Hormonal receptor positive human epidermal receptor 2 negative (HR⁺/HER2^-) is the commonest molecular subtype of breast cancer (BC). Patients with HR⁺/HER2^- BC may manifest clinically a late recurrence whose BC metastasizes 10-15 years post-operatively. We report one case who presented with pulmonary mass in upper lobe of lung and Horner syndrome 16 years after BC surgery. FDG PET/CT suggested pulmonary malignancy but could not differentiate between primary or metastatic cancer when invasive biopsy was quite risky. Novel ¹⁸F-FES PET/CT facilitated the non-invasive functional diagnosis of estrogen-receptor positive (ER+) pulmonary metastasis of BC, and the patient experienced partial response (PR) after CDK4/6 inhibitor and aromatase inhibitor as endocrine therapy. This article reviews the diagnosis and treatment process of this case, to provide guidance for non-invasive global evaluation of ER status among metastatic HR⁺/HER2^- BC patients with ¹⁸F-FES PET/CT.

VHL (von Hipple-Lindau) syndrome is a rare autosomal dominant genetic disease with complex and diverse clinical manifestations, which primarily presents as multiple tumors in the retina, central nervous system, kidneys, pancreas, and other areas. Patients often require comprehensive multi-organ assessment. Carbonic anhydrase Ⅸ (CAⅨ) is ubiquitously expressed in VHL-related lesions, and ⁶⁸Ga-NY104, a novel small-molecule tracer, can perform whole-body imaging of CAⅨ-positive lesions. This case report introduces a 32-year-old female patient with VHL syndrome who underwent sequential ¹⁸F-FDG PET/CT and ⁶⁸Ga-NY104 PET/CT for lesion assessment. Notably, ⁶⁸Ga-NY104 PET/CT demonstrated uptake in a broader range of lesions (including renal, pancreatic, hepatic metastatic lesions and cerebellar lesions). This article discusses the process of evaluating the relevant lesions in this patient, with the aim of exploring a "one-stop" evaluation tool for patients with VHL syndrome.

The accurate segmentation of medical images is crucial to medical care and research; however, many efficient supervised image segmentation methods require sufficient pixel level labels. Such requirement is difficult to meet in practice and even impossible in some cases, e.g., rare Pathoma images. Inspired by traditional unsupervised methods, we propose a novel Chan-Vese model based on the Markov chain for unsupervised medical image segmentation. It combines local information brought by superpixels with the global difference between the target tissue and the background. Based on the Chan-Vese model, we utilize weight maps generated by the Markov chain to model and solve the segmentation problem iteratively using the min-cut algorithm at the superpixel level. Our method exploits abundant boundary and local region information in segmentation and thus can handle images with intensity inhomogeneity and object sparsity. In our method, users gain the power of fine-tuning parameters to achieve satisfactory results for each segmentation. By contrast, the result from deep learning based methods is rigid. The performance of our method is assessed by using four Computerized Tomography (CT) datasets. Experimental results show that the proposed method outperforms traditional unsupervised segmentation techniques.