Abstract Library

#4586 Base on neuroendocrine tumour classification in CT imaging using pretrained vision transformers and data augmentation

Introduction: Neuroendocrine tumours (NETs) are a group of cancers that can be difficult to distinguish from other malignancies in CT imaging. Their diverse appearance often leads to diagnostic challenges, requiring advanced techniques to improve classification accuracy. Pretrained Vision Transformers (ViTs) have shown promise in medical image analysis, but additional methods are needed to enhance model robustness, particularly when dealing with complex and heterogeneous tumour characteristics.

Conference:

Presenting Author:

Authors: Li H, Tang Z, Ding Z, Chen Y, Li H,

Keywords: Vision transformers, Cancer Detection, Transfer Learning, Medical Image Analysis,

#4578 Dissecting the role of collagen quantitation via tissue-tethered digital analysis in small bowel neuroendocrine tumours and related mesenteric tumour deposits

Introduction: Small bowel neuroendocrine tumours (sb-NETs) and related mesenteric tumour deposits (MTDs) can present dense collagen and fibrosis. Despite well-known clinical consequences of this characteristic (bowel obstruction and ischemia), the relationship between SB-NETs and MTDs collagen deposition has been poorly evaluated.

Conference:

Presenting Author: Ali M

Authors: Ali M, Gambella A, Checchin F, Malerba D, Sambuceti V,

Keywords: neuroendocrine tumour, small intestine, collagen, fibrosis,

#4281 Automated (artificial intelligence) vs. manual evaluation of the somatostatin-receptor 2A and proliferation marker Ki-67 in neuroendocrine neoplasms: A pilot study

Introduction: Digital image analysis methods are currently being equipped with artificial intelligence (AI). Various AI applications are already in use to determine Ki-67. To date, there is no specialised AI application available to determine the somatostatin-receptor 2A (SSTR2A).

Conference:

Presenting Author:

Authors: Kaemmerer D, Lupp A, Klöppel G, Ayako I, Kasajima A,

Keywords: artificial intelligence, Ki-67, SSTR2A, usability, neuroendocrine neoplasm,

#4028 Clinical application of digital pathology: Proposal of a new G0 category useful in small intestinal NET (SI-NET)

Introduction: SI-NET display low proliferation rate despite a high frequency of metastases. Ki67 index is frequently reported as “

Conference:

Presenting Author: Couvelard A

Authors: Guedj N, Cléry G, Chassac A, Hentic O, Colnot N,

Keywords: Small Intestinal NET-, grade, survival, prognosis, G1,

#3845 The lungNENomics project – A comprehensive multidisciplinary characterisation of pulmonary carcinoids

Introduction: Lung neuroendocrine tumors (LNETs) are subdivided into low-grade (typical) and intermediate-grade (atypical) carcinoids, at higher risk of developing metastases. We have previously identified 3 LNETs molecular groups with different prognoses, as well as “supra-carcinoids” with molecular profiles of higher-grade neuroendocrine carcinomas. Despite promising results, there is still no consensus on their differential diagnosis and treatment and little is known about how some tumors evolve toward more aggressive phenotypes.

Conference:

Presenting Author:

Authors: Foll M, Sexton-Oates A, Mathian E, Alcala N, Mangiante L,

Keywords: lung carcinoid, deep learning, genomic, evolution, multi-omics, spatial analyses,