-
Nature Medicine May 2021Machine learning techniques have great potential to improve medical diagnostics, offering ways to improve accuracy, reproducibility and speed, and to ease workloads for... (Review)
Review
Machine learning techniques have great potential to improve medical diagnostics, offering ways to improve accuracy, reproducibility and speed, and to ease workloads for clinicians. In the field of histopathology, deep learning algorithms have been developed that perform similarly to trained pathologists for tasks such as tumor detection and grading. However, despite these promising results, very few algorithms have reached clinical implementation, challenging the balance between hope and hype for these new techniques. This Review provides an overview of the current state of the field, as well as describing the challenges that still need to be addressed before artificial intelligence in histopathology can achieve clinical value.
Topics: Algorithms; Deep Learning; Humans; Pathology, Molecular; Precision Medicine
PubMed: 33990804
DOI: 10.1038/s41591-021-01343-4 -
Current Opinion in Oncology May 2021Pathology is the cornerstone of cancer care. Pathomics, which represents the use of artificial intelligence in digital pathology, is an emerging and promising field that... (Review)
Review
PURPOSE OF REVIEW
Pathology is the cornerstone of cancer care. Pathomics, which represents the use of artificial intelligence in digital pathology, is an emerging and promising field that will revolutionize medical and surgical pathology in the coming years. This review provides an overview of pathomics, its current and future applications and its most relevant applications in Head and Neck cancer care.
RECENT FINDINGS
The number of studies investigating the use of artificial intelligence in pathology is rapidly growing, especially as the utilization of deep learning has shown great potential with Whole Slide Images. Even though numerous steps still remain before its clinical use, Pathomics has been used for varied applications comprising of computer-assisted diagnosis, molecular anomalies prediction, tumor microenvironment and biomarker identification as well as prognosis evaluation. The majority of studies were performed on the most frequent cancers, notably breast, prostate, and lung. Interesting results were also found in Head and Neck cancers.
SUMMARY
Even if its use in Head and Neck cancer care is still low, Pathomics is a powerful tool to improve diagnosis, identify prognostic factors and new biomarkers. Important challenges lie ahead before its use in a clinical practice, notably the lack of information on how AI makes its decisions, the slow deployment of digital pathology, and the need for extensively validated data in order to obtain authorities approval. Regardless, pathomics will most likely improve pathology in general, including Head and Neck cancer care in the coming years.
Topics: Artificial Intelligence; Biomarkers, Tumor; Head and Neck Neoplasms; Humans; Image Processing, Computer-Assisted; Pathology; Tumor Microenvironment
PubMed: 33782358
DOI: 10.1097/CCO.0000000000000731 -
Advances in Anatomic Pathology Jul 2018There have been rapid and significant advances in diagnostic and predictive molecular techniques in recent years with profound impact on patient care. In situ... (Review)
Review
There have been rapid and significant advances in diagnostic and predictive molecular techniques in recent years with profound impact on patient care. In situ hybridization (ISH) studies have become well entrenched in surgical pathology practice and their role in the evaluation of HER2 in breast carcinoma and their diagnostic utility in soft tissue pathology are well known. Fluorescent ISH is being increasingly used in other sites such as the head and neck and the gynecologic tract. Like most tests in surgical pathology, ISH studies require good quality tissue, correlation with clinical and histopathologic findings, and adherence to guidelines for optimal assay performance and interpretation. Although ISH studies are largely performed in tertiary centers, the tissue is often processed by a variety of laboratories and the referring pathologists are required to discuss the need, relevance, and significance of these tests and the results with their clinical colleagues. Here we review the predictive and diagnostic utility of fluorescent ISH studies in a variety of organ systems, the preanalytical factors that may affect the results, and the pitfalls in the interpretation that all practicing surgical pathologists should be aware of.
Topics: Biomarkers, Tumor; Humans; In Situ Hybridization, Fluorescence; Neoplasms; Pathology, Surgical
PubMed: 29727321
DOI: 10.1097/PAP.0000000000000194 -
American Journal of Clinical Pathology May 2022The value of consultation in pathology has been well documented in surgical pathology, but there are few comprehensive studies of consultation cases in cytopathology.... (Review)
Review
OBJECTIVES
The value of consultation in pathology has been well documented in surgical pathology, but there are few comprehensive studies of consultation cases in cytopathology. Here we report our experience with cytopathology consultation cases at a large academic center.
METHODS
A review of consultation cases at our institution was performed by searching our laboratory information system. The contributing institution's diagnosis was compared with that rendered by the reviewing cytopathologist to assess major and/or minor diagnostic discrepancies.
RESULTS
In total, 928 cases were reviewed with the following distribution: fine-needle aspiration (FNA, 79.4%), exfoliative nongynecologic cytology (18.3%), and cases with both FNA and nongynecologic cytology (2.3%). There were 379 (40.8%) true consults and 549 (59.2%) confirming consults. A total of 586 (63.1%) cases were in agreement with the outside pathologist, 78 (8.4%) cases had major discrepancies, and 264 (28.4%) cases had minor discrepancies. Major discrepancies were most common for pancreas (38.5%), lymph node (11.5%), and soft tissue sites (9.0%).
CONCLUSIONS
Of the cases, 8.4% had major diagnostic discrepancies between the original diagnosis and the consultation diagnosis, which is consistent with reported values in surgical pathology consultation studies. The findings support the importance of second-opinion consultation in cytopathology to guide patient care.
Topics: Biopsy, Fine-Needle; Cytodiagnosis; Humans; Pancreas; Pathology, Surgical; Referral and Consultation
PubMed: 34724037
DOI: 10.1093/ajcp/aqab182 -
Journal of Clinical Apheresis Dec 2017Physicians from diverse training backgrounds practice apheresis medicine. Pathology residents' exposure to apheresis may vary depending on which department performs...
INTRODUCTION
Physicians from diverse training backgrounds practice apheresis medicine. Pathology residents' exposure to apheresis may vary depending on which department performs these procedures. Milestones for Apheresis education were published in 2012, but the degree of utilization in residency curriculum development is unknown. This study describes the current state of apheresis education for pathology residents.
METHODS
We sent a 15 question electronic survey to 141 pathology programs identified through the American Medical Association Residency and Fellowship Database.
RESULTS
Forty-three (30.5%) of the 141 programs responded. Pathology performed apheresis procedures in 29 (67.4%) programs. In the remaining 14 programs, apheresis was performed by nephrology (10), hematology (4), and a regional blood center (1); in one program, both nephrology and hematology performed apheresis procedures. For combined anatomic and clinical pathology (AP/CP) residents, 26 of 28 (93%) were required to train in apheresis medicine when pathology performed the procedures compared to only 5 of 14 (36%) when they were performed by another department (P = 0.0002). For CP-only residents, 18 of 19 (95%) were required to train in apheresis medicine when pathology performed the procedures compared to 5 of 7 (71%) when they were performed by another department (P = 0.1669). Thirty (68.9%) respondents had a written apheresis medicine curriculum. Seventeen (39.5%) of the 43 respondents were aware of the Milestones for Apheresis education, and 8 (18.6%) used the milestones in creating their apheresis curriculum.
CONCLUSIONS
The pathology department performed apheresis procedures in two-thirds of pathology residency programs surveyed. AP/CP residents were more likely to be required to train in apheresis medicine if the pathology department performed these procedures at their institution. Apheresis medicine practitioners should review the Milestones for Apheresis education with their residency program director to optimize learning and clinical skills development.
Topics: Adult; Blood Component Removal; Clinical Competence; Curriculum; Education, Medical, Graduate; Female; Humans; Internship and Residency; Male; Pathology; Surveys and Questionnaires; Young Adult
PubMed: 28485096
DOI: 10.1002/jca.21531 -
JAMA Pediatrics Nov 2023Currently, the diagnostic yield of exome sequencing (ES) and chromosomal microarray analysis (CMA) for short stature cohorts is uncertain. Despite previous studies...
IMPORTANCE
Currently, the diagnostic yield of exome sequencing (ES) and chromosomal microarray analysis (CMA) for short stature cohorts is uncertain. Despite previous studies reporting the widespread use of ES and CMA, a definitive diagnostic yield has not been established.
OBJECTIVE
To investigate the diagnostic yield of ES and CMA in short stature.
DATA SOURCES
A systematic literature search was conducted using relevant keywords in 3 databases (PubMed, Embase, and Web of Science) in February 2023.
STUDY SELECTION
Eligible studies for meta-analysis were those that had at least 10 participants with short stature who were diagnosed using either ES or CMA and the number of diagnosed patients was reported. Of 5222 identified studies, 20 were eventually included in the study.
DATA EXTRACTION AND SYNTHESIS
Two independent investigators extracted relevant information from each study, which was then synthesized using proportional meta-analysis to obtain the overall diagnostic yield of ES and CMA.
MAIN OUTCOMES AND MEASURES
The primary outcome measure was to determine the overall diagnostic yield of ES and CMA. A subgroup meta-analysis was also performed to assess if the diagnostic yield varied depending on whether ES was used as a first-tier or last-resort test. Additionally, a meta-regression was carried out to investigate how the diagnostic yield varied over time.
RESULTS
Twenty studies were included, comprising 1350 patients with short stature who underwent ES and 1070 patients who completed CMA. The overall diagnostic yield of ES among the cohorts and CMA among the cohorts was found to be 27.1% (95% CI, 18.1%-37.2%) and 13.6% (95% CI, 9.2%-18.7%), respectively. No statistically significant difference was observed between the first-tier (27.8%; 95% CI, 15.7%-41.8%) and last-resort groups (25.6%; 95% CI, 13.6%-39.6%) (P = .83) or in the percentage of positively diagnosed patients over time. No statistically significant difference was observed between the first-tier (27.8%; 95% CI, 15.7%-41.8%) and last-resort groups (25.6%; 95% CI, 13.6%-39.6%) (P = .83) or in the percentage of positively diagnosed patients over time.
CONCLUSION AND RELEVANCE
This systematic review and meta-analysis provides high-level evidence supporting the diagnostic efficacy of ES and CMA in patients with short stature. The findings serve as a solid reference for clinicians when making informed decisions about recommending these genetic tests.
Topics: Humans; Exome Sequencing; Pathology, Molecular; Genetic Testing; Microarray Analysis
PubMed: 37695591
DOI: 10.1001/jamapediatrics.2023.3566 -
Langenbeck's Archives of Surgery Jul 2015Due to a tremendous organ shortage, livers from donors with extended criteria are increasingly considered for transplantation. Pathologists are more and more requested... (Review)
Review
BACKGROUND
Due to a tremendous organ shortage, livers from donors with extended criteria are increasingly considered for transplantation. Pathologists are more and more requested to evaluate these livers histopathologically using frozen sections at high urgency for acceptability.
METHODS
This article reviews the current knowledge on pre-transplant histology in liver transplantation. Prerequisites and conditions for proper pre-transplant evaluation of donor liver tissue are discussed as well as frozen section evaluation and reporting. Data sources include the relevant medical literature, web sites specialized in organ transplantation, and the authors' experiences in liver transplant centers.
CONCLUSIONS
Pre-transplant histopathological evaluation is a time-effective, accurate, and reliable tool to assess liver quality from candidate deceased donors. Pre-transplant biopsies are of value in the selection of donor livers for transplantation, especially in case of extended criteria donors, and should be performed more frequently in order to avoid unnecessary loss of organs suitable for transplantation and transplantation of inappropriate organs. Correlation of histopathological findings with clinical conditions is essential and requires excellent communication between pathologists, surgeons, and the other members of the transplant team.
Topics: Biopsy; Donor Selection; Frozen Sections; Humans; Liver; Liver Transplantation; Pathology, Surgical; Tissue Donors; Tissue and Organ Harvesting
PubMed: 25809015
DOI: 10.1007/s00423-015-1298-7 -
Forensic Science International Jan 2022Identification by STR analysis of bones is time-consuming, mainly due to the lengthy decalcification required and complex DNA extraction process. To streamline this...
Identification by STR analysis of bones is time-consuming, mainly due to the lengthy decalcification required and complex DNA extraction process. To streamline this process, we developed a direct STR typing protocol from bone samples. We optimized bone sample amounts using femur and tibia and two commercial PCR kits (Identifiler™ Plus and IDplex Plus kits). Optimally, 100 mg of bone powder in 300 µL PBS buffer was heated at 98 °C for three minutes to produce a supernatant for DNA amplification. IDplex Plus performed better than Identifiler™ Plus in terms of allele recovery and peak height. Fifteen samples of each of seven bone elements (1st distal phalange of hand, capitate, femur, metacarpal 4, patella, talus, and tibia; N = 105) were then subjected to direct STR typing with the optimized protocol, and 94.3% were high partial to full profiles. The performance of the developed protocol was similar for all bone elements. Median peak heights were significantly better in profiles of cancellous bone than compact bone (p = 0.033) and significantly different across the bone elements (p < 0.001). Ten casework samples from various conditions and up to 7-year-PMI were subjected to both direct STR and conventional STR typing. No significant difference in the number of alleles was seen (95% HDI of -13.5 to 5.15). As well as being rapid, convenient, and safe, the protocol could help improve STR typing from bones.
Topics: DNA; DNA Fingerprinting; Forensic Pathology; Humans; Microsatellite Repeats; Patella; Polymerase Chain Reaction
PubMed: 34794063
DOI: 10.1016/j.forsciint.2021.111099 -
European Journal of Radiology Apr 2017Background Postmortem imaging has been used for more than a century as a complement to medico-legal autopsies. The technique has also emerged as a possible alternative... (Review)
Review
Background Postmortem imaging has been used for more than a century as a complement to medico-legal autopsies. The technique has also emerged as a possible alternative to compensate for the continuous decline in the number of clinical autopsies. To evaluate the diagnostic accuracy of postmortem imaging for various types of findings, we performed this systematic literature review. Data sources The literature search was performed in the databases PubMed, Embase and Cochrane Library through January 7, 2015. Relevant publications were assessed for risk of bias using the QUADAS tool and were classified as low, moderate or high risk of bias according to pre-defined criteria. Autopsy and/or histopathology were used as reference standard. Findings The search generated 2600 abstracts, of which 340 were assessed as possibly relevant and read in full-text. After further evaluation 71 studies were finally included, of which 49 were assessed as having high risk of bias and 22 as moderate risk of bias. Due to considerable heterogeneity - in populations, techniques, analyses and reporting - of included studies it was impossible to combine data to get a summary estimate of the diagnostic accuracy of the various findings. Individual studies indicate, however, that imaging techniques might be useful for determining organ weights, and that the techniques seem superior to autopsy for detecting gas Conclusions and Implications In general, based on the current scientific literature, it was not possible to determine the diagnostic accuracy of postmortem imaging and its usefulness in conjunction with, or as an alternative to autopsy. To correctly determine the usefulness of postmortem imaging, future studies need improved planning, improved methodological quality and larger materials, preferentially obtained from multi-center studies.
Topics: Adolescent; Adult; Aged; Autopsy; Child; Diagnostic Imaging; Epidemiologic Methods; Forensic Pathology; Humans; Middle Aged; Young Adult
PubMed: 28089245
DOI: 10.1016/j.ejrad.2016.08.003 -
Virchows Archiv : An International... Aug 2019Machine learning techniques, especially deep learning techniques such as convolutional neural networks, have been successfully applied to general image recognitions... (Review)
Review
Machine learning techniques, especially deep learning techniques such as convolutional neural networks, have been successfully applied to general image recognitions since their overwhelming performance at the 2012 ImageNet Large Scale Visual Recognition Challenge. Recently, such techniques have also been applied to various medical, including histopathological, images to assist the process of medical diagnosis. In some cases, deep learning-based algorithms have already outperformed experienced pathologists for recognition of histopathological images. However, pathological images differ from general images in some aspects, and thus, machine learning of histopathological images requires specialized learning methods. Moreover, many pathologists are skeptical about the ability of deep learning technology to accurately recognize histopathological images because what the learned neural network recognizes is often indecipherable to humans. In this review, we first introduce various applications incorporating machine learning developed to assist the process of pathologic diagnosis, and then describe machine learning problems related to histopathological image analysis, and review potential ways to solve these problems.
Topics: Humans; Machine Learning; Pathology, Clinical
PubMed: 31222375
DOI: 10.1007/s00428-019-02594-w