Subtopic Deep Dive
Computer-Aided Diagnosis Infrared Thermography
Research Guide
What is Computer-Aided Diagnosis Infrared Thermography?
Computer-Aided Diagnosis in Infrared Thermography uses machine learning algorithms to automate analysis of thermal images for medical diagnosis, focusing on feature extraction and pattern recognition.
This subtopic develops CAD systems to enhance thermography's objectivity in detecting breast cancer and diabetic foot complications. Key papers include Roslidar et al. (2020) with 142 citations on deep learning for breast cancer and Cruz-Vega et al. (2020) with 127 citations on diabetic foot classification. Over 10 high-citation papers from 2014-2021 demonstrate growing integration of CNNs like Inception V3.
Why It Matters
CAD systems in infrared thermography reduce diagnostic subjectivity, enabling early breast cancer detection as shown by Al Husaini et al. (2021, 120 citations) using Inception networks on thermal images. For diabetic foot, Cruz-Vega et al. (2020) and Adam et al. (2017, 93 citations) improve complication prediction via automated thermogram analysis. These tools boost clinical reproducibility, supporting non-invasive screening in resource-limited settings.
Key Research Challenges
Feature Extraction Variability
Thermal images suffer from noise and asymmetry, complicating reliable feature extraction for CAD. Faust et al. (2014, 117 citations) highlight inconsistencies in texture-based methods. Deep learning mitigates this but requires large annotated datasets.
Dataset Scarcity
Limited public thermogram databases hinder ML model training, as noted in Hernandez-Contreras et al. (2019, 85 citations) for diabetic foot. Models like those in Roslidar et al. (2020) rely on small cohorts. Synthetic data generation remains underexplored.
Clinical Integration Barriers
CAD outputs must align with multi-modal imaging for validation, per Mashekova et al. (2021, 105 citations). Sensitivity to environmental factors affects reproducibility. Regulatory approval demands prospective trials beyond retrospective studies.
Essential Papers
A Review on Recent Progress in Thermal Imaging and Deep Learning Approaches for Breast Cancer Detection
Roslidar Roslidar, Aulia Rahman, Rusdha Muharar et al. · 2020 · IEEE Access · 142 citations
Developing a breast cancer screening method is very important to facilitate early breast cancer detection and treatment. Building a screening method using medical imaging modality that does not cau...
Deep Learning Classification for Diabetic Foot Thermograms
Israel Cruz-Vega, D. Hernandez-Contreras, Hayde Peregrina‐Barreto et al. · 2020 · Sensors · 127 citations
According to the World Health Organization (WHO), Diabetes Mellitus (DM) is one of the most prevalent diseases in the world. It is also associated with a high mortality index. Diabetic foot is one ...
Thermal-based early breast cancer detection using inception V3, inception V4 and modified inception MV4
Mohammed Abdulla Salim Al Husaini, Mohamed Hadi Habaebi, Teddy Surya Gunawan et al. · 2021 · Neural Computing and Applications · 120 citations
Abstract Breast cancer is one of the most significant causes of death for women around the world. Breast thermography supported by deep convolutional neural networks is expected to contribute signi...
Application of infrared thermography in computer aided diagnosis
Oliver Faust, U. Rajendra Acharya, E. Y. K. Ng et al. · 2014 · Infrared Physics & Technology · 117 citations
Early detection of the breast cancer using infrared technology – A comprehensive review
Aigerim Mashekova, Yong Zhao, E. Y. K. Ng et al. · 2021 · Thermal Science and Engineering Progress · 105 citations
Breast cancer is one of the most common and deadly diseases in women, which can also affect men. Early \ndetection and treatment of this disease can increase the chances of cure. Currently, th...
A Systematic Review of Breast Cancer Detection Using Thermography and Neural Networks
Mohammed Abdulla Salim Al Husaini, Mohamed Hadi Habaebi, Shihab A. Hameed et al. · 2020 · IEEE Access · 100 citations
Breast cancer plays a significant role in affecting female mortality. Researchers are actively seeking to develop early detection methods of breast cancer. Several technologies contributed to the r...
Computer aided diagnosis of diabetic foot using infrared thermography: A review
Muhammad Adam, E. Y. K. Ng, Jen Hong Tan et al. · 2017 · Computers in Biology and Medicine · 93 citations
Reading Guide
Foundational Papers
Start with Faust et al. (2014, 117 citations) for CAD principles in thermography, then Ng-linked works like Adam et al. (2017) for diabetic applications, establishing automated analysis baselines.
Recent Advances
Study Roslidar et al. (2020, 142 citations) and Al Husaini et al. (2021, 120 citations) for deep learning advances in breast cancer, plus Cruz-Vega et al. (2020) for diabetic foot.
Core Methods
Core techniques: CNNs (Inception V3/V4, ResNet), swarm optimization (salp algorithm), texture features (GLCM), and databases like plantar thermograms (Hernandez-Contreras et al., 2019).
How PapersFlow Helps You Research Computer-Aided Diagnosis Infrared Thermography
Discover & Search
Research Agent uses searchPapers and exaSearch to find top papers like Roslidar et al. (2020) on breast cancer deep learning, then citationGraph reveals clusters around Faust et al. (2014). findSimilarPapers expands to diabetic foot works like Cruz-Vega et al. (2020).
Analyze & Verify
Analysis Agent applies readPaperContent to extract CNN architectures from Al Husaini et al. (2021), verifies claims with CoVe against ablation studies, and runs PythonAnalysis for ROC curve replication using NumPy on thermogram metrics. GRADE grading scores evidence strength for clinical claims.
Synthesize & Write
Synthesis Agent detects gaps in diabetic foot datasets via contradiction flagging across Adam et al. (2017) and Hernandez-Contreras et al. (2019), then Writing Agent uses latexEditText, latexSyncCitations, and latexCompile for a review paper with exportMermaid diagrams of Inception pipelines.
Use Cases
"Reproduce diabetic foot classification accuracy from Cruz-Vega et al. 2020 using Python."
Research Agent → searchPapers → Analysis Agent → readPaperContent + runPythonAnalysis (pandas for dataset stats, sklearn ROC curves) → outputs replicated AUC scores and matplotlib plots.
"Draft LaTeX review on breast cancer thermography CAD methods."
Synthesis Agent → gap detection → Writing Agent → latexEditText (structure sections) → latexSyncCitations (Roslidar 2020 et al.) → latexCompile → outputs PDF with integrated figures.
"Find GitHub code for thermal image segmentation in breast cancer papers."
Research Agent → paperExtractUrls (Ibrahim et al. 2020) → Code Discovery → paperFindGithubRepo → githubRepoInspect → outputs salp swarm algorithm code and usage examples.
Automated Workflows
Deep Research workflow scans 50+ papers via citationGraph on Faust et al. (2014), generating structured reports on CAD evolution. DeepScan's 7-step chain analyzes thermogram datasets with runPythonAnalysis checkpoints for ML reproducibility. Theorizer builds hypothesis on hybrid CNN-feature models from Roslidar et al. (2020) and Al Husaini et al. (2021).
Frequently Asked Questions
What defines Computer-Aided Diagnosis in Infrared Thermography?
CAD applies ML algorithms like CNNs to automate thermal image analysis for diseases such as breast cancer and diabetic foot ulcers, reducing human bias (Faust et al., 2014).
What are common methods in this subtopic?
Methods include Inception V3/V4 for classification (Al Husaini et al., 2021) and chaotic salp swarm for segmentation (Ibrahim et al., 2020), often with texture analysis (Abdel-Nasser et al., 2019).
What are key papers?
Top papers: Roslidar et al. (2020, 142 citations) on deep learning for breast cancer; Cruz-Vega et al. (2020, 127 citations) on diabetic foot; Faust et al. (2014, 117 citations) on general CAD applications.
What are open problems?
Challenges include dataset scarcity (Hernandez-Contreras et al., 2019), environmental noise robustness, and multi-modal fusion for clinical trials (Mashekova et al., 2021).
Research Infrared Thermography in Medicine with AI
PapersFlow provides specialized AI tools for Medicine researchers. Here are the most relevant for this topic:
Systematic Review
AI-powered evidence synthesis with documented search strategies
AI Literature Review
Automate paper discovery and synthesis across 474M+ papers
Find Disagreement
Discover conflicting findings and counter-evidence
Paper Summarizer
Get structured summaries of any paper in seconds
See how researchers in Health & Medicine use PapersFlow
Field-specific workflows, example queries, and use cases.
Start Researching Computer-Aided Diagnosis Infrared Thermography with AI
Search 474M+ papers, run AI-powered literature reviews, and write with integrated citations — all in one workspace.
See how PapersFlow works for Medicine researchers
Part of the Infrared Thermography in Medicine Research Guide