Multi-center external validation of an automated method segmenting and differentiating atypical lipomatous tumors from lipomas using radiomics and deep-learning on MRI.

Background: As differentiating between lipomas and atypical lipomatous tumors (ALTs) based on imaging is challenging and requires biopsies, radiomics has been proposed to aid the diagnosis. This study aimed to externally and prospectively validate a radiomics model differentiating between lipomas and ALTs on MRI in three large, multi-center cohorts, and extend it with automatic and minimally interactive segmentation methods to increase clinical feasibility. Methods: Three study cohorts were formed, two for external validation containing data from medical centers in the United States (US) collected from 2008 until 2018 and the United Kingdom (UK) collected from 2011 until 2017, and one for prospective validation consisting of data collected from 2020 until 2021 in the Netherlands. Patient characteristics, MDM2 amplification status, and MRI scans were collected. An automatic segmentation method was developed to segment all tumors on T1-weighted MRI scans of the validation cohorts. Segmentations were subsequently quality scored. In case of insufficient quality, an interactive segmentation method was used. Radiomics performance was evaluated for all cohorts and compared to two radiologists. Findings: The validation cohorts included 150 (54% ALT), 208 (37% ALT), and 86 patients (28% ALT) from the US, UK and NL. Of the 444 cases, 78% were automatically segmented. For 22%, interactive segmentation was necessary due to insufficient quality, with only 3% of all patients requiring manual adjustment. External validation resulted in an AUC of 0.74 (95% CI: 0.66, 0.82) in US data and 0.86 (0.80, 0.92) in UK data. Prospective validation resulted in an AUC of 0.89 (0.83, 0.96). The radiomics model performed similar to the two radiologists (US: 0.79 and 0.76, UK: 0.86 and 0.86, NL: 0.82 and 0.85). Interpretation: The radiomics model extended with automatic and minimally interactive segmentation methods accurately differentiated between lipomas and ALTs in two large, multi-center external cohorts, and in prospective validation, performing similar to expert radiologists, possibly limiting the need for invasive diagnostics. Funding: Hanarth fonds.

Reliability and agreement of manual and automated morphological radiographic hip measurements.

Objective: To determine the reliability and agreement of manual and automated morphological measurements, and agreement in morphological diagnoses. Methods: Thirty pelvic radiographs were randomly selected from the World COACH consortium. Manual and automated measurements of acetabular depth-width ratio (ADR), modified acetabular index (mAI), alpha angle (AA), Wiberg center edge angle (WCEA), lateral center edge angle (LCEA), extrusion index (EI), neck-shaft angle (NSA), and triangular index ratio (TIR) were performed. Bland-Altman plots and intraclass correlation coefficients (ICCs) were used to test reliability. Agreement in diagnosing acetabular dysplasia, pincer and cam morphology by manual and automated measurements was assessed using percentage agreement. Visualizations of all measurements were scored by a radiologist. Results: The Bland-Altman plots showed no to small mean differences between automated and manual measurements for all measurements except for ADR. Intraobserver ICCs of manual measurements ranged from 0.26 (95%-CI 0-0.57) for TIR to 0.95 (95%-CI 0.87-0.98) for LCEA. Interobserver ICCs of manual measurements ranged from 0.43 (95%-CI 0.10-0.68) for AA to 0.95 (95%-CI 0.86-0.98) for LCEA. Intermethod ICCs ranged from 0.46 (95%-CI 0.12-0.70) for AA to 0.89 (95%-CI 0.78-0.94) for LCEA. Radiographic diagnostic agreement ranged from 47% to 100% for the manual observers and 63%-96% for the automated method as assessed by the radiologist. Conclusion: The automated algorithm performed equally well compared to manual measurement by trained observers, attesting to its reliability and efficiency in rapidly computing morphological measurements. This validated method can aid clinical practice and accelerate hip osteoarthritis research.

Presacral myelolipoma, case report and literature review.

INTRODUCTION: Myelolipomas are very rare benign tumours consisting of hematopoietic cells and mature adipose tissues. They are most commonly found in the adrenal glands. However, there have been several reported cases of extra-adrenal myelolipomas, most commonly in the presacral region. Nearly all presacral lesions are small and asymptomatic; thus, most are discovered incidentally on imaging studies. PRESENTATION OF CASE: We report two cases of presacral myelolipomas. The first is a 48-year-old female presenting with atypical back pain, found to have a mass in her presacral region with a size of 3,3 cm. The second case is a 59-year-old female, who presented for evaluation of a hip fracture, found to have a 4,7 cm presacral lesion. Both presacral myelolipomas were discovered incidentally and were confirmed by percutaneous guided fine-needle aspiration biopsy. Both were treated conservatively. DISCUSSION: Accepted indications for the surgical excision of myelolipomas are symptomatic tumour, size >4 cm, metabolically active tumour, and a suspicion of malignancy on an imaging study. However, previous reports have documented that nearly half of the conservatively managed myelolipomas with a mean initial size of 5,1 cm, has increased in size or became symptomatic over a 3-years period. CONCLUSION: We conclude that symptomatic presacral myelolipomas or lesions larger than 4 cm should be en-bloc resected, and we present an intuitive decision-making algorithm.

Differential diagnosis and mutation stratification of desmoid-type fibromatosis on MRI using radiomics.

PURPOSE: Diagnosing desmoid-type fibromatosis (DTF) requires an invasive tissue biopsy with ß-catenin staining and CTNNB1 mutational analysis, and is challenging due to its rarity. The aim of this study was to evaluate radiomics for distinguishing DTF from soft tissue sarcomas (STS), and in DTF, for predicting the CTNNB1 mutation types. METHODS: Patients with histologically confirmed extremity STS (non-DTF) or DTF and at least a pretreatment T1-weighted (T1w) MRI scan were retrospectively included. Tumors were semi-automatically annotated on the T1w scans, from which 411 features were extracted. Prediction models were created using a combination of various machine learning approaches. Evaluation was performed through a 100x random-split cross-validation. The model for DTF vs. non-DTF was compared to classification by two radiologists on a location matched subset. RESULTS: The data included 203 patients (72 DTF, 131 STS). The T1w radiomics model showed a mean AUC of 0.79 on the full dataset. Addition of T2w or T1w post-contrast scans did not improve the performance. On the location matched cohort, the T1w model had a mean AUC of 0.88 while the radiologists had an AUC of 0.80 and 0.88, respectively. For the prediction of the CTNNB1 mutation types (S45 F, T41A and wild-type), the T1w model showed an AUC of 0.61, 0.56, and 0.74. CONCLUSIONS: Our radiomics model was able to distinguish DTF from STS with high accuracy similar to two radiologists, but was not able to predict the CTNNB1 mutation status.

Severity classification of Tenosynovial Giant Cell Tumours on MR imaging.

AIM: Current development of novel systemic agents requires identification and monitoring of extensive Tenosynovial Giant Cell Tumours (TGCT). This study defines TGCT extension on MR imaging to classify severity. METHODS: In part one, six MR parameters were defined by field-experts to assess disease extension on MR images: type of TGCT, articular involvement, cartilage-covered bone invasion, and involvement of muscular/tendinous tissue, ligaments or neurovascular structures. Inter- and intra-rater agreement were calculated using 118 TGCT MR scans. In part two, the previously defined MR parameters were evaluated in 174 consecutive, not previously used, MR-scans. TGCT severity classification was established based on highest to lowest Hazard Ratios (HR) on first recurrence. RESULTS: In part one, all MR parameters showed good inter- and intra-rater agreement (Kappa≥0.66). In part two, cartilage-covered bone invasion and neurovascular involvement were rarely appreciated (<13%) and therefore excluded for additional analyses. Univariate analyses for recurrent disease yielded positive associations for type of TGCT HR12.84(95%CI4.60-35.81), articular involvement HR6.00(95%CI2.14-16.80), muscular/tendinous tissue involvement HR3.50(95%CI1.75-7.01) and ligament-involvement HR4.59(95%CI2.23-9.46). With these, a TGCT severity classification was constructed with four distinct severity-stages. Recurrence free survival at 4 years (log rank p < 0.0001) was 94% in mild localized (n56, 1 recurrence), 88% in severe localized (n31, 3 recurrences), 59% in moderate diffuse (n32, 12 recurrences) and 36% in severe diffuse (n55, 33 recurrences). CONCLUSION: The proposed TGCT severity classification informs physicians and patients on disease extent and risk for recurrence after surgical treatment. Definition of the most severe subgroup attributes to a universal identification of eligible patients for systemic therapy or trials for novel agents.