LEADER 10278nam 22006975 450 001 9910631089003321 005 20251004083402.0 010 $a9783031196607 010 $a3031196600 024 7 $a10.1007/978-3-031-19660-7 035 $a(MiAaPQ)EBC7143532 035 $a(Au-PeEL)EBL7143532 035 $a(CKB)25402365100041 035 $a(DE-He213)978-3-031-19660-7 035 $a(PPN)266348300 035 $a(EXLCZ)9925402365100041 100 $a20221119d2022 u| 0 101 0 $aeng 135 $aurcnu|||||||| 181 $ctxt$2rdacontent 182 $cc$2rdamedia 183 $acr$2rdacarrier 200 10$aArtificial Intelligence over Infrared Images for Medical Applications and Medical Image Assisted Biomarker Discovery $eFirst MICCAI Workshop, AIIIMA 2022, and First MICCAI Workshop, MIABID 2022, Held in Conjunction with MICCAI 2022, Singapore, September 18 and 22, 2022, Proceedings /$fedited by Siva Teja Kakileti, Maria Gabrani, Geetha Manjunath, Michal Rosen-Zvi, Nathaniel Braman, Robert G. Schwartz, Alejandro F. Frangi, Pau-Choo Chung, Christopher Weight, Vekataraman Jagadish 205 $a1st ed. 2022. 210 1$aCham :$cSpringer Nature Switzerland :$cImprint: Springer,$d2022. 215 $a1 online resource (200 pages) 225 1 $aLecture Notes in Computer Science,$x1611-3349 ;$v13602 311 08$aPrint version: Kakileti, Siva Teja Artificial Intelligence over Infrared Images for Medical Applications and Medical Image Assisted Biomarker Discovery Cham : Springer,c2022 9783031196591 327 $aIntro -- Preface AIIIMA 2022 -- Preface MIABID 2022 -- Organization -- Contents -- Artificial Intelligence over Infrared Images for Medical Applications -- Thermal Radiomics for Improving the Interpretability of Breast Cancer Detection from Thermal Images -- 1 Introduction -- 2 Methodology -- 2.1 Thermal Radiomics -- 2.2 Classification -- 3 Experimentation and Results -- 4 Conclusions -- References -- Radiomics for Breast IR-Imaging Classification -- 1 Introduction -- 2 Breast IR Classification in the Literature -- 3 Dataset Description -- 4 Region of Interest Segmentation -- 5 Radiomic Feature Extraction -- 6 Classification Methodology -- 7 Experiments and Results -- 8 Conclusion -- References -- Early Thermographic Screening of Breast Abnormality in Women with Dense Breast by Thermal, Fractal, and Statistical Analysis -- 1 Background -- 2 Methods -- 3 Results -- 3.1 Thermal Feature-Based Analysis -- 3.2 Fractal Feature-Based Analysis -- 3.3 Statistical Feature-Based Analysis -- 4 Discussion -- 5 Conclusion and Futurescope -- References -- A Novel Thermography-Based Artificial Intelligence-Powered Solution for Screening Breast Cancer -- 1 Introduction -- 1.1 Thermography -- 1.2 Related Work -- 1.3 AI-Powered Breast Cancer Prediction Tool by AI Talos -- 2 Materials and Methods -- 2.1 Dataset Description -- 2.2 CNN Methodology -- 3 Experimental Results -- 4 Conclusion -- References -- Thermographic Toothache Screening by Artificial Intelligence -- 1 Introduction, Review and Objectives -- 2 Materials and Methods -- 3 Results -- 4 Discussion -- 5 Conclusion -- References -- Non-fever COVID-19 Detection by Infrared Imaging -- 1 Introduction -- 2 Materials and Methods -- 2.1 Infrared Camera Calibration and Precision Assessment -- 2.2 Standard Data Bank Construction (Phase 1) -- 2.3 Classification Algorithm -- 2.4 Prospective Study (Phase 2). 327 $a2.5 Statistical Analysis -- 3 Results -- 4 Discussion -- 5 Conclusion -- References -- Automated Thermal Screening for COVID-19 Using Machine Learning -- 1 Introduction -- 2 Dataset -- 2.1 Thermal Surveillance Dataset -- 2.2 Augmented Surveillance Dataset -- 2.3 Lighting Dataset -- 3 Methodology -- 3.1 Image Preprocessing -- 3.2 Face Detection -- 3.3 Fever Detection -- 3.4 Mask Classification -- 4 Experiments and Results -- 4.1 Face Detection -- 4.2 Mask Classification -- 5 Conclusion -- References -- An Automated Approach for Screening COVID-19 from Thermal Images Using Convolutional Neural Network -- 1 Introduction -- 2 Dataset -- 3 Methodology -- 3.1 Overview -- 3.2 YOLOv5 as Mask Detection Module -- 3.3 Fever Detection Module -- 4 Results and Discussion -- 5 Conclusion -- References -- Infrared Technology for Vascular Abnormality in Finding of Abdominal Aortic Aneurysm -- 1 Introduction -- 1.1 Objective -- 2 Methodology -- 2.1 Model Setup -- 2.2 Boundary Conditions -- 2.3 Physical and Thermal Properties -- 3 Verification Studies for FSI Analysis -- 4 Result and Discussions -- 4.1 Transient FSI Analysis -- 5 Limitations -- 6 Conclusion -- References -- Non-invasive Thermal Imaging for Estimation of the Fecundity of Live Female Onchocerca Worms -- 1 Introduction -- 2 Dataset Description -- 2.1 Study Site and Population -- 2.2 Imaging Protocol -- 2.3 Histopathology and Ground truth -- 3 Methodology -- 3.1 Data Pre-processing -- 3.2 Feature Extraction -- 3.3 Classification -- 4 Experiments and Results -- 5 Conclusion -- References -- Medical Image Assisted Biomarker Discovery -- Counterfactual Image Synthesis for Discovery of Personalized Predictive Image Markers -- 1 Introduction -- 2 Methods -- 3 Experiments and Results -- 3.1 Dataset and Implementation Details -- 3.2 Evaluating Counterfactuals and Discovered Image-Based Markers. 327 $a3.3 Counterfactual Results -- 4 Conclusions -- References -- CoRe: An Automated Pipeline for the Prediction of Liver Resection Complexity from Preoperative CT Scans -- 1 Introduction -- 2 Methods -- 2.1 Liver, Lesion, and Vessel Segmentation -- 2.2 Topological Analysis of the Liver Vasculature -- 2.3 Quantitative Imaging Biomarkers for LR Complexity Prediction -- 3 Experiments -- 3.1 Datasets and Preprocessing -- 3.2 Training, Evaluation, and Inference -- 4 Results -- 4.1 Quantitative Results -- 4.2 Qualitative Results -- 5 Discussion and Conclusion -- References -- Diffusion Tensor Imaging Biomarkers for Parkinson's Disease Symptomatology -- 1 Introduction -- 1.1 Voxel-Based Diffusion Analysis and Voxel-Based Diktiometry -- 2 Materials and Methods -- 2.1 Patient Images and Clinical Scores -- 2.2 Preprocessing -- 2.3 Convolutional Neural Network -- 2.4 Diffusion Measures, Sensitivity Maps, and Statistical Processing -- 3 Results and Discussion -- 4 Conclusion -- References -- Prediction of Immune and Stromal Cell Population Abundance from Hepatocellular Carcinoma Whole Slide Images Using Weakly Supervised Learning -- 1 Introduction -- 2 Materials and Methods -- 2.1 Dataset -- 2.2 Gene Expression Processing -- 2.3 Image Preprocessing -- 2.4 Deep Learning Models -- 2.5 Attention Map Generation and Statistical Analysis -- 2.6 Inflammatory Cell Density Map Generation -- 3 Results -- 3.1 Unsupervised Hierarchical Clustering of Samples -- 3.2 Evaluation of Deep Learning Models for the Prediction of Activation of Cell Populations -- 3.3 Interpretability and Relationships with Immunotherapy-Related Gene Signatures and with Inflammatory Cells -- 4 Discussion and Conclusion -- References -- Enhancing Local Context of Histology Features in Vision Transformers -- 1 Introduction -- 2 Methods -- 3 Experiments -- 4 Conclusion -- References. 327 $aDCIS AI-TIL: Ductal Carcinoma In Situ Tumour Infiltrating Lymphocyte Scoring Using Artificial Intelligence -- 1 Introduction -- 2 Materials -- 3 Methodology -- 3.1 Cell Detection, Cell Classification and Hotspot Analysis -- 3.2 DCIS Segmentation Using GAN -- 3.3 Stromal TIL Scoring Using Artificial Intelligence -- 3.4 Statistical Analysis -- 4 Results and Discussion -- References -- Predictive Biomarkers in Melanoma: Detection of BRAF Mutation Using Dermoscopy -- 1 Introduction -- 2 Methodology -- 2.1 Pre-training Phase -- 2.2 BRAF Classification -- 3 Experimental Setup -- 3.1 Dataset and Evaluation Metrics -- 3.2 Experimental Challenges -- 3.3 Network Training and Computational Environment -- 4 Results and Discussion -- 5 Conclusion -- References -- Author Index. 330 $aThis book constitutes the refereed proceedings of the First Workshop on Artificial Intelligence over Infrared Images for Medical Applications, AIIIMA 2022, and the First Workshop on Medical Image Assisted Biomarker Discovery, MIABID 2022, both held in conjunction with MICCAI 2022, Singapore, during September 18 and 22, 2022. For MIABID 2022, 7 papers from 10 submissions were accepted for publication. This workshop created a forum to discuss this specific sub-topic at MICCAI and promote this novel area of research among the research community that has the potential to hugely impact our society. For AIIIMA 2022, 10 papers from 15 submissions were accepted for publication. The first workshop on AIIIMA aimed to create a forum to discuss this specific sub-topic of AI over Infrared Images for Medical Applications at MICCAI and promote this novel area of research that has the potential to hugely impact our society, among the research community. 410 0$aLecture Notes in Computer Science,$x1611-3349 ;$v13602 606 $aImage processing$xDigital techniques 606 $aComputer vision 606 $aMachine learning 606 $aEducation$xData processing 606 $aSocial sciences$xData processing 606 $aComputer Imaging, Vision, Pattern Recognition and Graphics 606 $aMachine Learning 606 $aComputers and Education 606 $aComputer Application in Social and Behavioral Sciences 615 0$aImage processing$xDigital techniques. 615 0$aComputer vision. 615 0$aMachine learning. 615 0$aEducation$xData processing. 615 0$aSocial sciences$xData processing. 615 14$aComputer Imaging, Vision, Pattern Recognition and Graphics. 615 24$aMachine Learning. 615 24$aComputers and Education. 615 24$aComputer Application in Social and Behavioral Sciences. 676 $a610.28563 702 $aKakileti$b Siva Teja 801 0$bMiAaPQ 801 1$bMiAaPQ 801 2$bMiAaPQ 906 $aBOOK 912 $a9910631089003321 996 $aArtificial intelligence over infrared images for medical applications and medical image assisted biomarker discovery$93084143 997 $aUNINA