-
The American Journal of Pathology Sep 2019With the rapid development of image scanning techniques and visualization software, whole slide imaging (WSI) is becoming a routine diagnostic method. Accelerating... (Review)
Review
With the rapid development of image scanning techniques and visualization software, whole slide imaging (WSI) is becoming a routine diagnostic method. Accelerating clinical diagnosis from pathology images and automating image analysis efficiently and accurately remain significant challenges. Recently, deep learning algorithms have shown great promise in pathology image analysis, such as in tumor region identification, metastasis detection, and patient prognosis. Many machine learning algorithms, including convolutional neural networks, have been proposed to automatically segment pathology images. Among these algorithms, segmentation deep learning algorithms such as fully convolutional networks stand out for their accuracy, computational efficiency, and generalizability. Thus, deep learning-based pathology image segmentation has become an important tool in WSI analysis. In this review, the pathology image segmentation process using deep learning algorithms is described in detail. The goals are to provide quick guidance for implementing deep learning into pathology image analysis and to provide some potential ways of further improving segmentation performance. Although there have been previous reviews on using machine learning methods in digital pathology image analysis, this is the first in-depth review of the applications of deep learning algorithms for segmentation in WSI analysis.
Topics: Algorithms; Deep Learning; Diagnostic Imaging; Humans; Image Processing, Computer-Assisted; Pathology, Clinical
PubMed: 31199919
DOI: 10.1016/j.ajpath.2019.05.007 -
JAMA Dec 2017Application of deep learning algorithms to whole-slide pathology images can potentially improve diagnostic accuracy and efficiency. (Comparative Study)
Comparative Study
IMPORTANCE
Application of deep learning algorithms to whole-slide pathology images can potentially improve diagnostic accuracy and efficiency.
OBJECTIVE
Assess the performance of automated deep learning algorithms at detecting metastases in hematoxylin and eosin-stained tissue sections of lymph nodes of women with breast cancer and compare it with pathologists' diagnoses in a diagnostic setting.
DESIGN, SETTING, AND PARTICIPANTS
Researcher challenge competition (CAMELYON16) to develop automated solutions for detecting lymph node metastases (November 2015-November 2016). A training data set of whole-slide images from 2 centers in the Netherlands with (n = 110) and without (n = 160) nodal metastases verified by immunohistochemical staining were provided to challenge participants to build algorithms. Algorithm performance was evaluated in an independent test set of 129 whole-slide images (49 with and 80 without metastases). The same test set of corresponding glass slides was also evaluated by a panel of 11 pathologists with time constraint (WTC) from the Netherlands to ascertain likelihood of nodal metastases for each slide in a flexible 2-hour session, simulating routine pathology workflow, and by 1 pathologist without time constraint (WOTC).
EXPOSURES
Deep learning algorithms submitted as part of a challenge competition or pathologist interpretation.
MAIN OUTCOMES AND MEASURES
The presence of specific metastatic foci and the absence vs presence of lymph node metastasis in a slide or image using receiver operating characteristic curve analysis. The 11 pathologists participating in the simulation exercise rated their diagnostic confidence as definitely normal, probably normal, equivocal, probably tumor, or definitely tumor.
RESULTS
The area under the receiver operating characteristic curve (AUC) for the algorithms ranged from 0.556 to 0.994. The top-performing algorithm achieved a lesion-level, true-positive fraction comparable with that of the pathologist WOTC (72.4% [95% CI, 64.3%-80.4%]) at a mean of 0.0125 false-positives per normal whole-slide image. For the whole-slide image classification task, the best algorithm (AUC, 0.994 [95% CI, 0.983-0.999]) performed significantly better than the pathologists WTC in a diagnostic simulation (mean AUC, 0.810 [range, 0.738-0.884]; P < .001). The top 5 algorithms had a mean AUC that was comparable with the pathologist interpreting the slides in the absence of time constraints (mean AUC, 0.960 [range, 0.923-0.994] for the top 5 algorithms vs 0.966 [95% CI, 0.927-0.998] for the pathologist WOTC).
CONCLUSIONS AND RELEVANCE
In the setting of a challenge competition, some deep learning algorithms achieved better diagnostic performance than a panel of 11 pathologists participating in a simulation exercise designed to mimic routine pathology workflow; algorithm performance was comparable with an expert pathologist interpreting whole-slide images without time constraints. Whether this approach has clinical utility will require evaluation in a clinical setting.
Topics: Algorithms; Breast Neoplasms; Female; Humans; Lymphatic Metastasis; Machine Learning; Pathologists; Pathology, Clinical; ROC Curve
PubMed: 29234806
DOI: 10.1001/jama.2017.14585 -
Wiener Medizinische Wochenschrift (1946) Sep 2021Dementia is the clinical consequence of various neurological disorders with a multitude of etiologies. Precise knowledge of the underlying pathologies is essential for... (Review)
Review
Dementia is the clinical consequence of various neurological disorders with a multitude of etiologies. Precise knowledge of the underlying pathologies is essential for an accurate treatment of patients and for the development of suitable disease biomarkers. A definite diagnosis of many of the disorders, particularly for neurodegenerative ones, can only be made after a thorough postmortem neuropathological examination. This highlights the importance of performing a brain autopsy and the relevance of a close interaction between clinicians, neuroimaging disciplines and neuropathologists as well as with basic researchers. This article aims to give a brief overview on the neuropathology of dementia focusing on neurodegenerative diseases, to further facilitate interdisciplinary collaboration.
Topics: Autopsy; Brain; Dementia; Humans; Neurodegenerative Diseases; Neuropathology
PubMed: 34129141
DOI: 10.1007/s10354-021-00848-4 -
Analytical Chemistry Oct 2019Fourier transform-infrared spectroscopy (FT-IR) represents an attractive molecular diagnostic modality for translation to the clinic, where comprehensive chemical... (Review)
Review
Fourier transform-infrared spectroscopy (FT-IR) represents an attractive molecular diagnostic modality for translation to the clinic, where comprehensive chemical profiling of biological samples may revolutionize a myriad of pathways in clinical settings. Principally, FT-IR provides a rapid, cost-effective platform to obtain a molecular fingerprint of clinical samples based on vibrational transitions of chemical bonds upon interaction with infrared light. To date, considerable research activities have demonstrated competitive to superior performance of FT-IR strategies in comparison to conventional techniques, with particular promise for earlier, accessible disease diagnostics, thereby improving patient outcomes. However, amidst the changing healthcare landscape in times of aging populations and increased prevalence of cancer and chronic disease, routine adoption of FT-IR within clinical laboratories has remained elusive. Hence, this perspective shall outline the significant clinical potential of FT-IR diagnostics and subsequently address current barriers to translation from the perspective of all stakeholders, in the context of biofluid, histopathology, cytology, microbiology, and biomarker discovery frameworks. Thereafter, future perspectives of FT-IR for healthcare will be discussed, with consideration of recent technological advances that may facilitate future clinical translation.
Topics: Bacterial Infections; Biomarkers; Body Fluids; Humans; Pathology, Clinical; Precision Medicine; Spectroscopy, Fourier Transform Infrared; Translational Research, Biomedical
PubMed: 31503460
DOI: 10.1021/acs.analchem.9b02280 -
American Journal of Clinical Pathology Apr 2016To describe the strengths and limitations of the available influenza diagnostics, with a focus on rapid antigen detection assays and nucleic acid detection assays. (Review)
Review
OBJECTIVES
To describe the strengths and limitations of the available influenza diagnostics, with a focus on rapid antigen detection assays and nucleic acid detection assays.
METHODS
A case-based presentation is used to illustrate the potential limitations of rapid antigen detection assays for influenza.
RESULTS
Influenza is a seasonal illness; estimates attribute influenza to approximately 200,000 hospitalizations and 41,000 deaths in the United States annually. Antigen detection assays for influenza are rapid and convenient, and thus are widely used in a variety of health care settings, even though the sensitivity of these assays may be suboptimal. The United States Food and Drug Administration has recently created new guidelines intended to improve the oversight and performance characteristics of influenza antigen detection assays. Molecular assays, although more costly and complex, are more sensitive and may be designed to simultaneously detect multiple respiratory pathogens within a single assay.
CONCLUSIONS
Diagnostic assays for influenza can vary greatly with regards to analytical performance characteristics, complexity, turnaround time and cost. This can have important patient care and infection prevention implications.
Topics: Humans; Influenza, Human; Molecular Diagnostic Techniques; Pathology, Clinical; Referral and Consultation
PubMed: 27124947
DOI: 10.1093/ajcp/aqw039 -
Turk Patoloji Dergisi 2023In Turkey, autopsy performers, namely forensic medicine practitioners, are neither pathologists nor have properly received pathology training during residency in...
OBJECTIVE
In Turkey, autopsy performers, namely forensic medicine practitioners, are neither pathologists nor have properly received pathology training during residency in contrast to the Anglo-Saxon model of forensic medicine practices, since the current curriculum of forensic medicine residency lacks adequate training in post-mortem histopathology. Likewise, pathologists lack a specific post-mortem pathology clerkship. In this study, we intended to determine whether forensic physicians in Turkey find themselves competent in post-mortem histopathology or were adequately trained during their residencies.
MATERIAL AND METHOD
Turkish forensic medicine practitioners were administered an online questionnaire whereby self-evaluations of their histopathology knowledge and their views on histopathology training during forensic medicine residency were assessed. The 151 physicians who completed the questionnaire made up the study group.
RESULTS
It was found out that the majority of Turkish forensic medicine practitioners (85.4%) did not find the histopathology training during their residency adequate. Similarly, 85.4% of the participants indicated their incompetence in histopathological examination of post-mortem tissue of any kind, and showed their willingness for further training in pathology. 66.9% strongly agreed that post-mortem histopathology requires training that is distinct from surgical pathology. In case of providing post-mortem histopathology training within the scope of forensic medicine residency, topics such as microscopic morphology of post-mortem changes, histological changes related to injuries, and estimation of wound age are expected to be beneficial to 88.7% 83.4%, and 83.4% of the participants respectively.
CONCLUSION
The current curriculum should be revised in a way that the surgical pathology clerkship meets forensic physicians' needs, so that they can then refer more difficult, non-routine histopathological consultations to pathologists who are also well-trained in postmortem histopathology. Consideration should also be given to establishing a subspecialty training - a master's or doctoral degree programs in forensic pathology.
Topics: Humans; Autopsy; Forensic Medicine; Pathologists; Pathology, Surgical; Turkey
PubMed: 35102540
DOI: 10.5146/tjpath.2022.01569 -
Military Medical Research Mar 2022Traditional diagnostic strategies for infectious disease detection require benchtop instruments that are inappropriate for point-of-care testing (POCT). Emerging... (Review)
Review
Traditional diagnostic strategies for infectious disease detection require benchtop instruments that are inappropriate for point-of-care testing (POCT). Emerging microfluidics, a highly miniaturized, automatic, and integrated technology, are a potential substitute for traditional methods in performing rapid, low-cost, accurate, and on-site diagnoses. Molecular diagnostics are widely used in microfluidic devices as the most effective approaches for pathogen detection. This review summarizes the latest advances in microfluidics-based molecular diagnostics for infectious diseases from academic perspectives and industrial outlooks. First, we introduce the typical on-chip nucleic acid processes, including sample preprocessing, amplification, and signal read-out. Then, four categories of microfluidic platforms are compared with respect to features, merits, and demerits. We further discuss application of the digital assay in absolute nucleic acid quantification. Both the classic and recent microfluidics-based commercial molecular diagnostic devices are summarized as proof of the current market status. Finally, we propose future directions for microfluidics-based infectious disease diagnosis.
Topics: Communicable Diseases; Humans; Lab-On-A-Chip Devices; Microfluidic Analytical Techniques; Microfluidics; Pathology, Molecular
PubMed: 35300739
DOI: 10.1186/s40779-022-00374-3 -
Archives of Pathology & Laboratory... Aug 2019Fatal dermatologic diseases and ones with high morbidity can occur in the inpatient setting. In such cases, prompt and accurate assessment of a bedside skin biopsy is... (Review)
Review
CONTEXT.—
Fatal dermatologic diseases and ones with high morbidity can occur in the inpatient setting. In such cases, prompt and accurate assessment of a bedside skin biopsy is required. This may be challenging for many pathologists who are not familiar with the complexity of skin pathology and skin terminology within the fields of dermatopathology and dermatology.
OBJECTIVE.—
To provide the pathologist with a practical, up-to-date, and "must-know" reference guide on dermatologic urgencies and emergencies from a real-world perspective, highlighting diagnostic pearls, diagnostic pitfalls, and commonly encountered practice gaps. This review will focus on key diseases with which every pathologist should be familiar, including angioinvasive fungal infections, Stevens-Johnson syndrome/toxic epidermal necrolysis, staph-scalded-skin syndrome, acute graft-versus-host disease, bullous pemphigoid, calciphylaxis, Sweet syndrome and its histiocytoid variant, pyoderma gangrenosum, and leukocytoclastic vasculitis, as well as those in their clinical and histopathologic differential.
DATA SOURCES.—
This review is based on peer-reviewed literature and our personal experiences with these diseases at major academic institutions, including one where a large number of stem cell transplants are performed. This review is unique as it represents collaborative expert opinion from both a dermatopathology and a dermatology standpoint.
CONCLUSIONS.—
This review outlines the critical role that the pathologist plays in the outcomes of patients with dermatologic urgencies and emergencies. Improved patient care will result from prompt and accurate histopathologic diagnoses as well as an open line of communication with the dermatologist.
Topics: Acute Disease; Biopsy; Dermatology; Graft vs Host Disease; Hematopoietic Stem Cell Transplantation; Humans; Pathologists; Pathology, Clinical; Skin; Skin Diseases
PubMed: 30785787
DOI: 10.5858/arpa.2018-0239-RA -
Clinical Neuropathology 2012Nerve biopsy is a valuable tool in the diagnostic work-up of peripheral neuropathies. Currently, major indications include interstitial pathologies such as suspected... (Review)
Review
Nerve biopsy is a valuable tool in the diagnostic work-up of peripheral neuropathies. Currently, major indications include interstitial pathologies such as suspected vasculitis and amyloidosis, atypical cases of inflammatory neuropathy and the differential diagnosis of hereditary neuropathies that cannot be specified otherwise. However, surgical removal of a piece of nerve causes a sensory deficit and - in some cases - chronic pain. Therefore, a nerve biopsy is usually performed only when other clinical, laboratory and electrophysiological methods have failed to clarify the cause of disease. The neuropathological work-up should include at least paraffin and resin semithin histology using a panel of conventional and immunohistochemical stains. Cryostat section staining, teased fiber preparations, electron microscopy and molecular genetic analyses are potentially useful additional methods in a subset of cases. Being performed, processed and read by experienced physicians and technicians nerve biopsies can provide important information relevant for clinical management.
Topics: Biopsy; Histocytological Preparation Techniques; Humans; Neurology; Pathology, Clinical; Peripheral Nerves; Peripheral Nervous System Diseases; Practice Guidelines as Topic; Specimen Handling
PubMed: 22192700
DOI: 10.5414/np300468 -
Modern Pathology : An Official Journal... Apr 2019The interpretation of muscle biopsies is complex and provides the most useful information when integrated with the clinical presentation of the patient. These biopsies... (Review)
Review
The interpretation of muscle biopsies is complex and provides the most useful information when integrated with the clinical presentation of the patient. These biopsies are performed for workup of a wide range of diseases including dystrophies, metabolic diseases, and inflammatory processes. Recent insights have led to changes in the classification of inflammatory myopathies and have changed the role that muscle biopsies have in the workup of inherited diseases. These changes will be reviewed. This review follows a morphology-driven approach by discussing diseases of skeletal muscle based on a few basic patterns that include cases with (1) active myopathic damage and inflammation, (2) active myopathic damage without associated inflammation, (3) chronic myopathic changes, (4) myopathies with distinctive inclusions or vacuoles, (5) biopsies mainly showing atrophic changes, and (6) biopsies that appear normal on routine preparations. Each of these categories goes along with certain diagnostic considerations and pitfalls. Individual biopsy features are only rarely pathognomonic. Establishing a firm diagnosis therefore typically requires integration of all of the biopsy findings and relevant clinical information. With this approach, a muscle biopsy can often provide helpful information in the diagnostic workup of patients presenting with neuromuscular problems.
Topics: Biopsy; Humans; Muscle, Skeletal; Muscular Diseases; Pathology, Clinical
PubMed: 30401945
DOI: 10.1038/s41379-018-0164-x