Informatics, digital & computational pathology

Artificial intelligence

Computer aided diagnosis



Last author update: 5 October 2023
Last staff update: 5 October 2023

Copyright: 2020-2024, PathologyOutlines.com, Inc.

PubMed Search: Computer aided diagnosis

Kunal Nagpal, M.S.
Yun Liu, Ph.D.
Page views in 2024 to date: 22
Cite this page: Nagpal K, Chen PHC, Steiner DF, Mermel C, Liu Y. Computer aided diagnosis. PathologyOutlines.com website. https://www.pathologyoutlines.com/topic/informaticscompaiddiagnosis.html. Accessed March 29th, 2024.
Definition / general
Essential features
  • Computer aided diagnosis algorithms that interpret histologic findings need to be validated using rigorous reference standards
  • A thoughtfully designed user interface is needed to effectively assist in diagnosis
  • Systems need to be seamlessly integrated into the diagnostic workflow
Key components
  • An effective computer aided diagnosis tool typically requires (Am J Surg Pathol 2018;42:1636)
    • An accurate classification algorithm
    • Thoughtful user interface that may be quite different than that for a computer aided detection tool
    • Integration with existing workflows
  • Algorithm: typically a machine learning approach based on feature engineering or more recently, convolutional neural networks (CNNs)
  • User interface: due to the subjective nature of image interpretation and imperfections in models, an effective user interface may leverage
    • Explanations: why the algorithm interpreted an image in a certain way
    • Interactive tools: to allow a pathologist to correct algorithm predictions while benefiting from other features, such as quantitation
Terminology
  • Computer aided diagnosis: refers to a technology or system that interprets findings on medical images, such as tumor grade
  • Computer aided detection: refers to a technology or system to detect findings of interest on medical images, typically with the goal of reducing the false negative rate, improving efficiency or reducing fatigue
  • Model: the machine learning algorithm underlying the computer aided diagnosis system
  • Reference standard: the standard against which the model is evaluated (JAMA 2019;322:1806)
  • Calibration: in addition to categorizations such as yes / no, computer systems generally also produce continuous probabilities
  • Calibration refers to whether these probabilities match real world rates
    • For example: among 100 examples predicted to be cancer with a probability of 0.2, are ~20% of them actually cancer? (JAMA 2017;318:1377)
Applications
  • While comparison of automated system accuracy to pathologist accuracy has been promising, more work describing integration into pathologist workflows and impact on diagnosis is necessary
  • Breast carcinoma: classification of grade, ER status, histologic subtype and intrinsic subtype (NPJ Breast Cancer 2018;4:30)
    • Key takeaway: convolutional neural network based automated system achieved > 75% accuracy at each of these tasks
    • Reference standard: central pathologic review, with immunohistochemical staining for determination of ER status
  • Colon polyps: classification of polyps (hyperplastic, sessile serrated, traditional serrated, tubular or tubulovillious / villious) (J Pathol Inform 2017;8:30)
    • Key takeaway: convolutional neural network based automated system achieved > 90% accuracy in these classifications
    • Reference standard: initial review by 2 pathologists and adjudication with a third senior pathologist in cases of disagreement
  • Lung carcinoma: classification of histological subtype (Nat Med 2018;24:1559)
    • Key takeaway: convolutional neural network based automated system trended toward greater accuracy than pathologists in classifying lung cancer resections as adenocarcinoma or squamous cell carcinoma
    • Reference standard: diagnostic review with central pathologic confirmation
  • Prostate adenocarcinoma: Gleason grading (Nat Med 2022;28:154, Lancet Oncol 2020;21:233, Lancet Oncol 2020;21:222, JAMA Oncol 2020;6:1372)
    • Key takeaway: convolutional neural network based system graded resections or tissue microarrays with similar or greater accuracy than general or expert pathologists and trended toward better risk stratification
    • Use of algorithm as an assistive tool resulted in higher interpathologist agreement and high concordance with urologic pathologist reference standard (JAMA Netw Open 2020;3:e2023267, Mod Pathol 2021;34:660)
    • Reference standard: subspecialist provided grades and clinical outcomes
  • Lymphoma: evaluation of automated systems for lymphoma classification and several other tasks (J Pathol Inform 2016;7:29)
    • Key takeaway: convolutional neural network based automated system achieved 97% accuracy in distinguishing between chronic lymphocytic leukemia, follicular lymphoma and mantle cell lymphoma for region subsections of whole slide images
    • Reference standard: curated dataset provided by expert pathologists
  • Skin lesions: 3 classification tasks as basal cell carcinoma, dermal nevi and seborrheic keratosis (J Pathol Inform 2018;9:32)
    • Key takeaway: convolutional neural network based automated system achieved > 0.99 area under the curve (AUC) in diagnosing the class of interest versus distractors
    • Reference standard: prior diagnoses by pathologists
  • Renal cell carcinoma: nuclear grading for clear cell renal cell carcinoma (J Pathol Inform 2014;5:23)
    • Key takeaway: support vector machine (SVM) based system can help distinguish low and high grade tumors with an AUC of 0.97
    • Reference standard: grades from an experienced subspecialty pathologist
  • Liver cancer classification
    • Key takeaway: deep learning system for liver cancer classification used as an assistant tool improved agreement with subspecialists, with a notable finding that when the model's prediction was incorrect, assistance had a negative impact on accuracy (NPJ Digit Med 2020;3:23)
Implementation
  • Similar to computer aided detection, use of systems for computer aided diagnosis requires algorithm development, inference and integration into pathology workflows (Arch Pathol Lab Med 2020;144:221)
  • Evaluation of computer aided diagnosis systems can present challenges relative to computer aided detection due to the inherent subjectivity of image interpretation
  • Algorithms can be evaluated against
    • Pathologist provided annotations
    • Independent gold standard (such as a molecular test)
    • Clinical outcomes
  • If pathologist provided annotations are used as the reference standard, steps should be taken to reduce variability from subjective interpretation and improve reproducibility of the study (Cancer 2001;91:1284, Arch Pathol Lab Med 2001;125:736, Eur Urol 2013;64:199)
    • Having experienced experts with subspecialist training and substantial clinical experience provide annotations
    • Using the consensus opinion of multiple experts
  • Subanalyses may be useful to evaluate performance differences based on
    • Characteristics of the population being evaluated, such as patient population or disease subtype
    • Sensitivity to preanalytic variables such as surgical or staining protocol, imaging hardware and software postprocessing such as image compression (Nat Med 2019;25:1301, Arch Pathol Lab Med 2019;143:859)
Advantages
  • Improves accuracy or consistency by classifying findings in a way that is more concordant with a rigorous reference standard
  • Reduces the workload of technicians and pathologists by flagging suspicious slides for review (Clin Transl Sci 2021;14:86, Med Phys 2013;40:087001)
Limitations
  • Evaluation of computer aided diagnosis systems can present challenges relative to computer aided detection due to the inherent subjectivity of image interpretation
  • Algorithms can be evaluated against
    • Pathologist provided annotations
    • Independent gold standard (such as a molecular test)
    • Clinical outcomes
  • If pathologist provided annotations are used as the reference standard, steps should be taken to reduce variability from subjective interpretation and improve reproducibility of the study (Cancer 2001;91:1284, Arch Pathol Lab Med 2001;125:736, Eur Urol 2013;64:199)
    • Having experienced experts with subspecialist training and substantial clinical experience provide annotations
    • Using the consensus opinion of multiple experts
Future changes
  • There are many promising image analysis algorithms, as briefly and nonexhaustively summarized above
  • The key next steps are
    • Reference standard improvements: though much of the work so far has focused on classification compared to an existing grading system or molecular test, future work will need to focus on directly predicting clinical outcomes in order to improve patient risk stratification (Med Phys 2013;40:087001)
    • Workflow integration: better understanding of how to integrate artificial intelligence algorithms into the actual workflow
    • User interface: thoughtful optimization of the user interface such that pathologists can effectively integrate insights from algorithm predictions to improve diagnostic accuracy
    • Measuring impact: studies to quantify the benefits of using computer aided diagnosis devices in pathology and to assess if there are negative consequences such as overdiagnosis or underdiagnosis
    • Continuous monitoring: similar to postmarketing safety surveillance for approved drugs, computer aided diagnosis systems should be monitored in real use for quality control purposes
Board review style question #1
    Which of the following is a difference between computer aided detection (CADe) systems and computer aided diagnosis systems?

  1. CADe systems require a thoughtful user interface and integration pathology workflow, while computer aided diagnosis systems run in an automated manner
  2. Computer aided diagnosis systems assist in characterization or interpretation of histology, while computer aided detection systems assist in detection of findings
  3. Computer aided diagnosis systems need to be validated against rigorous reference standards, while CADe systems do not
  4. Computer aided diagnosis systems require an algorithm to assist with diagnosis, while computer aided detection systems do not
Board review style answer #1
B. Computer aided diagnosis systems assist in characterization or interpretation of histology, while computer aided detection systems assist in detection of findings. Computer aided diagnosis systems in pathology share many similarities with computer aided detection (CADe) systems but focus on characterization and interpretation rather than detection. Answer A is incorrect because both CADe and computer aided diagnosis systems require a thoughtfully designed user interface. Answers C and D are incorrect because both systems must be validated against rigorous reference standards and require an algorithm.

Comment Here

Reference: Computer aided diagnosis
Board review style question #2
    Which of the following is a typical goal in application of computer aided diagnosis in pathology?

  1. Improve consistency by making reproducible classifications on subjective tasks
  2. Improve consistency by showing the current grading guidelines
  3. Improve exhaustive review by classifying all diagnostic features of histopathology images
  4. Remind a pathologist of workflow tasks
Board review style answer #2
A. Improve consistency by making reproducible classifications on subjective tasks. Computer aided diagnosis systems generally aim to improve diagnostic accuracy by improving consistency and making reproducible classifications on subjective tasks. Answer B is incorrect because the goal is not to show current grading guidelines but to improve the reproducibility of grading. Answer C is incorrect because the goal is to develop a better classification system for diagnostic entities, not for their features. Answer D is incorrect because the goal is to integrate artificial intelligence algorithms into the actual workflow, not to serve as a reminder system.

Comment Here

Reference: Computer aided diagnosis
Back to top
Image 01 Image 02