Conversational LLM-Based Decision Support for Defect Classification in AFM Images

Atomic force microscopy (AFM) has emerged as a powerful tool for nanoscale imaging and quantitative characterization of organic (e.g., live cells, proteins, DNA, and lipid bilayers) and inorganic (e.g., silicon wafers and polymers) specimens. However, image artifacts in AFM height and peak force err...

Full description

Saved in:
Bibliographic Details
Main Authors: Angona Biswas, Jaydeep Rade, Nabila Masud, Md Hasibul Hasan Hasib, Aditya Balu, Juntao Zhang, Soumik Sarkar, Adarsh Krishnamurthy, Juan Ren, Anwesha Sarkar
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Open Journal of Instrumentation and Measurement
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11096088/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849228533406105600
author Angona Biswas
Jaydeep Rade
Nabila Masud
Md Hasibul Hasan Hasib
Aditya Balu
Juntao Zhang
Soumik Sarkar
Adarsh Krishnamurthy
Juan Ren
Anwesha Sarkar
author_facet Angona Biswas
Jaydeep Rade
Nabila Masud
Md Hasibul Hasan Hasib
Aditya Balu
Juntao Zhang
Soumik Sarkar
Adarsh Krishnamurthy
Juan Ren
Anwesha Sarkar
author_sort Angona Biswas
collection DOAJ
description Atomic force microscopy (AFM) has emerged as a powerful tool for nanoscale imaging and quantitative characterization of organic (e.g., live cells, proteins, DNA, and lipid bilayers) and inorganic (e.g., silicon wafers and polymers) specimens. However, image artifacts in AFM height and peak force error images directly affect the precision of nanomechanical measurements. Experimentalists face considerable challenges in obtaining high-quality AFM images due to the requirement of specialized expertise and constant manual monitoring. Another challenge is the lack of high-quality AFM datasets to train machine learning models for automated defect detection. In this work, we propose a two-step AI framework that combines a vision-based deep learning (DL) model for classifying AFM image defects with a large language model (LLM)-based conversational assistant that provides real-time corrective guidance in natural language, making it particularly valuable for non-AFM experts aiming to obtain high-quality images. We curated an annotated AFM defect dataset spanning organic and inorganic samples to train the defect detection model. Our defect classification model achieves 91.43% overall accuracy, with a recall of 93% for tip contamination and 60% not-tracking defects. We further develop an intuitive user interface that enables seamless interaction with the DL model and integrates an LLM-based guidance feature to support users in understanding defects and improving future experiments. We then evaluate the performance of multiple state-of-the-art LLMs on AFM-related queries, offering users flexibility in LLM selection based on their specific needs. LLM evaluations and the benchmark questions are available at: <uri>https://github.com/idealab-isu/AFM-LLM-Defect-Guidance</uri>.
format Article
id doaj-art-af19782eb8dd437e9c54c65bd353fb93
institution Kabale University
issn 2768-7236
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Open Journal of Instrumentation and Measurement
spelling doaj-art-af19782eb8dd437e9c54c65bd353fb932025-08-22T23:17:35ZengIEEEIEEE Open Journal of Instrumentation and Measurement2768-72362025-01-01411210.1109/OJIM.2025.359228411096088Conversational LLM-Based Decision Support for Defect Classification in AFM ImagesAngona Biswas0https://orcid.org/0009-0004-8916-0728Jaydeep Rade1https://orcid.org/0000-0002-6831-8416Nabila Masud2https://orcid.org/0009-0006-0125-4055Md Hasibul Hasan Hasib3https://orcid.org/0000-0001-5132-5161Aditya Balu4https://orcid.org/0000-0003-2005-2548Juntao Zhang5https://orcid.org/0009-0007-7913-4261Soumik Sarkar6https://orcid.org/0000-0002-6775-9199Adarsh Krishnamurthy7https://orcid.org/0000-0002-5900-1863Juan Ren8https://orcid.org/0000-0002-5616-7219Anwesha Sarkar9https://orcid.org/0000-0002-4267-7242Department of Electrical and Computer Engineering, Iowa State University, Ames, IA, USADepartment of Electrical and Computer Engineering, Iowa State University, Ames, IA, USADepartment of Electrical and Computer Engineering, Iowa State University, Ames, IA, USADepartment of Electrical and Computer Engineering, Iowa State University, Ames, IA, USATranslational AI Center, Iowa State University, Ames, IA, USADepartment of Mechanical Engineering, Iowa State University, Ames, IA, USADepartment of Mechanical Engineering, Iowa State University, Ames, IA, USADepartment of Electrical and Computer Engineering, Iowa State University, Ames, IA, USADepartment of Mechanical Engineering, Iowa State University, Ames, IA, USADepartment of Electrical and Computer Engineering, Iowa State University, Ames, IA, USAAtomic force microscopy (AFM) has emerged as a powerful tool for nanoscale imaging and quantitative characterization of organic (e.g., live cells, proteins, DNA, and lipid bilayers) and inorganic (e.g., silicon wafers and polymers) specimens. However, image artifacts in AFM height and peak force error images directly affect the precision of nanomechanical measurements. Experimentalists face considerable challenges in obtaining high-quality AFM images due to the requirement of specialized expertise and constant manual monitoring. Another challenge is the lack of high-quality AFM datasets to train machine learning models for automated defect detection. In this work, we propose a two-step AI framework that combines a vision-based deep learning (DL) model for classifying AFM image defects with a large language model (LLM)-based conversational assistant that provides real-time corrective guidance in natural language, making it particularly valuable for non-AFM experts aiming to obtain high-quality images. We curated an annotated AFM defect dataset spanning organic and inorganic samples to train the defect detection model. Our defect classification model achieves 91.43% overall accuracy, with a recall of 93% for tip contamination and 60% not-tracking defects. We further develop an intuitive user interface that enables seamless interaction with the DL model and integrates an LLM-based guidance feature to support users in understanding defects and improving future experiments. We then evaluate the performance of multiple state-of-the-art LLMs on AFM-related queries, offering users flexibility in LLM selection based on their specific needs. LLM evaluations and the benchmark questions are available at: <uri>https://github.com/idealab-isu/AFM-LLM-Defect-Guidance</uri>.https://ieeexplore.ieee.org/document/11096088/atomic force microscopy (AFM)conversational LLMimage defect classificationlarge language models (LLMs)
spellingShingle Angona Biswas
Jaydeep Rade
Nabila Masud
Md Hasibul Hasan Hasib
Aditya Balu
Juntao Zhang
Soumik Sarkar
Adarsh Krishnamurthy
Juan Ren
Anwesha Sarkar
Conversational LLM-Based Decision Support for Defect Classification in AFM Images
IEEE Open Journal of Instrumentation and Measurement
atomic force microscopy (AFM)
conversational LLM
image defect classification
large language models (LLMs)
title Conversational LLM-Based Decision Support for Defect Classification in AFM Images
title_full Conversational LLM-Based Decision Support for Defect Classification in AFM Images
title_fullStr Conversational LLM-Based Decision Support for Defect Classification in AFM Images
title_full_unstemmed Conversational LLM-Based Decision Support for Defect Classification in AFM Images
title_short Conversational LLM-Based Decision Support for Defect Classification in AFM Images
title_sort conversational llm based decision support for defect classification in afm images
topic atomic force microscopy (AFM)
conversational LLM
image defect classification
large language models (LLMs)
url https://ieeexplore.ieee.org/document/11096088/
work_keys_str_mv AT angonabiswas conversationalllmbaseddecisionsupportfordefectclassificationinafmimages
AT jaydeeprade conversationalllmbaseddecisionsupportfordefectclassificationinafmimages
AT nabilamasud conversationalllmbaseddecisionsupportfordefectclassificationinafmimages
AT mdhasibulhasanhasib conversationalllmbaseddecisionsupportfordefectclassificationinafmimages
AT adityabalu conversationalllmbaseddecisionsupportfordefectclassificationinafmimages
AT juntaozhang conversationalllmbaseddecisionsupportfordefectclassificationinafmimages
AT soumiksarkar conversationalllmbaseddecisionsupportfordefectclassificationinafmimages
AT adarshkrishnamurthy conversationalllmbaseddecisionsupportfordefectclassificationinafmimages
AT juanren conversationalllmbaseddecisionsupportfordefectclassificationinafmimages
AT anweshasarkar conversationalllmbaseddecisionsupportfordefectclassificationinafmimages