Benign Diagnosis Research Articles

Differential Diagnosis of Benign and Malignant Pulmonary Nodules in CT Images Based on Multitask Learning.

Artificial intelligence-based aided diagnostic systems for pulmonary nodules can be divided into subtasks such as nodule detection, segmentation, and benign and malignant differentiation. Most current studies are limited to single-target tasks. However, aided diagnosis aims to distinguish benign from malignant pulmonary nodules, which requires the fusion of multiple-scale features and comprehensive discrimination based on the results of multiple learning tasks. This study focuses on the aspects of model design, network structure, and constraints and proposes a novel model that integrates the learning tasks of pulmonary nodule detection, segmentation, and classification under weakly supervised conditions. The main innovations include the following three aspects: (1) a two-dimensional sequence detection model based on a ConvLSTM (Convolutional Long Short-Term Memory) network and U-shaped structure network is proposed to obtain the context space features of image slices fully; (2) a differential diagnosis of benign and malignant pulmonary nodules based on multitask learning is proposed, which uses the annotated data of different types of tasks to mine the potential common features among tasks; and (3) an optimization strategy incorporating prior knowledge of computed tomography images and dynamic weight adjustment of multiple tasks is proposed to ensure that each task can efficiently complete training and learning. Experiments on the LIDC-IDRI and LUNA16 datasets showed that our proposed method achieved a final competition performance metric score of 87.80% for nodule detection and a Dice similarity coefficient score of 83.95% for pulmonary nodule segmentation. The cross-validation results of the LIDC-IDRI and LUNA16 datasets show that our model achieved 87.80% of the final competition performance metric score for nodule detection and 83.95% of the DSC score for pulmonary nodule segmentation, representing the optimal result for that dataset.

Optimizing diagnostic success for vitreoretinal lymphoma

Aims/Purpose: To determine the diagnostic yield and pathological entities in a retrospective cohort of diagnostic vitrectomy patients.Methods: A retrospective cohort of diagnostic vitrectomy samples submitted to a tertial referral hospital pathology laboratory was identified by database search. The specimen submission protocol for this cohort consisted of two components: (i) intraoperative preparation of a neat vitreous aspirate as well as submission of the casette washings in RPMI and (ii) laboratory triage of each sample for microbiology culture, flow cytometry, cytological assessment and cell block preparation.Results: A total of 133 diagnostic vitrectomy samples were submitted between November 2015 and January 2022 (mean age 74 years, 0.8 M:F). A diagnostic report resulted in 132 (99.2%) of cases. Benign diagnoses (infectious and non‐infectious vitritis, degenerative or reactive changes, haemorrhage) were found in 88 of the cases (66.1%), while 20 cases (15%) were malignant. Of the malignant diagnoses, 18 (13.5%) were vitreoretinal lymphoma (17 diffuse large B cells; 1 T cell) by cytology and flow cytometry. The other two malignant diagnoses consisted of metastatic adenocarcinoma and metastatic cutaneous melanoma. 24 cases (18%) were classified as atypical, consisting of a lymphocytosis without demonstrable clonality by flow cytometry.Conclusions: This intraoperative and laboratory protocol maximizes the sample for all diagnostic tests required to discern infectious, inflammatory and malignant causes of increased vitreous cellularity. Importantly, the protocol allows for immunophenotyping of vitreoretinal lymphoma by flow cytometry and immunohistochemistry to WHO classification standards, essential for treatment and surveillance decision‐making.

Unplanned Sarcoma Excisions: Understanding How They Happen.

Soft-tissue sarcomas present as a mass with nonspecific symptoms, and unplanned excisions commonly occur. The purpose of this study was to analyze the incidence of unplanned excisions performed by orthopaedic surgeons and to conduct a root cause analysis (RCA) of the steps that led to unplanned excisions in all the cases. A retrospective case-control study was conducted. Two cohorts were identified, one including patients who underwent an unplanned excision of a soft-tissue sarcoma (n = 107) and a second cohort with patients whose entire care was performed at our sarcoma center (n = 102). A RCA was conducted with the whole sample to identify the preventable causes that led to sarcoma unplanned excisions. Orthopedic surgeons were the second group of physicians to perform the most unplanned excisions, only behind general surgeons. Inadequate imaging was encountered in 76.6% of the patients (n = 82, 95% confidence interval, 67.8 to 83.6). Forty-five patients (42.1%) had no imaging studies before the unplanned procedure. In the RCA, the most notable obstacles found were (1) incorrect assumption of a benign diagnosis, (2) failure to obtain the appropriate imaging study, (3) incorrectly reported imaging studies, (4) failure to order a biopsy, and (5) incorrect reporting of the biopsy. Despite educational efforts, unplanned excisions and the devastating consequences that sometimes follow continue to occur. Orthopaedic surgeons persist in playing a role in the unplanned procedure burden.

Diagnostic Yield vs Diagnostic Accuracy for Peripheral Lung Biopsy Evaluation: Evidence Supporting a Future Pragmatic End Point

Diagnostic yield and accuracy endpoints have been used inconsistently in the evaluation of advanced diagnostic bronchoscopy devices and techniques, limiting between-study comparisons. In addition, diagnostic accuracy can only be adjudicated after prolonged clinical follow-up which delays reporting on the performance of novel devices. Will a conservative diagnostic yield definition would result in few false negative initial results to closely approximate diagnostic accuracy and represent a useful outcome for future studies of diagnostic utility? Commonly utilized definitions of diagnostic yield were applied to a prospective dataset of consecutive peripheral pulmonary lesions sampled by navigational bronchoscopy from 2017 to 2019. All consider malignancy to be diagnostic but differ in their classification of non-malignant biopsy findings, which were subcategorized as specific benign, nonspecific benign, or normal lung. Diagnostic yield calculations were also compared to diagnostic accuracy, defined as the proportion of biopsies deemed diagnostic by each definition that were confirmed accurate through two years of follow-up. A total of 450 biopsied lesions were analyzed. The prevalence of malignancy was 60.9% (274 of 450). On initial bronchoscopy pathology, there were 227 malignant diagnoses (50.4%), with a single false-positive (0.4%). Among 104 biopsies with specific benign findings, only two were false negative for malignancy (1.9%). There were 119 nonspecific benign biopsies with 46 false negatives for malignancy (38.7%). The discrepancy between diagnostic yield and accuracy was 0.7% for the conservative definition which only considered malignant or specific benign findings as diagnostic. A conservative diagnostic yield definition excluding nonspecific benign diagnoses closely approximated diagnostic accuracy through two years follow-up, with a less than 1% discrepancy. Using this conservative yield definition may allow for dissemination of reliable diagnostic utility data without protracted delays needed for follow-up data in this era of rapid technological change in advanced diagnostic bronchoscopy.

Concordance between core needle biopsy and surgical excision specimen in the diagnosis of malignancy and benignity for patients with breast tumours

Core Needle Biopsy (CNB) has been widely used as a diagnostic tool for breast tumors. However, this technique involves tissue sampling as opposed to complete surgical lesion excision, introducing the possibility of underestimation of disease. The purpose of this study was to assess the reliability of CNB in breast tumors. This was a retrospective cross-sectional study from January 2023 to July 2023. All included patients underwent Core Needle Biopsy (CNB) and subsequent Surgical Excision (SE) of a breast tumor. One hundred fifty patients were assessed. All patients were female. The median age for malignancies was 45 years and 31 years for benign tumors. Concordance regarding the tumor type was globally moderate (k= 0.67; p<0,001) with a rate of 97.6% for CNB-diagnosed malignant tumors and 62.5% for CNB-diagnosed benign tumors. Concordance for histological types was perfect for CNB-diagnosed ILC (rate= 100%; k= 1; p<0,001) and almost perfect for IDC (rate= 96.7%; k= 0.94; p<0,001). The concordance between Core Needle Biopsy (CNB) and surgical excision specimen in the diagnosis of malignancy and benignity of breast tumors is almost perfect for CNB-diagnosed malignancies and moderate for benign tumors.

Navigator nurse implementation within a fast track program of liver resections: How to improve the healthcare service and perioperative results.

The introduction into the clinical practice of the navigator nurse (NaNu) to address the task of counseling and short term follow-up help the effective implementation of the fast track protocol. The aim of the present study was to investigate the impact of the standardization of the NaNu's role in patients undergoing liver surgery. Patients undergoing elective liver surgery for all diagnosis and approach, from 2015, received counseling and postoperative follow-up by NaNu and constituted the study group (n=890). This group was compared with the control group (n=712) including patients treated in the era before the implementation of the NaNu role (2011-2014). Outcome was evaluated in terms of discrepancy between functional recovery and discharge, number of ER accesses, number of readmissions. Preoperative characteristics of patients and disease, as well as type of resection and postoperative outcomes were similar between the two groups. The proportion of laparoscopic cases was higher in the study group (51.2% vs. 32% in the control). Time for discharge, interval between functional recovery and discharge, number of ER accesses and number of readmissions were reduced in the study group. Benign diagnosis, absence of complications, laparoscopic approach and presence of NaNu were independent predictors of shorter length of stay. The positive effect of NaNu's activation was recorded in patients with complications and undergoing open surgery. The implementation of NaNu's role has allowed to us optimize the level of healthcare service offered to patients. The wider benefit was offered in the setting of complex patients.

Diagnosis of Benign and Malignant BI-RADS 4 Breast Masses by Contrastenhanced Ultrasound Combined with Shear Wave Elastography.

Breast cancer, one of the most prevalent malignant tumors in females, usually occurs in the breast epithelial tissues. The study aimed to explore the diagnostic value of contrast-enhanced ultrasound (CEUS) combined with shear wave elastography (SWE) in the diagnosis of benign and malignant breast masses in BI-RADS (Breast Imaging Reporting and Data System) 4. Examination outcomes and clinical information of 83 patients with BI-RADS 4 breast masses were analyzed retrospectively. These included patients who received CEUS, SWE, and pathological examinations. The difference of CEUS in determining the classification of BI-RADS 4 breast masses was evaluated using histopathological outcomes of breast masses as a reference standard. The diagnostic value of CEUS, SWE, and CEUS combined with SWE in the diagnosis of benign and malignant breast masses in BI-RADS 4 was also explored. Pathological biopsy results revealed 63 malignant masses and 20 benign masses among 83 BI-RADS 4 breast masses, with a 75.9% incidence of malignant masses. After the diagnosis of BI-RADS 4 breast masses with CEUS, SWE, and CEUS+SWE, the incidence of malignancy was 56.6%, 78.3%, and 73.5%, respectively. CEUS+SWE showed higher sensitivity (93.7% vs. 81% and 68.3%), specificity (90% vs. 30% and 80%), positive predictive value (96.7% vs. 78.5% and 91.5%), negative predictive value (81.8% vs. 33.3% and 44.4%), and diagnostic coincidence rate (92.8% vs. 68.7% and 71.1%) than SWE and CEUS alone in diagnosing pathological type of breast masses. Moreover, CEUS combined with SWE exhibited a larger area under the receiver operating characteristic (ROC) curve (0.918) than SWE (0.741, p = 0.028) and CEUS (0.555, p < 0.001) alone in the diagnosis of BI-RADS 4 breast masses. Overall, the diagnostic value of CEUS+SWE for the pathological type of BI-RADS is preferred over CEUS and SWE alone. CEUS+SWE showed higher values than CEUS and SWE alone in diagnosing BI-RADS 4 breast masses. Specifically, CEUS+SWE can correctly identify benign and malignant masses, reduce unnecessary trauma, and avoid misdiagnosis. In summary, CEUS combined with SWE can serve as an effective diagnostic method and avoid delaying the best treatment opportunity for some malignant lesions.

Inflammatory Tongue Conditions and Risk of Oral Tongue Cancer Among the US Elderly Individuals.

The incidence of oral tongue cancers has increased since the 1980s among US men and women for unknown reasons. We investigated associations of inflammatory tongue conditions with risk of cancers of the oral tongue, other oral cavity, and oropharynx among the US elderly individuals (age 65 years or older). We conducted a case-control study (2,534 oral tongue cancers, 6,832 other oral cavity cancers, 9,373 oropharyngeal cancers, and 200,000 controls) within the SEER-Medicare data set (1992-2013). Medicare records were used to identify patients with clinically diagnosed inflammatory tongue conditions (glossitis, benign migratory glossitis, median rhomboid glossitis, atrophic glossitis, glossodynia, other specified conditions [eg, atrophy and hypertrophy], and other unspecified conditions) and oral precancer (leukoplakia/erythroplakia). Only conditions preceding cancer/control selection by >12 months were included. The prevalence of inflammatory tongue conditions was significantly higher in patients with tongue cancer than controls (6.0% v 0.6%; odds ratios [ORs], adjusted for age, sex, race, Medicare utilization, and precancer, 5.8 [95% CI, 4.7 to 7.2]). This overall association primarily arose from glossitis, 5.6 (95% CI, 4.4 to 7.2); other specified conditions, 9.1 (95% CI, 5.5 to 15.2); and other unspecified conditions, 13.7 (95% CI, 8.0 to 23.7). These associations remained strongly elevated >5 years preceding tongue cancer (arguing against reverse causation), for conditions diagnosed by a specialist (arguing against misclassification), and among patients who received an oral biopsy (arguing against missed cancer). During 2013, an estimated 1 in 11 patients with oral tongue cancer had a preceding diagnosis of inflammatory tongue conditions. Associations of inflammatory tongue conditions were relatively weak for other oral cavity cancers (ORs, 1.8 [95% CI, 1.5 to 2.3]) and oropharyngeal cancer (OR, 1.3 [95% CI, 1.0 to 1.6]) and were observed only closest to cancer diagnosis. Inflammatory tongue conditions were associated with strongly increased risks of oral tongue cancers and preceded cancer diagnosis by several years, underscoring the need for increased clinical surveillance among patients with such apparently benign diagnoses.

Cytologic analysis of metaplastic breast carcinoma: Review of 66 cases diagnosed at the Institut Curie.

Cytology reports of metaplastic breast carcinoma (MBC) are rare and limited to short series and simple case reports. To adapt cytology diagnostic criteria to the most recent fifth edition of the World Health Organization Classification of Breast Tumours from 2019, we have reviewed our series from the files of the Institut Curie. A cohort of 66 female patients investigated by cytology with corresponding histologic diagnosis of MBC was identified. Eight cytologic characteristics were analyzed: cellularity, adenocarcinoma cells, squamous cells, spindle cells, giant cells, cytonuclear atypia, necrosis, and osseous/chondroid matrix and compared with histology. Cytologic diagnoses were malignant in 58 (88%) cases (of which 29 cases were typed cytologically as MBC), suspicious in 6 (9%) cases, and nondiagnostic in 2 (3%) cases. None of the cytologic examinations was a benign diagnosis. Low-grade adenosquamous carcinoma and fibromatosis-like metaplastic carcinoma exhibited a low degree of cellular atypia. Fibromatosis-like metaplastic carcinoma and spindle cell carcinoma (SpCC) presented spindle cells, while SpCC also demonstrated varying degrees of atypia, the presence of giant cells, and necrosis. Squamous cell carcinoma was characterized by the presence of squamous cells, and metaplastic carcinoma with osseous/chondroid differentiation displayed an osseous/chondroid matrix. Fine-needle aspiration holds considerable potential as a valid, independent, and complementary approach to histologic examination of MBC.

Benefits of the Enhanced Recovery After Surgery (ERAS) Pathway With Quadratus Lumborum Blocks for Minimally Invasive Gynecologic Surgery Patients: A Retrospective Cohort Study.

This study aimed to determine the effect of the implementation of the Enhanced Recovery After Surgery (ERAS) protocol among patients receiving minimally invasive gynecologic surgery. This retrospective cohort study was performed in a tertiary care hospital. A total of 328 females who underwent minimally invasive gynecologic surgeries requiring at least one overnight stay at Keck HospitalofUniversity of Southern California (USC), California, USA, from 2016 to 2020 were included in this study. The institutional ERAS protocol was implemented in late 2018. A total of 186 patients from 2016 to 2018 prior to the implementation were compared to 142 patients from 2018 to 2020 after the implementation. Intraoperatively, the ERAS group received a multimodal analgesic regimen (including bilateral quadratus lumborum (QL) blocks) and postoperative care geared towarda satisfactory, safe, and expeditious discharge. The two groups were similar in demographics, except for the shorter surgical time noted in the ERAS group. The median opioid use was significantly less among the ERAS patients compared with the non-ERAS patients on postoperative day 1 (7.5 vs. 14.3 mg; p<0.001) and throughout the hospital stay (17.4 vs. 36.2 mg; p<0.001). The ERAS group also had a shorter median hospital length of stay compared to the non-ERAS group (p<0.01). Among patients with a malignant diagnosis, patients in the ERAS group had significantly less postoperative day 1 and total opioid use and a shorter hospital stay (p<0.01). Within the ERAS group, 20% of the patients did not end up receiving a QL block. Opioid use and length of stay were similar between patients who did and did not receive the QL block. The ERAS pathway was associated with a reduction in opioid use postoperatively and a shorter length of hospital stay after minimally invasive gynecologic surgery. There was a more significant decrease in opioid use and hospital length of stay for patients with malignant diagnoses compared to patients with benign diagnoses. Further research can be done to fully delineate the effect of QL blocks in ERAS protocols.

Surgical Resection of Benign Nodules in Lung Cancer Screening: Incidence and Features

IntroductionInterventions and surgical procedures are common for nonmalignant lung lesions detected on lung cancer screening (LCS). Inadvertent surgical resection of benign nodules with a clinical suspicion of lung cancer can occur, can be associated with complications, and adds to the cost of screening. The objective of this study is to assess the characteristics of surgically resected benign nodules detected on LCS computed tomography which were presumed to be lung cancers. MethodsThis retrospective study included 4798 patients who underwent LCS between June 2014 and January 2021. The benign lung nodules, surgically resected with a presumed cancer diagnosis, were identified from the LCS registry. Patient demographics, imaging characteristics, and pathologic diagnoses of benign nodules were analyzed. ResultsOf the 4798 patients who underwent LCS, 148 (3.1%) underwent surgical resection of a lung nodule, and of those who had a resection, 19 of 148 (12.8%) had a benign diagnosis (median age = 64 y, range: 56–77 y; F = 12 of 19, 63.2%; M = seven of 19, 36.8%). The median nodule size was 10 mm (range: 6–31 mm). Most nodules were solid (15 of 19, 78.9%), located in the upper lobes (11 of 19; 57.9%), and were peripheral (17 of 19, 89.5%). Most nodules (13 of 17; 76.5%) had interval growth, and four of 17 (23.5%) had increased fluorodeoxyglucose uptake. Of the 19 patients, 17 (89.5%) underwent sublobar resection (16 wedge resection and one segmentectomy), whereas two central nodules (10.5%) had lobectomies. Pathologies identified included focal areas of fibrosis or scarring (n = 8), necrotizing granulomatous inflammation (n = 3), other nonspecific inflammatory focus (n = 3), benign tumors (n = 3), reactive lymphoid hyperplasia (n = 1), and organizing pneumonia (n = 1). ConclusionsSurgical resections of benign nodules that were presumed malignant are infrequent and may be unavoidable given overlapping imaging features of benign and malignant nodules. Knowledge of benign pathologies that can mimic malignancy may help reduce the incidence of unnecessary surgeries.

Investigating misdiagnosis of suspected cancer among patients undergoing pancreatoduodenectomy: three decades of experience

BackgroundDiagnostic error can result in pancreatoduodenectomy (PD) being mistakenly performed for benign disease. The aims of this study were to observe the error rate in PD over three decades and identify characteristics of benign disease that can mimic malignancy. MethodsPatients with a benign histological diagnosis after having PD performed for suspected malignancy between 1988 and 2019 were selected for review. Preoperative clinical features, imaging and pathological samples were reviewed alongside resection specimens to identify features that may have led to misdiagnosis. ResultsOver the study period, 1812 patients underwent PD for suspected malignancy and 97 (5.2 %) of these had a final benign diagnosis. The rate of benign cases reduced across the study period. Some 62 patients proceeded to surgery without a preoperative tissue diagnosis; the decision to operate was made upon clinical and radiologic features alone. There were six patients who had a preoperative pathological sample suspicious for malignancy, of which two had autoimmune pancreatitis in the postoperative histology specimen. DiscussionBenign conditions, notably autoimmune and chronic pancreatitis, can mimic malignancy even with the use of EUS-FNA. The results of all available diagnostic modalities should be interpreted by a multidisciplinary team and honest discussions with the patient should follow.

Integrating social care into gynecologic oncology: Identifying and addressing patient's social needs

ObjectiveWe aimed to identify social needs of gynecologic oncology patients using a self-administered social needs assessment tool (SNAT), compare the SNAT to a formal social work assessment performed by cancer care navigators (CCN), and provide SNAT-informed community resources. MethodsWe analyzed prospectively collected data from a performance improvement initiative in a safety-net gynecologic oncology clinic between October 2021 and July 2022. We screened for eight social needs domains, health literacy, desire for social work, and presence of urgent needs. Clinicodemographic data were abstracted from the electronic medical record. Univariate descriptive statistics were used. Inter-rater reliability for social needs domains was assessed using percent agreement. Results1010 unique patients were seen over this study period. 488 (48%) patients completed the SNAT, of which 265 (54%) screened positive for ≥1 social need. 83 (31%) patients were actively receiving cancer treatment, 140 (53%) were in post-treatment surveillance, and 42 (16%) had benign gynecologic diagnoses. Transportation (19% vs 25%), housing insecurity (18% vs 19%), and desire to speak with a social worker (16% vs 27%) were the 3 most common needs in both the entire cohort and among patients actively receiving cancer treatment. 78% patients in active treatment were seen by a CCN and received SNAT informed community resources. The percent agreement between the SNAT and formal CCN assessment ranged from 72%–94%. ConclusionsThe self-administered SNAT identified many unmet social needs among gynecologic oncology patients, corresponded well with the formal social work CCN assessment, and informed the provision of community resources.

The success rate of small renal mass core needle biopsy and its impact on lowering benign resection rate

BackgroundSmall renal mass (SRM) biopsy remains under-utilized due to stigma. Meanwhile, the alarmingly high benign findings in resected kidney masses highlight the need for improved preoperative diagnosis and patient selection.MethodsThe purpose of this study is to review the success rate of SRM biopsy and to evaluate its impact on patient management. A total of 168 percutaneous image-guided core needle biopsies (CNBs) of SRMs were retrieved at a tertiary academic center between 2015 and 2019. Subsequent treatment choices, side effects and outcomes were retrospectively reviewed.ResultsThe diagnostic rate of CNB was 86.9%. Benign neoplasms accounted for a significant portion (14.3%) of SRM. Renal cell carcinomas (RCCs) were the most common diagnoses (69.6%) as expected. In biopsy-resection correlation, the positive predictive value of CNB was 100%. Tumor typing and subtyping by CNB were highly accurate, 100% and 98.3% respectively. Nuclear grading for clear cell RCC was accurate in 83.8% cases. The CNB results had significant impact on treatment. Most patients with RCCs underwent either resection (54.1%) or ablation (33.9%), in contrast to observation in benign neoplasms (90.5%). Most importantly, the benign resection rate (3.2%) in this series was much lower than the national average.ConclusionCNB provided accurate diagnoses for the majority of SRMs and revealed benign diagnoses in a subset of clinically suspicious lesions. Employment of CNB in suspicious SRM may help avoid overtreatment for benign lesions.

Beta-2 Microglobulin As a Seric Marker for Diagnosis of Hematologic Neoplasms in First Contact Consultation with the Hematologist

Introduction Beta-2 microglobulin is a protein component of the Major histocompatibility complex I. Its concentration in blood has been long used as prognostic marker in some hematologic neoplasms, and even used as a tool for surveillance of relapse in other neoplasms. It is frequently elevated in non-Hodgkin lymphoma (NHL), Myelodysplastic syndrome (MDS), myeloma multiple (MM), chronic lymphocytic leukemia (CLL) and other Lymphoproliferative disorders. Although its utility as a diagnostic tool has been poorly described. Aim Describe the blood levels of Beta-2 Microglobulin in patients who are sent without established diagnosis to be evaluated by hematology department and its association with the different definitive diagnosis. Methods We captured information from outpatients who were evaluated in the first consultation at hematology department because of any citopenia or clinical suspicion of any hematologic neoplasm from September 2022 to July 2023. If the patient consented, we recorded it in database and measured blood levels of beta-2 microglobulin on first consultation, and then followed until definitive diagnosis was established. Analysis of data was made with IBM SPSS Statistics for Windows, Version 27.0. Armonk, NY: IBM Corp; we used Mann Whitney U Test for quantitative variable comparison, and Fisher exact test to determine differences between groups. Statistical significances were calculates using p&amp;lt;0.05. Results We captured a total of 87 patients, but 11 had to be excluded because of lack of information. Of the 76 patients included for analysis, 34 were male (44.7%) and 42 were female (55.3%). The medium age was 45.1 years (Range: 15-95 years). After the first consultation, 30 patients (39.5%) were suspected to have a neoplasm, and in follow-up, 35 (46.05%) ended up with a definitive diagnosis of hematologic neoplasm. Only one patient with initial suspected neoplasm ended up with benign disease, but 6 patients in which a bening condition was suspected ended up with a neoplasm diagnosis. There was a total of 35 (46.05%) patients with definitive neoplastic diagnostic, being the most frequent: NHL (n=15, 19.7%), Myeloproliferative neoplasm (MPNs) (n=6, 7.8%), and MM (4, 5.2%). In the no neoplastic pathology, the most frequent diagnosis was iron-deficit anemia (n=17; 22.36%), followed by megaloblastic anemia (n=4, 5.26%) and infectious disease (n=4, 26%). Beta-2 microglobulin was higher in the group with definitive neoplastic diagnosis (5.4mg/L vs 2.4mg/L, x 2=0.053), and was also, significatively higher in the NHL (4.94mg/L, x 2=0.005), MM (13.43mg/L, x 2=0.008), CLL (6.3mg/L, x 2=0.02) and MDS (8.05mg/L, x 2=0.034) subgroups. The sensibility for any hematologic neoplasm was 48.5% and specificity was 82.93%, with a positive LR of 2.84 and a Negative LR of 0.62. The subgroups with higher sensibility were MM (75%), CLL (66.6%), MPNs (66.6%) and MDS (100%), being the Positive LR of 4.3 for MM, 3.9 for CLL, 3.9 for MPNs and 5.86 for MDS. Groups with the lowest correlation were Hodgkin lymphoma (HL) with sensibility of 33.3%, and isolated plasmacytoma (PC) with sensibility of 0%. In the group with benign diagnosis, only 6 (7.89%) presented levels above upper normal limit of blood Beta-2 microglobulin, 4 (5.26%) with iron-deficit anemia, 1 (1.31%) with liver disease, 1 (1.31%) with Pulmonary tuberculosis and 1 (1.31%) with systemic lupus erythematosus; being the highest levels in pulmonary tuberculosis (14.9mg/L). Conclusions The blood levels of beta-2 microglobulin in our work were in concordance with other previous described papers, in which is frequently elevated in NHL, MM, and CCL. But in our case, it showed a marked elevation in MPNs, and MDS (higher correlation). It should be noted, no tumor burden was recorded in our study, which could directly affect beta-2 microglobulin levels. In conclusion, although not a strong correlation as an expert hematologist clinical evaluation, beta-2microglobulin could be of use to strengthen clinical suspicion of those hematologic neoplasms or reassess cases in which MDS/MPNs are a possible differential diagnosis.

Improving access to care with implementation of a virtual anemia clinic.

113 Background: In 2022, our cancer center saw a rapidly rising number of new hematology consult requests, specifically for anemia. This increase created access challenges, especially for our regional hematology oncology practices, who see both malignant and benign consult diagnoses. Our enterprise target metric for assessing access is defined as “median of appointments within 7 days.” This metric was rapidly as far out as 15 days (YTD) in the hematology disease group briefly, therefore calling the leadership team to action. An additional concern was provider dissatisfaction from frequent add-on requests for consults and a pivot from an even split of hematology oncology patients to heavily classical hematology consults. Timely triage and assessment of anemia is necessary for identification of potentially serious underlying cancer diagnoses. Methods: Upon investigation, opportunities to improve patient access were identified as: 1) underutilized APPs; 2) scheduler turnover, communication barriers resulting in up to 30% of new patient slots going unused; 3) anemia consults scheduled at 60 minutes which typically take 30-45 minutes to complete; 4) patients are interested in a virtual appointment for non-oncologic consult diagnoses but scheduling these visit types has been challenging. An APP lead virtual only anemia clinic (VAC) was launched in Sept 2022. The clinic consisted of with five 45-minute consults per day. A decision tree was created to for efficiency and to assist in appropriate diagnoses scheduled. Biweekly huddles for quality assurance of patient care were initiated. No additional FTEs were required to initiate this clinic. Results: In 6 weeks, we were able launch the VAC with utilization strongly in the upper 90%. 5 APPs trained in anemia consults divided Monday-Friday with one virtual day per week. Follow up patients were scheduled in person at regional or main campus locations as indicated. The access metric for hematology consults improved from 15 days (YTD) to 8 (YTD) within the initial 6 months. More specifically, anemia consult diagnoses improved to less than 7 days almost immediately. Anecdotally, patients were satisfied with the appointment availability and care received. Patient experience scores for the participating APPs remained steady throughout the initial first 6 months and are continuing to be followed. Conclusions: A VAC is a potential way to achieve improved patient access to an anemia consult, further providing timely evaluation and treatment. Additional professional revenue that does not utilize physical space, caregivers, building facilities is a positive outcome, in addition to expedited triage, assessment, diagnosis, and treatment for anemia in straightforward and complex patients. There is an added benefit for patients who have an opportunity for virtual care such as quick access to care, decreased financial toxicity, and removal of barriers to care like transportation and taking time off work.

Thermal liquid biopsy (TLB): A new diagnostic technique for the differentiation of benign and premalignant pancreatic cyst diagnosis

Thermal liquid biopsy (TLB): A new diagnostic technique for the differentiation of benign and premalignant pancreatic cyst diagnosis

Vertical Stenosis as a Morphological Risk Factor for Anterior Cruciate Ligament Ruptures in Children: A Magnetic Resonance Imaging–Based Comparison

Background: There are known anatomic variations that may lead to traumatic disruption of the anterior cruciate ligament (ACL) identified within adult and adolescent patients. Purpose/Hypothesis: The purpose of this study was to compare the parameters of pediatric knees diagnosed with and without an ACL injury by magnetic resonance imaging. The hypothesis was that children with ACL abnormalities would demonstrate an equivalent notch width index (NWI), but a larger notch height index (NHI), in comparison with age-matched patients without ACL abnormalities, suggesting an association with congenital morphology. Study Design: Cross-sectional study; Level of evidence, 3. Methods: A retrospective comparison cohort study of pediatric knees was performed by evaluating those with a confirmed ACL rupture/deficiency and those with a benign diagnosis on magnetic resonance imaging. Overall, 6 osseous and cartilaginous measurements and 3 ratios (2 newly described) were determined. They were then grouped for statistical purposes by age: children aged 5 to 11 years and adolescents aged 12 to 19 years. Results: A total of 119 (49 children) consecutive patients with an ACL injury and 139 (72 children) healthy patients met inclusion criteria. The interaction between ACL status and age was significant for condylar measurements (P≤ .001), tibial spine height (P = .003), vertical space above tibial spine (P≤ .001), and NWI (P≤ .001) by 2-way analysis of variance. Although the NHI (P < 0.001) and tibial spine prominence (P = 0.039) demonstrated stenosis in the adolescent group, they did not have significant interactions with age and ACL status (P > 0.05). Regarding the transcondylar width, only the children's group had a significant difference regarding ACL status (P < .001), and the mean values in the children's group with ACL tears were nearly identical to those in the adolescent group both with and without ACL tears. The children's group with ACL tears also had a significantly larger tibial spine height compared with healthy children (P < .001). Conclusion: Children, similar to adolescents, demonstrated the effect of the NWI on the risk of ACL tears, but only the adolescent group demonstrated stenosis with the NHI. The morphology of the knee in a child at risk for ACL rupture was not the same as that of an adolescent when considering all dimensions, but it did seem that it was more adolescent-like than child-like at the time of an ACL rupture, refuting the idea of congenital hypoplasia as a common cause.

Screening in Patients With Dense Breasts: Comparison of Mammography, Artificial Intelligence, and Supplementary Ultrasound.

BACKGROUND. Screening mammography has decreased performance in patients with dense breasts. Supplementary screening ultrasound is a recommended option in such patients, although it has yielded mixed results in prior investigations. OBJECTIVE. The purpose of this article is to compare the performance characteristics of screening mammography alone, standalone artificial intelligence (AI), ultrasound alone, and mammography in combination with AI and/or ultrasound in patients with dense breasts. METHODS. This retrospective study included 1325 women (mean age, 53 years) with dense breasts who underwent both screening mammography and supplementary breast ultrasound within a 1-month interval from January 2017 to December 2017; prior mammography and prior ultrasound examinations were available for comparison in 91.2% and 91.8%, respectively. Mammography and ultrasound examinations were interpreted by one of 15 radiologists (five staff; 10 fellows); clinical reports were used for the present analysis. A commercial AI tool was used to retrospectively evaluate mammographic examinations for presence of cancer. Screening performances were compared among mammography, AI, ultrasound, and test combinations, using generalized estimating equations. Benign diagnoses required 24 months or longer of imaging stability. RESULTS. Twelve cancers (six invasive ductal carcinoma; six ductal carcinoma in situ) were diagnosed. Mammography, standalone AI, and ultrasound showed cancer detection rates (per 1000 patients) of 6.0, 6.8, and 6.0 (all p > .05); recall rates of 4.4%, 11.9%, and 9.2% (all p < .05); sensitivity of 66.7%, 75.0%, and 66.7% (all p > .05); specificity of 96.2%, 88.7%, and 91.3% (all p < .05); and accuracy of 95.9%, 88.5%, and 91.1% (all p < .05). Mammography with AI, mammography with ultrasound, and mammography with both ultrasound and AI showed cancer detection rates of 7.5, 9.1, and 9.1 (all p > .05); recall rates of 14.9, 11.7, and 21.4 (all p < .05); sensitivity of 83.3%, 100.0%, and 100.0% (all p > .05); specificity of 85.8%, 89.1%, and 79.4% (all p < .05); and accuracy of 85.7%, 89.2%, and 79.5% (all p < .05). CONCLUSION. Mammography with supplementary ultrasound showed higher accuracy, higher specificity, and lower recall rate in comparison with mammography with AI and in comparison with mammography with both ultrasound and AI. CLINICAL IMPACT. The findings fail to show benefit of AI with respect to screening mammography performed with supplementary breast ultrasound in patients with dense breasts.

Rapid Segmentation and Diagnosis of Breast Tumor Ultrasound Images at the Sonographer Level Using Deep Learning.

Breast cancer is one of the most common malignant tumors in women. A noninvasive ultrasound examination can identify mammary-gland-related diseases and is well tolerated by dense breast, making it a preferred method for breast cancer screening and of significant clinical value. However, the diagnosis of breast nodules or masses via ultrasound is performed by a doctor in real time, which is time-consuming and subjective. Junior doctors are prone to missed diagnoses, especially in remote areas or grass-roots hospitals, due to limited medical resources and other factors, which bring great risks to a patient's health. Therefore, there is an urgent need to develop fast and accurate ultrasound image analysis algorithms to assist diagnoses. We propose a breast ultrasound image-based assisted-diagnosis method based on convolutional neural networks, which can effectively improve the diagnostic speed and the early screening rate of breast cancer. Our method consists of two stages: tumor recognition and tumor classification. (1) Attention-based semantic segmentation is used to identify the location and size of the tumor; (2) the identified nodules are cropped to construct a training dataset. Then, a convolutional neural network for the diagnosis of benign and malignant breast nodules is trained on this dataset. We collected 2057 images from 1131 patients as the training and validation dataset, and 100 images of the patients with accurate pathological criteria were used as the test dataset. The experimental results based on this dataset show that the MIoU of tumor location recognition is 0.89 and the average accuracy of benign and malignant diagnoses is 97%. The diagnosis performance of the developed diagnostic system is basically consistent with that of senior doctors and is superior to that of junior doctors. In addition, we can provide the doctor with a preliminary diagnosis so that it can be diagnosed quickly. Our proposed method can effectively improve diagnostic speed and the early screening rate of breast cancer. The system provides a valuable aid for the ultrasonic diagnosis of breast cancer.