-
Journal of Translational Medicine Jan 2021Hysteroscopy is a commonly used technique for diagnosing endometrial lesions. It is essential to develop an objective model to aid clinicians in lesion diagnosis, as...
BACKGROUND
Hysteroscopy is a commonly used technique for diagnosing endometrial lesions. It is essential to develop an objective model to aid clinicians in lesion diagnosis, as each type of lesion has a distinct treatment, and judgments of hysteroscopists are relatively subjective. This study constructs a convolutional neural network model that can automatically classify endometrial lesions using hysteroscopic images as input.
METHODS
All histopathologically confirmed endometrial lesion images were obtained from the Shengjing Hospital of China Medical University, including endometrial hyperplasia without atypia, atypical hyperplasia, endometrial cancer, endometrial polyps, and submucous myomas. The study included 1851 images from 454 patients. After the images were preprocessed (histogram equalization, addition of noise, rotations, and flips), a training set of 6478 images was input into a tuned VGGNet-16 model; 250 images were used as the test set to evaluate the model's performance. Thereafter, we compared the model's results with the diagnosis of gynecologists.
RESULTS
The overall accuracy of the VGGNet-16 model in classifying endometrial lesions is 80.8%. Its sensitivity to endometrial hyperplasia without atypia, atypical hyperplasia, endometrial cancer, endometrial polyp, and submucous myoma is 84.0%, 68.0%, 78.0%, 94.0%, and 80.0%, respectively; for these diagnoses, the model's specificity is 92.5%, 95.5%, 96.5%, 95.0%, and 96.5%, respectively. When classifying lesions as benign or as premalignant/malignant, the VGGNet-16 model's accuracy, sensitivity, and specificity are 90.8%, 83.0%, and 96.0%, respectively. The diagnostic performance of the VGGNet-16 model is slightly better than that of the three gynecologists in both classification tasks. With the aid of the model, the overall accuracy of the diagnosis of endometrial lesions by gynecologists can be improved.
CONCLUSIONS
The VGGNet-16 model performs well in classifying endometrial lesions from hysteroscopic images and can provide objective diagnostic evidence for hysteroscopists.
Topics: China; Deep Learning; Endometrial Hyperplasia; Endometrial Neoplasms; Female; Humans; Hysteroscopy; Pregnancy; Sensitivity and Specificity; Uterine Diseases
PubMed: 33407588
DOI: 10.1186/s12967-020-02660-x -
Scientific Reports Mar 2021The reverse transcription-polymerase chain reaction (RT-PCR) assay is the accepted standard for coronavirus disease 2019 (COVID-19) diagnosis. As any test, RT-PCR...
The reverse transcription-polymerase chain reaction (RT-PCR) assay is the accepted standard for coronavirus disease 2019 (COVID-19) diagnosis. As any test, RT-PCR provides false negative results that can be rectified by clinicians by confronting clinical, biological and imaging data. The combination of RT-PCR and chest-CT could improve diagnosis performance, but this would requires considerable resources for its rapid use in all patients with suspected COVID-19. The potential contribution of machine learning in this situation has not been fully evaluated. The objective of this study was to develop and evaluate machine learning models using routine clinical and laboratory data to improve the performance of RT-PCR and chest-CT for COVID-19 diagnosis among post-emergency hospitalized patients. All adults admitted to the ED for suspected COVID-19, and then hospitalized at Rennes academic hospital, France, between March 20, 2020 and May 5, 2020 were included in the study. Three model types were created: logistic regression, random forest, and neural network. Each model was trained to diagnose COVID-19 using different sets of variables. Area under the receiving operator characteristics curve (AUC) was the primary outcome to evaluate model's performances. 536 patients were included in the study: 106 in the COVID group, 430 in the NOT-COVID group. The AUC values of chest-CT and RT-PCR increased from 0.778 to 0.892 and from 0.852 to 0.930, respectively, with the contribution of machine learning. After generalization, machine learning models will allow increasing chest-CT and RT-PCR performances for COVID-19 diagnosis.
Topics: Area Under Curve; COVID-19; COVID-19 Testing; Diagnosis, Computer-Assisted; Humans; Machine Learning; Proof of Concept Study; Reverse Transcriptase Polymerase Chain Reaction; Tomography, X-Ray Computed
PubMed: 33785852
DOI: 10.1038/s41598-021-86735-9 -
Medical & Biological Engineering &... Mar 2022Cancer is among the common causes of death around the world. Skin cancer is one of the most lethal types of cancer. Early diagnosis and treatment are vital in skin...
Cancer is among the common causes of death around the world. Skin cancer is one of the most lethal types of cancer. Early diagnosis and treatment are vital in skin cancer. In addition to traditional methods, method such as deep learning is frequently used to diagnose and classify the disease. Expert experience plays a major role in diagnosing skin cancer. Therefore, for more reliable results in the diagnosis of skin lesions, deep learning algorithms can help in the correct diagnosis. In this study, we propose InSiNet, a deep learning-based convolutional neural network to detect benign and malignant lesions. The performance of the method is tested on International Skin Imaging Collaboration HAM10000 images (ISIC 2018), ISIC 2019, and ISIC 2020, under the same conditions. The computation time and accuracy comparison analysis was performed between the proposed algorithm and other machine learning techniques (GoogleNet, DenseNet-201, ResNet152V2, EfficientNetB0, RBF-support vector machine, logistic regression, and random forest). The results show that the developed InSiNet architecture outperforms the other methods achieving an accuracy of 94.59%, 91.89%, and 90.54% in ISIC 2018, 2019, and 2020 datasets, respectively. Since the deep learning algorithms eliminate the human factor during diagnosis, they can give reliable results in addition to traditional methods.
Topics: Algorithms; Dermoscopy; Humans; Neural Networks, Computer; Skin; Skin Diseases; Skin Neoplasms
PubMed: 35028864
DOI: 10.1007/s11517-021-02473-0 -
International Journal of Clinical... Nov 2022Sinusoidal obstruction syndrome (SOS) refers to liver injury caused by hematopoietic stem cell transplantation (HSCT) and anticancer drugs including oxaliplatin.... (Observational Study)
Observational Study
BACKGROUND
Sinusoidal obstruction syndrome (SOS) refers to liver injury caused by hematopoietic stem cell transplantation (HSCT) and anticancer drugs including oxaliplatin. Increased splenic volume (SV) on computed tomography (CT) indicates oxaliplatin-induced SOS. Similarly, ultrasonography and liver stiffness measurement (LSM) by shear-wave elastography (SWE) can help diagnose SOS after HSCT; however, their usefulness for diagnosing oxaliplatin-induced SOS remains unclear. We investigated the usefulness of the Hokkaido ultrasonography-based scoring system with 10 ultrasonographic parameters (HokUS-10) and SWE in diagnosing oxaliplatin-induced SOS early.
METHODS
In this prospective observational study, ultrasonography and SWE were performed before and at 2, 4, and 6 months after oxaliplatin-based chemotherapy. HokUS-10 was used for assessment. CT volumetry of the SV was performed in clinical practice, and an SV increase ≥ 30% was considered the diagnostic indicator of oxaliplatin-induced SOS. We assessed whether HokUS-10 and SWE can lead to an early detection of oxaliplatin-induced SOS before an increased SV on CT.
RESULTS
Of the 30 enrolled patients with gastrointestinal cancers, 12 (40.0%) with an SV increase ≥ 30% on CT were diagnosed with SOS. The HokUS-10 score was not correlated with an SV increase ≥ 30% (r = 0.18). The change in rate of three HokUS-10 parameters were correlated with an SV increase ≥ 30% (r = 0.32-0.41). The change in rate of LSM by SWE was correlated with an SV increase ≥ 30% (r = 0.40).
CONCLUSIONS
The usefulness of HokUS-10 score was not demonstrated; however, some HokUS-10 parameters and SWE could be useful for the early diagnosis of oxaliplatin-induced SOS.
Topics: Humans; Hepatic Veno-Occlusive Disease; Oxaliplatin; Elasticity Imaging Techniques; Ultrasonography; Antineoplastic Agents
PubMed: 36042137
DOI: 10.1007/s10147-022-02235-4 -
Spine Deformity Oct 2020Retrospective case series.
STUDY DESIGN
Retrospective case series.
OBJECTIVES
To describe how pediatric patients with spinal and pelvic osteomyelitis are diagnosed and treated and assess the diagnostic value of magnetic resonance imaging (MRI), needle aspiration biopsy (NAB), and blood cultures in this population. Spinal and pelvic osteomyelitis de novo are uncommon in children and minimal literature exists on the subject. Research has shown that NAB and blood cultures have variable diagnostic yield in adult native osteomyelitis. At our institution, there is no standard protocol for diagnosing and treating pediatric spinal and pelvic osteomyelitis de novo.
METHODS
All diagnoses of spinal and pelvic osteomyelitis at a pediatric tertiary care center from 2003 to 2017 were reviewed. Patients aged 0-21 at diagnosis were included. Patients with osteomyelitis resulting from prior spinal operations, wounds, or infections and those with chronic recurrent multifocal osteomyelitis were eliminated. All eligible patients' diagnoses were confirmed by MRI.
RESULTS
29 patients (18 men, 11 women) met the inclusion criteria. The median age at diagnosis was 11 years old (range 1-18). More than half of all cases (17/29, 59%) affected the lumbar spine. The most common symptoms were back pain (20/29, 69%), fever (18/29, 62%), hip pain (11/29, 38%), and leg pain (8/29, 28%). The majority of NABs and blood cultures performed were negative, but of the positive tests Staphylococcus aureus was the most prevalent bacteria. 86% (25/29) had an MRI before a diagnosis was made and 72% (13/18) had an NAB performed post-diagnosis.
CONCLUSIONS
MRI is a popular and helpful tool in diagnosing spinal osteomyelitis de novo. NAB cultures are often negative but can be useful in determining antibiotic treatment.
LEVEL OF EVIDENCE
Level IV.
Topics: Adolescent; Biopsy, Fine-Needle; Blood Culture; Child; Child, Preschool; Female; Humans; Infant; Lumbar Vertebrae; Magnetic Resonance Imaging; Male; Osteomyelitis; Pelvic Inflammatory Disease; Retrospective Studies; Sensitivity and Specificity; Spinal Diseases; Staphylococcal Infections
PubMed: 32306283
DOI: 10.1007/s43390-020-00110-8 -
Cancer Cytopathology Feb 2022Despite widespread clinical use, lymph node fine-needle aspiration cytology (LN-FNAC) lacks universal acceptance for definitively diagnosing lymphomas. This is likely...
BACKGROUND
Despite widespread clinical use, lymph node fine-needle aspiration cytology (LN-FNAC) lacks universal acceptance for definitively diagnosing lymphomas. This is likely due to reports of lower diagnostic performance, inconsistent terminology use in cytopathology diagnostic reports, and only limited data on the clinical implications of LN-FNAC diagnoses. Recently, a uniform LN-FNAC cytopathological diagnostic reporting system was proposed (the Sydney System). This study evaluated LN-FNAC diagnostic performance and risks of malignancy associated with the proposed diagnostic categories.
METHODS
LN-FNAC specimens obtained in 2018-2019, with and without concurrent core biopsy, to evaluate for suspected lymphoma were analyzed (n = 349). LN-FNAC diagnoses were compared with final diagnoses obtained via subsequent tissue biopsy and/or clinical assessment.
RESULTS
The mean patient age was 57.6 years, and 41% were female. LN-FNAC was the initial diagnostic test in 223 (63.9%), and it was used to evaluate for recurrence in 126 (36.1%). LN-FNAC diagnosed 202 hematological malignancies (57.9%), 23 nonhematological malignancies (6.6%), and 124 reactive processes (35.5%). Subsequent tissue biopsy was performed in 42 (12%). The risks of malignancy per diagnostic category were as follows: inadequate, 58.3%; benign, 6.4%; atypical, 69.2%; suspicious, 96.7%; and malignant, 99.3%. LN-FNAC demonstrated up to 96.3% sensitivity, 91.91% specificity, and 87.35% accuracy. Optimal specimen quality and the use of intradepartmental consultation reduced diagnostic error rates in FNA cases without concurrent core biopsy (P = .029 and P = .0002 respectively).
CONCLUSIONS
LN-FNAC is accurate and reliable for the diagnosis of lymphoma. Inadequate LN-FNAC samples should be resampled due to a significant associated risk of lymphoma. The diagnostic performance of LN-FNAC may be improved with good specimen quality and reviews by multiple pathologists. Understanding the risks of malignancy associated with LN-FNAC diagnostic categories will help to guide optimal patient management.
Topics: Biopsy, Fine-Needle; Biopsy, Large-Core Needle; Cytological Techniques; Female; Humans; Lymph Nodes; Male; Middle Aged; Neoplasms; Sensitivity and Specificity
PubMed: 34661975
DOI: 10.1002/cncy.22523 -
Frontiers in Oncology 2023Pancreatic cystic neoplasms are increasingly diagnosed with the development of medical imaging technology and people's self-care awareness. However, two of their...
BACKGROUND
Pancreatic cystic neoplasms are increasingly diagnosed with the development of medical imaging technology and people's self-care awareness. However, two of their sub-types, serous cystic neoplasms (SCN) and mucinous cystic neoplasms (MCN), are often misclassified from each other. Because SCN is primarily benign and MCN has a high rate of malignant transformation. Distinguishing SCN and MCN is challenging and essential.
PURPOSE
MRIs have many different modalities, complete with SCN and MCN diagnosis information. With the help of an artificial intelligence-based algorithm, we aimed to propose a multi-modal hybrid deep learning network that can efficiently diagnose SCN and MCN using multi-modality MRIs.
METHODS
A cross-modal feature fusion structure was innovatively designed, combining features of seven modalities to realize the classification of SCN and MCN. 69 Patients with multi-modalities of MRIs were included, and experiments showed performances of every modality.
RESULTS
The proposed method with the optimized settings outperformed all other techniques and human radiologists with high accuracy of 75.07% and an AUC of 82.77%. Besides, the proposed disentanglement method outperformed other fusion methods, and delayed contrast-enhanced T1-weighted MRIs proved most valuable in diagnosing SCN and MCN.
CONCLUSIONS
Through the use of a contemporary artificial intelligence algorithm, physicians can attain high performance in the complex challenge of diagnosing SCN and MCN, surpassing human radiologists to a significant degree.
PubMed: 37795452
DOI: 10.3389/fonc.2023.1181270 -
European Radiology Jan 2023To compare the performance of radiologists in characterizing and diagnosing pulmonary nodules/masses with and without deep learning (DL)-based computer-aided diagnosis...
Radiologists with and without deep learning-based computer-aided diagnosis: comparison of performance and interobserver agreement for characterizing and diagnosing pulmonary nodules/masses.
OBJECTIVES
To compare the performance of radiologists in characterizing and diagnosing pulmonary nodules/masses with and without deep learning (DL)-based computer-aided diagnosis (CAD).
METHODS
We studied a total of 101 nodules/masses detected on CT performed between January and March 2018 at Osaka University Hospital (malignancy: 55 cases). SYNAPSE SAI Viewer V1.4 was used to analyze the nodules/masses. In total, 15 independent radiologists were grouped (n = 5 each) according to their experience: L (< 3 years), M (3-5 years), and H (> 5 years). The likelihoods of 15 characteristics, such as cavitation and calcification, and the diagnosis (malignancy) were evaluated by each radiologist with and without CAD, and the assessment time was recorded. The AUCs compared with the reference standard set by two board-certified chest radiologists were analyzed following the multi-reader multi-case method. Furthermore, interobserver agreement was compared using intraclass correlation coefficients (ICCs).
RESULTS
The AUCs for ill-defined boundary, irregular margin, irregular shape, calcification, pleural contact, and malignancy in all 15 radiologists, irregular margin and irregular shape in L and ill-defined boundary and irregular margin in M improved significantly (p < 0.05); no significant improvements were found in H. L showed the greatest increase in the AUC for malignancy (not significant). The ICCs improved in all groups and for nearly all items. The median assessment time was not prolonged by CAD.
CONCLUSIONS
DL-based CAD helps radiologists, particularly those with < 5 years of experience, to accurately characterize and diagnose pulmonary nodules/masses, and improves the reproducibility of findings among radiologists.
KEY POINTS
• Deep learning-based computer-aided diagnosis improves the accuracy of characterizing nodules/masses and diagnosing malignancy, particularly by radiologists with < 5 years of experience. • Computer-aided diagnosis increases not only the accuracy but also the reproducibility of the findings across radiologists.
Topics: Humans; Deep Learning; Observer Variation; Reproducibility of Results; Multiple Pulmonary Nodules; Radiologists; Diagnosis, Computer-Assisted; Computers; Lung Neoplasms; Sensitivity and Specificity; Solitary Pulmonary Nodule
PubMed: 35751697
DOI: 10.1007/s00330-022-08948-4 -
European Radiology Aug 2022To evaluate the feasibility and accuracy of diagnosing acute heart failure (HF) with CT pulmonary angiography (CTPA) in emergency department patients.
OBJECTIVES
To evaluate the feasibility and accuracy of diagnosing acute heart failure (HF) with CT pulmonary angiography (CTPA) in emergency department patients.
METHODS
In this retrospective single-center study, we evaluated 150 emergency department patients (mean age 65 ± 17 years) undergoing CTPA with a fixed scan (100 kVp) and contrast media protocol (60 mL, 4 mL/s) who had no pulmonary embolism (PE). Patients were subdivided into training cohort (n = 100) and test cohort (n = 50). Three independent, blinded readers measured the attenuation in the right ventricle (RV) and left ventricle (LV) on axial images. The ratio (HU) and difference (HU) between RV and LV attenuation were calculated. Diagnosis of acute HF was made on the basis of clinical, laboratory, and echocardiography data. Optimal thresholds, sensitivity, and specificity were calculated using the area under the curve (AUC) from receiver operating characteristics analysis.
RESULTS
Fifty-nine of the 150 patients (40%) were diagnosed with acute HF. Attenuation measurements showed an almost perfect interobserver agreement (intraclass correlation coefficient: 0.986, 95%CI: 0.980-0.991). NT-pro BNP exhibited moderate correlations with HU (r = 0.50, p < 0.001) and HU (r = 0.50, p < 0.001). In the training cohort, HU (AUC: 0.89, 95%CI: 0.82-0.95) and HU (AUC: 0.88, 95%CI: 0.81-0.95) showed a very good performance to diagnose HF. Optimal cutoff values were 1.42 for HU (sensitivity 93%; specificity 75%) and 113 for HU (sensitivity 93%; specificity 73%). Applying these thresholds to the test cohort yielded a sensitivity of 89% and 89% and a specificity of 69% and 63% for HU and HU, respectively.
CONCLUSION
In emergency department patients undergoing CTPA and showing no PE, both HU and HU have a high sensitivity for diagnosing acute HF.
KEY POINTS
• Heart failure is a common differential diagnosis in patients undergoing CT pulmonary angiography. • In emergency department patients undergoing CT pulmonary angiography and showing no pulmonary embolism, attenuation differences of the left and right ventricle have a high sensitivity for diagnosing acute heart failure.
Topics: Aged; Aged, 80 and over; Angiography; Computed Tomography Angiography; Feasibility Studies; Heart Failure; Humans; Middle Aged; Pulmonary Embolism; Retrospective Studies; Sensitivity and Specificity; Tomography, X-Ray Computed
PubMed: 35294585
DOI: 10.1007/s00330-022-08676-9 -
International Journal of Infectious... Jul 2020Diagnosing pulmonary blastomycosis (PB) requires the detection of Blastomyces dermatitidis in pulmonary secretions or tissue, which can be achieved via bronchoscopic...
OBJECTIVES
Diagnosing pulmonary blastomycosis (PB) requires the detection of Blastomyces dermatitidis in pulmonary secretions or tissue, which can be achieved via bronchoscopic procedures like bronchoalveolar lavage (BAL) or brush and transbronchial biopsy (TBBx). This descriptive study retrieved the data of PB that was diagnosed by bronchoscopy to define which bronchoscopic procedure produced the highest yield.
METHODS
Retrospectively, all patients diagnosed with PB via bronchoscopic approach were identified. Non-invasive BAL was referred to when performed first in the order of bronchoscopic procedures, and invasive BAL was used when it was performed after other bronchoscopic procedures.
RESULTS
A total of 111 patients were included in the study. BAL produced the highest yield of all bronchoscopic procedures (>87%), regardless if it was performed first in order (non-invasive, 87.3%) or not (invasive BAL, 89.6%) (p = 0.43). Performing bronchoscopy and BAL earlier in the course of the disease resulted in a significantly better diagnostic yield.
CONCLUSIONS
BAL is probably enough to diagnose PB. Also, it had the best yield when performed earlier, regardless of whether it was performed first in order or not. BAL culture had a better yield in detecting Blastomyces dermatitidis over fungal stain and cytology.
Topics: Adolescent; Adult; Aged; Aged, 80 and over; Blastomycosis; Bronchoalveolar Lavage; Bronchoscopy; Female; Humans; Male; Middle Aged; Retrospective Studies; Young Adult
PubMed: 32371194
DOI: 10.1016/j.ijid.2020.04.077