BSc-DARTS: Neural Architecture Search for Automatic Diagnosis of Bone Metastases in Bone Scintigrams

The proposed neural architecture search method effectively detects bone metastasis in bone scintigrams and outperforms existing state-of-the-art approaches. The newly developed candidate operations and supernet optimizations successfully address the limited representational capacity of standard convolutions in the original DARTS operations, leading to substantial improvements in classification performance.