Giant cell angiofibroma or localized periorbital lymphedema?

Giant cell-rich solitary fibrous tumour of the urinary bladder: case report of an unusual histological variant and literature review

BACKGROUND

Giant cell-rich solitary fibrous tumour (GCR-SFT), previously referred to as giant cell angiofibroma, is an uncommon soft tissue tumour that classically occurs in the orbit but very rarely presents in deep organs. Here, we present a case of GCR-SFT occurring in the urinary bladder, which is one of the unusual histological subtypes of SFT.

CASE PRESENTATION

A 56-year-old man was incidentally found to have a mass measuring 4.5 × 4.3 × 4.0 cm located in the left posterior wall of the bladder by computed tomography during a physical examination. The lesion was confirmed as GCR-SFT by pathological examination after laparoscopic radical surgery. Histopathologically, the tumour was a well-circumscribed, nonencapsulated lesion that was composed of bland spindle-ovoid tumour cells alternating with hypocellular and hypercellular areas, staghorn-like vasculatures and scattered large dark-stained multinucleate giant cells lining pseudovascular spaces. The spindle-ovoid cells and multinucleate giant cells showed strong and diffuse expression of CD34 and nuclear STAT6. In addition, the hallmark of the NAB2ex4-STAT6ex5 fusion gene was detected by RT‒PCR. The patient was classified as having a low risk of recurrence or metastasis according to the risk stratification criteria. The patient underwent regular follow-up for 34 months after surgery, and there was no evidence of local recurrence or metastasis.

CONCLUSION

This is the first reported case of GCR-SFT occurring in the urinary bladder with underlying NAB2ex4-STAT6ex5 fusion. Complete surgical excision of the tumour and long-term follow-up are recommended to ensure no local recurrence or metastasis.

Towards Real-Time Reinforcement Learning Control of a Wave Energy Converter

The levellised cost of energy of wave energy converters (WECs) is not competitive with fossil fuel-powered stations yet. To improve the feasibility of wave energy, it is necessary to develop effective control strategies that maximise energy absorption in mild sea states, whilst limiting motions in high waves. Due to their model-based nature, state-of-the-art control schemes struggle to deal with model uncertainties, adapt to changes in the system dynamics with time, and provide real-time centralised control for large arrays of WECs. Here, an alternative solution is introduced to address these challenges, applying deep reinforcement learning (DRL) to the control of WECs for the first time. A DRL agent is initialised from data collected in multiple sea states under linear model predictive control in a linear simulation environment. The agent outperforms model predictive control for high wave heights and periods, but suffers close to the resonant period of the WEC. The computational cost at deployment time of DRL is also much lower by diverting the computational effort from deployment time to training. This provides confidence in the application of DRL to large arrays of WECs, enabling economies of scale. Additionally, model-free reinforcement learning can autonomously adapt to changes in the system dynamics, enabling fault-tolerant control.