An appropriate classification system with which to individualize Craniopharyngioma treatment is absent.
The 2022 World Health Organization classification of tumors of the pituitary gland distinguishes the anterior lobe of the pituitary gland (Adenohypophysis) from the posterior lobe (neurohypophysis) and hypothalamic tumors.
Anterior lobe tumors include (i) well-differentiated adenohypophyseal tumors that are now classified as pituitary neuroendocrine tumors (PitNETs; formerly known as pituitary neuroendocrine tumors), (ii) pituitary blastoma, and (iii) the two types of craniopharyngioma.
Most craniopharyngiomas can be classified as either “prechiasmatic” or “retrochiasmatic” according to their growth patterns.
The terms “suprasellar craniopharyngioma” and “supradiaphragmatic craniopharyngioma” often refer to the same type of tumor, as both describe a craniopharyngioma located above the diaphragma sellae (the diaphragm of the sella turcica).
A QST classification system based on tumor origin was used to classify tumors into 3 types as follows: infrasellar/subdiaphragmatic CPs (Q-CPs), subarachnoidal CPs (S-CPs), and pars tuberalis CPs (T-CPs). Within each tumor type, patients were further arranged into two groups: those treated via the TCA and those treated via the EEA. Patient and tumor characteristics, surgical outcomes, and postoperative complications were obtained. All variables were statistically analyzed between surgical groups for each tumor type 1)
The QST classification has been developed according to the origin of craniopharyngiomas; however, accurate preoperative automatic segmentation and the QST classification remain challenging. This study aimed to establish a method to automatically segment multiple structures in MRIs, detect craniopharyngiomas, and design a deep learning model and a diagnostic scale for automatic QST preoperative classification.
Methods: We trained a deep learning network based on sagittal MRI to automatically segment six tissues, including tumors, pituitary gland, sphenoid sinus, brain, superior saddle cistern, and lateral ventricle. A deep learning model with multiple inputs was designed to perform preoperative QST classification. A scale was constructed by screening the images.
Results: The results were calculated based on the fivefold cross-validation method. A total of 133 patients with craniopharyngioma were included, of whom 29 (21.8%) were diagnosed with type Q, 22 (16.5%) with type S and 82 (61.7%) with type T. The automatic segmentation model achieved a tumor segmentation Dice coefficient of 0.951 and a mean tissue segmentation Dice coefficient of 0.8668 for all classes. The automatic classification model and clinical scale achieved accuracies of 0.9098 and 0.8647, respectively, in predicting the QST classification.
Conclusions: The automatic segmentation model can perform accurate multi-structure segmentation based on MRI, which is conducive to clearing tumor location and initiating intraoperative neuronavigation. The proposed automatic classification model and clinical scale based on automatic segmentation results achieve high accuracy in the QST classification, which is conducive to developing surgical plans and predicting patient prognosis 2).
Adamantinomatous craniopharyngioma, the most frequent histological variety in children.
see Anaplastic Craniopharyngioma.
Zhou L, You C. Craniopharyngioma classification. J Neurosurg. 2009 Jul;111(1):197-9; author reply 199. doi: 10.3171/2009.2.JNS081430. PMID: 19569961.
Pascual JM, Carrasco R, Prieto R, Gonzalez-Llanos F, Alvarez F, Roda JM. Craniopharyngioma classification. J Neurosurg. 2008 Dec;109(6):1180-2; author reply 1182-3. doi: 10.3171/JNS.2008.109.12.1180. PMID: 19035739.
see Magill ST, Jane JA, Prevedello DM. Editorial. Craniopharyngioma classification. J Neurosurg. 2021 Mar 5:1-3. doi: 10.3171/2020.8.JNS202666. Epub ahead of print. PMID: 33668034. 3).