days of the CT studies. The DL model training/validation dataset consisted of 316/358 (88%) and the test set of 42/358 (12%) CT studies. Training/validation and test datasets were labeled in consensus by two subspecialized radiologists (6 and 11-years-experience) using the MRI studies as the reference standard. Test sets were labeled by the developed DL models and four radiologists (2-7 years of experience) for comparison.

Results

DL models showed almost-perfect interobserver agreement for classification of CT spine images into normal, low, and high-grade MESCC, with kappas ranging from 0.873-0.911 (p < 0.001). The DL models (lowest κ = 0.873, 95% CI 0.858-0.887) also showed superior interobserver agreement compared to two of the four radiologists for three-class classification, including a specialist (κ = 0.820, 95% CI 0.803-0.837) and general radiologist (κ = 0.726, 95% CI 0.706-0.747), both p < 0.001.

Conclusion

DL models for the MESCC classification on a CT showed comparable to superior interobserver agreement to radiologists and could be used to aid earlier diagnosis.

SUBMITTER: Hallinan JTPD

PROVIDER: S-EPMC9264856 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundMetastatic epidural spinal cord compression (MESCC) is a devastating complication of advanced cancer. A deep learning (DL) model for automated MESCC classification on MRI could aid earlier diagnosis and referral.PurposeTo develop a DL model for automated classification of MESCC on MRI.Materials and methodsPatients with known MESCC diagnosed on MRI between September 2007 and September 2017 were eligible. MRI studies with instrumentation, suboptimal image quality, and non-thoracic regions were excluded. Axial T2-weighted images were utilized. The internal dataset split was 82% and 18% for training/validation and test sets, respectively. External testing was also performed. Internal training/validation data were labeled using the Bilsky MESCC classification by a musculoskeletal radiologist (10-year experience) and a neuroradiologist (5-year experience). These labels were used to train a DL model utilizing a prototypical convolutional neural network. Internal and external test sets were labeled by the musculoskeletal radiologist as the reference standard. For assessment of DL model performance and interobserver variability, test sets were labeled independently by the neuroradiologist (5-year experience), a spine surgeon (5-year experience), and a radiation oncologist (11-year experience). Inter-rater agreement (Gwet's kappa) and sensitivity/specificity were calculated.ResultsOverall, 215 MRI spine studies were analyzed [164 patients, mean age = 62 ± 12(SD)] with 177 (82%) for training/validation and 38 (18%) for internal testing. For internal testing, the DL model and specialists all showed almost perfect agreement (kappas = 0.92-0.98, p < 0.001) for dichotomous Bilsky classification (low versus high grade) compared to the reference standard. Similar performance was seen for external testing on a set of 32 MRI spines with the DL model and specialists all showing almost perfect agreement (kappas = 0.94-0.95, p < 0.001) compared to the reference standard.ConclusionA DL model showed comparable agreement to a subspecialist radiologist and clinical specialists for the classification of malignant epidural spinal cord compression and could optimize earlier diagnosis and surgical referral.

Project description:Background:Patient-reported outcomes (PRO) represent an important measure of cancer therapy effect. For patients with metastatic epidural spinal cord compression (MESCC), hybrid therapy using separation surgery and stereotactic radiosurgery preserves neurologic function and provides tumor control. There is currently a paucity of data reporting PRO after such combined modality therapy for MESCC. Delineation of hybrid surgery-radiosurgery therapy effect on PRO validates the hybrid approach as an effective therapy resulting in meaningful symptom relief. Patients and Methods:Brief Pain Inventory (BPI) and MD Anderson Symptom Inventory-Spine Tumor (MDASI-SP), PROs validated in the cancer population, were prospectively collected. Patients with MESCC who underwent separation surgery followed by stereotactic radiosurgery were included. Separation surgery included a posterolateral approach without extensive cytoreductive tumor excision. A median postoperative radiosurgery dose of 2700 cGy was delivered. The change in PRO 3 months after the hybrid therapy represented the primary study outcome. Preoperative and postoperative evaluations were analyzed using the Wilcoxon signed-rank test for matched pairs. Results:One hundred eleven patients were included. Hybrid therapy resulted in a significant reduction in the BPI items "worst" and "right now" pain (P < .0001), and in all BPI constructs (severity, interference with daily activities, and pain experience, P < .001). The MDASI-SP demonstrated reduction in spine-specific pain severity and interference with general activity (P < .001), along with decreased symptom interference (P < .001). Conclusions:Validated PRO instruments showed that in patients with MESCC, hybrid therapy with separation surgery and radiosurgery results in a significant decrease in pain severity and symptom interference. These prospective data confirm the benefit of hybrid therapy for treatment of MESCC and should facilitate referral of patients with MESCC for surgical evaluation.

Project description:IntroductionSpinal metastasis is the most common metastatic skeletal disease in cancer patients. Metastatic epidural spinal cord compression (MESCC), which occurs in 5-14% of cancer patients, is an oncological emergency because it may cause a permanent neurological deficit. Separation surgery followed by stereotactic ablative radiotherapy (SABR), so-called "hybrid therapy," has shown effectiveness in local control of spinal metastasis and has become an integral treatment option for patients with MESCC. Therefore, we performed a meta-analysis and meta-regression analysis to clarify the local progression rate of hybrid therapy and the risk factors for local progression.MethodsWe searched PubMed, EMBASE, Scopus, Cochrane Library, and Web of Science databases from inception to December 2021. Meta-analyses of proportions were used to analyze the data using a random-effects model to calculate the pooled 1-year local progression rate and confidence interval. Subgroup analyses were performed using meta-analyses of odds ratio (OR) for comparisons between groups. We also conducted a meta-regression analysis to identify the factors that caused heterogeneity.ResultsA total of 661 patients from 13 studies (10 retrospective and 3 prospective) were included in the final meta-analysis. The quality of the included studies assessed using the Newcastle - Ottawa scale ranged from poor to fair (range, 4-6). The pooled local progression rate was 10.2 % (95 % confidence interval [CI], 7.8-12.8 %; I2 = 30 %) and 13.7 % (95 % CI, 9.3-18.8 %; I2 = 55 %) at postoperative 1 and 2 years, respectively. The subgroup analysis indicated that patients with a history of prior radiotherapy (OR, 5.14; 95 % CI, 1.71-15.51) and lower radiation dose per fraction (OR, 4.57; 95 % CI, 1.88-11.13) showed significantly higher pooled 1-year local progression rates. In the moderator analysis, the 1-year local progression rate was significantly associated with the proportion of patients with a history of prior radiotherapy (p = 0.036) and those with colorectal cancer as primary origin (p < 0.001).ConclusionsThe pooled 1-year local progression rate of hybrid therapy for MESCC was 10.2%. In subgroup and moderator analyses, a lower radiation dose per fraction, history of prior radiotherapy, and colorectal cancer showed a significant association with the 1-year local progression rate.

Project description:PurposeMetastatic epidural spinal cord compression (MESCC) is a devastating complication of advanced malignancy, which can result in neurologic complications and significant deterioration in overall function and quality of life. Most patients are not candidates for optimal surgical decompression and as a result, receive urgent 3D conformal radiotherapy (3DCRT) to prevent or attempt to reverse neurologic progression. Multiple trials indicate that response and ambulatory rates after 3DCRT are inferior to surgery. The advent of stereotactic body radiation therapy (SBRT) has created a method with which a "radiosurgical decompression" boost may facilitate improve outcomes for MESCC patients.MethodsWe are conducting a pilot study to investigate SBRT boost after urgent 3D CRT for patients with MESCC. The aim of the study is to establish feasibility of this two-phase treatment regimen, and secondarily to characterize post-treatment ambulation status, motor response, pain control, quality of life and survival.DiscussionWe describe the study protocol and present a case report of one patient. A quality assurance review was conducted after the first seven patients, and resultant dose-constraints were revised to improve safety and feasibility of planning through more conservative organ at risk constraints. There have been no severe adverse events (grade 3-5) to date. We have illustrated clinical and dosimetric data of an example case, where a patient regained full strength and ambulatory capacity.ConclusionsOur study aims to determine if SBRT is a feasible option in addition to standard 3DCRT for MESCC patients, with the goal to consider future randomized trials if successful. Having a robust quality assurance process in this study ensures translatability going forward if future trials with multicenter and increased patient representation are to be considered.Trial registrationclinicaltrials.gov; registration no. NCT03529708; https://clinicaltrials.gov/ct2/show/NCT03529708 ; First posted May 18, 2018.