Genetic and Histopathological Heterogeneity of Neuroblastoma and Precision Therapeutic Approaches for Extremely Unfavorable Histology Subgroups

Peripheral neuroblastic tumors (neuroblastoma, ganglioneuroblastoma and ganglioneuroma) are heterogeneous and their diverse and wide range of clinical behaviors (spontaneous regression, tumor maturation and aggressive progression) are closely associated with genetic/molecular properties of the individual tumors. The International Neuroblastoma Pathology Classification, a biologically relevant and prognostically significant morphology classification distinguishing the favorable histology (FH) and unfavorable histology (UH) groups in this disease, predicts survival probabilities of the patients with the highest hazard ratio. The recent advance of neuroblastoma research with precision medicine approaches demonstrates that tumors in the UH group are also heterogeneous and four distinct subgroups—MYC, TERT, ALT and null—are identified. Among them, the first three subgroups are collectively named extremely unfavorable histology (EUH) tumors because of their highly aggressive clinical behavior. As indicated by their names, these EUH tumors are individually defined by their potential targets detected molecularly and immunohistochemically, such as MYC-family protein overexpression, TERT overexpression and ATRX (or DAXX) loss. In the latter half on this paper, the current status of therapeutic targeting of these EUH tumors is discussed for the future development of effective treatments of the patients.

Underdiagnosis bias of artificial intelligence algorithms applied to chest radiographs in under-served patient populations

Artificial intelligence (AI) systems have increasingly achieved expert-level performance in medical imaging applications. However, there is growing concern that such AI systems may reflect and amplify human bias, and reduce the quality of their performance in historically under-served populations such as female patients, Black patients, or patients of low socioeconomic status. Such biases are especially troubling in the context of underdiagnosis, whereby the AI algorithm would inaccurately label an individual with a disease as healthy, potentially delaying access to care. Here, we examine algorithmic underdiagnosis in chest X-ray pathology classification across three large chest X-ray datasets, as well as one multi-source dataset. We find that classifiers produced using state-of-the-art computer vision techniques consistently and selectively underdiagnosed under-served patient populations and that the underdiagnosis rate was higher for intersectional under-served subpopulations, for example, Hispanic female patients. Deployment of AI systems using medical imaging for disease diagnosis with such biases risks exacerbation of existing care biases and can potentially lead to unequal access to medical treatment, thereby raising ethical concerns for the use of these models in the clinic.

NI-16 Verification of APT image and relationship with T2/FLAIR mismatch sign in WHO2016 brain tumor pathology classification

Introduction: Amide Proton Transfer Imaging(APT)is an MRI imaging method that images the increased concentration of amide groups in tumors and is expected to be clinically applied to the diagnostic imaging of gliomas.On the other hand,T2/FLAIR mismatch sign(T2/FLms)has been proposed as an MRI finding specific to astrocytoma with IDH gene mutation.This time,in the WHO2016 Brain Tumor Pathological Classification,we report the verification of the pathological gene classification of APT and the retrospective verification based on the pathological diagnosis results of whether there is a relationship between APT and T2/FLms. Method: We examined 88 cases of preoperative glioma (Grade:G2/3/4)in which APT/T2/FLAIR was imaged.resultIt showed a high value in high malignancy and a significant difference was observed.In the verification of genetic classification, the measured APT values were 1.91 ±0.71 for oligodendroglioma(16 cases),2.58±0.17 for astrocytoma(2 cases),2.40±0.90 for anaplastic oligodendroglioma(12 cases),Anaplastic astrocytoma(20 cases)2.63±0.42,The oligodendroglioma system showed lower values than the astrocytoma system.For anaplastic astrocytoma IDH mutant and glioblastoma IDH mutant,APT measurement values were measured after evaluating the presence or absence of T2/FL ms. APT measured values are anaplastic astrocytoma IDH mutant T2/FL ms present(7 cases) 2.63±0.38,T2/FL ms not (5 cases) 2.76±0.37, glioblastoma IDH mutant T2/FL ms present(5 cases)2.67±0.50, no T2/FL ms(3 cases)3.48±0.27,suggesting low APT measured values with T2/FL ms,respectively.ConclusionIn the verification of genetic classification, the oligodendroglioma system shows a lower value than the astrocytoma system,and it is considered that it can be one of the options such as treatment policy.Regarding the relationship between T2/FL ms and APT,it was suggested that the APT measured value with T2/FL ms tended to be low,but since it wasreported that the sensitivity of T2/FL ms was 30%,it was verified by accumulating cases.is required.

Review on Deep Learning Methods for Chest X-Ray based Abnormality Detection and Thoracic Pathology Classification

Backed by more powerful computational resources and optimized training routines, deep learning models have proven unprecedented performance and several benefits to extract information from chest X-ray data. This is one of the most common imaging exams, whose increasing demand is reflected in the aggravated radiologists’ workload. Consequently, healthcare would benefit from computer-aided diagnosis systems to prioritize certain exams and further identify possible pathologies. Pioneering work in chest X-ray analysis has focused on the identification of specific diseases, but to the best of the authors' knowledge no paper has specifically reviewed relevant work on abnormality detection and multi-label thoracic pathology classification. This paper focuses on those issues, selecting the leading chest X-ray based deep learning strategies for comparison. In addition, the paper discloses the current annotated public chest X-ray databases, covering the common thorax diseases.

Determining a threshold measurement of Endometrial Thickness for Asymptomatic Postmenopausal Women: A single-centre case series

Objective: To determine the endometrial thickness at which endometrial sampling is indicated in asymptomatic post-menopausal women referred with thickened endometrium on ultrasound. Design: Retrospective case series Setting: Mercy Hospital for Women, Melbourne Population: Post-menopausal women without bleeding, undergoing hysteroscopy for thickened endometrium Methods: Logistic regression was used to examine the association between a range of variables and pre-malignant or malignant pathology and endometrial thickness Main outcome measures: The primary outcome was endometrial malignancy/pre-malignancy and its relation to endometrial thickness. Secondary outcomes focused on identifying additional predictors which may influence endometrial malignancy such as ultrasound findings, years since menopause, age, obesity, diabetes, and tamoxifen use. Results: A total of 404 postmenopausal women met the inclusion criteria for this study. The mean (SD) age of patients at presentation was 65 (9.09) years and the mean BMI was 29.86 kg/m2 (6.52). Of these women, nine (2.2%) were diagnosed with endometrial carcinoma and 7 (1.7%) had endometrial hyperplasia with atypia. The most common histopathological finding was of a benign endometrial polyp (153, 37.9%). When including hyperplasia with or without atypia in histopathology of interest, a cut-off of ≥9mm provides the greatest sensitivity (83.3%) and specificity (63.8%) for a diagnosis of pre-malignant or malignant pathology (classification accuracy of 64.8%; AUROC: 0.7358, 95%CI: 0.6439, 0.8278) in this cohort. Conclusions: Using an endometrial thickness of ≥9mm can be safely used as a cut-off for endometrial sampling in post-menopausal women without bleeding. Funding: Norman Beischer Medical Research Foundation, 2018 NBMRF Grant Keywords: Endometrial thickness, Post-menopausal, endometrial hyperplasia

Kidney Pathology and Outcomes in Anca-Associated Vasculitis: Retrospective Analysis of 85 Patients

ANCA-associated vasculitis (AAV) pose a significant risk of kidney failure, kidney biopsy remains a key prognostic tool. Pathology classification of the AAV glomerulonephritis (GN) developed by Berden et al showed correlation between GN classes and kidney outcomes; ANCA Renal Risk Score (ARRS) included tubular atrophy and interstitial fibrosis (TA/IF) as an additional parameter for risk assessment. We aimed to evaluate kidney survival across AAV GN classes and ARRS groups. A single-center retrospective study included 85 adult patients with biopsy-proven AAV kidney disease followed in 2000-2020. Primary outcome was kidney survival at the end of 18 [5; 66] months follow-up, kidney death considered as CKD stage 5. We found significant difference in the kidney survival for sclerotic, mixed, crescentic and focal AAV GN classes: 19%, 76.2%, 91.7% and 100% respectively (p=0.009). Kidney survival was 0%, 75.6% and 100% for the high, median and low risk ARRS groups respectively (p<0.001); TA/IF analysis showed kidney survival 49.6% vs 87.7% for widespread and mild TA/IF respectively (р=0.003). Kidney survival was significantly lower in anti-MPO-ANCA versus anti-PR3-ANCA carriers (50.3% and 78.1% respectively, р=0.045). We conclude that unfavorable AAV kidney outcomes associated with sclerotic GN class by Berden’s classification, ARRS high risk group, and anti-MPO-ANCA subtype.