Deep learning approaches and applications in toxicologic histopathology: Current status and future perspectives
Whole slide imaging enables the use of a wide array of digital image analysis tools that are revolutionizing pathology. Recent advances in digital pathology and deep convolutional neural networks have created an enormous opportunity to improve workflow efficiency, provide more quantitative, objectiv...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2021-01-01
|
| Series: | Journal of Pathology Informatics |
| Subjects: | |
| Online Access: | http://www.jpathinformatics.org/article.asp?issn=2153-3539;year=2021;volume=12;issue=1;spage=42;epage=42;aulast=Mehrvar |
| _version_ | 1811233250729787392 |
|---|---|
| author | Shima Mehrvar Lauren E Himmel Pradeep Babburi Andrew L Goldberg Magali Guffroy Kyathanahalli Janardhan Amanda L Krempley Bhupinder Bawa |
| author_facet | Shima Mehrvar Lauren E Himmel Pradeep Babburi Andrew L Goldberg Magali Guffroy Kyathanahalli Janardhan Amanda L Krempley Bhupinder Bawa |
| author_sort | Shima Mehrvar |
| collection | DOAJ |
| description | Whole slide imaging enables the use of a wide array of digital image analysis tools that are revolutionizing pathology. Recent advances in digital pathology and deep convolutional neural networks have created an enormous opportunity to improve workflow efficiency, provide more quantitative, objective, and consistent assessments of pathology datasets, and develop decision support systems. Such innovations are already making their way into clinical practice. However, the progress of machine learning - in particular, deep learning (DL) - has been rather slower in nonclinical toxicology studies. Histopathology data from toxicology studies are critical during the drug development process that is required by regulatory bodies to assess drug-related toxicity in laboratory animals and its impact on human safety in clinical trials. Due to the high volume of slides routinely evaluated, low-throughput, or narrowly performing DL methods that may work well in small-scale diagnostic studies or for the identification of a single abnormality are tedious and impractical for toxicologic pathology. Furthermore, regulatory requirements around good laboratory practice are a major hurdle for the adoption of DL in toxicologic pathology. This paper reviews the major DL concepts, emerging applications, and examples of DL in toxicologic pathology image analysis. We end with a discussion of specific challenges and directions for future research. |
| first_indexed | 2024-04-12T11:17:54Z |
| format | Article |
| id | doaj.art-6b8c2a277adc427bafccc947cc650b17 |
| institution | Directory Open Access Journal |
| issn | 2153-3539 |
| language | English |
| last_indexed | 2024-04-12T11:17:54Z |
| publishDate | 2021-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of Pathology Informatics |
| spelling | doaj.art-6b8c2a277adc427bafccc947cc650b172022-12-22T03:35:27ZengElsevierJournal of Pathology Informatics2153-35392021-01-01121424210.4103/jpi.jpi_36_21Deep learning approaches and applications in toxicologic histopathology: Current status and future perspectivesShima MehrvarLauren E HimmelPradeep BabburiAndrew L GoldbergMagali GuffroyKyathanahalli JanardhanAmanda L KrempleyBhupinder BawaWhole slide imaging enables the use of a wide array of digital image analysis tools that are revolutionizing pathology. Recent advances in digital pathology and deep convolutional neural networks have created an enormous opportunity to improve workflow efficiency, provide more quantitative, objective, and consistent assessments of pathology datasets, and develop decision support systems. Such innovations are already making their way into clinical practice. However, the progress of machine learning - in particular, deep learning (DL) - has been rather slower in nonclinical toxicology studies. Histopathology data from toxicology studies are critical during the drug development process that is required by regulatory bodies to assess drug-related toxicity in laboratory animals and its impact on human safety in clinical trials. Due to the high volume of slides routinely evaluated, low-throughput, or narrowly performing DL methods that may work well in small-scale diagnostic studies or for the identification of a single abnormality are tedious and impractical for toxicologic pathology. Furthermore, regulatory requirements around good laboratory practice are a major hurdle for the adoption of DL in toxicologic pathology. This paper reviews the major DL concepts, emerging applications, and examples of DL in toxicologic pathology image analysis. We end with a discussion of specific challenges and directions for future research.http://www.jpathinformatics.org/article.asp?issn=2153-3539;year=2021;volume=12;issue=1;spage=42;epage=42;aulast=Mehrvardeep learningdigital image analysishistopathologymachine learningpreclinical safetytoxicologic pathologywhole slide imaging |
| spellingShingle | Shima Mehrvar Lauren E Himmel Pradeep Babburi Andrew L Goldberg Magali Guffroy Kyathanahalli Janardhan Amanda L Krempley Bhupinder Bawa Deep learning approaches and applications in toxicologic histopathology: Current status and future perspectives Journal of Pathology Informatics deep learning digital image analysis histopathology machine learning preclinical safety toxicologic pathology whole slide imaging |
| title | Deep learning approaches and applications in toxicologic histopathology: Current status and future perspectives |
| title_full | Deep learning approaches and applications in toxicologic histopathology: Current status and future perspectives |
| title_fullStr | Deep learning approaches and applications in toxicologic histopathology: Current status and future perspectives |
| title_full_unstemmed | Deep learning approaches and applications in toxicologic histopathology: Current status and future perspectives |
| title_short | Deep learning approaches and applications in toxicologic histopathology: Current status and future perspectives |
| title_sort | deep learning approaches and applications in toxicologic histopathology current status and future perspectives |
| topic | deep learning digital image analysis histopathology machine learning preclinical safety toxicologic pathology whole slide imaging |
| url | http://www.jpathinformatics.org/article.asp?issn=2153-3539;year=2021;volume=12;issue=1;spage=42;epage=42;aulast=Mehrvar |
| work_keys_str_mv | AT shimamehrvar deeplearningapproachesandapplicationsintoxicologichistopathologycurrentstatusandfutureperspectives AT laurenehimmel deeplearningapproachesandapplicationsintoxicologichistopathologycurrentstatusandfutureperspectives AT pradeepbabburi deeplearningapproachesandapplicationsintoxicologichistopathologycurrentstatusandfutureperspectives AT andrewlgoldberg deeplearningapproachesandapplicationsintoxicologichistopathologycurrentstatusandfutureperspectives AT magaliguffroy deeplearningapproachesandapplicationsintoxicologichistopathologycurrentstatusandfutureperspectives AT kyathanahallijanardhan deeplearningapproachesandapplicationsintoxicologichistopathologycurrentstatusandfutureperspectives AT amandalkrempley deeplearningapproachesandapplicationsintoxicologichistopathologycurrentstatusandfutureperspectives AT bhupinderbawa deeplearningapproachesandapplicationsintoxicologichistopathologycurrentstatusandfutureperspectives |