Case Reports and Artificial Intelligence Challenges on Squamous Cell Carcinoma Developed on Chronic Radiodermitis

TL;DR

This paper presents two cases of squamous cell carcinoma developing on chronic radiodermitis and proposes an AI system to aid diagnosis when clinical data is limited.

Contribution

The paper introduces a novel intelligent system for radiodermitis diagnosis using hybrid AI models in low-data scenarios.

Findings

Two clinical cases of squamous cell carcinoma on chronic radiodermitis were confirmed by histology.

An AI system named IntMediSys was proposed to support diagnosis in complex radiodermitis cases.

The system integrates agents, intelligent computing, and blackboard systems for collaborative decision-making.

Abstract

Background/Objectives: Radiodermitis is an inflammatory or dystrophic skin process caused by the direct action of ionizing radiation. The primary objective was to study two clinical cases. The secondary objective was to propose the foundations of an intelligent system for decision support in complex cases of radiodermitis diagnosis that can operate even in the case of a low amount of available clinical data that can be used for training. Methods: The first case is a female patient, aged 74 years, with squamous cell carcinoma on a chronic radiodermitis site, which appeared after 20 years of local radiotherapy treatment for mammary adenocarcinoma. Dermatologic examination revealed five round-oval nodules between 2 and 8 cm in diameter. They were pink colored with lilac edges, hard and infiltrated on palpation, adherent to the subcutaneous tissue, painless, and located above and lateral on the right chest and the upper region of the right hypochondrium. The second case concerns a 60-year-old patient with verrucous squamous cell carcinoma appearing on a chronic radiodermatitis 40 years after local radio-therapeutic treatment with Chaoul rays for a deep right temporal region mycosis. There are presented artificial intelligence (AI) challenges regarding the application of advanced hybrid models in decision support for diagnosis of difficult radiodermitis cases, in that intelligent computing must be made in the context of very little available data, and collaboration between physicians is necessary. Results: Both cases were confirmed by histology as squamos cell carcinomas. In the AI research, the adaptation of the IntMediSys intelligent system was proposed for solving complex cases of radiodermitis. The proposal integrates different AI technologies, which include agents, intelligent computing, and blackboard systems. Conclusions: The presented first cases confirm the presence of a squamous cell carcinoma that appeared on chronic radiodermitis after a long latency. The foundations of a highly complex collaboration and decision support system that can assist physicians in the radiodermitis diagnostics establishment that opens the path for further development are presented.

Figures