RESUMEN
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.
RESUMEN
BACKGROUND: Well differentiated liposarcoma (WDLPS) can be difficult to distinguish from lipoma. Currently, this distinction is made by testing for MDM2 amplification, which requires a biopsy. The aim of this study was to develop a noninvasive method to predict MDM2 amplification status using radiomics features derived from MRI. METHODS: Patients with an MDM2-negative lipoma or MDM2-positive WDLPS and a pretreatment T1-weighted MRI scan who were referred to Erasmus MC between 2009 and 2018 were included. When available, other MRI sequences were included in the radiomics analysis. Features describing intensity, shape and texture were extracted from the tumour region. Classification was performed using various machine learning approaches. Evaluation was performed through a 100 times random-split cross-validation. The performance of the models was compared with the performance of three expert radiologists. RESULTS: The data set included 116 tumours (58 patients with lipoma, 58 with WDLPS) and originated from 41 different MRI scanners, resulting in wide heterogeneity in imaging hardware and acquisition protocols. The radiomics model based on T1 imaging features alone resulted in a mean area under the curve (AUC) of 0·83, sensitivity of 0·68 and specificity of 0·84. Adding the T2-weighted imaging features in an explorative analysis improved the model to a mean AUC of 0·89, sensitivity of 0·74 and specificity of 0·88. The three radiologists scored an AUC of 0·74 and 0·72 and 0·61 respectively; a sensitivity of 0·74, 0·91 and 0·64; and a specificity of 0·55, 0·36 and 0·59. CONCLUSION: Radiomics is a promising, non-invasive method for differentiating between WDLPS and lipoma, outperforming the scores of the radiologists. Further optimization and validation is needed before introduction into clinical practice.
ANTECEDENTES: Es difícil distinguir los liposarcomas bien diferenciados (well-differentiated liposarcomas, WDLPS) de los lipomas. En la actualidad, esta distinción se realiza mediante la prueba de amplificación del gen MDM2 por biopsia. El objetivo de este estudio fue predecir de forma no invasiva el estado de amplificación del gen MDM2 para diferenciar los lipomas de los WDLPS utilizando características radiómicas a partir de la resonancia magnética. MÉTODOS: Se incluyeron los pacientes remitidos al instituto Erasmus MC entre 2009-2018 por un lipoma MDM2 negativo o WDLPS MDM2 positivo y las resonancias magnéticas potenciadas en T1 correspondientes antes del tratamiento. Cuando estaban disponibles, se incluyeron otras secuencias de MRI en el análisis radiómico. Se describieron la intensidad, forma y textura de la región tumoral. Para la clasificación se utilizaron varios modelos de aprendizaje automático (machine learning). La evaluación se realizó mediante una validación cruzada aleatoria 100x. Se comparó el rendimiento de los modelos con la clasificación realizada por tres radiólogos expertos. RESULTADOS: Se incluyeron 116 pacientes (58 lipomas, 58 WDLPS) y 41 aparatos de MRI, con una gran heterogeneidad en las técnicas y protocolos para la adquisición de imágenes. El modelo radiómico basado únicamente en las características de las imagen en T1 dio como resultado una AUC media de 0,83, con una sensibilidad de 0,68 y una especificidad de 0,84. Un análisis adicional incorporando las imágenes ponderadas en T2 mejoró el modelo con una AUC media de 0,89, una sensibilidad de 0,74 y una especificidad de 0,88. Los tres radiólogos obtuvieron una AUC de 0,74/0,72/0,61, una sensibilidad de 0,74/0,91/0,64 y una especificidad de 0,55/0,36/0,59, respectivamente. CONCLUSIÓN: La radiómica es un método prometedor y no invasivo para diferenciar entre WDLPS y lipomas, superando la valoración de los radiólogos. Sin embargo, se necesita la optimización y validación de esta técnica antes de su introducción en la práctica clínica diaria.
