Magnetic resonance imaging of pilonidal sinus disease: interobserver agreement and practical MRI reporting tips.

OBJECTIVE: To evaluate the interobserver agreement for the features of natal cleft pilonidal sinus disease (PSD) on magnetic resonance imaging (MRI) and propose a standardized checklist for reporting PSD on MRI. MATERIALS AND METHODS: Forty MRI studies of 39 discrete patients with PSD were retrospectively evaluated by five independent radiologists using a standardized checklist. Fleiss' Kappa (k) coefficients of agreement were used to test the agreement between categorical variables. The MRI features of the natal cleft sepsis associated with PSD were classified into four main categories: morphology, branching and extensions, external skin openings, and the relationship of the PSD to the coccyx. A survey was created and disseminated online among general surgeons who treat patients with PSD to assess the relevance of the MRI features proposed in the standardized checklist. RESULTS: The overall agreement regarding the identification of morphology of the natal cleft sepsis was moderate (k = 0.59). Lateral and caudal extensions interobserver agreement was substantial (k = 0.64 and 0.71, respectively). However, the overall agreement regarding the individual parts of anal sphincter involved was moderate (k = 0.47). Substantial interobserver agreement was found in assessing the proximity of the PSD to the coccyx (k = 0.62). CONCLUSION: Preoperative MRI can delineate the extensions and branching of PSD with substantial agreement. MRI is superior in describing the deep extensions of PSD with better reliability than assessing the number and locations of the external openings. Expert consensus agreement is needed to establish the MRI features necessary for optimal reporting of PSD. CLINICAL RELEVANCE STATEMENT: MRI can offer valuable information about the extent of sepsis associated with pilonidal sinus disease, particularly in cases with involvement of critical anatomical structures such as the coccyx and anal triangle. MRI can potentially contribute to more accurate patient stratification and surgical planning. KEY POINTS: • The interobserver agreement for assessing PSD's lateral and caudal extension on MRI is substantial. • MRI can describe deep extensions and branching of PSD with superior reliability than assessing the number and site of external openings. • Reporting the relationship between natal cleft sepsis in PSD and the anal region may influence the surgical approach and postoperative healing.

NS-HGlio: A generalizable and repeatable HGG segmentation and volumetric measurement AI algorithm for the longitudinal MRI assessment to inform RANO in trials and clinics.

Background: Accurate and repeatable measurement of high-grade glioma (HGG) enhancing (Enh.) and T2/FLAIR hyperintensity/edema (Ed.) is required for monitoring treatment response. 3D measurements can be used to inform the modified Response Assessment in Neuro-oncology criteria. We aim to develop an HGG volumetric measurement and visualization AI algorithm that is generalizable and repeatable. Methods: A single 3D-Convoluted Neural Network, NS-HGlio, to analyze HGG on MRIs using 5-fold cross validation was developed using retrospective (557 MRIs), multicentre (38 sites) and multivendor (32 scanners) dataset divided into training (70%), validation (20%), and testing (10%). Six neuroradiologists created the ground truth (GT). Additional Internal validation (IV, three institutions) using 70 MRIs, and External validation (EV, single institution) using 40 MRIs through measuring the Dice Similarity Coefficient (DSC) of Enh., Ed. ,and Enh. + Ed. (WholeLesion/WL) tumor tissue and repeatability testing on 14 subjects from the TCIA MGH-QIN-GBM dataset using volume correlations between timepoints were performed. Results: IV Preoperative median DSC Enh. 0.89 (SD 0.11), Ed. 0.88 (0.28), WL 0.88 (0.11). EV Preoperative median DSC Enh. 0.82 (0.09), Ed. 0.83 (0.11), WL 0.86 (0.06). IV Postoperative median DSC Enh. 0.77 (SD 0.20), Ed 0.78. (SD 0.09), WL 0.78 (SD 0.11). EV Postoperative median DSC Enh. 0.75 (0.21), Ed 0.74 (0.12), WL 0.79 (0.07). Repeatability testing; Intraclass Correlation Coefficient of 0.95 Enh. and 0.92 Ed. Conclusion: NS-HGlio is accurate, repeatable, and generalizable. The output can be used for visualization, documentation, treatment response monitoring, radiation planning, intra-operative targeting, and estimation of Residual Tumor Volume among others.