Bladder cancer patients' stratification into risk groups relies on grade, stage and clinical factors. For non-muscle invasive bladder cancer, T1 tumours that invade the subepithelial tissue are high-risk lesions with a high probability to progress into an aggressive muscle-invasive disease. Detecting invasive cancerous areas is the main factor for dictating the treatment strategy for the patient. However, defining invasion is often subject to intra/interobserver variability among pathologists, thus leading to over or undertreatment. Computer-aided diagnosis systems can help pathologists reduce overheads and erratic reproducibility. We propose a multi-scale model that detects invasive cancerous areas patterns across the whole slide image. The model extracts tiles of different tissue types at multiple magnification levels and processes them to predict invasive patterns based on local and regional information for accurate T1 staging. Our proposed method yields an F1 score of 71.9, in controlled settings 74.9, and without infiltration 90.0.
|Title of host publication||IVMSP 2022 - 2022 IEEE 14th Image, Video, and Multidimensional Signal Processing Workshop|
|Publisher||Institute of Electrical and Electronics Engineers Inc.|
|Publication status||Published - 29 Jun 2022|
|Event||14th IEEE Image, Video, and Multidimensional Signal Processing Workshop, IVMSP 2022 - Nafplio, Greece|
Duration: 26 Jun 2022 → 29 Jun 2022
|Conference||14th IEEE Image, Video, and Multidimensional Signal Processing Workshop, IVMSP 2022|
|Period||26/06/22 → 29/06/22|
Bibliographical noteFunding Information: This work has received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska Curie grant agreement No 860627 (CLARIFY Project).
Publisher Copyright: © 2022 IEEE.