Sellar Region Lesion Differential Diagnosis

• Radiomic study of common sellar region lesions differentiation in magnetic resonance imaging based on multi-classification machine learning model
• Rathke's cleft cyst: From history to molecular genetics
• Intrasellar Tuberculosis Presenting as Pituitary Apoplexy: A Case Report
• Challenges in intraoperative differentiation of craniopharyngioma and Rathke cleft cyst on endoscopic visualization
• A rare case of atypical teratoid rhabdoid tumor at the sellar region in an adult: Case report and review of literature
• Neuropathology Entities Involving the Sinonasal Tract
• Sellar Schwannoma Masquerading as Giant Pituitary Adenoma: A Diagnostic Challenge
• Intrasellar chordoma masquerading as a pituitary neuroendocrine tumor: Illustrative case

The sellar region contains a variety of lesions with overlapping clinical and imaging features. A structured differential diagnosis is essential.

1. Pituitary neuroendocrine tumor

• Most common sellar mass in adults.
• Symptoms:
  • Hormonal: hyperprolactinemia, acromegaly, Cushing’s disease.
  • Mass effect: bitemporal hemianopsia, headache.
• MRI: Iso- to hypointense on T1, may enhance heterogeneously.

2. Craniopharyngioma

• Common in children and older adults.
• Symptoms: vision loss, endocrine dysfunction, Diabetes Insipidus.
• MRI: Mixed cystic-solid mass, often with calcifications (especially adamantinomatous type).

3. Rathke's Cleft Cyst

• Often asymptomatic; can cause headache, visual, or pituitary dysfunction.
• MRI: Non-enhancing, well-circumscribed cystic lesion between the anterior and posterior pituitary.

• Arises from tuberculum sellae or planum sphenoidale.
• MRI: Isointense with strong homogeneous enhancement and “dural tail.”

• Common in children; may be associated with NF1.
• MRI: Fusiform enlargement of optic chiasm or hypothalamus.

• More common in adolescents/young adults.
• Symptoms: Diabetes insipidus, visual loss, precocious puberty.
• MRI: Homogeneously enhancing midline mass; often involves pineal and suprasellar regions.

• Mimics pituitary mass.
• Symptoms: Visual deficits, cranial nerve palsy.
• MRI: Flow void; CT angiogram confirms vascular origin.

• Rapid onset of diabetes insipidus and pituitary insufficiency.
• Common primaries: breast, lung.
• MRI: Enhancing lesion, often involving infundibulum or posterior pituitary.

• Autoimmune inflammation; more common in peripartum women.
• Symptoms: Headache, hypopituitarism, DI.
• MRI: Symmetric pituitary enlargement with thickened stalk.

• Sudden hemorrhage or infarction in pituitary adenoma.
• Symptoms: Sudden headache, visual loss, ophthalmoplegia, hypotension.
• MRI: Hemorrhagic mass with peripheral enhancement.

• Arises from clivus, invades sellar region.
• MRI: Lobulated midline mass, high T2 signal, bone destruction.

• May involve pituitary stalk or hypothalamus.
• Symptoms: DI, pituitary dysfunction.
• MRI: Thickened stalk, nodular enhancement.

Hang Qu et al and the neurosurgeons LiangXue Zhou from the West China Hospital, and AiJun Peng from the Affiliated Hospital of Yangzhou University in a Retrospective radiomics-based diagnostic performance study using supervised machine learning studied two hundred and fifty-eight pathologically diagnosed sellar region lesions, including 54 TSMs, 81 CRs, 61 RCCs, and 63 PAs. All patients underwent conventional MR examinations. Feature extraction and data normalization, and balance were performed. Extreme gradient boosting (XGBoost), support vector machine (SVM), and logistic regression (LR) models were trained with the radiomics features. Five-fold cross-validation was used to evaluate model performance.

The XGBoost model showed better performance than the SVM and LR models built from contrast-enhanced T1-weighted MRI features (balanced accuracy 0.83, 0.77, 0.75; AUC 0.956, 0.938, 0.929, respectively). Additionally, these models demonstrated significant differences in sensitivity (P = 0.032) and specificity (P = 0.045). The performance of the XGBoost model was superior to that of the SVM and LR models in differentiating sellar region lesions by using contrast-enhanced T1-weighted MRI features.

The proposed model has the potential to improve the diagnostic accuracy in differentiating sellar region lesions ¹⁾.

• Innovative Use of Radiomics: The application of quantitative radiomic features to differentiate complex sellar pathologies is timely and clinically relevant, especially given the overlapping imaging characteristics of these lesions.

• Multi-class Design: Unlike many prior works focused on binary classification (e.g., tumor vs. no tumor), this study addresses a more challenging and realistic multi-classification problem (TSM vs. CR vs. RCC vs. PA).

• Robust Validation: The use of five-fold cross-validation enhances the reliability of the reported results and guards against overfitting, especially important in retrospective studies.

• Comparative Modeling: The inclusion of three distinct supervised learning methods allows a meaningful comparison, where XGBoost showed superior balanced accuracy (0.83) and AUC (0.956), suggesting strong discriminative capability using only contrast-enhanced T1-weighted MR images.

• Limited Imaging Modalities: The study relies solely on contrast-enhanced T1-weighted MRI. Including additional sequences (e.g., T2, FLAIR, DWI) might have enriched the radiomics dataset and improved performance or generalizability.

• Single-Center Retrospective Design: The study’s retrospective and likely single-institution nature may introduce selection bias and limit external validity. Prospective multicenter validation is needed before clinical deployment.

• Unclear Feature Interpretability: While XGBoost outperformed other models, the interpretability of the selected radiomic features is not deeply discussed. This limits the translational impact for clinicians who need to understand why the model makes certain predictions.

• No External Test Set: Despite cross-validation, the absence of an external validation cohort means model generalizability remains unproven in real-world unseen data.

The study supports the utility of advanced machine learning techniques, especially Extreme gradient boosting, for non-invasive differentiation of sellar region lesions. If externally validated, such models could aid radiologists and neurosurgeons in prioritizing differential diagnoses, potentially reducing diagnostic delays or unnecessary interventions.

This study represents a solid contribution to the growing field of radiomics and machine learning in neuroimaging. The use of multi-classification modeling and comparative performance evaluation is commendable. Future directions should include multi-sequence MRI integration, prospective validation, and improved model explainability.