Multi-Slice Net: A novel light weight framework for COVID-19 Diagnosis
This work addresses the problem of efficient and accurate COVID-19 diagnosis for medical practitioners, but it is incremental as it builds on existing deep learning methods for medical imaging.
The paper tackles COVID-19 diagnosis from CT scans by proposing a lightweight two-stage framework that aggregates slice-level features for patient-level predictions, achieving a significant performance increase over baselines with only 2.5 million parameters and 0.623 seconds per patient on an Nvidia-GeForce RTX 2080 GPU.
This paper presents a novel lightweight COVID-19 diagnosis framework using CT scans. Our system utilises a novel two-stage approach to generate robust and efficient diagnoses across heterogeneous patient level inputs. We use a powerful backbone network as a feature extractor to capture discriminative slice-level features. These features are aggregated by a lightweight network to obtain a patient level diagnosis. The aggregation network is carefully designed to have a small number of trainable parameters while also possessing sufficient capacity to generalise to diverse variations within different CT volumes and to adapt to noise introduced during the data acquisition. We achieve a significant performance increase over the baselines when benchmarked on the SPGC COVID-19 Radiomics Dataset, despite having only 2.5 million trainable parameters and requiring only 0.623 seconds on average to process a single patient's CT volume using an Nvidia-GeForce RTX 2080 GPU.