From b84b2fda2d9e4215f01af834285a8293a48929a4 Mon Sep 17 00:00:00 2001 From: MarcoParola Date: Fri, 22 Nov 2024 17:50:22 +0100 Subject: [PATCH] add web page --- .nojekyll | 1 + index.html | 191 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 192 insertions(+) create mode 100644 .nojekyll create mode 100644 index.html diff --git a/.nojekyll b/.nojekyll new file mode 100644 index 0000000..8b13789 --- /dev/null +++ b/.nojekyll @@ -0,0 +1 @@ + diff --git a/index.html b/index.html new file mode 100644 index 0000000..40bac15 --- /dev/null +++ b/index.html @@ -0,0 +1,191 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + Academic Project Page + + + + + + + + + + + + + + + + + + + + +
+
+
+
+
+

Towards explainable oral cancer recognition: Screening on imperfect images via Informed Deep Learning and Case-Based Reasoning

+
+ + + Marco Parola1, + + Federico A. Galatolo1, + + Gaetano La Mantia1,
+ + Mario GCA Cimino1, + + Giuseppina Campisi1, + + Olga Di Fede2,3, +
+ +
+ 1Department of Information Engineering, University of Pisa, Italy
+ 2Department Di.Chir.On.S, University of Palermo, Palermo, Italy + 3Unit of Oral Medicine and Dentistry for fragile patients, Department of Rehabilitation, fragility, and continuity of care University Hospital Palermo, Palermo, Italy + 4Department of Biomedical and Dental Sciences and Morphofunctional Imaging, University of Messina, Messina, Italy +
+ +
+
+ + + + + + + Paper + + + + + + + + + + + Code + + + + + + + + + + Data + + +
+
+
+
+
+
+
+ + + + +
+
+
+
+

Abstract

+
+

+ Oral squamous cell carcinoma recognition presents a challenge due to late diagnosis and costly data acquisition. A cost-efficient, computerized screening system is crucial for early disease detection, minimizing the need for expert intervention and expensive analysis. Besides, transparency is essential to align these systems with critical sector applications. Explainable Artificial Intelligence (XAI) provides techniques for understanding models. However, current XAI is mostly data-driven and focused on addressing developers’ requirements of improving models rather than clinical users’ demands for expressing relevant insights. Among different XAI strategies, we propose a solution composed of Case-Based Reasoning paradigm to provide visual output explanations and Informed Deep Learning (IDL) to integrate medical knowledge within the system. A key aspect of our solution lies in its capability to handle data imperfections, including labeling inaccuracies and artifacts, thanks to an ensemble architecture on top of the deep learning (DL) workflow. We conducted several experimental benchmarks on a dataset collected in collaboration with medical centers. Our findings reveal that employing the IDL approach yields an accuracy of 85%, surpassing the 77% accuracy achieved by DL alone. Furthermore, we measured the human-centered explainability of the two approaches and IDL generates explanations more congruent with the clinical user demands. +

+
+
+
+
+
+ + + + + +
+
+

BibTeX

+ 

+        @article{PAROLA2024102433,
+          title = {Towards explainable oral cancer recognition: Screening on imperfect images via Informed Deep Learning and Case-Based Reasoning},
+          journal = {Computerized Medical Imaging and Graphics},
+          volume = {117},
+          pages = {102433},
+          year = {2024},
+          issn = {0895-6111},
+          doi = {https://doi.org/10.1016/j.compmedimag.2024.102433},
+          url = {https://www.sciencedirect.com/science/article/pii/S0895611124001101},
+          author = {Marco Parola and Federico A. Galatolo and Gaetano {La Mantia} and Mario G.C.A. Cimino and Giuseppina Campisi and Olga {Di Fede}},
+          keywords = {Oral cancer, Oncology, Medical imaging, Case-based reasoning, Informed deep learning, Explainable artificial intelligence},
+        }
+
+
+
+ + + + + + + + + + + + +