Explainability is a key requirement for computer-aided diagnosis systems in clinical decision-making. Multiple instance learning with attention pooling provides instance-level explainability, however for many clinical applications a deeper, pixel-level explanation is desirable, but missing so far. In this work, we investigate the use of four attribution methods to explain a multiple instance learning models: GradCAM, Layer-Wise Relevance Propagation (LRP), Information Bottleneck Attribution (IBA), and InputIBA. With this collection of methods, we can derive pixel-level explanations on for the task of diagnosing blood cancer from patients' blood smears. We study two datasets of acute myeloid leukemia with over 100 000 single cell images and observe how each attribution method performs on the multiple instance learning architecture focusing on different properties of the white blood single cells. Additionally, we compare attribution maps with the annotations of a medical expert to see how the model's decision-making differs from the human standard. Our study addresses the challenge of implementing pixel-level explainability in multiple instance learning models and provides insights for clinicians to better understand and trust decisions from computer-aided diagnosis systems.

Pixel-Level Explanation of Multiple Instance Learning Models in Biomedical Single Cell Images

Explainability is a key requirement for computer-aided diagnosis systems in clinical decision-making. Multiple instance learning with attention pooling provides instance-level explainability, however for many clinical applications a deeper, pixel-level explanation is desirable, but missing so far. In this work, we investigate the use of four attribution methods to explain a multiple instance learning models: GradCAM, Layer-Wise Relevance Propagation (LRP), Information Bottleneck Attribution (IBA), and InputIBA. With this collection of methods, we can derive pixel-level explanations on for the task of diagnosing blood cancer from patients’ blood smears. We study two datasets of acute myeloid leukemia with over 100 000 single cell images and observe how each attribution method performs on the multiple instance learning architecture focusing on different properties of the white blood single cells. Additionally, we compare attribution maps with the annotations of a medical expert to see how the model’s decision-making differs from the human standard. Our study addresses the challenge of implementing pixel-level explainability in multiple instance learning models and provides insights for clinicians to better understand and trust decisions from computer-aided diagnosis systems. 

A lot of deep learning (DL) research these days is mainly focused on improving on quantitative metrics regardless of other factors. In human centered applications, like skin lesion classification in dermatology, DL-driven clinical decision support systems are still in their infancy due to the limited transparency of their decision-making process. Moreover, the lack of procedures that can explain the behavior of trained DL algorithms leads to almost no trust from the clinical physicians. To diagnose skin lesions, dermatologists rely on both visual assessment of the disease and the data gathered from the anamnesis of the patient. Data-driven algorithms dealing with multi-modal data are limited by the separation of feature-level and decision-level fusion procedures required by convolutional architectures. To address this issue, we enable single-stage multi-modal data fusion via the attention mechanism of transformer-based architectures to aid in the diagnosis of skin diseases. Our method beats other state-of-the-art single- and multi-modal DL architectures in both image rich and patient-data rich environments. Additionally, the choice of the architecture enables native interpretability support for the classification task both in image and metadata domain with no additional modifications necessary.

Transformer-based interpretable multi-modal data fusion for skin lesion classification

Journal of the European Academy of Dermatology and VenereologyAccepted Articles LETTER TO THE EDITOR Automated dermatoscopic pattern discovery by clustering neural network output for human-computer interaction Lidia Talavera-Martinez, Lidia Talavera-Martinez orcid.org/0000-0002-9255-6342 SCOPIA Research Group, University of the Balearic IslandsSearch for more papers by this authorPhilipp Tschandl, Corresponding Author Philipp Tschandl [email protected] orcid.org/0000-0003-0391-7810 Department of Dermatology, Medical University of Vienna Correspondence Philipp Tschandl, Department of Dermatology, Medical University of Vienna, Währinger Gürtel 18-20, 1090 Vienna – AUSTRIA. Email: [email protected]Search for more papers by this author Lidia Talavera-Martinez, Lidia Talavera-Martinez orcid.org/0000-0002-9255-6342 SCOPIA Research Group, University of the Balearic IslandsSearch for more papers by this authorPhilipp Tschandl, Corresponding Author Philipp Tschandl [email protected] orcid.org/0000-0003-0391-7810 Department of Dermatology, Medical University of Vienna Correspondence Philipp Tschandl, Department of Dermatology, Medical University of Vienna, Währinger Gürtel 18-20, 1090 Vienna – AUSTRIA. Email: [email protected]Search for more papers by this author First published: 31 May 2023 https://doi.org/10.1111/jdv.19234 This article has been accepted for publication and undergone full peer review but has not been through the copyediting, typesetting, pagination and proofreading process, which may lead to differences between this version and the Version of Record. Please cite this article as doi:10.1111/jdv.19234. AboutPDF ToolsExport citationAdd to favoritesTrack citation ShareShare Give accessShare full text accessShare full-text accessPlease review our Terms and Conditions of Use and check box below to share full-text version of article.I have read and accept the Wiley Online Library Terms and Conditions of UseShareable LinkUse the link below to share a full-text version of this article with your friends and colleagues. Learn more.Copy URL Accepted ArticlesAccepted, unedited articles published online and citable. The final edited and typeset version of record will appear in the future. RelatedInformation 

pdf/automated-dermatoscopic-pattern-discovery-by-clustering-1z7l6wdp.pdf

Automated dermatoscopic pattern discovery by clustering neural network output for human-computer interaction.

Importance Artificial intelligence (AI) excels in dermatology. However, its applications to sexually transmitted infections (STIs) remain unclear. Objective To assess the performance of AI algorithms and their applications in detecting STIs and anogenital dermatoses from clinical images in sexual health. Data Sources Six databases (IEEE Xplore, Embase, Scopus, Medline, Web of Science, and CINAHL) were searched for studies published from January 1, 2010, to April 12, 2024, using 3 main concepts: artificial intelligence , diagnosis , and sexually transmitted infections . Study Selection Studies that used AI to identify anogenital skin conditions from clinical images were included. Studies that used non-AI approaches or nonanogenital conditions, as well as reviews and studies lacking performance metrics, were excluded. Data Extraction and Synthesis Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, 2 reviewers independently assessed full-text articles and extracted data using a standardized spreadsheet. Another 2 reviewers resolved any disagreements. A modified Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) critical appraisal tool and the Checklist for Evaluation of Image-Based AI Reports in Dermatology (CLEAR Derm) were used for quality assessment. Main Outcomes and Measures Pooled sensitivity and specificity of AI applications for detecting anogenital skin conditions. A bivariate random-effects meta-analysis was conducted for conditions with more than 3 studies. Results Of 5381 studies screened and 258 full texts selected, 140 met the inclusion criteria. Most studies reported on mpox (110 [78.6%]), while other anogenital conditions, including genital herpes (7 [5.0%]), genital warts (8 [5.7%]), scabies (8 [5.7%]), and molluscum contagiosum (6 [4.3%]), received less attention. Meta-analyses showed high performance of AI for identification of mpox (pooled sensitivity: 0.96 [95% CI, 0.93-0.97]; pooled specificity: 0.98 [95% CI, 0.97-0.99]), herpes simplex (sensitivity: 0.91 [95% CI, 0.71-0.98]; specificity: 0.97 [95% CI, 0.94-0.98]), genital warts (sensitivity: 0.87 [95% CI, 0.67-0.96]; specificity: 0.98 [95% CI, 0.95-0.99]), psoriasis (sensitivity: 0.90 [95% CI, 0.78-0.95]; specificity: 0.98 [95% CI, 0.96-0.99]), and scabies (sensitivity: 0.89 [95% CI, 0.84-0.93]; specificity: 0.98 [95% CI, 0.95-0.99]). Study quality was variable, and the assessment identified high risk of bias across the population selection (76.1%), reference standards (76.1%), and index tests (20.0%). Most studies relied on open-source datasets (121 [86.4%]); only 17 (12.1%) used external validation. All but 1 study (0.7%) remained at the proof-of-concept stage, and models were not publicly available for external evaluation. Conclusions and Relevance The findings suggest that AI shows promise in identifying STIs and anogenital dermatoses but that significant research gaps exist. Future work should prioritize understudied STIs and differential conditions while improving data quality, conducting external validation, and validating findings in clinical settings. 

Use of AI in Identification of Sexually Transmitted Infections and Anogenital Dermatoses

Artificial Intelligence for early identification of Amyloid positivity in transgenic Alzheimer mice

Artificial intelligence (AI) techniques are promising in early diagnosis of skin diseases. However, a precondition for their success is the access to large‐scaled annotated data. Until now, obtaining this data has only been feasible with very high personnel and financial resources.

https://onlinelibrary.wiley.com/doi/pdfdirect/10.1111/jdv.18460

Deep learning‐based classification of dermatological lesions given a limited amount of labelled data

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Y. Li

Author Tools

Chat about Author

Papers

Artificial Intelligence for early identification of Amyloid positivity in transgenic Alzheimer mice

Deep learning‐based classification of dermatological lesions given a limited amount of labelled data