Trained on a vast amount of data, Large Language models (LLMs) have achieved unprecedented success and generalization in modeling fairly complex textual inputs in the abstract space, making them powerful tools for zero-shot learning. Such capability is extended to other modalities such as the visual domain using cross-modal foundation models such as CLIP, and as a result, semantically meaningful representation are extractable from visual inputs.
In this work, we leverage this capability and propose an approach that can provide semantic insights into a model's patterns of failures and biases. Given a black box model, its training data, and task definition, we first calculate its task-related loss for each data point. We then extract a semantically meaningful representation for each training data point (such as CLIP embeddings from its visual encoder) and train a lightweight diagnosis model which maps this semantically meaningful representation of a data point to its task loss. We show that an ensemble of such lightweight models can be used to generate insights on the performance of the black-box model, in terms of identifying its patterns of failures and biases.
Towards Explainable Conversational AI for Early Diagnosis with Large Language Models
Department of Information and Communication Technology（信息与通信技术系）；Bangladesh University of Professionals（孟加拉专业大学）；Institute of Information Technology（信息技术研究所）；Jahangirnagar University（贾汗吉尔纳瓦德大学）
Large Language Models for Explainable Decisions in Dynamic Digital Twins
Southern University of Science and Technology（南方科技大学）；University of Birmingham（伯明翰大学）；University of Thessaly（塞萨利大学）；Research Institute of Trustworthy Autonomous Systems (RITAS)（可信自主系统研究院（RITAS））
SkinGEN: an Explainable Dermatology Diagnosis-to-Generation Framework with Interactive Vision-Language Models
Zhejiang University（浙江大学）；Binjiang Institute of Zhejiang University（浙江大学滨江研究院）；The First Affiliated Hospital, Zhejiang University School of Medicine（浙江大学医学院附属第一医院）；Shanghai Institute for Advanced Study of Zhejiang University（浙江大学上海高等研究院）；Hunan University（湖南大学）
Dermatologist-like explainable AI enhances melanoma diagnosis accuracy: eye-tracking study
German Cancer Research Center (DKFZ)（德国癌症研究中心）；Medical University of Vienna（维也纳医科大学）；Uniklinikum Erlangen（埃尔朗根大学医院）；Friedrich-Alexander-Universität Erlangen-Nürnberg（弗里德里希-亚历山大-埃尔朗根-纽伦堡大学）；Bavarian Cancer Research Center (BZFK)（巴伐利亚癌症研究中心）；University Medical Center Mannheim（曼海姆大学医学中心）；Ruprecht-Karl University of Heidelberg（海德堡鲁普雷希特-卡尔大学（海德堡大学））；DKFZ Hector Cancer Institute at the University Medical Center Mannheim（曼海姆大学医学中心DKFZ赫克托癌症研究所）；University Hospital Frankfurt（法兰克福大学医院）；Goethe-University Frankfurt（法兰克福歌德大学）；Pontificia Universidad Católica de Chile（智利天主教大学）；University Hospital Würzburg（维尔茨堡大学医院）；National Center for Tumor Diseases (NCT)（国家肿瘤疾病中心）；TUD Dresden University of Technology（德累斯顿工业大学）；University Hospital Aachen（亚琛大学医院）；RWTH University of Aachen（亚琛工业大学）
KAIST（韩国科学技术院）；Technical University of Munich（慕尼黑工业大学）
The ambiguity of the decision-making process has been pointed out as the main obstacle to applying the deep learning-based method in a practical way in spite of its outstanding performance. Interpretability could guarantee the confidence of deep learning system, therefore it is particularly important in the medical field. In this study, a novel deep network is proposed to explain the diagnostic decision with visual pointing map and diagnostic sentence justifying result simultaneously. For the purpose of increasing the accuracy of sentence generation, a visual word constraint model is devised i…
Hosei University（法政大学）；Tokyo Women’s Medical University（东京女子医科大学）
Although highly accurate automated diagnostic techniques for melanoma have been reported, the realization of a system capable of providing diagnostic evidence based on medical indices remains an open issue because of difficulties in obtaining reliable training data. In this paper, we propose bulk production augmentation (BPA) to generate high-quality, diverse pseudo-skin tumor images with the desired structural malignant features for additional training images from a limited number of labeled images. The proposed BPA acts as an effective data augmentation in constructing the feature detector f…
Fraunhofer Institute for Manufacturing Engineering and Automation IPA（弗劳恩霍夫制造工程与自动化研究所）
Not only automation of manufacturing processes but also automation of automation procedures itself become increasingly relevant to automation research. In this context, automated capability assessment, mainly leveraged by deep learning systems driven from 3D CAD data, have been presented. Current assessment systems may be able to assess CAD data with regards to abstract features, e.g. the ability to automatically separate components from bulk goods, or the presence of gripping surfaces. Nevertheless, they suffer from the factor of black box systems, where an assessment can be learned and gener…
OMNI-Dent: Towards an Accessible and Explainable AI Framework for Automated Dental Diagnosis
University of Minnesota（明尼苏达大学）；Khon Kaen University（科恩卡恩大学）；Minnesota State University（明尼苏达州立大学）；The University of Western Australia（西澳大学）；Kaohsiung Medical University（高雄医学院）；Auckland University of Technology（奥克兰理工大学）
MedXplain-VQA: Multi-Component Explainable Medical Visual Question Answering
Faculty Of Information Technology VNU University of Engineering（信息科技学院越南工程大学）；IT-BT Convergence Technology Division Vietnam-Korea Institute of Science（IT-BT融合技术部门越南-韩国科学技术院）；TADI Global Lab TADI Global Company Limited（TADI全球实验室TADI全球有限公司）；Faculty of Finance Banking Academy of Vietnam（金融学院越南银行学院）
EPFL（洛桑联邦理工学院）；IBM Research Zürich（IBM苏黎世研究院）；ETH Zürich（苏黎世联邦理工学院）；National Cancer Institute - IRCCS-Fondazione Pascale（国家癌症研究所 - IRCCS帕斯卡尔基金会）
Explainability of machine learning (ML) techniques in digital pathology (DP) is of great significance to facilitate their wide adoption in clinics. Recently, graph techniques encoding relevant biological entities have been employed to represent and assess DP images. Such paradigm shift from pixel-wise to entity-wise analysis provides more control over concept representation. In this paper, we introduce a post-hoc explainer to derive compact per-instance explanations emphasizing diagnostically important entities in the graph. Although we focus our analyses to cells and cellular interactions in …
A Graph-Augmented knowledge Distillation based Dual-Stream Vision Transformer with Region-Aware Attention for Gastrointestinal Disease Classification with Explainable AI
Department of Computer Science and Engineering（计算机科学与工程系）
ProjectedEx: Enhancing Generation in Explainable AI for Prostate Cancer
Flinders University（弗林德斯大学）；The University of Adelaide（阿德莱德大学）；The Australian National University（澳大利亚国立大学）；The University of Sydney（悉尼大学）；Zhejiang University of Technology（浙江工业大学）；Guangdong Technion – Israel Institute of Technology（广东以色列理工学院）；University of Chinese Academy of Sciences（中国科学院大学）；Rice University（莱斯大学）；Johns Hopkins University（约翰斯·霍普金斯大学）；The Pennsylvania State University（宾夕法尼亚州立大学）；La Trobe University（拉筹伯大学）
SilVar-Med: A Speech-Driven Visual Language Model for Explainable Abnormality Detection in Medical Imaging
Florida Institute of Technology（佛罗里达理工学院）；Knovel Engineering Lab（诺维尔工程实验室）；Vietnam Military Medical University（越南军事医科大学）；Military Central Hospital（108陆军中央医院）；Can Tho University of Medicine and Pharmacy（芹苴医药大学）；University of Alabama at Birmingham（阿拉巴马大学伯明翰分校）
In a worldwide health crisis as exigent as COVID-19, there has become a pressing need for rapid, reliable diagnostics. Currently, popular testing methods such as reverse transcription polymerase chain reaction (RT-PCR) can have high false negative rates. Consequently, COVID-19 patients are not accurately identified nor treated quickly enough to prevent transmission of the virus. However, the recent rise of medical CT data has presented promising avenues, since CT manifestations contain key characteristics indicative of COVID-19. This study aimed to take a novel approach in the machine learning…
A Deep Learning Approach for Automated Skin Lesion Diagnosis with Explainable AI
1 ,2,3Department of Computer Science \& Engineering, Green University of Bangladesh, Dhaka, Bangladesh；4Department of Computer Science \& Engineering, Bangladesh University of Business；5Department of Internet of Things \& Robotics Engineering, University of Frontier Technology, Bangladesh
Fraunhofer Institute for Integrated Circuits IIS（弗劳恩霍夫集成电路研究所IIS）；Nuremberg Institute of Technology Georg Simon Ohm（纽伦堡乔治·西蒙·欧姆技术学院）
Would you trust physicians if they cannot explain their decisions to you? Medical diagnostics using machine learning gained enormously in importance within the last decade. However, without further enhancements many state-of-the-art machine learning methods are not suitable for medical application. The most important reasons are insufficient data set quality and the black-box behavior of machine learning algorithms such as Deep Learning models. Consequently, end-users cannot correct the model's decisions and the corresponding explanations. The latter is crucial for the trustworthiness of machi…
