Feasibility study of ResNet-50 in the distinction of intraoral neural tumors using histopathological images.

BACKGROUND: Neural tumors are difficult to distinguish based solely on cellularity and often require immunohistochemical staining to aid in identifying the cell lineage. This article investigates the potential of a Convolutional Neural Network for the histopathological classification of the three most prevalent benign neural tumor types: neurofibroma, perineurioma, and schwannoma. METHODS: A model was developed, trained, and evaluated for classification using the ResNet-50 architecture, with a database of 30 whole-slide images stained in hematoxylin and eosin (106, 782 patches were generated from and divided among the training, validation, and testing subsets, with strategies to avoid data leakage). RESULTS: The model achieved an accuracy of 70% (64% normalized), and showed satisfactory results for differentiating two of the three classes, reaching approximately 97% and 77% as true positives for neurofibroma and schwannoma classes, respectively, and only 7% for perineurioma class. The AUROC curves for neurofibroma and schwannoma classes was 0.83%, and 0.74% for perineurioma. However, the specificity rate for the perineurioma class was greater (83%) than in the other two classes (neurofibroma with 61%, and schwannoma with 60%). CONCLUSION: This investigation demonstrated significant potential for proficient performance with a limitation regarding the perineurioma class (the limited feature variability observed contributed to a lower performance).

Artificial intelligence and radiomics in the diagnosis of intraosseous lesions of the gnathic bones: A systematic review.

BACKGROUND: The purpose of this systematic review (SR) is to gather evidence on the use of machine learning (ML) models in the diagnosis of intraosseous lesions in gnathic bones and to analyze the reliability, impact, and usefulness of such models. This SR was performed in accordance with the PRISMA 2022 guidelines and was registered in the PROSPERO database (CRD42022379298). METHODS: The acronym PICOS was used to structure the inquiry-focused review question "Is Artificial Intelligence reliable for the diagnosis of intraosseous lesions in gnathic bones?" The literature search was conducted in various electronic databases, including PubMed, Embase, Scopus, Cochrane Library, Web of Science, Lilacs, IEEE Xplore, and Gray Literature (Google Scholar and ProQuest). Risk of bias assessment was performed using PROBAST, and the results were synthesized by considering the task and sampling strategy of the dataset. RESULTS: Twenty-six studies were included (21 146 radiographic images). Ameloblastomas, odontogenic keratocysts, dentigerous cysts, and periapical cysts were the most frequently investigated lesions. According to TRIPOD, most studies were classified as type 2 (randomly divided). The F1 score was presented in only 13 studies, which provided the metrics for 20 trials, with a mean of 0.71 (±0.25). CONCLUSION: There is no conclusive evidence to support the usefulness of ML-based models in the detection, segmentation, and classification of intraosseous lesions in gnathic bones for routine clinical application. The lack of detail about data sampling, the lack of a comprehensive set of metrics for training and validation, and the absence of external testing limit experiments and hinder proper evaluation of model performance.

Oral manifestations of amyloidosis and the diagnostic applicability of oral tissue biopsy.

BACKGROUND: Amyloidosis exhibits a variable spectrum of systemic signs and oral manifestations that can be difficult to diagnose. This study aimed to characterize the clinical, demographic, and microscopic features of amyloidosis in the oral cavity. METHODS: This collaborative study involved three Brazilian oral pathology centers and described cases with a confirmed diagnosis of amyloidosis on available oral tissue biopsies. Clinical data were obtained from medical records. H&E, Congo-red, and immunohistochemically stained slides were analyzed. RESULTS: Twenty-six oral biopsies from 23 individuals (65.2% males; mean age: 59.6 years) were included. Oral involvement was the first sign of the disease in 67.0% of cases. Two patients had no clinical manifestation in the oral mucosa, although the histological analysis confirmed amyloid deposition. Amyloid deposits were distributed in perivascular (88.0%), periacinar and periductal (80.0%), perineurial (80.0%), endoneurial (33.3%), perimuscular (88.2%), intramuscular (94.1%), and subepithelial (35.3%) sites as well as around fat cells (100.0%). Mild/moderate inflammation was found in 65.4% of cases and 23.1% had giant cells. CONCLUSIONS: Amyloid deposits were consistently found in oral tissues, exhibiting distinct deposition patterns. Oral biopsy is less invasive than internal organ biopsy and enables the reliable identification of amyloid deposits even in the absence of oral manifestations. These findings corroborate the relevance of oral biopsy for the diagnosis of amyloidosis.

A primary oral mucosal melanoma of the hard palate with no recurrence: Report of a 10 years follow-up.

BACKGROUND: Primary oral mucosal melanoma (OMM) represents an extremely rare and aggressive tumor that arises from malignant transformation and clonal expansion of melanocytes in the oral cavity. The prognosis of patients affected by OMM is quite unfavorable, with survival rates lower than those described for patients with cutaneous melanoma. CASE REPORT: Here, we report a case of OMM in a 59-year-old Caucasian woman, who was referred for evaluation of a large asymptomatic pigmented lesion on the left side of the hard palate under the removable total denture. Incisional biopsy was performed, and histopathological analysis revealed the proliferation of spindle-shaped and pigmented epithelioid cells, with cellular pleomorphism. These cells were positive for Melan A, S-100, HMB-45, SOX-10, and Ki-67 confirming the diagnosis of OMM. The patient underwent partial maxillectomy and adjuvant radiotherapy. After treatment, she was rehabilitated with a palatal obturator prosthesis and has been in follow-up for 10 years with no evidence of disease. Due to the rarity in the oral cavity and the nonspecific signs and symptoms, the diagnosis of OMM is difficult and often overlooked. CONCLUSION: Therefore, multidisciplinary management from diagnosis, treatment, and rehabilitation is important to increase the expectation of cure.

The use of deep learning state-of-the-art architectures for oral epithelial dysplasia grading: A comparative appraisal.

BACKGROUND: Dysplasia grading systems for oral epithelial dysplasia are a source of disagreement among pathologists. Therefore, machine learning approaches are being developed to mitigate this issue. METHODS: This cross-sectional study included a cohort of 82 patients with oral potentially malignant disorders and correspondent 98 hematoxylin and eosin-stained whole slide images with biopsied-proven dysplasia. All whole-slide images were manually annotated based on the binary system for oral epithelial dysplasia. The annotated regions of interest were segmented and fragmented into small patches and non-randomly sampled into training/validation and test subsets. The training/validation data were color augmented, resulting in a total of 81,786 patches for training. The held-out independent test set enrolled a total of 4,486 patches. Seven state-of-the-art convolutional neural networks were trained, validated, and tested with the same dataset. RESULTS: The models presented a high learning rate, yet very low generalization potential. At the model development, VGG16 performed the best, but with massive overfitting. In the test set, VGG16 presented the best accuracy, sensitivity, specificity, and area under the curve (62%, 62%, 66%, and 65%, respectively), associated with the higher loss among all Convolutional Neural Networks (CNNs) tested. EfficientB0 has comparable metrics and the lowest loss among all convolutional neural networks, being a great candidate for further studies. CONCLUSION: The models were not able to generalize enough to be applied in real-life datasets due to an overlapping of features between the two classes (i.e., high risk and low risk of malignization).

Deep learning applied to the histopathological diagnosis of ameloblastomas and ameloblastic carcinomas.

BACKGROUND: Odontogenic tumors (OT) are composed of heterogeneous lesions, which can be benign or malignant, with different behavior and histology. Within this classification, ameloblastoma and ameloblastic carcinoma (AC) represent a diagnostic challenge in daily histopathological practice due to their similar characteristics and the limitations that incisional biopsies represent. From these premises, we wanted to test the usefulness of models based on artificial intelligence (AI) in the field of oral and maxillofacial pathology for differential diagnosis. The main advantages of integrating Machine Learning (ML) with microscopic and radiographic imaging is the ability to significantly reduce intra-and inter observer variability and improve diagnostic objectivity and reproducibility. METHODS: Thirty Digitized slides were collected from different diagnostic centers of oral pathology in Brazil. After performing manual annotation in the region of interest, the images were segmented and fragmented into small patches. In the supervised learning methodology for image classification, three models (ResNet50, DenseNet, and VGG16) were focus of investigation to provide the probability of an image being classified as class0 (i.e., ameloblastoma) or class1 (i.e., Ameloblastic carcinoma). RESULTS: The training and validation metrics did not show convergence, characterizing overfitting. However, the test results were satisfactory, with an average for ResNet50 of 0.75, 0.71, 0.84, 0.65, and 0.77 for accuracy, precision, sensitivity, specificity, and F1-score, respectively. CONCLUSIONS: The models demonstrated a strong potential of learning, but lack of generalization ability. The models learn fast, reaching a training accuracy of 98%. The evaluation process showed instability in validation; however, acceptable performance in the testing process, which may be due to the small data set. This first investigation opens an opportunity for expanding collaboration to incorporate more complementary data; as well as, developing and evaluating new alternative models.

Clinicians' perception of oral potentially malignant disorders: a pitfall for image annotation in supervised learning.

OBJECTIVE: The present study aims to quantify clinicians' perceptions of oral potentially malignant disorders (OPMDs) when evaluating, classifying, and manually annotating clinical images, as well as to understand the source of inter-observer variability when assessing these lesions. The hypothesis was that different interpretations could affect the quality of the annotations used to train a Supervised Learning model. STUDY DESIGN: Forty-six clinical images from 37 patients were reviewed, classified, and manually annotated at the pixel level by 3 labelers. We compared the inter-examiner assessment based on clinical criteria through the κ statistics (Fleiss's kappa). The segmentations were also compared using the mean pixel-wise intersection over union (IoU). RESULTS: The inter-observer agreement for homogeneous/non-homogeneous criteria was substantial (κ = 63, 95% CI: 0.47-0.80). For the subclassification of non-homogeneous lesions, the inter-observer agreement was moderate (κ = 43, 95% CI: 0.34-0.53) (P < .001). The mean IoU of 0.53 (±0.22) was considered low. CONCLUSION: The subjective clinical assessment (based on human visual observation, variable criteria that have suffered adjustments over the years, different educational backgrounds, and personal experience) may explain the source of inter-observer discordance for the classification and annotation of OPMD. Therefore, there is a strong probability of transferring the subjectivity of human analysis to artificial intelligence models. The use of large data sets and segmentation based on the union of all labelers' annotations holds the potential to overcome this limitation.

Machine learning for the prediction of toxicities from head and neck cancer treatment: A systematic review with meta-analysis.

INTRODUCTION: The aim of the present systematic review (SR) is to summarize Machine Learning (ML) models currently used to predict head and neck cancer (HNC) treatment-related toxicities, and to understand the impact of image biomarkers (IBMs) in prediction models (PMs). The present SR was conducted following the guidelines of the PRISMA 2022 and registered in PROSPERO database (CRD42020219304). METHODS: The acronym PICOS was used to develop the focused review question (Can PMs accurately predict HNC treatment toxicities?) and the eligibility criteria. The inclusion criteria enrolled Prediction Model Studies (PMSs) with patient cohorts that were treated for HNC and developed toxicities. Electronic database search encompassed PubMed, EMBASE, Scopus, Cochrane Library, Web of Science, LILACS, and Gray Literature (Google Scholar and ProQuest). Risk of Bias (RoB) was assessed through PROBAST and the results were synthesized based on the data format (with and without IBMs) to allow comparison. RESULTS: A total of 28 studies and 4,713 patients were included. Xerostomia was the most frequently investigated toxicity (17; 60.71 %). Sixteen (57.14 %) studies reported using radiomics features in combination with clinical or dosimetrics/dosiomics for modelling. High RoB was identified in 23 studies. Meta-analysis (MA) showed an area under the receiver operating characteristics curve (AUROC) of 0.82 for models with IBMs and 0.81 for models without IBMs (p value < 0.001), demonstrating no difference among IBM- and non-IBM-based models. DISCUSSION: The development of a PM based on sample-specific features represents patient selection bias and may affect a model's performance. Heterogeneity of the studies as well as non-standardized metrics prevent proper comparison of studies, and the absence of an independent/external test does not allow the evaluation of the model's generalization ability. CONCLUSION: IBM-featured PMs are not superior to PMs based on non-IBM predictors. The evidence was appraised as of low certainty.

Machine learning for detection and classification of oral potentially malignant disorders: A conceptual review.

Oral potentially malignant disorders represent precursor lesions that may undergo malignant transformation to oral cancer. There are many known risk factors associated with the development of oral potentially malignant disorders, and contribute to the risk of malignant transformation. Although many advances have been reported to understand the biological behavior of oral potentially malignant disorders, their clinical features that indicate the characteristics of malignant transformation are not well established. Early diagnosis of malignancy is the most important factor to improve patients' prognosis. The integration of machine learning into routine diagnosis has recently emerged as an adjunct to aid clinical examination. Increased performances of artificial intelligence AI-assisted medical devices are claimed to exceed the human capability in the clinical detection of early cancer. Therefore, the aim of this narrative review is to introduce artificial intelligence terminology, concepts, and models currently used in oncology to familiarize oral medicine scientists with the language skills, best research practices, and knowledge for developing machine learning models applied to the clinical detection of oral potentially malignant disorders.

Diagnostic Accuracy of Liquid Biopsy for Oral Potentially Malignant Disorders and Head and Neck Cancer: an Overview of Systematic Reviews.

PURPOSE OF REVIEW: The aim of this overview is to appraise the evidence on salivary biomarkers for H&N cancer diagnosis. The acronym PICOS was used to develop the eligibility criteria and the focused review question: are liquid biopsies (saliva biomarkers) reliable for cancer detection in H&N cancer patients? Electronic database search encompassed PubMed, EMBASE, Scopus, Cochrane Library, Web of Science, and LILACS. Risk of Bias (RoB) was assessed through AMSTAR 2. RECENT FINDINGS: A total of 20 SRs were included. Only seven SRs were able to reach more solid conclusions around the retrieved findings by calculating the pooled sensitivity, specificity, and the overall area under the curve (AUC). Despite the limitations, significant RoB, and lack of test metrics in primary studies, all SRs recognize and encourage the potential role of saliva in the early diagnosis of oral cancer.

Machine learning concepts applied to oral pathology and oral medicine: A convolutional neural networks' approach.

INTRODUCTION: Artificial intelligence models and networks can learn and process dense information in a short time, leading to an efficient, objective, and accurate clinical and histopathological analysis, which can be useful to improve treatment modalities and prognostic outcomes. This paper targets oral pathologists, oral medicinists, and head and neck surgeons to provide them with a theoretical and conceptual foundation of artificial intelligence-based diagnostic approaches, with a special focus on convolutional neural networks, the state-of-the-art in artificial intelligence and deep learning. METHODS: The authors conducted a literature review, and the convolutional neural network's conceptual foundations and functionality were illustrated based on a unique interdisciplinary point of view. CONCLUSION: The development of artificial intelligence-based models and computer vision methods for pattern recognition in clinical and histopathological image analysis of head and neck cancer has the potential to aid diagnosis and prognostic prediction.

FGFR1 is an important prognostic factor in oral leukoplakia and tongue squamous cell carcinoma.

BACKGROUND: Fibroblast growth factor receptor 1 is a potential prognostic factor for tongue squamous cell carcinoma and is associated with oral epithelial dysplasia grade in oral leukoplakia. METHODS: Thirty cases of tongue squamous cell carcinoma and 30 cases of oral leukoplakia were analyzed. Fibroblast growth factor receptor 1 and phosphorylated Akt protein expression were analyzed by immunohistochemistry and quantified using a digital algorithm. Fibroblast growth factor receptor 1 gene amplification was analyzed by fluorescent in situ hybridization in the tongue squamous cell carcinoma cases. RESULTS: Clinical appearance and dysplasia grade were correlated with oral leukoplakia malignant transformation. Oral leukoplakia cases presenting high fibroblast growth factor receptor 1 expression showed a higher risk of malignant transformation (p = 0.016, HR: 7.3, 95% CI: 1.4-37.4). Phosphorylated Akt showed faint to no expression in oral leukoplakia, which did not correlate with dysplasia grade or malignant transformation. High expression of fibroblast growth factor receptor 1 and phosohorylated Akt were associated with poor overall survival and disease-free survival in tongue squamous cell carcinoma, although only fibroblast growth factor receptor 1 expression was significantly associated with poor overall survival (p = 0.024; HR: 4.9, 95% CI: 1.2-19.9). Cases presenting double fibroblast growth factor receptor 1/phosphorylated Akt overexpression (n = 8) showed markedly impaired overall survival (p = 0.020; HR: 6.4, 95% CI: 1.3-31.1) and disease-free survival (p = 0.001, HR: 13.0, 95% CI: 3.0-55.7). Fibroblast growth factor receptor 1 amplification was observed in 16.6% of tongue squamous cell carcinoma cases, being correlated with vascular and neural invasion (p = 0.001 and 0.017, respectively), but not with fibroblast growth factor receptor 1 protein expression, overall survival, or disease-free survival. CONCLUSION: Fibroblast growth factor receptor 1 protein expression is an important prognostic factor in oral leukoplakia and tongue squamous cell carcinoma.

Molecular profile of head and neck rhabdomyosarcomas: A systematic review and meta-analysis.

OBJECTIVE: This systematic review aimed to identify the molecular alterations of head and neck rhabdomyosarcomas (HNRMS) and their prognostic values. STUDY DESIGN: An electronic search was performed using PubMed, Embase, Scopus, and Web of Science with a designed search strategy. Inclusion criteria comprised cases of primary HNRMS with an established histopathological diagnosis and molecular analysis. Forty-nine studies were included and were appraised for methodological quality using the Joanna Briggs Institute Critical Appraisal tools. Five studies were selected for meta-analysis. RESULTS: HNRMS predominantly affects pediatric patients (44.4%), and the parameningeal region (57.7%) is the most common location. The alveolar variant (43.2%) predominates over the embryonal and spindle cell/sclerosing types, followed by the epithelioid and pleomorphic variants. PAX-FOXO1 fusion was observed in 103 cases of alveolar RMS (79.8%). MYOD1 mutation was found in 39 cases of sclerosing/spindle cell RMS (53.4%). FUS/EWSR1-TFCP2 gene fusions were identified in 21 cases of RMS with epithelioid and spindle cell morphologies (95.5%). The 5-year overall survival rate of patients was 61.3%, and MYOD1 mutation correlated with significantly higher mortality. CONCLUSION: The genotypic profile of histologic variants of HNRMS is widely variable, and MYOD1 mutation could be a potential prognostic factor, but more studies are required to establish this.

Fully digital pathology laboratory routine and remote reporting of oral and maxillofacial diagnosis during the COVID-19 pandemic: a validation study.

The role of digital pathology in remote reporting has seen an increase during the COVID-19 pandemic. Recently, recommendations had been made regarding the urgent need of reorganizing head and neck cancer diagnostic services to provide a safe work environment for the staff. A total of 162 glass slides from 109 patients over a period of 5 weeks were included in this validation and were assessed by all pathologists in both analyses (digital and conventional) to allow intraobserver comparison. The intraobserver agreement between the digital method (DM) and conventional method (CM) was considered almost perfect (κ ranged from 0.85 to 0.98, with 95% CI, ranging from 0.81 to 1). The most significant and frequent disagreements within trainees encompassed epithelial dysplasia grading and differentiation among severe dysplasia (carcinoma in situ) and oral squamous cell carcinoma. The most frequent pitfall from DM was lag in screen mirroring. The lack of details of inflammatory cells and the need for a higher magnification to assess dysplasia were pointed in one case each. The COVID-19 crisis has accelerated and consolidated the use of online meeting tools, which would be a valuable resource even in the post-pandemic scenario. Adaptation in laboratory workflow, the advent of digital pathology and remote reporting can mitigate the impact of similar future disruptions to the oral and maxillofacial pathology laboratory workflow avoiding delays in diagnosis and report, to facilitate timely management of head and neck cancer patients. Graphical abstract.

Cost-effectiveness of photobiomodulation therapy for the prevention and management of cancer treatment toxicities: a systematic review.

PURPOSE: To identify and summarize the evidence on the cost-effectiveness of photobiomodulation (PBM) therapy for the prevention and treatment of cancer treatment-related toxicities. METHODS: This systematic review was performed according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses statement (PRISMA) and Meta-analysis Of Observational Studies in Epidemiology (MOOSE). Scopus, MEDLINE/PubMed, and Embase were searched electronically. RESULTS: A total of 1490 studies were identified, and after a two-step review, 4 articles met the inclusion criteria. The included studies analyzed the cost-effectiveness of PBM therapy used in the context of lymphedema for breast cancer and oral mucositis (OM) induced by chemotherapy and radiotherapy. Better outcomes were associated with PBM therapy. The incremental cost-effectiveness ratio ranged from 3050.75 USD to 5592.10 USD per grade 3-4 OM case prevented. PBM therapy cost 21.47 USD per percentage point reduction in lymphedema in comparison with 80.51 USD for manual lymph drainage and physical therapy. CONCLUSION: There is limited evidence that PBM therapy is cost-effective in the prevention and treatment of specific cancer treatment-related toxicities, namely, OM and breast cancer-related lymphedema. Studies may have underreported the benefits due to a lack of a comprehensive cost evaluation. This suggests a wider acceptance of PBM therapy at cancer treatment centers, which has thus far been limited by the number of robust clinical studies that demonstrate cost-effectiveness for the prevention and treatment of toxicities.

Oral leukoplakia and erythroplakia in young patients: a systematic review.

OBJECTIVE: The aim of this study was to estimate the frequency of oral leukoplakia and oral erythroplakia in young patients. STUDY DESIGN: The systematic review was based on the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines and performed in the following electronic databases: PubMed, Scopus, and Embase. The studies included were cross-sectional, cohort, and diagnostic, which provided with clinical and microscopic data of patients younger than 40 years. The Critical Appraisal Checklist for Prevalence Studies from the Joanna Briggs Institute and the Quality Assessment Tool for Diagnostic Accuracy Studies were used to assess the risk of bias. RESULTS: Five studies met eligibility criteria and were included. The total number of patients from the studies was 1246, of which 115 were young patients (9.2%) with oral leukoplakia as the only oral potentially malignant disorder reported. Oral epithelial dysplasia was identified in 40 cases (34.7%), of which 8 (6.9%) presented malignant transformation. CONCLUSIONS: The frequency of oral leukoplakia is low in young patients. Observational studies are necessary for understanding oral leukoplakia and other oral potentially malignant disorders in younger patients.

The use of digital microscopy as a teaching method for human pathology: a systematic review.

Since digital microscopy (DM) has become a useful alternative to conventional light microscopy (CLM), several approaches have been used to evaluate students' performance and perception. This systematic review aimed to integrate data regarding the use of DM for education in human pathology, determining whether this technology can be an adequate learning tool, and an appropriate method to evaluate students' performance. Following a specific search strategy and eligibility criteria, three electronic databases were searched and several articles were screened. Eight studies involving medical and dental students were included. The test of performance comprised diagnostic and microscopic description, clinical features, differential, and final diagnoses of the specimens. The students' achievements were equivalent, similar or higher using DM in comparison with CLM in four studies. All publications employed question surveys to assess the students' perceptions, especially regarding the easiness of equipment use, quality of images, and preference for one method. Seven studies (87.5%) indicated the students' support of DM as an appropriate method for learning. The quality assessment categorized most studies as having a low bias risk (75%). This study presents the efficacy of DM for human pathology education, although the high heterogeneity of the included articles did not permit outlining a specific method of performance evaluation.

Prognostic value of CRTC1-MAML2 translocation in salivary mucoepidermoid carcinoma: Systematic review and meta-analysis.

The presence of the CRTC1-MAML2 translocation has been described in mucoepidermoid carcinoma (MEC) as a predictor of better survival rates. However, the real prognostic value of the translocation has been debated due to recent controversial findings. The aim of this study was to perform a systematic review to understand the prognostic potential of the CRTC1-MAML2 translocation in MEC. An electronic search was carried out using the MEDLINE/PubMed, EMBASE and Scopus databases. Articles that assessed the association between the CRTC1-MAML2 translocation and survival of MEC patients were selected for the systematic review. Ten published articles were included in the qualitative synthesis. The prevalence of the translocation varied from 33.7% to 69.7%. Seven studies observed a significant association between the presence of the CRTC1-MAML2 translocation and a favourable clinical outcome, which could improve disease-free, disease-specific or overall survival. Five studies were included in the quantitative synthesis. Fixed-effects model confirmed that translocation-positive patients have a decreased risk of death (combined odds ratio 0.08, 95% confidence interval - 0.03-0.23, P < .00001). The detection of the CRTC1-MAML2 translocation appears to be useful as a prognostic factor in MEC. However, the level of evidence is not as high as it could be once important limitations were found in the published studies.

Tumor safety and side effects of photobiomodulation therapy used for prevention and management of cancer treatment toxicities. A systematic review.

Photobiomodulation therapy (PBMT), also known as low-level laser therapy (LLLT), has been increasingly used for the treatment of toxicities related to cancer treatment. One of the challenges for the universal acceptance of PBMT use in cancer patients is whether or not there is a potential for the light to stimulate the growth of residual malignant cells that evaded oncologic treatment, increasing the risk for tumor recurrences and development of a second primary tumor. Current science suggests promising effects of PBMT in the prevention and treatment of breast cancer-related lymphedema and oral mucositis, among other cancer treatment toxicities. Nevertheless, this seems to be the first systematic review to analyze the safety of the use of PBMT for the management of cancer-related toxicities. Scopus, MEDLINE/PubMed, and Embase were searched electronically. A total of 27 articles met the search criteria. Selected studies included the use of PBMT for prevention and treatment of oral mucositis, lymphedema, radiodermatitis, and peripheral neuropathy. Most studies showed that no side effects were observed with the use of PBMT. The results of this systematic review, based on current literature, suggest that the use of PBMT in the prevention and management of cancer treatment toxicities does not lead to the development of tumor safety issues.

The performance of digital microscopy for primary diagnosis in human pathology: a systematic review.

Validation studies of whole slide imaging (WSI) systems produce evidence regarding digital microscopy (DM). This systematic review aimed to provide information about the performance of WSI devices by evaluating intraobserver agreement reported in previously published studies as the best evidence to elucidate whether DM is reliable for primary diagnostic purposes. In addition, this review delineates the reasons for the occurrence of discordant diagnoses. Scopus, MEDLINE/PubMed, and Embase were searched electronically. A total of 13 articles were included. The total sample of 2145 had a majority of 695 (32.4%) cases from dermatopathology, followed by 200 (9.3%) cases from gastrointestinal pathology. Intraobserver agreements showed an excellent concordance, with values ranging from 87% to 98.3% (κ coefficient range 0.8-0.98). Ten studies (77%) reported a total of 128 disagreements. The remaining three studies (23%) did not report the exact number and nature of disagreements. Borderline/challenging cases were the most frequently reported reason for disagreements (53.8%). Six authors reported limitations of the equipment and/or limited image resolution as reasons for the discordant diagnoses. Within these articles, the reported pitfalls were as follows: difficulties in the identification of eosinophilic granular bodies in brain biopsies; eosinophils and nucleated red blood cells; and mitotic figures, nuclear details, and chromatin patterns in neuropathology specimens. The lack of image clarity was reported to be associated with difficulties in the identification of microorganisms (e.g., Candida albicans, Helicobacter pylori, and Giardia lamblia). However, authors stated that the intraobserver variances do not derive from technical limitations of WSI. A lack of clinical information was reported by four authors as a source for disagreements. Two studies (15.4%) reported poor quality of the biopsies, specifically small size of the biopsy material or inadequate routine laboratory processes as reasons for disagreements. One author (7.7%) indicated the lack of immunohistochemistry and special stains as a source for discordance. Furthermore, nine studies (69.2%) did not consider the performance of the digital method-limitations of the equipment, insufficient magnification/limited image resolution-as reasons for disagreements. To summarize the pitfalls of digital pathology practice and better address the root cause of the diagnostic discordance, we suggest a Categorization for Digital Pathology Discrepancies to be used in further validations studies. Among 99 discordances, only 37 (37.3%) had preferred diagnosis rendered by means of WSI. The risk of bias and applicability concerns were judged with the QUADAS-2. Two studies (15.4%) presented an unclear risk of bias in the sample selection domain and 2 (15.4%) presented a high risk of bias in the index test domain. Regarding applicability, all studies included were classified as a low concern in all domains. The included studies were optimally designed to validate WSI for general clinical use, providing evidence with confidence. In general, this systematic review showed a high concordance between diagnoses achieved by using WSI and conventional light microscope (CLM), summarizes difficulties related to specific findings of certain areas of pathology-including dermatopathology, pediatric pathology, neuropathology, and gastrointestinal pathology-and demonstrated that WSI can be used to render primary diagnoses in several subspecialties of human pathology.