OBJECTIVES: We propose a novel deep learning segmentation algorithm (DSRF) based on multi-scale supervision and residual feedback strategy for precise segmentation of the optic chiasm and optic nerves in CT images of nasopharyngeal carcinoma (NPC) patients. METHODS: We collected 212 NPC CT images and their ground truth labels from SegRap2023, StructSeg2019 and HaN-Seg2023 datasets. Based on a hybrid pooling strategy, we designed a decoder (HPS) to reduce small organ feature loss during pooling in convolutional neural networks. This decoder uses adaptive and average pooling to refine high-level semantic features, which are integrated with primary semantic features to enable network learning of finer feature details. We employed multi-scale deep supervision layers to learn rich multi-scale and multi-level semantic features under deep supervision, thereby enhancing boundary identification of the optic chiasm and optic nerves. A residual feedback module that enables multiple iterations of the network was designed for contrast enhancement of the optic chiasm and optic nerves in CT images by utilizing information from fuzzy boundaries and easily confused regions to iteratively refine segmentation results under supervision. The entire segmentation framework was optimized with the loss from each iteration to enhance segmentation accuracy and boundary clarity. Ablation experiments and comparative experiments were conducted to evaluate the effectiveness of each component and the performance of the proposed model. RESULTS: The DSRF algorithm could effectively enhance feature representation of small organs to achieve accurate segmentation of the optic chiasm and optic nerves with an average DSC of 0.837 and an ASSD of 0.351. Ablation experiments further verified the contributions of each component in the DSRF method. CONCLUSIONS The proposed deep learning segmentation algorithm can effectively enhance feature representation to achieve accurate segmentation of the optic chiasm and optic nerves in CT images of NPC.
Humans ; Tomography, X-Ray Computed/methods* ; Optic Chiasm/diagnostic imaging* ; Optic Nerve/diagnostic imaging* ; Algorithms ; Nasopharyngeal Carcinoma ; Deep Learning ; Nasopharyngeal Neoplasms/diagnostic imaging* ; Neural Networks, Computer ; Image Processing, Computer-Assisted/methods*

OBJECTIVES: To investigate the characteristics and objective assessment method of visual field defects caused by optic chiasm and its posterior visual pathway injury. METHODS: Typical cases of visual field defects caused by injuries to the optic chiasm, optic tracts, optic radiations, and visual cortex were selected. Visual field examinations, visual evoked potential (VEP) and multifocal visual evolved potential (mfVEP) measurements, craniocerebral CT/MRI, and retinal optical coherence tomography (OCT) were performed, respectively, and the aforementioned visual electrophysiological and neuroimaging indicators were analyzed comprehensively. RESULTS: The electrophysiological manifestations of visual field defects caused by optic chiasm injuries were bitemporal hemianopsia mfVEP abnormalities. The visual field defects caused by optic tract, optic radiation, and visual cortex injuries were all manifested homonymous hemianopsia mfVEP abnormalities contralateral to the lesion. Mild relative afferent pupil disorder (RAPD) and characteristic optic nerve atrophy were observed in hemianopsia patients with optic tract injuries, but not in patients with optic radiation or visual cortex injuries. Neuroimaging could provide morphological evidence of damages to the optic chiasm and its posterior visual pathway. CONCLUSIONS Visual field defects caused by optic chiasm, optic tract, optic radiation, and visual cortex injuries have their respective characteristics. The combined application of mfVEP and static visual field measurements, in combination with neuroimaging, can maximize the assessment of the location and degree of visual pathway damage, providing an effective scheme for the identification of such injuries.
Humans ; Optic Chiasm/pathology* ; Visual Pathways/pathology* ; Visual Fields ; Evoked Potentials, Visual ; Random Amplified Polymorphic DNA Technique ; Hemianopsia/complications* ; Vision Disorders/pathology* ; Optic Nerve Injuries/diagnostic imaging* ; Brain Injuries, Traumatic/diagnostic imaging*

Adenoma ; diagnosis ; surgery ; Aged ; Female ; Humans ; Magnetic Resonance Imaging ; Neoplasm Invasiveness ; Optic Chiasm ; pathology ; Pituitary Neoplasms ; diagnosis ; diagnostic imaging ; surgery ; Recurrence ; Treatment Outcome