Application of Artificial Intelligence in Diagnosis of Craniopharyngioma

Abstract

Craniopharyngioma is a congenital brain tumor with clinical characteristics of hypothalamic-pituitary dysfunction, increased intracranial pressure, and visual field disorder, among other injuries. Its clinical diagnosis mainly depends on radiological examinations (such as Computed Tomography, Magnetic Resonance Imaging). However, assessing numerous radiological images manually is a challenging task, and the experience of doctors has a great influence on the diagnosis result. The development of artificial intelligence has brought about a great transformation in the clinical diagnosis of craniopharyngioma. This study reviewed the application of artificial intelligence technology in the clinical diagnosis of craniopharyngioma from the aspects of differential classification, prediction of tissue invasion and gene mutation, prognosis prediction, and so on. Based on the reviews, the technical route of intelligent diagnosis based on the traditional machine learning model and deep learning model were further proposed. Additionally, in terms of the limitations and possibilities of the development of artificial intelligence in craniopharyngioma diagnosis, this study discussed the attentions required in future research, including few-shot learning, imbalanced data set, semi-supervised models, and multi-omics fusion.

The Challenging Management of Craniopharyngiomas in Adults: Time for a Reappraisal?

“…In general, they less frequently contain calcification; however, for both subtypes, there is a lack of specificity in the radiological appearance that can clearly differentiate ACPs from PCPs. Apart from patient age and the location of the tumor, recent concepts using artificial intelligence have been proposed for distinguishing ACPs from PCPs based on morphological imaging [ 61 ]. In 2018, Yue et al showed in a series of 52 adult CPs patients that suprasellar ( p < 0.001), spherical ( p = 0.005), predominantly solid ( p = 0.003), homogeneous enhancement ( p < 0.001), and a thickened pituitary stalk ( p = 0.014) were all significantly more frequently observed in tumors with BRAF mutations (i.e., PCPs) as compared to tumors without BRAF mutations (that were de facto mainly ACPs).…”

A Clinical, Immunohistochemical, Doble Fluoresce Immunostaining and Ultrastructure Analysis of Papillary Craniopharyngioma

“…Despite their benign histology, these tumors offer several clinical problems [1]. CPs are rare primary brain epithelial tumors with a modest growth rate and symptoms associated to bulk impact and local infiltration of adjacent tissues [3,4], There are two types of CPs, namely, adamantinomatous craniopharyngiomas (AdaCPs) and papillary craniopharyngiomas (PaCPs) [1]. AdaCP affects both children and adults, whereas PaCP affects virtually solely adults [1].…”

“…

Background: Craniopharyngioma is epithelial tumor located in the parasellar region, classified into histopathologically, genetically, clinically and prognostically as adamantinomatous and papillary subtypes Aim: A descriptive design, to determine the immunohistochemical expression of BRAFV600E, occludin, TNFα, IL6,10,20,3,4, βFGF, IGF, EGFR, DPGF, Ki-67li and MVD in PaCPs. Materials and Methods: clinic, pathological immunostaining and ultrastructure correlation on paraffin embedded tissue sections of 13 cases of papillary craniopharyngioma.

…”

Commentary: Resection of Giant Craniopharyngioma: Contending With Multiple Compartments and Myriad Perforating Arteries: 2-Dimensional Operative Video

“…17,18 Moreover, artificial intelligence approaches may soon offer reliable tools to aid in differential diagnosis from neuroimaging including molecular profiling, assessing tumor invasiveness, and predicting postoperative outcomes. 19 In summary, this operative video is an exceptional demonstration of a complex craniopharyngioma resection where deep knowledge of skull base and intradural anatomy is crucial in achieving favorable outcomes. The senior author should be thanked for investing the time and effort to share wisdom and knowledge gained over several decades through narrated video.…”

“…17,18 Moreover, artificial intelligence approaches may soon offer reliable tools to aid in differential diagnosis from neuroimaging including molecular profiling, assessing tumor invasiveness, and predicting postoperative outcomes. 19…”