Academic Journal
XRelevanceCAM: towards explainable tissue characterization with improved localisation of pathological structures in probe-based confocal laser endomicroscopy
| Title: | XRelevanceCAM: towards explainable tissue characterization with improved localisation of pathological structures in probe-based confocal laser endomicroscopy |
|---|---|
| Authors: | You, Jianzhong, Ajlouni, Serine, Kakaletri, Irini, Charalampaki, Patra, Giannarou, Stamatia |
| Source: | Int J Comput Assist Radiol Surg |
| Publisher Information: | Springer Science and Business Media LLC, 2024. |
| Publication Year: | 2024 |
| Subject Terms: | 03 medical and health sciences, Microscopy, Confocal, Deep Learning, 0302 clinical medicine, Brain Neoplasms, 0202 electrical engineering, electronic engineering, information engineering, Humans, Original Article, 02 engineering and technology, Microscopy, Confocal/methods [MeSH], Deep Learning [MeSH], Explainable Artificial Intelligence, Humans [MeSH], Brain Neoplasms/surgery [MeSH], Probe-based confocal laser endomicroscopy, Brain Neoplasms/diagnostic imaging [MeSH], Class Activation Map, Brain Neoplasms/pathology [MeSH] |
| Description: | Purpose Probe-based confocal laser endomicroscopy (pCLE) enables intraoperative tissue characterization with improved resection rates of brain tumours. Although a plethora of deep learning models have been developed for automating tissue characterization, their lack of transparency is a concern. To tackle this issue, techniques like Class Activation Map (CAM) and its variations highlight image regions related to model decisions. However, they often fall short of providing human-interpretable visual explanations for surgical decision support, primarily due to the shattered gradient problem or insufficient theoretical underpinning. Methods In this paper, we introduce XRelevanceCAM, an explanation method rooted in a better backpropagation approach, incorporating sensitivity and conservation axioms. This enhanced method offers greater theoretical foundation and effectively mitigates the shattered gradient issue when compared to other CAM variants. Results Qualitative and quantitative evaluations are based on ex vivo pCLE data of brain tumours. XRelevanceCAM effectively highlights clinically relevant areas that characterize the tissue type. Specifically, it yields a remarkable 56% improvement over our closest baseline, RelevanceCAM, in the network’s shallowest layer as measured by the mean Intersection over Union (mIoU) metric based on ground-truth annotations (from 18 to 28.07%). Furthermore, a 6% improvement in mIoU is observed when generating the final saliency map from all network layers. Conclusion We introduce a new CAM variation, XRelevanceCAM, for precise identification of clinically important structures in pCLE data. This can aid introperative decision support in brain tumour resection surgery, as validated in our performance study. |
| Document Type: | Article Other literature type |
| Language: | English |
| ISSN: | 1861-6429 |
| DOI: | 10.1007/s11548-024-03096-0 |
| Access URL: | https://pubmed.ncbi.nlm.nih.gov/38538880 https://repository.publisso.de/resource/frl:6523486 |
| Rights: | CC BY |
| Accession Number: | edsair.doi.dedup.....c120a38e48bce82c5bc7493c24ff358e |
| Database: | OpenAIRE |
| ISSN: | 18616429 |
|---|---|
| DOI: | 10.1007/s11548-024-03096-0 |