This paper presents the submission of team Medical-XAI for the Medico: Transparency in Medical Image Segmentation task held at MediaEval 2021. We propose an unsupervised method that utilizes tools from the field of explainable artificial intelligence to create segmentation masks. We extract heat maps, which are useful in order to explain how the `black box' model predicts the category of a certain image, and the segmentation masks are directly derived from the heat maps. Our results show that the created masks can capture the relevant findings to a certain extent using only a small amount of image-level labeled data for the classification model and no segmentation masks at all for the training. This is promising for addressing different challenges within the intersection of artificial intelligence for medicine such as availability of data, cost of labeling and interpretable and explainable results. 

Colonoscopy is a gold standard procedure but is highly operator-dependent. Efforts have been made to automate the detection and segmentation of polyps, a precancerous precursor, to effectively minimize missed rate. Widely used computer-aided polyp segmentation systems actuated by encoder-decoder have achieved high performance in terms of accuracy. However, polyp segmentation datasets collected from varied centers can follow different imaging protocols leading to difference in data distribution. As a result, most methods suffer from performance drop when trained and tested on different distributions and therefore, require re-training for each specific dataset. We address this generalizability issue by proposing a global multi-scale residual fusion network (GMSRF-Net). Our proposed network maintains high-resolution representations by performing multi-scale fusion operations across all resolution scales through dense connections while preserving low-level information. To further leverage scale information, we design cross multi-scale attention (CMSA) module that uses multi-scale features to identify, keep, and propagate informative features. Additionally, we introduce multi-scale feature selection (MSFS) modules to perform channel-wise attention that gates irrelevant features gathered through global multi-scale fusion within the GMSRF-Net. The repeated fusion operations gated by CMSA and MSFS demonstrate improved generalizability of our network. Experiments conducted on two different polyp segmentation datasets show that our proposed GMSRF-Net outperforms the previous top-performing state-of-the-art method by 8.34% and 10.31% on unseen CVC-ClinicDB and on unseen Kvasir-SEG, in terms of dice coefficient. Additionally, when tested on unseen CVC-ColonDB, we surpass the state-of-the-art method by 9.38% and 4.04% in terms of dice coefficient, when source dataset is Kvasir-SEG and CVC-ClinicDB, respectively.