-
European Journal of Cancer (Oxford,... Sep 2023Convolutional neural networks (CNNs) have outperformed dermatologists in classifying pigmented skin lesions under artificial conditions. We investigated, for the first...
Diagnostic performance of augmented intelligence with 2D and 3D total body photography and convolutional neural networks in a high-risk population for melanoma under real-world conditions: A new era of skin cancer screening?
BACKGROUND
Convolutional neural networks (CNNs) have outperformed dermatologists in classifying pigmented skin lesions under artificial conditions. We investigated, for the first time, the performance of three-dimensional (3D) and two-dimensional (2D) CNNs and dermatologists in the early detection of melanoma in a real-world setting.
METHODS
In this prospective study, 1690 melanocytic lesions in 143 patients with high-risk criteria for melanoma were evaluated by dermatologists, 2D-FotoFinder-ATBM and 3D-Vectra WB360 total body photography (TBP). Excision was based on the dermatologists' dichotomous decision, an elevated CNN risk score (study-specific malignancy cut-off: FotoFinder >0.5, Vectra >5.0) and/or the second dermatologist's assessment with CNN support. The diagnostic accuracy of the 2D and 3D CNN classification was compared with that of the dermatologists and the augmented intelligence based on histopathology and dermatologists' assessment. Secondary end-points included reproducibility of risk scores and naevus counts per patient by medical staff (gold standard) compared to automated 3D and 2D TBP CNN counts.
RESULTS
The sensitivity, specificity, and receiver operating characteristics area under the curve (ROC-AUC) for risk-score-assessments compared to histopathology of 3D-CNN with 95% confidence intervals (CI) were 90.0%, 64.6% and 0.92 (CI 0.85-1.00), respectively. While dermatologists and augmented intelligence achieved the same sensitivity (90%) and comparable classification ROC-AUC (0.91 [CI 0.80-1.00], 0.88 [CI 0.77-1.00]) with 3D-CNN, their specificity was superior (92.3% and 86.2%, respectively). The 2D-CNN (sensitivity: 70%, specificity: 40%, ROC-AUC: 0.68 [CI 0.46-0.90]) was outperformed by 3D CNN and dermatologists. The 3D-CNN showed a higher correlation coefficient for repeated measurements of 246 lesions (R = 0.89) than the 2D-CNN (R = 0.79). The mean naevus count per patient varied significantly (gold standard: 210 lesions; 3D-CNN: 469; 2D-CNN: 1324; p < 0.0001).
CONCLUSIONS
Our study emphasises the importance of validating the classification of CNNs in real life. The novel 3D-CNN device outperformed the 2D-CNN and achieved comparable sensitivity with dermatologists. The low specificity of CNNs and the lack of automated counting of TBP nevi currently limit the use of augmented intelligence in clinical practice.
Topics: Humans; Reproducibility of Results; Prospective Studies; Dermatologists; Early Detection of Cancer; Skin Neoplasms; Melanoma; Neural Networks, Computer; Nevus; Nevus, Pigmented; Risk Factors; Photography
PubMed: 37453242
DOI: 10.1016/j.ejca.2023.112954 -
Medicine and Pharmacy Reports Jul 2023To evaluate the performance of magnetic resonance imaging (MRI) in restaging locally advanced rectal cancers (LARC) after neoadjuvant chemoradiotherapy (nCRT), with...
BACKGROUND AND AIMS
To evaluate the performance of magnetic resonance imaging (MRI) in restaging locally advanced rectal cancers (LARC) after neoadjuvant chemoradiotherapy (nCRT), with pathologic correlation.
METHODS
80 patients with LARC treated with neoadjuvant therapy, with restaging MRI and surgery, were enrolled and prospectively reviewed. The diagnostic accuracy of the restaging MRI was assessed for tumor (ymrT), nodal status (ymrN), circumferential resection margin (ymrCRM), extramural vascular invasion (ymrEMVI) and tumoral deposits (ymrN1c) by calculating the sensitivity (Se), specificity (Sp), negative predictive values (NPV) and positive predictive values (PPV). Response to treatment was classified as good response (complete/near complete) vs. poor response (poor/partial response). The agreement between the tumor regression grade at MRI (mrTRG) and pathology (pTRG) was reported, as well the performance of mrTRG to identify good responders. The correlation between restaging MRI and histopathology was assessed by Spearman correlation coefficient.
RESULTS
The MRI accuracy ranged between 63.8% and 92.5% for T stage and was 81.3% for N stage. All MRI parameters evaluated at restaging were statistically significant correlated with histopathology evaluation, but EMVI. There was moderate correlation for N and N1c and a positive strong correlation for T, CRM and TRG (Spearman correlation coefficient of 0.390 for mrN1c-pN1c, 0.428 for mrN-pN, 0.522 for mrCRM-pCRM, 0.550 for mrT-pT and 0.731 for mrTRG-pTRG). Diagnostic accuracy of anal sphincter invasion was 91.3%, with a negative predictive value (NPV) of 100%. Accuracy rate varied between 70% for partial response to 93.75% for complete response after nCRT.
CONCLUSIONS
MR imaging had good accuracy in restaging LARCs after nCRT. Our results showed high MRI accuracy in detecting anal sphincter involvement for low rectal tumors, with high NPV to exclude tumoral invasion. Restaging MRI predicted well the tumor regression grade, with good diagnostic performance in differentiating good responders from poor/partial responders. The accuracy was high for detecting complete response.
PubMed: 37577010
DOI: 10.15386/mpr-2542 -
Journal of Translational Medicine Sep 2023Heart diseases are among the leading causes of death worldwide, many of which lead to pathological cardiomyocyte hypertrophy and capillary rarefaction in both patients...
BACKGROUND
Heart diseases are among the leading causes of death worldwide, many of which lead to pathological cardiomyocyte hypertrophy and capillary rarefaction in both patients and animal models, the quantification of which is both technically challenging and highly time-consuming. Here we developed a semiautomated pipeline for quantification of the size of cardiomyocytes and capillary density in cardiac histology, termed HeartJ, by generating macros in ImageJ, a broadly used, open-source, Java-based software.
METHODS
We have used modified Gomori silver staining, which is easy to perform and digitize in high throughput, or Fluorescein-labeled lectin staining. The latter can be easily combined with other stainings, allowing additional quantitative analysis on the same section, e.g., the size of cardiomyocyte nuclei, capillary density, or single-cardiomyocyte protein expression. We validated the pipeline in a mouse model of cardiac hypertrophy induced by transverse aortic constriction, and in autopsy samples of patients with and without aortic stenosis.
RESULTS
In both animals and humans, HeartJ-based histology quantification revealed significant hypertrophy of cardiomyocytes reflecting other parameters of hypertrophy and rarefaction of microvasculature and enabling the analysis of protein expression in individual cardiomyocytes. The analysis also revealed that murine and human cardiomyocytes had similar diameters in health and extent of hypertrophy in disease confirming the translatability of our murine cardiac hypertrophy model. HeartJ enables a rapid analysis that would not be feasible by manual methods. The pipeline has little hardware requirements and is freely available.
CONCLUSIONS
In summary, our analysis pipeline can facilitate effective and objective quantitative histological analyses in preclinical and clinical heart samples.
Topics: Humans; Animals; Mice; Myocytes, Cardiac; Aortic Valve Stenosis; Cell Nucleus; Disease Models, Animal; Cardiomegaly
PubMed: 37752535
DOI: 10.1186/s12967-023-04544-2 -
PloS One 2023The liver, the most important metabolic organ of the body, performs a wide variety of vital functions. Hepatic cell injury occurs by the activation of reactive oxygen...
INTRODUCTION
The liver, the most important metabolic organ of the body, performs a wide variety of vital functions. Hepatic cell injury occurs by the activation of reactive oxygen species (ROS) that are generated by carbon tetrachloride (CCl4), xenobiotics, and other toxic substances through cytochrome P450-dependent steps resulting from the covalent bond formation with lipoproteins and nucleic acids. Observing the urgent state of hepatotoxic patients worldwide, different medicinal plants and their properties can be explored to combat such free radical damage to the liver. In vivo and in silico studies were designed and conducted to evaluate the antioxidant and hepatoprotective properties of Gynura procumbens in rats.
MATERIALS AND METHODS
Gynura procumbens leaves were collected and extracted using 70% ethanol. The required chemicals CCl4, standard drug (silymarin), and blood serum analysis kits were stocked. The in vivo tests were performed in 140 healthy Wister albino rats of either sex under well-controlled parameters divided into 14 groups, strictly maintaining Institutional Animal Ethics Committee (IEAC) protocols. For the histopathology study, 10% buffered neutral formalin was used for organ preservation. Later the specimens were studied under a fluorescence microscope. In silico molecular docking and absorption, distribution, metabolism, excretion, and toxicity (ADMET) studies were performed, and the results were analyzed statistically.
RESULTS AND DISCUSSION
Gynura procumbens partially negate the deleterious effect of carbon tetrachloride on normal weight gain in rats. The elevated level of serum glutamate pyruvate transaminase (SGPT), serum glutamate oxaloacetate transaminase (SGOT), alkaline phosphatase (ALP), creatinine, LDH, total cholesterol (TC), low-density lipoprotein (LDL), triglycerides (TG), malondialdehyde (MDA), deoxyribonucleic acid (DNA) fragmentation ranges, gamma-glutamyl transferase (γ-GT) in CCl4 treated groups were decreased by both standard drug silymarin and G. procumbens leaf extract. We have found significant & highly significant changes statistically for different doses, here p<0.05 & p<0.01, respectively. On the other hand, G. procumbens and silymarin displayed Statistically significant (p<0.05) and high significant(p<0.01) increased levels of HDL, CAT SOD (here p<0.05 & p<0.01 for different doses) when the treatment groups were compared with the disease control group. Because the therapeutic activity imparted by plants and drugs accelerates the movement of the disturbed pathophysiological state toward the healthy state. In the molecular docking analysis, G. procumbens phytoconstituents performed poorly against transforming growth factor-beta 1 (TGF-β1) compared to the control drug silymarin. In contrast, 26 phytoconstituents scored better than the control bezafibrate against peroxisome proliferator-activated receptor alpha (PPAR-α). The top scoring compounds for both macromolecules were observed to form stable complexes in the molecular dynamics simulations. Flavonoids and phenolic compounds performed better than other constituents in providing hepatoprotective activity. It can, thus, be inferred that the extract of G. procumbens showed good hepatoprotective properties in rats.
Topics: Animals; Rats; Rats, Wistar; Carbon Tetrachloride; Molecular Docking Simulation; Alanine Transaminase; Asteraceae; Chemical and Drug Induced Liver Injury; Glutamates
PubMed: 37713406
DOI: 10.1371/journal.pone.0291125 -
Histopathology Dec 2023Myeloid/lymphoid neoplasms with eosinophilia (M/LN-eo) and tyrosine kinase (TK) gene fusions are a rare group of haematopoietic neoplasms with a broad range of clinical... (Review)
Review
Myeloid/lymphoid neoplasms with eosinophilia and tyrosine kinase fusion genes: A workshop report with focus on novel entities and a literature review including paediatric cases.
Myeloid/lymphoid neoplasms with eosinophilia (M/LN-eo) and tyrosine kinase (TK) gene fusions are a rare group of haematopoietic neoplasms with a broad range of clinical and morphological presentations. Paediatric cases have increasingly been recognised. Importantly, not all appear as a chronic myeloid neoplasm and eosinophilia is not always present. In addition, standard cytogenetic and molecular methods may not be sufficient to diagnose M/LN-eo due to cytogenetically cryptic aberrations. Therefore, additional evaluation with fluorescence in-situ hybridisation and other molecular genetic techniques (array-based comparative genomic hybridisation, RNA sequencing) are recommended for the identification of specific TK gene fusions. M/LN-eo with JAK2 and FLT3-rearrangements and ETV6::ABL1 fusion were recently added as a formal member to this category in the International Consensus Classification (ICC) and the 5th edition of the WHO classification (WHO-HAEM5). In addition, other less common defined genetic alterations involving TK genes have been described. This study is an update on M/LN-eo with TK gene fusions with focus on novel entities, as illustrated by cases submitted to the Bone Marrow Workshop, organised by the European Bone Marrow Working Group (EBMWG) within the frame of the 21st European Association for Haematopathology congress (EAHP-SH) in Florence 2022. A literature review was performed including paediatric cases of M/LN-eo with TK gene fusions.
Topics: Humans; Child; Myeloproliferative Disorders; Eosinophilia; Lymphoma; Bone Marrow; Hematologic Neoplasms; Oncogene Proteins, Fusion
PubMed: 37551450
DOI: 10.1111/his.15021 -
Journal of Veterinary Diagnostic... Jul 2024Telepathology, as a subset of teleconsulting, is pathology interpretation performed at a distance. Telepathology is not a new phenomenon, but since ~2015, significant... (Review)
Review
Telepathology, as a subset of teleconsulting, is pathology interpretation performed at a distance. Telepathology is not a new phenomenon, but since ~2015, significant advances in information technology and telecommunications coupled with the pandemic have led to unprecedented sophistication, accessibility, and use of telepathology in human and veterinary medicine. Furthermore, telepathology can connect veterinary practices to distant laboratories and provide support for underserved animals and communities. Through our scoping review, we provide an overview of how telepathology is being used in veterinary medicine, identify gaps in the literature, and highlight future areas of research and service development. We searched MEDLINE, CAB Abstracts, and the gray literature, and included all relevant literature. Despite the widespread use of digital microscopy in large veterinary diagnostic laboratories, we identified a paucity of literature describing the use of telepathology in veterinary medicine, with a significant gap in studies addressing the validation of whole-slide imaging for primary diagnosis. Underutilization of telepathology to support postmortem examinations conducted in the field was also identified, which indicates a potential area for service development. The use of telepathology is increasing in veterinary medicine, and pathologists must keep pace with the changing technology, ensure the validation of innovative technologies, and identify novel uses to advance the profession.
Topics: Animals; Veterinary Medicine; Telepathology; Pathology, Veterinary
PubMed: 38742388
DOI: 10.1177/10406387241241270 -
JAMA Network Open Jul 2023Ultrasonography-based risk models can help nonexpert clinicians evaluate adnexal lesions and reduce surgical interventions for benign tumors. Yet, these models have...
IMPORTANCE
Ultrasonography-based risk models can help nonexpert clinicians evaluate adnexal lesions and reduce surgical interventions for benign tumors. Yet, these models have limited uptake in the US, and studies comparing their diagnostic accuracy are lacking.
OBJECTIVE
To evaluate, in a US cohort, the diagnostic performance of 3 ultrasonography-based risk models for differentiating between benign and malignant adnexal lesions: International Ovarian Tumor Analysis (IOTA) Simple Rules with inconclusive cases reclassified as malignant or reevaluated by an expert, IOTA Assessment of Different Neoplasias in the Adnexa (ADNEX), and Ovarian-Adnexal Reporting and Data System (O-RADS).
DESIGN, SETTING, AND PARTICIPANTS
This retrospective diagnostic study was conducted at a single US academic medical center and included consecutive patients aged 18 to 89 years with adnexal masses that were managed surgically or conservatively between January 2017 and October 2022.
EXPOSURE
Evaluation of adnexal lesions using the Simple Rules, ADNEX, and O-RADS.
MAIN OUTCOMES AND MEASURES
The main outcome was diagnostic performance, including area under the receiver operating characteristic (ROC) curve (AUC), sensitivity, specificity, positive and negative predictive values, and positive and negative likelihood ratios. Surgery or follow-up were reference standards. Secondary analyses evaluated the models' performances stratified by menopause status and race.
RESULTS
The cohort included 511 female patients with a 15.9% malignant tumor prevalence (81 patients). Mean (SD) ages of patients with benign and malignant adnexal lesions were 44.1 (14.4) and 52.5 (15.2) years, respectively, and 200 (39.1%) were postmenopausal. In the ROC analysis, the AUCs for discriminative performance of the ADNEX and O-RADS models were 0.96 (95% CI, 0.93-0.98) and 0.92 (95% CI, 0.90-0.95), respectively. After converting the ADNEX continuous individualized risk into the discrete ordinal categories of O-RADS, the ADNEX performance was reduced to an AUC of 0.93 (95% CI, 0.90-0.96), which was similar to that for O-RADS. The Simple Rules combined with expert reevaluation had 93.8% sensitivity (95% CI, 86.2%-98.0%) and 91.9% specificity (95% CI, 88.9%-94.3%), and the Simple Rules combined with malignant classification had 93.8% sensitivity (95% CI, 86.2%-98.0%) and 88.1% specificity (95% CI, 84.7%-91.0%). At a 10% risk threshold, ADNEX had 91.4% sensitivity (95% CI, 83.0%-96.5%) and 86.3% specificity (95% CI, 82.7%-89.4%) and O-RADS had 98.8% sensitivity (95% CI, 93.3%-100%) and 74.4% specificity (95% CI, 70.0%-78.5%). The specificities of all models were significantly lower in the postmenopausal group. Subgroup analysis revealed high performances independent of race.
CONCLUSIONS AND RELEVANCE
In this diagnostic study of a US cohort, the Simple Rules, ADNEX, and O-RADS models performed well in differentiating between benign and malignant adnexal lesions; this outcome has been previously reported primarily in European populations. Risk stratification models can lead to more accurate and consistent evaluations of adnexal masses, especially when used by nonexpert clinicians, and may reduce unnecessary surgeries.
Topics: Humans; Female; Retrospective Studies; Sensitivity and Specificity; Ovarian Neoplasms; Adnexal Diseases; Ultrasonography
PubMed: 37440228
DOI: 10.1001/jamanetworkopen.2023.23289 -
BMC Medical Education Nov 2023Oral histopathology is a bridge course connecting oral basic medicine and clinical dentistry. However, the application of outcomes-based education via flipped classroom...
INTRODUCTION
Oral histopathology is a bridge course connecting oral basic medicine and clinical dentistry. However, the application of outcomes-based education via flipped classroom (FC) in oral histopathology has not been well explored. This study has assessed the efficacy of outcomes-based education via FC in undergraduate oral histopathology module learning in Nanjing Medical University of China.
MATERIALS AND METHODS
A total of 214 third-year students were enrolled and assigned to the FC group of the batch 2022-23 (n = 110) and the traditional classroom (TC) group of the batch 2021-22 (n = 104) to participate the oral histopathology sessions respectively in the study. The FC group were required to preview the online course materials pre-class, followed by in-class quizz, in-class interactive group discussion, and slides microscopic observation. The outcomes-based formative and summative assessments for FC were designed. The TC group attended traditional laboratory class for the same glass slides microscopic observation. In addition, a questionnaire was performed to investigate the satisfaction of learning. Along with this, the performances of FC group in written theory tests and oral histopathology slide tests were compared with TC group.
RESULTS
Students in the FC group gained significantly final higher scores of the course than those in the TC group (score: 83.79 ± 11 vs. 76.73 ± 10.93, P<0.0001). Data from the student questionnaires indicated a preference for outcomes-based module education via FC. In the questionnaires, most students considered outcomes-based module education via FC to be beneficial to learning motivation, knowledge comprehension, critical thinking and teamwork. FC group had a higher level of satisfaction with oral histopathology teaching than TC group (satisfaction score: 4.599 ± 0.1027 vs. 4.423 ± 0.01366, P<0.01).
CONCLUSION
An outcomes-based module education via FC has a promising effect on undergraduate oral histopathology education.
Topics: Humans; Learning; Students; Thinking; Motivation; Surveys and Questionnaires; Problem-Based Learning; Curriculum
PubMed: 37946163
DOI: 10.1186/s12909-023-04753-9 -
Skin Research and Technology : Official... Jan 2024There are no standards for evaluating skin photoaging. Dermoscopy is a non-invasive detection method that might be useful for evaluating photoaging.
BACKGROUND
There are no standards for evaluating skin photoaging. Dermoscopy is a non-invasive detection method that might be useful for evaluating photoaging.
OBJECTIVE
To assess the correlation between the dermoscopic evaluation of photoaging and clinical and pathological evaluations.
METHODS
The age, clinical evaluation (Fitzpatrick classification, Glogau Photoaging Classification, and Chung's standardized image ruler), histopathology (Masson staining and MMP-1 immunohistochemistry), and dermoscopy (Hu's and Isik's) of 40 donor skin samples were analyzed statistically, and Spearman rank correlation analysis was performed.
RESULTS
There was a robust correlation between the total Hu scores and Isik dermoscopy. The correlation of dermoscopy with histopathology was higher than that of clinical evaluation methods. There is a strong correlation between telangiectases and lentigo. Xerosis, superficial wrinkle, diffuse erythema, telangiectases, and reticular pigmentation were significantly correlated with the three clinical evaluation methods. Superficial wrinkles were correlated with Masson, MMP-1, various clinical indicators, and other dermoscopic items.
CONCLUSION
There is a good correlation between dermoscopy and clinical and histopathological examination. Dermoscopy might help evaluate skin photoaging.
Topics: Humans; Skin Aging; Matrix Metalloproteinase 1; Dermoscopy; Lentigo; Telangiectasis; Skin Neoplasms
PubMed: 38221782
DOI: 10.1111/srt.13578 -
Cancer Medicine Aug 2023Endoscopic ultrasonography-guided fine-needle aspiration/biopsy (EUS-FNA/B) is considered to be a first-line procedure for the pathological diagnosis of pancreatic...
BACKGROUND AND AIMS
Endoscopic ultrasonography-guided fine-needle aspiration/biopsy (EUS-FNA/B) is considered to be a first-line procedure for the pathological diagnosis of pancreatic cancer owing to its high accuracy and low complication rate. The number of new cases of pancreatic ductal adenocarcinoma (PDAC) is increasing, and its accurate pathological diagnosis poses a challenge for cytopathologists. Our aim was to develop a hyperspectral imaging (HSI)-based convolution neural network (CNN) algorithm to aid in the diagnosis of pancreatic EUS-FNA cytology specimens.
METHODS
HSI images were captured of pancreatic EUS-FNA cytological specimens from benign pancreatic tissues (n = 33) and PDAC (n = 39) prepared using a liquid-based cytology method. A CNN was established to test the diagnostic performance, and Attribution Guided Factorization Visualization (AGF-Visualization) was used to visualize the regions of important classification features identified by the model.
RESULTS
A total of 1913 HSI images were obtained. Our ResNet18-SimSiam model achieved an accuracy of 0.9204, sensitivity of 0.9310 and specificity of 0.9123 (area under the curve of 0.9625) when trained on HSI images for the differentiation of PDAC cytological specimens from benign pancreatic cells. AGF-Visualization confirmed that the diagnoses were based on the features of tumor cell nuclei.
CONCLUSIONS
An HSI-based model was developed to diagnose cytological PDAC specimens obtained using EUS-guided sampling. Under the supervision of experienced cytopathologists, we performed multi-staged consecutive in-depth learning of the model. Its superior diagnostic performance could be of value for cytologists when diagnosing PDAC.
Topics: Humans; Endoscopic Ultrasound-Guided Fine Needle Aspiration; Cytology; Deep Learning; Pancreatic Neoplasms; Carcinoma, Pancreatic Ductal
PubMed: 37455599
DOI: 10.1002/cam4.6335